linux/tools/perf/builtin-report.c

553 lines
15 KiB
C
Raw Normal View History

/*
* builtin-report.c
*
* Builtin report command: Analyze the perf.data input file,
* look up and read DSOs and symbol information and display
* a histogram of results, along various sorting keys.
*/
#include "builtin.h"
#include "util/util.h"
#include "util/color.h"
#include <linux/list.h>
#include "util/cache.h"
#include <linux/rbtree.h>
#include "util/symbol.h"
#include "util/callchain.h"
#include "util/strlist.h"
#include "util/values.h"
#include "perf.h"
#include "util/debug.h"
#include "util/header.h"
#include "util/session.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/thread.h"
#include "util/sort.h"
#include "util/hist.h"
static char const *input_name = "perf.data";
static bool force, use_tui, use_stdio;
static bool hide_unresolved;
static bool dont_use_callchains;
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 show_threads;
static struct perf_read_values show_threads_values;
static const char default_pretty_printing_style[] = "normal";
static const char *pretty_printing_style = default_pretty_printing_style;
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
static char callchain_default_opt[] = "fractal,0.5";
2010-05-10 16:04:11 +00:00
static struct hists *perf_session__hists_findnew(struct perf_session *self,
u64 event_stream, u32 type,
u64 config)
{
2010-05-10 16:04:11 +00:00
struct rb_node **p = &self->hists_tree.rb_node;
struct rb_node *parent = NULL;
2010-05-10 16:04:11 +00:00
struct hists *iter, *new;
while (*p != NULL) {
parent = *p;
2010-05-10 16:04:11 +00:00
iter = rb_entry(parent, struct hists, rb_node);
if (iter->config == config)
return iter;
if (config > iter->config)
p = &(*p)->rb_right;
else
p = &(*p)->rb_left;
}
2010-05-10 16:04:11 +00:00
new = malloc(sizeof(struct hists));
if (new == NULL)
return NULL;
2010-05-10 16:04:11 +00:00
memset(new, 0, sizeof(struct hists));
new->event_stream = event_stream;
new->config = config;
new->type = type;
rb_link_node(&new->rb_node, parent, p);
2010-05-10 16:04:11 +00:00
rb_insert_color(&new->rb_node, &self->hists_tree);
return new;
}
static int perf_session__add_hist_entry(struct perf_session *session,
struct addr_location *al,
struct perf_sample *sample)
{
struct symbol *parent = NULL;
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
int err = 0;
struct hist_entry *he;
2010-05-10 16:04:11 +00:00
struct hists *hists;
struct perf_event_attr *attr;
if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
err = perf_session__resolve_callchain(session, al->thread,
sample->callchain, &parent);
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
if (err)
return err;
}
attr = perf_header__find_attr(sample->id, &session->header);
if (attr)
hists = perf_session__hists_findnew(session, sample->id, attr->type, attr->config);
else
hists = perf_session__hists_findnew(session, sample->id, 0, 0);
2010-05-10 16:04:11 +00:00
if (hists == NULL)
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
return -ENOMEM;
he = __hists__add_entry(hists, al, parent, sample->period);
if (he == NULL)
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
return -ENOMEM;
if (symbol_conf.use_callchain) {
err = callchain_append(he->callchain, &session->callchain_cursor,
sample->period);
if (err)
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
return err;
}
/*
* Only in the newt browser we are doing integrated annotation,
* so we don't allocated the extra space needed because the stdio
* code will not use it.
*/
if (use_browser > 0)
err = hist_entry__inc_addr_samples(he, al->addr);
perf callchain: Feed callchains into a cursor The callchains are fed with an array of a fixed size. As a result we iterate over each callchains three times: - 1st to resolve symbols - 2nd to filter out context boundaries - 3rd for the insertion into the tree This also involves some pairs of memory allocation/deallocation everytime we insert a callchain, for the filtered out array of addresses and for the array of symbols that comes along. Instead, feed the callchains through a linked list with persistent allocations. It brings several pros like: - Merge the 1st and 2nd iterations in one. That was possible before but in a way that would involve allocating an array slightly taller than necessary because we don't know in advance the number of context boundaries to filter out. - Much lesser allocations/deallocations. The linked list keeps persistent empty entries for the next usages and is extendable at will. - Makes it easier for multiple sources of callchains to feed a stacktrace together. This is deemed to pave the way for cfi based callchains wherein traditional frame pointer based kernel stacktraces will precede cfi based user ones, producing an overall callchain which size is hardly predictable. This requirement makes the static array obsolete and makes a linked list based iterator a much more flexible fit. Basic testing on a big perf file containing callchains (~ 176 MB) has shown a throughput gain of about 11% with perf report. Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1294977121-5700-2-git-send-email-fweisbec@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-01-14 03:51:58 +00:00
return err;
}
static int add_event_total(struct perf_session *session,
struct perf_sample *sample,
struct perf_event_attr *attr)
{
2010-05-10 16:04:11 +00:00
struct hists *hists;
if (attr)
hists = perf_session__hists_findnew(session, sample->id,
2010-05-10 16:04:11 +00:00
attr->type, attr->config);
else
hists = perf_session__hists_findnew(session, sample->id, 0, 0);
2010-05-10 16:04:11 +00:00
if (!hists)
return -ENOMEM;
hists->stats.total_period += sample->period;
/*
* FIXME: add_event_total should be moved from here to
* perf_session__process_event so that the proper hist is passed to
* the event_op methods.
*/
hists__inc_nr_events(hists, PERF_RECORD_SAMPLE);
session->hists.stats.total_period += sample->period;
return 0;
}
static int process_sample_event(union perf_event *event,
struct perf_sample *sample,
struct perf_session *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
struct addr_location al;
struct perf_event_attr *attr;
if (perf_event__preprocess_sample(event, session, &al, sample, NULL) < 0) {
fprintf(stderr, "problem processing %d event, skipping it.\n",
event->header.type);
return -1;
}
if (al.filtered || (hide_unresolved && al.sym == NULL))
return 0;
if (perf_session__add_hist_entry(session, &al, sample)) {
pr_debug("problem incrementing symbol period, skipping event\n");
return -1;
}
attr = perf_header__find_attr(sample->id, &session->header);
if (add_event_total(session, sample, attr)) {
pr_debug("problem adding event period\n");
return -1;
}
return 0;
}
static int process_read_event(union perf_event *event,
struct perf_sample *sample __used,
struct perf_session *session __used)
{
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 10:02:48 +00:00
struct perf_event_attr *attr;
attr = perf_header__find_attr(event->read.id, &session->header);
if (show_threads) {
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
const char *name = attr ? __event_name(attr->type, attr->config)
: "unknown";
perf_read_values_add_value(&show_threads_values,
event->read.pid, event->read.tid,
event->read.id,
name,
event->read.value);
}
dump_printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
attr ? __event_name(attr->type, attr->config) : "FAIL",
event->read.value);
return 0;
}
static int perf_session__setup_sample_type(struct perf_session *self)
{
if (!(self->sample_type & PERF_SAMPLE_CALLCHAIN)) {
if (sort__has_parent) {
fprintf(stderr, "selected --sort parent, but no"
" callchain data. Did you call"
" perf record without -g?\n");
return -EINVAL;
}
if (symbol_conf.use_callchain) {
fprintf(stderr, "selected -g but no callchain data."
" Did you call perf record without"
" -g?\n");
return -1;
}
} else if (!dont_use_callchains && callchain_param.mode != CHAIN_NONE &&
!symbol_conf.use_callchain) {
symbol_conf.use_callchain = true;
if (callchain_register_param(&callchain_param) < 0) {
fprintf(stderr, "Can't register callchain"
" params\n");
return -EINVAL;
}
}
return 0;
}
static struct perf_event_ops event_ops = {
.sample = process_sample_event,
.mmap = perf_event__process_mmap,
.comm = perf_event__process_comm,
.exit = perf_event__process_task,
.fork = perf_event__process_task,
.lost = perf_event__process_lost,
.read = process_read_event,
.attr = perf_event__process_attr,
.event_type = perf_event__process_event_type,
.tracing_data = perf_event__process_tracing_data,
.build_id = perf_event__process_build_id,
perf record,report,annotate,diff: Process events in order This patch changes perf report to ask for the ID info on all events be default if recording from multiple CPUs. Perf report, annotate and diff will now process the events in order if the kernel is able to provide timestamps on all events. This ensures that events such as COMM and MMAP which are necessary to correctly interpret samples are processed prior to those samples so that they are attributed correctly. Before: # perf record ./cachetest # perf report # Events: 6K cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ............................... # 74.11% :3259 [unknown] [k] 0x4a6c 1.50% cachetest ld-2.11.2.so [.] 0x1777c 1.46% :3259 [kernel.kallsyms] [k] .perf_event_mmap_ctx 1.25% :3259 [kernel.kallsyms] [k] restore 0.74% :3259 [kernel.kallsyms] [k] ._raw_spin_lock 0.71% :3259 [kernel.kallsyms] [k] .filemap_fault 0.66% :3259 [kernel.kallsyms] [k] .memset 0.54% cachetest [kernel.kallsyms] [k] .sha_transform 0.54% :3259 [kernel.kallsyms] [k] .copy_4K_page 0.54% :3259 [kernel.kallsyms] [k] .find_get_page 0.52% :3259 [kernel.kallsyms] [k] .trace_hardirqs_off 0.50% :3259 [kernel.kallsyms] [k] .__do_fault <SNIP> After: # perf report # Events: 6K cycles # # Overhead Command Shared Object Symbol # ........ ....... ................. ............................... # 44.28% cachetest cachetest [.] sumArrayNaive 22.53% cachetest cachetest [.] sumArrayOptimal 6.59% cachetest ld-2.11.2.so [.] 0x1777c 2.13% cachetest [unknown] [k] 0x340 1.46% cachetest [kernel.kallsyms] [k] .perf_event_mmap_ctx 1.25% cachetest [kernel.kallsyms] [k] restore 0.74% cachetest [kernel.kallsyms] [k] ._raw_spin_lock 0.71% cachetest [kernel.kallsyms] [k] .filemap_fault 0.66% cachetest [kernel.kallsyms] [k] .memset 0.54% cachetest [kernel.kallsyms] [k] .copy_4K_page 0.54% cachetest [kernel.kallsyms] [k] .find_get_page 0.54% cachetest [kernel.kallsyms] [k] .sha_transform 0.52% cachetest [kernel.kallsyms] [k] .trace_hardirqs_off 0.50% cachetest [kernel.kallsyms] [k] .__do_fault <SNIP> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1291872833-839-1-git-send-email-imunsie@au1.ibm.com> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-09 05:33:53 +00:00
.ordered_samples = true,
.ordering_requires_timestamps = true,
};
extern volatile int session_done;
static void sig_handler(int sig __used)
{
session_done = 1;
}
static size_t hists__fprintf_nr_sample_events(struct hists *self,
const char *evname, FILE *fp)
{
size_t ret;
char unit;
unsigned long nr_events = self->stats.nr_events[PERF_RECORD_SAMPLE];
nr_events = convert_unit(nr_events, &unit);
ret = fprintf(fp, "# Events: %lu%c", nr_events, unit);
if (evname != NULL)
ret += fprintf(fp, " %s", evname);
return ret + fprintf(fp, "\n#\n");
}
static int hists__tty_browse_tree(struct rb_root *tree, const char *help)
{
struct rb_node *next = rb_first(tree);
while (next) {
struct hists *hists = rb_entry(next, struct hists, rb_node);
const char *evname = NULL;
if (rb_first(&hists->entries) != rb_last(&hists->entries))
evname = __event_name(hists->type, hists->config);
hists__fprintf_nr_sample_events(hists, evname, stdout);
hists__fprintf(hists, NULL, false, stdout);
fprintf(stdout, "\n\n");
next = rb_next(&hists->rb_node);
}
if (sort_order == default_sort_order &&
parent_pattern == default_parent_pattern) {
fprintf(stdout, "#\n# (%s)\n#\n", help);
if (show_threads) {
bool style = !strcmp(pretty_printing_style, "raw");
perf_read_values_display(stdout, &show_threads_values,
style);
perf_read_values_destroy(&show_threads_values);
}
}
return 0;
}
static int __cmd_report(void)
{
int ret = -EINVAL;
struct perf_session *session;
struct rb_node *next;
perf report: Implement initial UI using newt Newt has widespread availability and provides a rather simple API as can be seen by the size of this patch. The work needed to support it will benefit other frontends too. In this initial patch it just checks if the output is a tty, if not it falls back to the previous behaviour, also if newt-devel/libnewt-dev is not installed the previous behaviour is maintaned. Pressing enter on a symbol will annotate it, ESC in the annotation window will return to the report symbol list. More work will be done to remove the special casing in color_fprintf, stop using fmemopen/FILE in the printing of hist_entries, etc. Also the annotation doesn't need to be done via spawning "perf annotate" and then browsing its output, we can do better by calling directly the builtin-annotate.c functions, that would then be moved to tools/perf/util/annotate.c and shared with perf top, etc But lets go by baby steps, this patch already improves perf usability by allowing to quickly do annotations on symbols from the report screen and provides a first experimentation with libnewt/TUI integration of tools. Tested on RHEL5 and Fedora12 X86_64 and on Debian PARISC64 to browse a perf.data file collected on a Fedora12 x86_64 box. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Avi Kivity <avi@redhat.com> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <1268349164-5822-5-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-11 23:12:44 +00:00
const char *help = "For a higher level overview, try: perf report --sort comm,dso";
signal(SIGINT, sig_handler);
perf session: Fallback to unordered processing if no sample_id_all If we are running the new perf on an old kernel without support for sample_id_all, we should fall back to the old unordered processing of events. If we didn't than we would *always* process events without timestamps out of order, whether or not we hit a reordering race. In other words, instead of there being a chance of not attributing samples correctly, we would guarantee that samples would not be attributed. While processing all events without timestamps before events with timestamps may seem like an intuitive solution, it falls down as PERF_RECORD_EXIT events would also be processed before any samples. Even with a workaround for that case, samples before/after an exec would not be attributed correctly. This patch allows commands to indicate whether they need to fall back to unordered processing, so that commands that do not care about timestamps on every event will not be affected. If we do fallback, this will print out a warning if report -D was invoked. This patch adds the test in perf_session__new so that we only need to test once per session. Commands that do not use an event_ops (such as record and top) can simply pass NULL in it's place. Acked-by: Thomas Gleixner <tglx@linutronix.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> LKML-Reference: <1291951882-sup-6069@au1.ibm.com> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-10 03:09:16 +00:00
session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
if (session == NULL)
return -ENOMEM;
if (show_threads)
perf_read_values_init(&show_threads_values);
ret = perf_session__setup_sample_type(session);
if (ret)
goto out_delete;
ret = perf_session__process_events(session, &event_ops);
if (ret)
goto out_delete;
if (dump_trace) {
perf_session__fprintf_nr_events(session, stdout);
goto out_delete;
}
if (verbose > 3)
perf_session__fprintf(session, stdout);
if (verbose > 2)
perf_session__fprintf_dsos(session, stdout);
2010-05-10 16:04:11 +00:00
next = rb_first(&session->hists_tree);
while (next) {
2010-05-10 16:04:11 +00:00
struct hists *hists;
2010-05-10 16:04:11 +00:00
hists = rb_entry(next, struct hists, rb_node);
hists__collapse_resort(hists);
hists__output_resort(hists);
2010-05-10 16:04:11 +00:00
next = rb_next(&hists->rb_node);
}
if (use_browser > 0)
hists__tui_browse_tree(&session->hists_tree, help);
else
hists__tty_browse_tree(&session->hists_tree, help);
out_delete:
/*
* Speed up the exit process, for large files this can
* take quite a while.
*
* XXX Enable this when using valgrind or if we ever
* librarize this command.
*
* Also experiment with obstacks to see how much speed
* up we'll get here.
*
* perf_session__delete(session);
*/
return ret;
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
static int
parse_callchain_opt(const struct option *opt __used, const char *arg,
int unset)
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
{
char *tok, *tok2;
2009-07-02 18:14:33 +00:00
char *endptr;
/*
* --no-call-graph
*/
if (unset) {
dont_use_callchains = true;
return 0;
}
symbol_conf.use_callchain = true;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
if (!arg)
return 0;
2009-07-02 18:14:33 +00:00
tok = strtok((char *)arg, ",");
if (!tok)
return -1;
/* get the output mode */
if (!strncmp(tok, "graph", strlen(arg)))
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.mode = CHAIN_GRAPH_ABS;
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
2009-07-02 18:14:33 +00:00
else if (!strncmp(tok, "flat", strlen(arg)))
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.mode = CHAIN_FLAT;
else if (!strncmp(tok, "fractal", strlen(arg)))
callchain_param.mode = CHAIN_GRAPH_REL;
else if (!strncmp(tok, "none", strlen(arg))) {
callchain_param.mode = CHAIN_NONE;
symbol_conf.use_callchain = false;
return 0;
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
else
return -1;
2009-07-02 18:14:33 +00:00
/* get the min percentage */
tok = strtok(NULL, ",");
if (!tok)
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
goto setup;
2009-07-02 18:14:33 +00:00
tok2 = strtok(NULL, ",");
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
callchain_param.min_percent = strtod(tok, &endptr);
2009-07-02 18:14:33 +00:00
if (tok == endptr)
return -1;
if (tok2)
callchain_param.print_limit = strtod(tok2, &endptr);
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
setup:
if (callchain_register_param(&callchain_param) < 0) {
perf report: Add "Fractal" mode output - support callchains with relative overhead rate The current callchain displays the overhead rates as absolute: relative to the total overhead. This patch provides relative overhead percentage, in which each branch of the callchain tree is a independant instrumentated object. This provides a 'fractal' view of the call-chain profile: each sub-graph looks like a profile in itself - relative to its parent. You can produce such output by using the "fractal" mode that you can abbreviate via f, fr, fra, frac, etc... ./perf report -s sym -c fractal Example: 8.46% [k] copy_user_generic_string | |--52.01%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--97.20%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --2.81%-- sys_read | system_call_fastpath | __read | |--39.85%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--97.05%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --2.95%-- sys_write | system_call_fastpath | __write_nocancel [...] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246772361-9960-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-05 05:39:21 +00:00
fprintf(stderr, "Can't register callchain params\n");
return -1;
}
perf report: Add support for callchain graph output Currently, the printing of callchains is done in a single vertical level, this is the "flat" mode: 8.25% [k] copy_user_generic_string 4.19% copy_user_generic_string generic_file_aio_read do_sync_read vfs_read sys_pread64 system_call_fastpath pread64 This patch introduces a new "graph" mode which provides a hierarchical output of factorized paths recursively sorted: 8.25% [k] copy_user_generic_string | |--4.31%-- generic_file_aio_read | do_sync_read | vfs_read | | | |--4.19%-- sys_pread64 | | system_call_fastpath | | pread64 | | | --0.12%-- sys_read | system_call_fastpath | __read | |--3.24%-- generic_file_buffered_write | __generic_file_aio_write_nolock | generic_file_aio_write | do_sync_write | reiserfs_file_write | vfs_write | | | |--3.14%-- sys_pwrite64 | | system_call_fastpath | | __pwrite64 | | | --0.10%-- sys_write [...] The command line has then changed. By providing the -c option, the callchain will output in the flat mode by default. But you can override it: perf report -c graph or perf report -c flat You can also pass the abreviated mode: perf report -c g or perf report -c gra will both make use of the graph mode. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <1246550301-8954-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-02 15:58:21 +00:00
return 0;
}
static const char * const report_usage[] = {
"perf report [<options>] <command>",
NULL
};
static const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
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 symbol address, etc)"),
OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
"dump raw trace in ASCII"),
OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
"file", "vmlinux pathname"),
OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
"file", "kallsyms pathname"),
OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
"load module symbols - WARNING: use only with -k and LIVE kernel"),
OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
"Show a column with the number of samples"),
OPT_BOOLEAN('T', "threads", &show_threads,
"Show per-thread event counters"),
OPT_STRING(0, "pretty", &pretty_printing_style, "key",
"pretty printing style key: normal raw"),
OPT_BOOLEAN(0, "tui", &use_tui, "Use the TUI interface"),
OPT_BOOLEAN(0, "stdio", &use_stdio, "Use the stdio interface"),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
"sort by key(s): pid, comm, dso, symbol, parent"),
OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_STRING('p', "parent", &parent_pattern, "regex",
"regex filter to identify parent, see: '--sort parent'"),
OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
"Only display entries with parent-match"),
OPT_CALLBACK_DEFAULT('g', "call-graph", NULL, "output_type,min_percent",
"Display callchains using output_type (graph, flat, fractal, or none) and min percent threshold. "
"Default: fractal,0.5", &parse_callchain_opt, callchain_default_opt),
OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
"only consider symbols in these dsos"),
OPT_STRING('C', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
"only consider symbols in these comms"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
"only consider these symbols"),
OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"width[,width...]",
"don't try to adjust column width, use these fixed values"),
OPT_STRING('t', "field-separator", &symbol_conf.field_sep, "separator",
perf report: Adjust column width to the values sampled Auto-adjust column width of perf report output to the longest occuring string length. Example: [acme@doppio pahole]$ perf report --sort comm,dso,symbol | head -13 12.79% pahole /usr/lib64/libdw-0.141.so [.] __libdw_find_attr 8.90% pahole /lib64/libc-2.10.1.so [.] _int_malloc 8.68% pahole /usr/lib64/libdw-0.141.so [.] __libdw_form_val_len 8.15% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 6.80% pahole /lib64/libc-2.10.1.so [.] __tsearch 5.54% pahole ./build/libdwarves.so.1.0.0 [.] tag__recode_dwarf_type [acme@doppio pahole]$ [acme@doppio pahole]$ perf report --sort comm,dso,symbol -d /lib64/libc-2.10.1.so | head -10 21.92% pahole /lib64/libc-2.10.1.so [.] _int_malloc 20.08% pahole /lib64/libc-2.10.1.so [.] __GI_strcmp 16.75% pahole /lib64/libc-2.10.1.so [.] __tsearch [acme@doppio pahole]$ Also add these extra options to control the new behaviour: -w, --field-width Force each column width to the provided list, for large terminal readability. -t, --field-separator: Use a special separator character and don't pad with spaces, replacing all occurances of this separator in symbol names (and other output) with a '.' character, that thus it's the only non valid separator. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> LKML-Reference: <20090711014728.GH3452@ghostprotocols.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-11 01:47:28 +00:00
"separator for columns, no spaces will be added between "
"columns '.' is reserved."),
OPT_BOOLEAN('U', "hide-unresolved", &hide_unresolved,
"Only display entries resolved to a symbol"),
OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
"Look for files with symbols relative to this directory"),
OPT_END()
};
int cmd_report(int argc, const char **argv, const char *prefix __used)
{
argc = parse_options(argc, argv, options, report_usage, 0);
if (use_stdio)
use_browser = 0;
else if (use_tui)
use_browser = 1;
if (strcmp(input_name, "-") != 0)
setup_browser(true);
else
use_browser = 0;
/*
* Only in the newt browser we are doing integrated annotation,
* so don't allocate extra space that won't be used in the stdio
* implementation.
*/
if (use_browser > 0) {
symbol_conf.priv_size = sizeof(struct sym_priv);
/*
* For searching by name on the "Browse map details".
* providing it only in verbose mode not to bloat too
* much struct symbol.
*/
if (verbose) {
/*
* XXX: Need to provide a less kludgy way to ask for
* more space per symbol, the u32 is for the index on
* the ui browser.
* See symbol__browser_index.
*/
symbol_conf.priv_size += sizeof(u32);
symbol_conf.sort_by_name = true;
}
}
if (symbol__init() < 0)
return -1;
setup_sorting(report_usage, options);
if (parent_pattern != default_parent_pattern) {
if (sort_dimension__add("parent") < 0)
return -1;
sort_parent.elide = 1;
} else
symbol_conf.exclude_other = false;
/*
* Any (unrecognized) arguments left?
*/
if (argc)
usage_with_options(report_usage, options);
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);
return __cmd_report();
}