linux/tools/perf/builtin-top.c

1097 lines
27 KiB
C
Raw Normal View History

/*
* builtin-top.c
*
* Builtin top command: Display a continuously updated profile of
* any workload, CPU or specific PID.
*
* Copyright (C) 2008, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
* 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Improvements and fixes by:
*
* Arjan van de Ven <arjan@linux.intel.com>
* Yanmin Zhang <yanmin.zhang@intel.com>
* Wu Fengguang <fengguang.wu@intel.com>
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include "builtin.h"
#include "perf.h"
#include "util/annotate.h"
#include "util/cache.h"
#include "util/color.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/session.h"
#include "util/symbol.h"
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
#include "util/thread.h"
#include "util/thread_map.h"
#include "util/top.h"
#include "util/util.h"
#include <linux/rbtree.h>
#include "util/parse-options.h"
#include "util/parse-events.h"
perf tools: Fix sparse CPU numbering related bugs At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 09:36:09 +00:00
#include "util/cpumap.h"
#include "util/xyarray.h"
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
#include "util/sort.h"
#include "util/debug.h"
#include <assert.h>
#include <fcntl.h>
#include <stdio.h>
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
#include <termios.h>
#include <unistd.h>
#include <inttypes.h>
#include <errno.h>
#include <time.h>
#include <sched.h>
#include <sys/syscall.h>
#include <sys/ioctl.h>
#include <sys/poll.h>
#include <sys/prctl.h>
#include <sys/wait.h>
#include <sys/uio.h>
#include <sys/mman.h>
#include <linux/unistd.h>
#include <linux/types.h>
static struct perf_top top = {
.count_filter = 5,
.delay_secs = 2,
.target_pid = -1,
.target_tid = -1,
.freq = 1000, /* 1 KHz */
};
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
static bool system_wide = false;
static bool use_tui, use_stdio;
static int default_interval = 0;
static bool kptr_restrict_warned;
static bool vmlinux_warned;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
static bool inherit = false;
static int realtime_prio = 0;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
static bool group = false;
static unsigned int mmap_pages = 128;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
static bool dump_symtab = false;
static struct winsize winsize;
static const char *sym_filter = NULL;
static int sym_pcnt_filter = 5;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
/*
* Source functions
*/
void get_term_dimensions(struct winsize *ws)
{
char *s = getenv("LINES");
if (s != NULL) {
ws->ws_row = atoi(s);
s = getenv("COLUMNS");
if (s != NULL) {
ws->ws_col = atoi(s);
if (ws->ws_row && ws->ws_col)
return;
}
}
#ifdef TIOCGWINSZ
if (ioctl(1, TIOCGWINSZ, ws) == 0 &&
ws->ws_row && ws->ws_col)
return;
#endif
ws->ws_row = 25;
ws->ws_col = 80;
}
static void update_print_entries(struct winsize *ws)
{
top.print_entries = ws->ws_row;
if (top.print_entries > 9)
top.print_entries -= 9;
}
static void sig_winch_handler(int sig __used)
{
get_term_dimensions(&winsize);
update_print_entries(&winsize);
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static int parse_source(struct hist_entry *he)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
struct symbol *sym;
struct annotation *notes;
perf tools: Rewrite and improve support for kernel modules Representing modules as struct map entries, backed by a DSO, etc, using /proc/modules to find where the module is loaded. DSOs now can have a short and long name, so that in verbose mode we can show exactly which .ko or vmlinux image was used. As kernel modules now are a DSO separate from the kernel, we can ask for just the hits for a particular set of kernel modules, just like we can do with shared libraries: [root@doppio linux-2.6-tip]# perf report -n --vmlinux /home/acme/git/build/tip-recvmmsg/vmlinux --modules --dsos \[drm\] | head -15 84.58% 13266 Xorg [k] drm_clflush_pages 4.02% 630 Xorg [k] trace_kmalloc.clone.0 3.95% 619 Xorg [k] drm_ioctl 2.07% 324 Xorg [k] drm_addbufs 1.68% 263 Xorg [k] drm_gem_close_ioctl 0.77% 120 Xorg [k] drm_setmaster_ioctl 0.70% 110 Xorg [k] drm_lastclose 0.68% 106 Xorg [k] drm_open 0.54% 85 Xorg [k] drm_mm_search_free [root@doppio linux-2.6-tip]# Specifying --dsos /lib/modules/2.6.31-tip/kernel/drivers/gpu/drm/drm.ko would have the same effect. Allowing specifying just 'drm.ko' is left for another patch. Processing kallsyms so that per kernel module struct map are instantiated was also left for another patch. That will allow removing the module name from each of its symbols. struct symbol was reduced by removing the ->module backpointer and moving it (well now the map) to struct symbol_entry in perf top, that is its only user right now. The total linecount went down by ~500 lines. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-02 06:29:58 +00:00
struct map *map;
int err = -1;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (!he || !he->ms.sym)
return -1;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
sym = he->ms.sym;
map = he->ms.map;
/*
* We can't annotate with just /proc/kallsyms
*/
if (map->dso->symtab_type == SYMTAB__KALLSYMS) {
pr_err("Can't annotate %s: No vmlinux file was found in the "
"path\n", sym->name);
sleep(1);
return -1;
}
notes = symbol__annotation(sym);
if (notes->src != NULL) {
pthread_mutex_lock(&notes->lock);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
goto out_assign;
}
pthread_mutex_lock(&notes->lock);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
if (symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
pthread_mutex_unlock(&notes->lock);
pr_err("Not enough memory for annotating '%s' symbol!\n",
sym->name);
sleep(1);
return err;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
err = symbol__annotate(sym, map, 0);
if (err == 0) {
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
out_assign:
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
top.sym_filter_entry = he;
}
pthread_mutex_unlock(&notes->lock);
return err;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static void __zero_source_counters(struct hist_entry *he)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct symbol *sym = he->ms.sym;
symbol__annotate_zero_histograms(sym);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static void record_precise_ip(struct hist_entry *he, int counter, u64 ip)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
struct annotation *notes;
struct symbol *sym;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (he == NULL || he->ms.sym == NULL ||
(he != top.sym_filter_entry && use_browser != 1))
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
return;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
sym = he->ms.sym;
notes = symbol__annotation(sym);
if (pthread_mutex_trylock(&notes->lock))
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
return;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (notes->src == NULL &&
symbol__alloc_hist(sym, top.evlist->nr_entries) < 0) {
pthread_mutex_unlock(&notes->lock);
pr_err("Not enough memory for annotating '%s' symbol!\n",
sym->name);
sleep(1);
return;
}
ip = he->ms.map->map_ip(he->ms.map, ip);
symbol__inc_addr_samples(sym, he->ms.map, counter, ip);
pthread_mutex_unlock(&notes->lock);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static void show_details(struct hist_entry *he)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
struct annotation *notes;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
struct symbol *symbol;
int more;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (!he)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
return;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
symbol = he->ms.sym;
notes = symbol__annotation(symbol);
pthread_mutex_lock(&notes->lock);
if (notes->src == NULL)
goto out_unlock;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
printf("Showing %s for %s\n", event_name(top.sym_evsel), symbol->name);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
printf(" Events Pcnt (>=%d%%)\n", sym_pcnt_filter);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
more = symbol__annotate_printf(symbol, he->ms.map, top.sym_evsel->idx,
0, sym_pcnt_filter, top.print_entries, 4);
if (top.zero)
symbol__annotate_zero_histogram(symbol, top.sym_evsel->idx);
else
symbol__annotate_decay_histogram(symbol, top.sym_evsel->idx);
if (more != 0)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
printf("%d lines not displayed, maybe increase display entries [e]\n", more);
out_unlock:
pthread_mutex_unlock(&notes->lock);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
static const char CONSOLE_CLEAR[] = "";
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static struct hist_entry *
perf_session__add_hist_entry(struct perf_session *session,
struct addr_location *al,
struct perf_sample *sample,
struct perf_evsel *evsel)
{
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct hist_entry *he;
he = __hists__add_entry(&evsel->hists, al, NULL, sample->period);
if (he == NULL)
return NULL;
session->hists.stats.total_period += sample->period;
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
return he;
}
static void print_sym_table(void)
{
char bf[160];
int printed = 0;
const int win_width = winsize.ws_col - 1;
perf top: Reduce display overhead Iterate over the symbol table once per display interval, and copy/sort/tally/decay only those symbols which are active. Before: top - 10:14:53 up 4:08, 17 users, load average: 1.17, 1.53, 1.49 Tasks: 273 total, 5 running, 268 sleeping, 0 stopped, 0 zombie Cpu(s): 6.9%us, 38.2%sy, 0.0%ni, 19.9%id, 0.0%wa, 0.0%hi, 35.0%si, 0.0%st PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ P COMMAND 28504 root 20 0 1044 260 164 S 58 0.0 0:04.19 2 netserver 28499 root 20 0 1040 412 316 R 51 0.0 0:04.15 0 netperf 28500 root 20 0 1040 408 316 R 50 0.0 0:04.14 1 netperf 28503 root 20 0 1044 260 164 S 50 0.0 0:04.01 1 netserver 28501 root 20 0 1044 260 164 S 49 0.0 0:03.99 0 netserver 28502 root 20 0 1040 412 316 S 43 0.0 0:03.96 2 netperf 28468 root 20 0 1892m 325m 972 S 16 10.8 0:10.50 3 perf 28467 root 20 0 1892m 325m 972 R 2 10.8 0:00.72 3 perf After: top - 10:16:30 up 4:10, 17 users, load average: 2.27, 1.88, 1.62 Tasks: 273 total, 6 running, 267 sleeping, 0 stopped, 0 zombie Cpu(s): 2.5%us, 39.7%sy, 0.0%ni, 24.6%id, 0.0%wa, 0.0%hi, 33.3%si, 0.0%st PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ P COMMAND 28590 root 20 0 1040 412 316 S 54 0.0 0:07.85 2 netperf 28589 root 20 0 1044 260 164 R 54 0.0 0:07.84 0 netserver 28588 root 20 0 1040 412 316 R 50 0.0 0:07.89 1 netperf 28591 root 20 0 1044 256 164 S 50 0.0 0:07.82 1 netserver 28587 root 20 0 1040 408 316 R 47 0.0 0:07.61 0 netperf 28592 root 20 0 1044 260 164 R 47 0.0 0:07.85 2 netserver 28378 root 20 0 8732 1300 860 R 2 0.0 0:01.81 3 top 28577 root 20 0 1892m 165m 972 R 2 5.5 0:00.48 3 perf 28578 root 20 0 1892m 165m 972 S 2 5.5 0:00.04 3 perf [ Impact: optimization ] Signed-off-by: Mike Galbraith <efault@gmx.de> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-25 07:57:56 +00:00
puts(CONSOLE_CLEAR);
perf_top__header_snprintf(&top, bf, sizeof(bf));
printf("%s\n", bf);
perf_top__reset_sample_counters(&top);
printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
if (top.total_lost_warned != top.session->hists.stats.total_lost) {
top.total_lost_warned = top.session->hists.stats.total_lost;
color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
top.total_lost_warned);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
++printed;
}
if (top.sym_filter_entry) {
show_details(top.sym_filter_entry);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
return;
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
hists__collapse_resort_threaded(&top.sym_evsel->hists);
hists__output_resort_threaded(&top.sym_evsel->hists);
hists__decay_entries(&top.sym_evsel->hists);
hists__output_recalc_col_len(&top.sym_evsel->hists, winsize.ws_row - 3);
putchar('\n');
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
hists__fprintf(&top.sym_evsel->hists, NULL, false, false,
winsize.ws_row - 4 - printed, win_width, stdout);
}
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
static void prompt_integer(int *target, const char *msg)
{
char *buf = malloc(0), *p;
size_t dummy = 0;
int tmp;
fprintf(stdout, "\n%s: ", msg);
if (getline(&buf, &dummy, stdin) < 0)
return;
p = strchr(buf, '\n');
if (p)
*p = 0;
p = buf;
while(*p) {
if (!isdigit(*p))
goto out_free;
p++;
}
tmp = strtoul(buf, NULL, 10);
*target = tmp;
out_free:
free(buf);
}
static void prompt_percent(int *target, const char *msg)
{
int tmp = 0;
prompt_integer(&tmp, msg);
if (tmp >= 0 && tmp <= 100)
*target = tmp;
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static void prompt_symbol(struct hist_entry **target, const char *msg)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
char *buf = malloc(0), *p;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct hist_entry *syme = *target, *n, *found = NULL;
struct rb_node *next;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
size_t dummy = 0;
/* zero counters of active symbol */
if (syme) {
__zero_source_counters(syme);
*target = NULL;
}
fprintf(stdout, "\n%s: ", msg);
if (getline(&buf, &dummy, stdin) < 0)
goto out_free;
p = strchr(buf, '\n');
if (p)
*p = 0;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
next = rb_first(&top.sym_evsel->hists.entries);
while (next) {
n = rb_entry(next, struct hist_entry, rb_node);
if (n->ms.sym && !strcmp(buf, n->ms.sym->name)) {
found = n;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
next = rb_next(&n->rb_node);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
if (!found) {
fprintf(stderr, "Sorry, %s is not active.\n", buf);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
sleep(1);
return;
} else
parse_source(found);
out_free:
free(buf);
}
static void print_mapped_keys(void)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
char *name = NULL;
if (top.sym_filter_entry) {
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct symbol *sym = top.sym_filter_entry->ms.sym;
name = sym->name;
}
fprintf(stdout, "\nMapped keys:\n");
fprintf(stdout, "\t[d] display refresh delay. \t(%d)\n", top.delay_secs);
fprintf(stdout, "\t[e] display entries (lines). \t(%d)\n", top.print_entries);
if (top.evlist->nr_entries > 1)
fprintf(stdout, "\t[E] active event counter. \t(%s)\n", event_name(top.sym_evsel));
fprintf(stdout, "\t[f] profile display filter (count). \t(%d)\n", top.count_filter);
fprintf(stdout, "\t[F] annotate display filter (percent). \t(%d%%)\n", sym_pcnt_filter);
fprintf(stdout, "\t[s] annotate symbol. \t(%s)\n", name?: "NULL");
fprintf(stdout, "\t[S] stop annotation.\n");
fprintf(stdout,
"\t[K] hide kernel_symbols symbols. \t(%s)\n",
top.hide_kernel_symbols ? "yes" : "no");
fprintf(stdout,
"\t[U] hide user symbols. \t(%s)\n",
top.hide_user_symbols ? "yes" : "no");
fprintf(stdout, "\t[z] toggle sample zeroing. \t(%d)\n", top.zero ? 1 : 0);
fprintf(stdout, "\t[qQ] quit.\n");
}
static int key_mapped(int c)
{
switch (c) {
case 'd':
case 'e':
case 'f':
case 'z':
case 'q':
case 'Q':
case 'K':
case 'U':
case 'F':
case 's':
case 'S':
return 1;
case 'E':
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 10:26:57 +00:00
default:
break;
}
return 0;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
static void handle_keypress(int c)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
{
if (!key_mapped(c)) {
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
struct termios tc, save;
print_mapped_keys();
fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
fflush(stdout);
tcgetattr(0, &save);
tc = save;
tc.c_lflag &= ~(ICANON | ECHO);
tc.c_cc[VMIN] = 0;
tc.c_cc[VTIME] = 0;
tcsetattr(0, TCSANOW, &tc);
poll(&stdin_poll, 1, -1);
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
if (!key_mapped(c))
return;
}
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
switch (c) {
case 'd':
prompt_integer(&top.delay_secs, "Enter display delay");
if (top.delay_secs < 1)
top.delay_secs = 1;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
case 'e':
prompt_integer(&top.print_entries, "Enter display entries (lines)");
if (top.print_entries == 0) {
sig_winch_handler(SIGWINCH);
signal(SIGWINCH, sig_winch_handler);
} else
signal(SIGWINCH, SIG_DFL);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
case 'E':
if (top.evlist->nr_entries > 1) {
/* Select 0 as the default event: */
int counter = 0;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
fprintf(stderr, "\nAvailable events:");
list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
fprintf(stderr, "\n\t%d %s", top.sym_evsel->idx, event_name(top.sym_evsel));
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
prompt_integer(&counter, "Enter details event counter");
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
if (counter >= top.evlist->nr_entries) {
top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
fprintf(stderr, "Sorry, no such event, using %s.\n", event_name(top.sym_evsel));
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
sleep(1);
break;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
list_for_each_entry(top.sym_evsel, &top.evlist->entries, node)
if (top.sym_evsel->idx == counter)
break;
} else
top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
case 'f':
prompt_integer(&top.count_filter, "Enter display event count filter");
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
case 'F':
prompt_percent(&sym_pcnt_filter, "Enter details display event filter (percent)");
break;
case 'K':
top.hide_kernel_symbols = !top.hide_kernel_symbols;
break;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
case 'q':
case 'Q':
printf("exiting.\n");
if (dump_symtab)
perf_session__fprintf_dsos(top.session, stderr);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
exit(0);
case 's':
prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
case 'S':
if (!top.sym_filter_entry)
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
else {
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct hist_entry *syme = top.sym_filter_entry;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
top.sym_filter_entry = NULL;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
__zero_source_counters(syme);
}
break;
case 'U':
top.hide_user_symbols = !top.hide_user_symbols;
break;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
case 'z':
top.zero = !top.zero;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
break;
perf: Enable more compiler warnings Related to a shadowed variable bug fix Valdis Kletnieks noticed that perf does not get built with -Wshadow, which could have helped us avoid the bug. So enable -Wshadow and also enable the following warnings on perf builds, in addition to the already enabled -Wall -Wextra -std=gnu99 warnings: -Wcast-align -Wformat=2 -Wshadow -Winit-self -Wpacked -Wredundant-decls -Wstack-protector -Wstrict-aliasing=3 -Wswitch-default -Wswitch-enum -Wno-system-headers -Wundef -Wvolatile-register-var -Wwrite-strings -Wbad-function-cast -Wmissing-declarations -Wmissing-prototypes -Wnested-externs -Wold-style-definition -Wstrict-prototypes -Wdeclaration-after-statement And change/fix the perf code to build cleanly under GCC 4.3.2. The list of warnings enablement is rather arbitrary: it's based on my (quick) reading of the GCC manpages and trying them on perf. I categorized the warnings based on individually enabling them and looking whether they trigger something in the perf build. If i liked those warnings (i.e. if they trigger for something that arguably could be improved) i enabled the warning. If the warnings seemed to come from language laywers spamming the build with tons of nuisance warnings i generally kept them off. Most of the sign conversion related warnings were in this category. (A second patch enabling some of the sign warnings might be welcome - sign bugs can be nasty.) I also kept warnings that seem to make sense from their manpage description and which produced no actual warnings on our code base. These warnings might still be turned off if they end up being a nuisance. I also left out a few warnings that are not supported in older compilers. [ Note that these changes might break the build on older compilers i did not test, or on non-x86 architectures that produce different warnings, so more testing would be welcome. ] Reported-by: Valdis.Kletnieks@vt.edu Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-08-15 10:26:57 +00:00
default:
break;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
}
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static void perf_top__sort_new_samples(void *arg)
{
struct perf_top *t = arg;
perf_top__reset_sample_counters(t);
if (t->evlist->selected != NULL)
t->sym_evsel = t->evlist->selected;
hists__collapse_resort_threaded(&t->sym_evsel->hists);
hists__output_resort_threaded(&t->sym_evsel->hists);
hists__decay_entries(&t->sym_evsel->hists);
hists__output_recalc_col_len(&t->sym_evsel->hists, winsize.ws_row - 3);
}
static void *display_thread_tui(void *arg __used)
{
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
const char *help = "For a higher level overview, try: perf top --sort comm,dso";
perf_top__sort_new_samples(&top);
perf_evlist__tui_browse_hists(top.evlist, help,
perf_top__sort_new_samples,
&top, top.delay_secs);
exit_browser(0);
exit(0);
return NULL;
}
static void *display_thread(void *arg __used)
{
struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
struct termios tc, save;
int delay_msecs, c;
tcgetattr(0, &save);
tc = save;
tc.c_lflag &= ~(ICANON | ECHO);
tc.c_cc[VMIN] = 0;
tc.c_cc[VTIME] = 0;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
repeat:
delay_msecs = top.delay_secs * 1000;
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
tcsetattr(0, TCSANOW, &tc);
/* trash return*/
getc(stdin);
do {
print_sym_table();
} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
c = getc(stdin);
tcsetattr(0, TCSAFLUSH, &save);
handle_keypress(c);
perf_counter tools: Fix/resurrect perf top annotation in a simple interactive form perf top used to have annotation support, but it has bitrotted and removed. This patch restores that: it allows the user to select any symbol in kernel space for source level annotation on the fly, switch between event counters and alter display variables. When symbol details are being displayed, stopping annotation reverts to normal. known keys: [d] select display delay. [e] select display entries (lines). [E] select annotation event counter. [f] select normal display count filter. [F] select annotation display count filter (percentage). [qQ] quit. [s] select annotation symbol and start annotation. [S] stop annotation, revert to normal display. [z] toggle event count zeroing. Sample: ------------------------------------------------------------------------------ PerfTop: 16719 irqs/sec kernel:78.7% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing cache-misses for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% /* adjust length to remove Ethernet CRC */ 0 0.0% if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) 0 0.0% length -= 4; 436 5.0% f039: 41 f6 84 24 5c 29 00 testb $0x1,0x295c(%r12) 0 0.0% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 0 0.0% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 811 9.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 0 0.0% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 7226 82.6% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Available events: 0 cache-misses 1 cache-references 2 instructions 3 cycles Enter details event counter: 2 ------------------------------------------------------------------------------ PerfTop: 15035 irqs/sec kernel:79.0% [cache-misses/cache-references/instructions/cycles], (all, 4 CPUs) ------------------------------------------------------------------------------ Showing instructions for e1000_clean_rx_irq Events Pcnt (>=3%) 0 0.0% int *work_done, int work_to_do) 0 0.0% { 175 0.9% eebf: 55 push %rbp 1898 9.8% eec0: 48 89 e5 mov %rsp,%rbp 0 0.0% 0 0.0% i = rx_ring->next_to_clean; 140 0.7% ef0a: 0f b7 41 1a movzwl 0x1a(%rcx),%eax 670 3.4% ef0e: 89 45 ac mov %eax,-0x54(%rbp) 0 0.0% { 0 0.0% memcpy(skb->data + offset, from, len); 91 0.5% f07b: 49 8b b6 e8 00 00 00 mov 0xe8(%r14),%rsi 1153 5.9% f082: 48 8b b8 e8 00 00 00 mov 0xe8(%rax),%rdi 42 0.2% f089: 8b 4d 84 mov -0x7c(%rbp),%ecx 14 0.1% f08c: 48 83 ef 02 sub $0x2,%rdi 0 0.0% f090: 48 83 ee 02 sub $0x2,%rsi 1618 8.3% f094: f3 a4 rep movsb %ds:(%rsi),%es:(%rdi) 0 0.0% 0 0.0% /* return some buffers to hardware, one at a time is too slow */ 0 0.0% if (cleaned_count >= E1000_RX_BUFFER_WRITE) { 867 4.5% f0e7: 83 7d b0 0f cmpl $0xf,-0x50(%rbp) 0 0.0% 0 0.0% while (rx_desc->status & E1000_RXD_STAT_DD) { 37 0.2% f114: 41 f6 47 0c 01 testb $0x1,0xc(%r15) 4047 20.8% f119: 0f 85 24 fe ff ff jne ef43 <e1000_clean_rx_irq+0x84> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-22 18:36:03 +00:00
goto repeat;
return NULL;
}
/* Tag samples to be skipped. */
static const char *skip_symbols[] = {
"default_idle",
"native_safe_halt",
"cpu_idle",
"enter_idle",
"exit_idle",
"mwait_idle",
"mwait_idle_with_hints",
"poll_idle",
"ppc64_runlatch_off",
"pseries_dedicated_idle_sleep",
NULL
};
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
static int symbol_filter(struct map *map __used, struct symbol *sym)
{
const char *name = sym->name;
int i;
/*
* ppc64 uses function descriptors and appends a '.' to the
* start of every instruction address. Remove it.
*/
if (name[0] == '.')
name++;
if (!strcmp(name, "_text") ||
!strcmp(name, "_etext") ||
!strcmp(name, "_sinittext") ||
!strncmp("init_module", name, 11) ||
!strncmp("cleanup_module", name, 14) ||
strstr(name, "_text_start") ||
strstr(name, "_text_end"))
return 1;
for (i = 0; skip_symbols[i]; i++) {
if (!strcmp(skip_symbols[i], name)) {
sym->ignore = true;
break;
}
}
return 0;
}
static void perf_event__process_sample(const union perf_event *event,
struct perf_sample *sample,
struct perf_session *session)
{
u64 ip = event->ip.ip;
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
struct addr_location al;
struct machine *machine;
u8 origin = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
++top.samples;
switch (origin) {
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
case PERF_RECORD_MISC_USER:
++top.us_samples;
if (top.hide_user_symbols)
return;
machine = perf_session__find_host_machine(session);
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
break;
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
case PERF_RECORD_MISC_KERNEL:
++top.kernel_samples;
if (top.hide_kernel_symbols)
return;
machine = perf_session__find_host_machine(session);
break;
case PERF_RECORD_MISC_GUEST_KERNEL:
++top.guest_kernel_samples;
machine = perf_session__find_machine(session, event->ip.pid);
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
break;
case PERF_RECORD_MISC_GUEST_USER:
++top.guest_us_samples;
/*
* TODO: we don't process guest user from host side
* except simple counting.
*/
return;
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
default:
return;
}
if (!machine && perf_guest) {
pr_err("Can't find guest [%d]'s kernel information\n",
event->ip.pid);
return;
}
if (event->header.misc & PERF_RECORD_MISC_EXACT_IP)
top.exact_samples++;
if (perf_event__preprocess_sample(event, session, &al, sample,
symbol_filter) < 0 ||
al.filtered)
perf tools: Consolidate symbol resolving across all tools Now we have a very high level routine for simple tools to process IP sample events: int event__preprocess_sample(const event_t *self, struct addr_location *al, symbol_filter_t filter) It receives the event itself and will insert new threads in the global threads list and resolve the map and symbol, filling all this info into the new addr_location struct, so that tools like annotate and report can further process the event by creating hist_entries in their specific way (with or without callgraphs, etc). It in turn uses the new next layer function: void thread__find_addr_location(struct thread *self, u8 cpumode, enum map_type type, u64 addr, struct addr_location *al, symbol_filter_t filter) This one will, given a thread (userspace or the kernel kthread one), will find the given type (MAP__FUNCTION now, MAP__VARIABLE too in the near future) at the given cpumode, taking vdsos into account (userspace hit, but kernel symbol) and will fill all these details in the addr_location given. Tools that need a more compact API for plain function resolution, like 'kmem', can use this other one: struct symbol *thread__find_function(struct thread *self, u64 addr, symbol_filter_t filter) So, to resolve a kernel symbol, that is all the 'kmem' tool needs, its just a matter of calling: sym = thread__find_function(kthread, addr, NULL); The 'filter' parameter is needed because we do lazy parsing/loading of ELF symtabs or /proc/kallsyms. With this we remove more code duplication all around, which is always good, huh? :-) Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: John Kacur <jkacur@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1259346563-12568-12-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-11-27 18:29:23 +00:00
return;
if (!kptr_restrict_warned &&
symbol_conf.kptr_restrict &&
al.cpumode == PERF_RECORD_MISC_KERNEL) {
ui__warning(
"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
"Check /proc/sys/kernel/kptr_restrict.\n\n"
"Kernel%s samples will not be resolved.\n",
!RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
" modules" : "");
if (use_browser <= 0)
sleep(5);
kptr_restrict_warned = true;
}
if (al.sym == NULL) {
const char *msg = "Kernel samples will not be resolved.\n";
/*
* As we do lazy loading of symtabs we only will know if the
* specified vmlinux file is invalid when we actually have a
* hit in kernel space and then try to load it. So if we get
* here and there are _no_ symbols in the DSO backing the
* kernel map, bail out.
*
* We may never get here, for instance, if we use -K/
* --hide-kernel-symbols, even if the user specifies an
* invalid --vmlinux ;-)
*/
if (!kptr_restrict_warned && !vmlinux_warned &&
al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
if (symbol_conf.vmlinux_name) {
ui__warning("The %s file can't be used.\n%s",
symbol_conf.vmlinux_name, msg);
} else {
ui__warning("A vmlinux file was not found.\n%s",
msg);
}
if (use_browser <= 0)
sleep(5);
vmlinux_warned = true;
}
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (al.sym == NULL || !al.sym->ignore) {
struct perf_evsel *evsel;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
struct hist_entry *he;
evsel = perf_evlist__id2evsel(top.evlist, sample->id);
assert(evsel != NULL);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
he = perf_session__add_hist_entry(session, &al, sample, evsel);
if (he == NULL) {
pr_err("Problem incrementing symbol period, skipping event\n");
return;
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
record_precise_ip(he, evsel->idx, ip);
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
}
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
return;
}
perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern <dsahern@gmail.com> Tested-by: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-15 12:39:00 +00:00
static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
{
struct perf_sample sample;
union perf_event *event;
int ret;
perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern <dsahern@gmail.com> Tested-by: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-15 12:39:00 +00:00
while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
ret = perf_session__parse_sample(self, event, &sample);
if (ret) {
pr_err("Can't parse sample, err = %d\n", ret);
continue;
}
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
if (event->header.type == PERF_RECORD_SAMPLE)
perf_event__process_sample(event, &sample, self);
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
else
perf_event__process(event, &sample, self);
}
}
static void perf_session__mmap_read(struct perf_session *self)
{
int i;
perf evlist: Fix per thread mmap setup The PERF_EVENT_IOC_SET_OUTPUT ioctl was returning -EINVAL when using --pid when monitoring multithreaded apps, as we can only share a ring buffer for events on the same thread if not doing per cpu. Fix it by using per thread ring buffers. Tested with: [root@felicio ~]# tuna -t 26131 -CP | nl 1 thread ctxt_switches 2 pid SCHED_ rtpri affinity voluntary nonvoluntary cmd 3 26131 OTHER 0 0,1 10814276 2397830 chromium-browse 4 642 OTHER 0 0,1 14688 0 chromium-browse 5 26148 OTHER 0 0,1 713602 115479 chromium-browse 6 26149 OTHER 0 0,1 801958 2262 chromium-browse 7 26150 OTHER 0 0,1 1271128 248 chromium-browse 8 26151 OTHER 0 0,1 3 0 chromium-browse 9 27049 OTHER 0 0,1 36796 9 chromium-browse 10 618 OTHER 0 0,1 14711 0 chromium-browse 11 661 OTHER 0 0,1 14593 0 chromium-browse 12 29048 OTHER 0 0,1 28125 0 chromium-browse 13 26143 OTHER 0 0,1 2202789 781 chromium-browse [root@felicio ~]# So 11 threads under pid 26131, then: [root@felicio ~]# perf record -F 50000 --pid 26131 [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fa4a2538000-7fa4a25b9000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fa4a25b9000-7fa4a263a000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 3 7fa4a263a000-7fa4a26bb000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 4 7fa4a26bb000-7fa4a273c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 5 7fa4a273c000-7fa4a27bd000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 6 7fa4a27bd000-7fa4a283e000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 7 7fa4a283e000-7fa4a28bf000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 8 7fa4a28bf000-7fa4a2940000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 9 7fa4a2940000-7fa4a29c1000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 10 7fa4a29c1000-7fa4a2a42000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 11 7fa4a2a42000-7fa4a2ac3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# 11 mmaps, one per thread since we didn't specify any CPU list, so we need one mmap per thread and: [root@felicio ~]# perf record -F 50000 --pid 26131 ^M ^C[ perf record: Woken up 79 times to write data ] [ perf record: Captured and wrote 20.614 MB perf.data (~900639 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 371310 26131 2 96516 26148 3 95694 26149 4 95203 26150 5 7291 26143 6 87 27049 7 76 661 8 60 29048 9 47 618 10 43 642 [root@felicio ~]# Ok, one of the threads, 26151 was quiescent, so no samples there, but all the others are there. Then, if I specify one CPU: [root@felicio ~]# perf record -F 50000 --pid 26131 --cpu 1 ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.680 MB perf.data (~29730 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 8444 26131 2 2584 26149 3 2518 26148 4 2324 26150 5 123 26143 6 9 661 7 9 29048 [root@felicio ~]# This machine has two cores, so fewer threads appeared on the radar, and: [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f484b922000-7f484b9a3000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Just one mmap, as now we can use just one per-cpu buffer instead of the per-thread needed in the previous case. For global profiling: [root@felicio ~]# perf record -F 50000 -a ^C[ perf record: Woken up 26 times to write data ] [ perf record: Captured and wrote 7.128 MB perf.data (~311412 samples) ] [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7fb49b435000-7fb49b4b6000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] 2 7fb49b4b6000-7fb49b537000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# It uses per-cpu buffers. For just one thread: [root@felicio ~]# perf record -F 50000 --tid 26148 ^C[ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.330 MB perf.data (~14426 samples) ] [root@felicio ~]# perf report -D | grep PERF_RECORD_SAMPLE | cut -d/ -f2 | cut -d: -f1 | sort -n | uniq -c | sort -nr | nl 1 9969 26148 [root@felicio ~]# [root@felicio ~]# grep perf_event /proc/`pidof perf`/maps | nl 1 7f286a51b000-7f286a59c000 rwxs 00000000 00:09 4064 anon_inode:[perf_event] [root@felicio ~]# Tested-by: David Ahern <dsahern@gmail.com> Tested-by: Lin Ming <ming.m.lin@intel.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Tom Zanussi <tzanussi@gmail.com> Link: http://lkml.kernel.org/r/20110426204401.GB1746@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-15 12:39:00 +00:00
for (i = 0; i < top.evlist->nr_mmaps; i++)
perf_session__mmap_read_idx(self, i);
}
static void start_counters(struct perf_evlist *evlist)
{
struct perf_evsel *counter;
list_for_each_entry(counter, &evlist->entries, node) {
struct perf_event_attr *attr = &counter->attr;
attr->sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_TID;
if (top.freq) {
attr->sample_type |= PERF_SAMPLE_PERIOD;
attr->freq = 1;
attr->sample_freq = top.freq;
}
if (evlist->nr_entries > 1) {
attr->sample_type |= PERF_SAMPLE_ID;
attr->read_format |= PERF_FORMAT_ID;
}
attr->mmap = 1;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
attr->comm = 1;
attr->inherit = inherit;
try_again:
if (perf_evsel__open(counter, top.evlist->cpus,
top.evlist->threads, group) < 0) {
int err = errno;
if (err == EPERM || err == EACCES) {
ui__warning_paranoid();
goto out_err;
}
/*
* If it's cycles then fall back to hrtimer
* based cpu-clock-tick sw counter, which
* is always available even if no PMU support:
*/
if (attr->type == PERF_TYPE_HARDWARE &&
attr->config == PERF_COUNT_HW_CPU_CYCLES) {
if (verbose)
ui__warning("Cycles event not supported,\n"
"trying to fall back to cpu-clock-ticks\n");
attr->type = PERF_TYPE_SOFTWARE;
attr->config = PERF_COUNT_SW_CPU_CLOCK;
goto try_again;
}
if (err == ENOENT) {
ui__warning("The %s event is not supported.\n",
event_name(counter));
goto out_err;
}
ui__warning("The sys_perf_event_open() syscall "
"returned with %d (%s). /bin/dmesg "
"may provide additional information.\n"
"No CONFIG_PERF_EVENTS=y kernel support "
"configured?\n", err, strerror(err));
goto out_err;
}
}
if (perf_evlist__mmap(evlist, mmap_pages, false) < 0) {
ui__warning("Failed to mmap with %d (%s)\n",
errno, strerror(errno));
goto out_err;
}
return;
out_err:
exit_browser(0);
exit(0);
}
static int __cmd_top(void)
{
pthread_t thread;
int ret __used;
/*
* FIXME: perf_session__new should allow passing a O_MMAP, so that all this
* mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
*/
top.session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
if (top.session == NULL)
return -ENOMEM;
if (top.target_tid != -1)
perf_event__synthesize_thread_map(top.evlist->threads,
perf_event__process, top.session);
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
else
perf_event__synthesize_threads(perf_event__process, top.session);
perf top: Support userspace symbols too Example: Compiling the kernel with 'make -k 22 allyesconfig' [root@emilia linux-2.6-tip]# perf top -r 90 ------------------------------------------------------------------------------ PerfTop: 3669 irqs/sec kernel:59.9% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ samples pcnt function DSO _______ _____ ________________________________ ________________ 3062.00 6.5% clear_page_c [kernel] 2233.00 4.8% _int_malloc /lib64/libc-2.5.so 2100.00 4.5% yylex /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 2029.00 4.3% memset /lib64/libc-2.5.so 1224.00 2.6% page_fault [kernel] 1075.00 2.3% __GI_strlen /lib64/libc-2.5.so 863.00 1.8% sub_preempt_count [kernel] 822.00 1.8% __GI_memcpy /lib64/libc-2.5.so 810.00 1.7% __GI_vfprintf /lib64/libc-2.5.so 786.00 1.7% _int_free /lib64/libc-2.5.so 775.00 1.7% __GI_strcmp /lib64/libc-2.5.so 748.00 1.6% _spin_lock [kernel] 699.00 1.5% main /home/acme/git/build/allyesconfig/scripts/basic/fixdep 659.00 1.4% add_preempt_count [kernel] 649.00 1.4% yyparse /home/acme/git/build/allyesconfig/scripts/genksyms/genksyms 645.00 1.4% preempt_trace [kernel] 635.00 1.4% __GI___libc_free /lib64/libc-2.5.so 597.00 1.3% trace_preempt_on [kernel] 551.00 1.2% __GI___libc_malloc /lib64/libc-2.5.so 516.00 1.1% _spin_lock_irqsave [kernel] 481.00 1.0% copy_user_generic_string [kernel] 479.00 1.0% unmap_vmas [kernel] 429.00 0.9% _IO_file_xsputn_internal /lib64/libc-2.5.so 425.00 0.9% __GI_strncpy /lib64/libc-2.5.so 416.00 0.9% get_page_from_freelist [kernel] 414.00 0.9% malloc_consolidate /lib64/libc-2.5.so 406.00 0.9% get_parent_ip [kernel] 362.00 0.8% __rmqueue [kernel] 347.00 0.7% in_lock_functions [kernel] 316.00 0.7% __d_lookup [kernel] [root@emilia linux-2.6-tip]# More polishing is needed to print just DSO basename when not --verbose, etc. Supporting a 'comm' column requires some more reworking of 'perf top' internals as we will need to use something like the hist entries 'perf report' uses and will be done in another patch. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1256592199-9608-3-git-send-email-acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-26 21:23:19 +00:00
start_counters(top.evlist);
top.session->evlist = top.evlist;
perf_session__update_sample_type(top.session);
/* Wait for a minimal set of events before starting the snapshot */
poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
perf_session__mmap_read(top.session);
if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
display_thread), NULL)) {
printf("Could not create display thread.\n");
exit(-1);
}
if (realtime_prio) {
struct sched_param param;
param.sched_priority = realtime_prio;
if (sched_setscheduler(0, SCHED_FIFO, &param)) {
printf("Could not set realtime priority.\n");
exit(-1);
}
}
while (1) {
u64 hits = top.samples;
perf_session__mmap_read(top.session);
if (hits == top.samples)
ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
}
return 0;
}
static const char * const top_usage[] = {
"perf top [<options>]",
NULL
};
static const struct option options[] = {
OPT_CALLBACK('e', "event", &top.evlist, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_INTEGER('c', "count", &default_interval,
"event period to sample"),
OPT_INTEGER('p', "pid", &top.target_pid,
"profile events on existing process id"),
OPT_INTEGER('t', "tid", &top.target_tid,
"profile events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('C', "cpu", &top.cpu_list, "cpu",
"list of cpus to monitor"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_BOOLEAN('K', "hide_kernel_symbols", &top.hide_kernel_symbols,
"hide kernel symbols"),
OPT_UINTEGER('m', "mmap-pages", &mmap_pages, "number of mmap data pages"),
OPT_INTEGER('r', "realtime", &realtime_prio,
"collect data with this RT SCHED_FIFO priority"),
OPT_INTEGER('d', "delay", &top.delay_secs,
"number of seconds to delay between refreshes"),
OPT_BOOLEAN('D', "dump-symtab", &dump_symtab,
"dump the symbol table used for profiling"),
OPT_INTEGER('f', "count-filter", &top.count_filter,
"only display functions with more events than this"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
OPT_BOOLEAN('i', "inherit", &inherit,
"child tasks inherit counters"),
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
OPT_STRING(0, "sym-annotate", &sym_filter, "symbol name",
"symbol to annotate"),
OPT_BOOLEAN('z', "zero", &top.zero,
"zero history across updates"),
OPT_INTEGER('F', "freq", &top.freq,
"profile at this frequency"),
OPT_INTEGER('E', "entries", &top.print_entries,
"display this many functions"),
OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
"hide user symbols"),
OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 08:37:33 +00:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
"Show a column with the sum of periods"),
OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING(0, "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING(0, "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
OPT_END()
};
int cmd_top(int argc, const char **argv, const char *prefix __used)
{
struct perf_evsel *pos;
int status = -ENOMEM;
top.evlist = perf_evlist__new(NULL, NULL);
if (top.evlist == NULL)
return -ENOMEM;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
symbol_conf.exclude_other = false;
argc = parse_options(argc, argv, options, top_usage, 0);
if (argc)
usage_with_options(top_usage, options);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
if (sort_order == default_sort_order)
sort_order = "dso,symbol";
setup_sorting(top_usage, options);
/*
* XXX For now start disabled, only using TUI if explicitely asked for.
* Change that when handle_keys equivalent gets written, live annotation
* done, etc.
*/
use_browser = 0;
if (use_stdio)
use_browser = 0;
else if (use_tui)
use_browser = 1;
setup_browser(false);
/* CPU and PID are mutually exclusive */
if (top.target_tid > 0 && top.cpu_list) {
printf("WARNING: PID switch overriding CPU\n");
sleep(1);
top.cpu_list = NULL;
}
if (top.target_pid != -1)
top.target_tid = top.target_pid;
if (perf_evlist__create_maps(top.evlist, top.target_pid,
top.target_tid, top.cpu_list) < 0)
usage_with_options(top_usage, options);
if (!top.evlist->nr_entries &&
perf_evlist__add_default(top.evlist) < 0) {
pr_err("Not enough memory for event selector list\n");
return -ENOMEM;
}
if (top.delay_secs < 1)
top.delay_secs = 1;
/*
* User specified count overrides default frequency.
*/
if (default_interval)
top.freq = 0;
else if (top.freq) {
default_interval = top.freq;
} else {
fprintf(stderr, "frequency and count are zero, aborting\n");
exit(EXIT_FAILURE);
}
list_for_each_entry(pos, &top.evlist->entries, node) {
if (perf_evsel__alloc_fd(pos, top.evlist->cpus->nr,
top.evlist->threads->nr) < 0)
goto out_free_fd;
/*
* Fill in the ones not specifically initialized via -c:
*/
if (pos->attr.sample_period)
continue;
pos->attr.sample_period = default_interval;
}
if (perf_evlist__alloc_pollfd(top.evlist) < 0 ||
perf_evlist__alloc_mmap(top.evlist) < 0)
goto out_free_fd;
top.sym_evsel = list_entry(top.evlist->entries.next, struct perf_evsel, node);
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
symbol_conf.priv_size = sizeof(struct annotation);
symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
if (symbol__init() < 0)
return -1;
perf top: Reuse the 'report' hist_entry/hists classes This actually fixes several problems we had in the old 'perf top': 1. Unresolved symbols not show, limitation that came from the old "KernelTop" codebase, to solve it we would need to do changes that would make sym_entry have most of the hist_entry fields. 2. It was using the number of samples, not the sum of sample->period. And brings the --sort code that allows us to have all the views in 'perf report', for instance: [root@emilia ~]# perf top --sort dso PerfTop: 5903 irqs/sec kernel:77.5% exact: 0.0% [1000Hz cycles], (all, 8 CPUs) ------------------------------------------------------------------------------ 31.59% libcrypto.so.1.0.0 21.55% [kernel] 18.57% libpython2.6.so.1.0 7.04% libc-2.12.so 6.99% _backend_agg.so 4.72% sshd 1.48% multiarray.so 1.39% libfreetype.so.6.3.22 1.37% perf 0.71% libgobject-2.0.so.0.2200.5 0.53% [tg3] 0.48% libglib-2.0.so.0.2200.5 0.44% libstdc++.so.6.0.13 0.40% libcairo.so.2.10800.8 0.38% libm-2.12.so 0.34% umath.so 0.30% libgdk-x11-2.0.so.0.1800.9 0.22% libpthread-2.12.so 0.20% libgtk-x11-2.0.so.0.1800.9 0.20% librt-2.12.so 0.15% _path.so 0.13% libpango-1.0.so.0.2800.1 0.11% libatlas.so.3.0 0.09% ft2font.so 0.09% libpangoft2-1.0.so.0.2800.1 0.08% libX11.so.6.3.0 0.07% [vdso] 0.06% cyclictest ^C All the filter lists can be used as well: --dsos, --comms, --symbols, etc. The 'perf report' TUI is also reused, being possible to apply all the zoom operations, do annotation, etc. This change will allow multiple simplifications in the symbol system as well, that will be detailed in upcoming changesets. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-xzaaldxq7zhqrrxdxjifk1mh@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-10-05 22:16:15 +00:00
sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list, "comm", stdout);
sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
get_term_dimensions(&winsize);
if (top.print_entries == 0) {
update_print_entries(&winsize);
signal(SIGWINCH, sig_winch_handler);
}
status = __cmd_top();
out_free_fd:
perf_evlist__delete(top.evlist);
return status;
}