Azat Khuzhin reported high loadavg in Linux v3.6
After checking the upstream scheduler code, I found Peter's commit:
5167e8d541 sched/nohz: Rewrite and fix load-avg computation -- again
not fully applied, missing the call to calc_load_exit_idle().
After that idle exit in sampling window will always be calculated
to non-idle, and the load will be higher than normal.
This patch adds the missing call to calc_load_exit_idle().
Signed-off-by: Charles Wang <muming.wq@taobao.com>
Cc: stable@kernel.org
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1345449754-27130-1-git-send-email-muming.wq@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull timer core changes from Ingo Molnar:
"Continued cleanups of the core time and NTP code, plus more nohz work
preparing for tick-less userspace execution."
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
time: Rework timekeeping functions to take timekeeper ptr as argument
time: Move xtime_nsec adjustment underflow handling timekeeping_adjust
time: Move arch_gettimeoffset() usage into timekeeping_get_ns()
time: Refactor accumulation of nsecs to secs
time: Condense timekeeper.xtime into xtime_sec
time: Explicitly use u32 instead of int for shift values
time: Whitespace cleanups per Ingo%27s requests
nohz: Move next idle expiry time record into idle logic area
nohz: Move ts->idle_calls incrementation into strict idle logic
nohz: Rename ts->idle_tick to ts->last_tick
nohz: Make nohz API agnostic against idle ticks cputime accounting
nohz: Separate idle sleeping time accounting from nohz logic
timers: Improve get_next_timer_interrupt()
timers: Add accounting of non deferrable timers
timers: Consolidate base->next_timer update
timers: Create detach_if_pending() and use it
Pull RCU changes from Ingo Molnar:
"Quoting from Paul, the major features of this series are:
1. Preventing latency spikes of more than 200 microseconds for
kernels built with NR_CPUS=4096, which is reportedly becoming the
default for some distros. This is a first step, as it does not
help with systems that actually -have- 4096 CPUs (work on this case
is in progress, but is not yet ready for mainline).
This category also includes improving concurrency of rcu_barrier(),
placed here due to conflicts. Posted to LKML at:
https://lkml.org/lkml/2012/6/22/381
Note that patches 18-22 of that series have been defered to 3.7, as
they have not yet proven themselves to be mainline-ready (and yes,
these are the ones intended to get rid of RCU's latency spikes for
systems that actually have 4096 CPUs).
2. Updates to documentation and rcutorture fixes, the latter category
including improvements to rcu_barrier() testing. Posted to LKML at
http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/04094.html.
3. Miscellaneous fixes posted to LKML at:
https://lkml.org/lkml/2012/6/22/500
with the exception of the last commit, which was posted here:
http://www.gossamer-threads.com/lists/linux/kernel/1561830
4. RCU_FAST_NO_HZ fixes and improvements. Posted to LKML at:
http://lkml.indiana.edu/hypermail/linux/kernel/1206.1/00006.htmlhttp://www.gossamer-threads.com/lists/linux/kernel/1561833
The first four patches of the first series went into 3.5 to fix a
regression.
5. Code-style fixes. These were posted to LKML at
http://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01180.htmlhttp://lkml.indiana.edu/hypermail/linux/kernel/1205.2/01181.html"
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
rcu: Fix broken strings in RCU's source code.
rcu: Fix code-style issues involving "else"
rcu: Introduce check for callback list/count mismatch
rcu: Make RCU_FAST_NO_HZ respect nohz= boot parameter
rcu: Fix qlen_lazy breakage
rcu: Round FAST_NO_HZ lazy timeout to nearest second
rcu: The rcu_needs_cpu() function is not a quiescent state
rcu: Dump only the current CPU's buffers for idle-entry/exit warnings
rcu: Add check for CPUs going offline with callbacks queued
rcu: Disable preemption in rcu_blocking_is_gp()
rcu: Prevent uninitialized string in RCU CPU stall info
rcu: Fix rcu_is_cpu_idle() #ifdef in TINY_RCU
rcu: Split RCU core processing out of __call_rcu()
rcu: Prevent __call_rcu() from invoking RCU core on offline CPUs
rcu: Make __call_rcu() handle invocation from idle
rcu: Remove function versions of __kfree_rcu and __is_kfree_rcu_offset
rcu: Consolidate tree/tiny __rcu_read_{,un}lock() implementations
rcu: Remove return value from rcu_assign_pointer()
key: Remove extraneous parentheses from rcu_assign_keypointer()
rcu: Remove return value from RCU_INIT_POINTER()
...
Reason: Update to upstream changes to avoid further conflicts.
Fixup a trivial merge conflict in kernel/time/tick-sched.c
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Thanks to Charles Wang for spotting the defects in the current code:
- If we go idle during the sample window -- after sampling, we get a
negative bias because we can negate our own sample.
- If we wake up during the sample window we get a positive bias
because we push the sample to a known active period.
So rewrite the entire nohz load-avg muck once again, now adding
copious documentation to the code.
Reported-and-tested-by: Doug Smythies <dsmythies@telus.net>
Reported-and-tested-by: Charles Wang <muming.wq@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/1340373782.18025.74.camel@twins
[ minor edits ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
If the nohz= boot parameter disables nohz, then RCU_FAST_NO_HZ needs to
also disable itself. This commit therefore checks for tick_nohz_enabled
being zero, disabling rcu_prepare_for_idle() if so. This commit assumes
that tick_nohz_enabled can change at runtime: If this is not the case,
then a simpler approach suffices.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The next idle expiry time record and idle sleeps tracking are
statistics that only concern idle.
Since we want the nohz APIs to become usable further idle
context, let's pull up the handling of these statistics to the
callers in idle.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@ti.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Since we want to prepare for making the nohz API to work further
the idle case, we need to pull ts->idle_calls incrementation up to
the callers in idle.
To perform this, we split tick_nohz_stop_sched_tick() in two parts:
a first one that checks if we can really stop the tick for idle,
and another that actually stops it. Then from the callers in idle,
we check if we can stop the tick and only then we increment idle_calls
and finally relay to the nohz API that won't care about these details
anymore.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@ti.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Now that idle and nohz logics are going to be independant each others,
ts->idle_tick becomes too much a biased name to describe the field that
saves the last scheduled tick on top of which we re-calculate the next
tick to schedule when the timer is restarted.
We want to reuse this even to stop the tick outside idle cases. So let's
rename it to some more generic name: ts->last_tick.
This changes a bit the timer list stat export so we need to increase its
version.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@ti.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
When the timer tick fires, it accounts the new jiffy as either part
of system, user or idle time. This is how we record the cputime
statistics.
But when the tick is stopped from the idle task, we still need
to record the number of jiffies spent tickless until we restart
the tick and fall back to traditional tick-based cputime accounting.
To do this, we take a snapshot of jiffies when the tick is stopped
and compute the difference against the new value of jiffies when
the tick is restarted. Then we account this whole difference to
the idle cputime.
However we are preparing to be able to stop the tick from other places
than idle. So this idle time accounting needs to be performed from
the callers of nohz APIs, not from the nohz APIs themselves because
we now want them to be agnostic against places that stop/restart tick.
Therefore, we pull the tickless idle time accounting out of generic
nohz helpers up to idle entry/exit callers.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@ti.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
As we plan to be able to stop the tick outside the idle task, we
need to prepare for separating nohz logic from idle. As a start,
this pulls the idle sleeping time accounting out of the tick
stop/restart API to the callers on idle entry/exit.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Alessio Igor Bogani <abogani@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Gilad Ben Yossef <gilad@benyossef.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@ti.com>
Cc: Max Krasnyansky <maxk@qualcomm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Sven-Thorsten Dietrich <thebigcorporation@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Merge RCU fixes from Paul E. McKenney:
" This series has four patches, the major point of which is to eliminate
some slowdowns (including boot-time slowdowns) resulting from some
RCU_FAST_NO_HZ changes. The issue with the changes is that posting timers
from the idle loop has no effect if the CPU has entered dyntick-idle
mode because the CPU has already computed its wakeup time, and posting
a timer does not cause it to be recomputed. The short-term fix is for
RCU to precompute the timeout value so that the CPU's calculation is
correct. "
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a CPU is entering dyntick-idle mode, tick_nohz_stop_sched_tick()
calls rcu_needs_cpu() see if RCU needs that CPU, and, if not, computes the
next wakeup time based on the timer wheels. Only later, when actually
entering the idle loop, rcu_prepare_for_idle() will be invoked. In some
cases, rcu_prepare_for_idle() will post timers to wake the CPU back up.
But all for naught: The next wakeup time for the CPU has already been
computed, and posting a timer afterwards does not force that wakeup
time to be recomputed. This means that rcu_prepare_for_idle()'s have
no effect.
This is not a problem on a busy system because something else will wake
up the CPU soon enough. However, on lightly loaded systems, the CPU
might stay asleep for a considerable length of time. If that CPU has
a callback that the rest of the system is waiting on, the system might
run very slowly or (in theory) even hang.
This commit avoids this problem by having rcu_needs_cpu() give
tick_nohz_stop_sched_tick() an estimate of when RCU will need the CPU
to wake back up, which tick_nohz_stop_sched_tick() takes into account
when programming the CPU's wakeup time. An alternative approach is
for rcu_prepare_for_idle() to use hrtimers instead of normal timers,
but timers are much more efficient than are hrtimers for frequently
and repeatedly posting and cancelling a given timer, which is exactly
what RCU_FAST_NO_HZ does.
Reported-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr>
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Tested-by: Pascal Chapperon <pascal.chapperon@wanadoo.fr>
Pull scheduler fixes from Ingo Molnar.
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched: Remove NULL assignment of dattr_cur
sched: Remove the last NULL entry from sched_feat_names
sched: Make sched_feat_names const
sched/rt: Fix SCHED_RR across cgroups
sched: Move nr_cpus_allowed out of 'struct sched_rt_entity'
sched: Make sure to not re-read variables after validation
sched: Fix SD_OVERLAP
sched: Don't try allocating memory from offline nodes
sched/nohz: Fix rq->cpu_load calculations some more
sched/x86: Use cpu_llc_shared_mask(cpu) for coregroup_mask
Follow up on commit 556061b00 ("sched/nohz: Fix rq->cpu_load[]
calculations") since while that fixed the busy case it regressed the
mostly idle case.
Add a callback from the nohz exit to also age the rq->cpu_load[]
array. This closes the hole where either there was no nohz load
balance pass during the nohz, or there was a 'significant' amount of
idle time between the last nohz balance and the nohz exit.
So we'll update unconditionally from the tick to not insert any
accidental 0 load periods while busy, and we try and catch up from
nohz idle balance and nohz exit. Both these are still prone to missing
a jiffy, but that has always been the case.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: pjt@google.com
Cc: Venkatesh Pallipadi <venki@google.com>
Link: http://lkml.kernel.org/n/tip-kt0trz0apodbf84ucjfdbr1a@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Let the user decide whether power consumption or jitter is the
more important consideration for their machines.
Quoting removal commit af5ab277de:
"Historically, Linux has tried to make the regular timer tick on the
various CPUs not happen at the same time, to avoid contention on
xtime_lock.
Nowadays, with the tickless kernel, this contention no longer happens
since time keeping and updating are done differently. In addition,
this skew is actually hurting power consumption in a measurable way on
many-core systems."
Problems:
- Contrary to the above, systems do encounter contention on both
xtime_lock and RCU structure locks when the tick is synchronized.
- Moderate sized RT systems suffer intolerable jitter due to the tick
being synchronized.
- SGI reports the same for their large systems.
- Fully utilized systems reap no power saving benefit from skew removal,
but do suffer from resulting induced lock contention.
- 0209f649 rcu: limit rcu_node leaf-level fanout
This patch was born to combat lock contention which testing showed
to have been _induced by_ skew removal. Skew the tick, contention
disappeared virtually completely.
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Link: http://lkml.kernel.org/r/1336472458.21924.78.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Fix tick_nohz_restart() to not use a stale ktime_t "now" value when
calling tick_do_update_jiffies64(now).
If we reach this point in the loop it means that we crossed a tick
boundary since we grabbed the "now" timestamp, so at this point "now"
refers to a time in the old jiffy, so using the old value for "now" is
incorrect, and is likely to give us a stale jiffies value.
In particular, the first time through the loop the
tick_do_update_jiffies64(now) call is always a no-op, since the
caller, tick_nohz_restart_sched_tick(), will have already called
tick_do_update_jiffies64(now) with that "now" value.
Note that tick_nohz_stop_sched_tick() already uses the correct
approach: when we notice we cross a jiffy boundary, grab a new
timestamp with ktime_get(), and *then* update jiffies.
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1332875377-23014-1-git-send-email-ncardwell@google.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
ts->inidle is set by tick_nohz_idle_enter() and unset by
tick_nohz_idle_exit(). However these two calls are assumed
to be always paired. This means that by the time we call
tick_nohz_idle_exit(), ts->inidle is supposed to be always
set to 1.
Remove the checks for ts->inidle in tick_nohz_idle_exit().
This simplifies a bit the code and improves its debuggability
(ie: ensure the call is paired with a tick_nohz_idle_enter()
call).
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Yong Zhang <yong.zhang0@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Ingo Molnar <mingo@elte.hu>
Link: http://lkml.kernel.org/r/1327427984-23282-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
There is no reason to call update_ts_time_stat from tick_nohz_start_idle
anymore (after e0e37c20 sched: Eliminate the ts->idle_lastupdate field)
when we updated idle_lastupdate unconditionally.
We haven't set idle_active yet and do not provide last_update_time so
the whole call end up being just 2 wasted branches.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Link: http://lkml.kernel.org/r/1322755222-6951-1-git-send-email-mhocko@suse.cz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
sched/tracing: Add a new tracepoint for sleeptime
sched: Disable scheduler warnings during oopses
sched: Fix cgroup movement of waking process
sched: Fix cgroup movement of newly created process
sched: Fix cgroup movement of forking process
sched: Remove cfs bandwidth period check in tg_set_cfs_period()
sched: Fix load-balance lock-breaking
sched: Replace all_pinned with a generic flags field
sched: Only queue remote wakeups when crossing cache boundaries
sched: Add missing rcu_dereference() around ->real_parent usage
[S390] fix cputime overflow in uptime_proc_show
[S390] cputime: add sparse checking and cleanup
sched: Mark parent and real_parent as __rcu
sched, nohz: Fix missing RCU read lock
sched, nohz: Set the NOHZ_BALANCE_KICK flag for idle load balancer
sched, nohz: Fix the idle cpu check in nohz_idle_balance
sched: Use jump_labels for sched_feat
sched/accounting: Fix parameter passing in task_group_account_field
sched/accounting: Fix user/system tick double accounting
sched/accounting: Re-use scheduler statistics for the root cgroup
...
Fix up conflicts in
- arch/ia64/include/asm/cputime.h, include/asm-generic/cputime.h
usecs_to_cputime64() vs the sparse cleanups
- kernel/sched/fair.c, kernel/time/tick-sched.c
scheduler changes in multiple branches
Those two APIs were provided to optimize the calls of
tick_nohz_idle_enter() and rcu_idle_enter() into a single
irq disabled section. This way no interrupt happening in-between would
needlessly process any RCU job.
Now we are talking about an optimization for which benefits
have yet to be measured. Let's start simple and completely decouple
idle rcu and dyntick idle logics to simplify.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
It is assumed that rcu won't be used once we switch to tickless
mode and until we restart the tick. However this is not always
true, as in x86-64 where we dereference the idle notifiers after
the tick is stopped.
To prepare for fixing this, add two new APIs:
tick_nohz_idle_enter_norcu() and tick_nohz_idle_exit_norcu().
If no use of RCU is made in the idle loop between
tick_nohz_enter_idle() and tick_nohz_exit_idle() calls, the arch
must instead call the new *_norcu() version such that the arch doesn't
need to call rcu_idle_enter() and rcu_idle_exit().
Otherwise the arch must call tick_nohz_enter_idle() and
tick_nohz_exit_idle() and also call explicitly:
- rcu_idle_enter() after its last use of RCU before the CPU is put
to sleep.
- rcu_idle_exit() before the first use of RCU after the CPU is woken
up.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: David Miller <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
The tick_nohz_stop_sched_tick() function, which tries to delay
the next timer tick as long as possible, can be called from two
places:
- From the idle loop to start the dytick idle mode
- From interrupt exit if we have interrupted the dyntick
idle mode, so that we reprogram the next tick event in
case the irq changed some internal state that requires this
action.
There are only few minor differences between both that
are handled by that function, driven by the ts->inidle
cpu variable and the inidle parameter. The whole guarantees
that we only update the dyntick mode on irq exit if we actually
interrupted the dyntick idle mode, and that we enter in RCU extended
quiescent state from idle loop entry only.
Split this function into:
- tick_nohz_idle_enter(), which sets ts->inidle to 1, enters
dynticks idle mode unconditionally if it can, and enters into RCU
extended quiescent state.
- tick_nohz_irq_exit() which only updates the dynticks idle mode
when ts->inidle is set (ie: if tick_nohz_idle_enter() has been called).
To maintain symmetry, tick_nohz_restart_sched_tick() has been renamed
into tick_nohz_idle_exit().
This simplifies the code and micro-optimize the irq exit path (no need
for local_irq_save there). This also prepares for the split between
dynticks and rcu extended quiescent state logics. We'll need this split to
further fix illegal uses of RCU in extended quiescent states in the idle
loop.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: David Miller <davem@davemloft.net>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Hans-Christian Egtvedt <hans-christian.egtvedt@atmel.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Earlier versions of RCU used the scheduling-clock tick to detect idleness
by checking for the idle task, but handled idleness differently for
CONFIG_NO_HZ=y. But there are now a number of uses of RCU read-side
critical sections in the idle task, for example, for tracing. A more
fine-grained detection of idleness is therefore required.
This commit presses the old dyntick-idle code into full-time service,
so that rcu_idle_enter(), previously known as rcu_enter_nohz(), is
always invoked at the beginning of an idle loop iteration. Similarly,
rcu_idle_exit(), previously known as rcu_exit_nohz(), is always invoked
at the end of an idle-loop iteration. This allows the idle task to
use RCU everywhere except between consecutive rcu_idle_enter() and
rcu_idle_exit() calls, in turn allowing architecture maintainers to
specify exactly where in the idle loop that RCU may be used.
Because some of the userspace upcall uses can result in what looks
to RCU like half of an interrupt, it is not possible to expect that
the irq_enter() and irq_exit() hooks will give exact counts. This
patch therefore expands the ->dynticks_nesting counter to 64 bits
and uses two separate bitfields to count process/idle transitions
and interrupt entry/exit transitions. It is presumed that userspace
upcalls do not happen in the idle loop or from usermode execution
(though usermode might do a system call that results in an upcall).
The counter is hard-reset on each process/idle transition, which
avoids the interrupt entry/exit error from accumulating. Overflow
is avoided by the 64-bitness of the ->dyntick_nesting counter.
This commit also adds warnings if a non-idle task asks RCU to enter
idle state (and these checks will need some adjustment before applying
Frederic's OS-jitter patches (http://lkml.org/lkml/2011/10/7/246).
In addition, validation of ->dynticks and ->dynticks_nesting is added.
Signed-off-by: Paul E. McKenney <paul.mckenney@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Introduce nr_busy_cpus in the struct sched_group_power [Not in sched_group
because sched groups are duplicated for the SD_OVERLAP scheduler domain]
and for each cpu that enters and exits idle, this parameter will
be updated in each scheduler group of the scheduler domain that this cpu
belongs to.
To avoid the frequent update of this state as the cpu enters
and exits idle, the update of the stat during idle exit is
delayed to the first timer tick that happens after the cpu becomes busy.
This is done using NOHZ_IDLE flag in the struct rq's nohz_flags.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20111202010832.555984323@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
time, s390: Get rid of compile warning
dw_apb_timer: constify clocksource name
time: Cleanup old CONFIG_GENERIC_TIME references that snuck in
time: Change jiffies_to_clock_t() argument type to unsigned long
alarmtimers: Fix error handling
clocksource: Make watchdog reset lockless
posix-cpu-timers: Cure SMP accounting oddities
s390: Use direct ktime path for s390 clockevent device
clockevents: Add direct ktime programming function
clockevents: Make minimum delay adjustments configurable
nohz: Remove "Switched to NOHz mode" debugging messages
proc: Consider NO_HZ when printing idle and iowait times
nohz: Make idle/iowait counter update conditional
nohz: Fix update_ts_time_stat idle accounting
cputime: Clean up cputime_to_usecs and usecs_to_cputime macros
alarmtimers: Rework RTC device selection using class interface
alarmtimers: Add try_to_cancel functionality
alarmtimers: Add more refined alarm state tracking
alarmtimers: Remove period from alarm structure
alarmtimers: Remove interval cap limit hack
...
RCU no longer uses this global variable, nor does anyone else. This
commit therefore removes this variable. This reduces memory footprint
and also removes some atomic instructions and memory barriers from
the dyntick-idle path.
Signed-off-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
When performing cpu hotplug tests the kernel printk log buffer gets flooded
with pointless "Switched to NOHz mode..." messages. Especially when afterwards
analyzing a dump this might have removed more interesting stuff out of the
buffer.
Assuming that switching to NOHz mode simply works just remove the printk.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Link: http://lkml.kernel.org/r/20110823112046.GB2540@osiris.boeblingen.de.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
get_cpu_{idle,iowait}_time_us update idle/iowait counters
unconditionally if the given CPU is in the idle loop.
This doesn't work well outside of CPU governors which are singletons
so nobody (except for IRQ) can race with them.
We will need to use both functions from /proc/stat handler to properly
handle nohz idle/iowait times.
Make the update depend on a non NULL last_update_time argument.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Link: http://lkml.kernel.org/r/11f23179472635ce52e78921d47a20216b872f23.1314172057.git.mhocko@suse.cz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
update_ts_time_stat currently updates idle time even if we are in
iowait loop at the moment. The only real users of the idle counter
(via get_cpu_idle_time_us) are CPU governors and they expect to get
cumulative time for both idle and iowait times.
The value (idle_sleeptime) is also printed to userspace by print_cpu
but it prints both idle and iowait times so the idle part is misleading.
Let's clean this up and fix update_ts_time_stat to account both counters
properly and update consumers of idle to consider iowait time as well.
If we do this we might use get_cpu_{idle,iowait}_time_us from other
contexts as well and we will get expected values.
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Dave Jones <davej@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Link: http://lkml.kernel.org/r/e9c909c221a8da402c4da07e4cd968c3218f8eb1.1314172057.git.mhocko@suse.cz
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
All callers of do_timer() are converted to xtime_update(). The only
users of xtime_lock are in kernel/time/. Make both local to
kernel/time/ and remove them from the global header files.
[ tglx: Reuse tick-internal.h instead of creating another local header
file. Massaged changelog ]
Signed-off-by: Torben Hohn <torbenh@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: johnstul@us.ibm.com
Cc: yong.zhang0@gmail.com
Cc: hch@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
When NOHZ=y and high res timers are disabled (via cmdline or
Kconfig) tick_nohz_switch_to_nohz() will notify the user about
switching into NOHZ mode. Nothing is printed for the case where
HIGH_RES_TIMERS=y. Fix this for the HIGH_RES_TIMERS=y case by
duplicating the printk from the low res NOHZ path in the high
res NOHZ path.
This confused me since I was thinking 'dmesg | grep -i NOHZ' would
tell me if NOHZ was enabled, but if I have hrtimers there is
nothing.
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1295419594-13085-1-git-send-email-sboyd@codeaurora.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
Documentation: Add timers/timers-howto.txt
timer: Added usleep_range timer
Revert "timer: Added usleep[_range] timer"
clockevents: Remove the per cpu tick skew
posix_timer: Move copy_to_user(created_timer_id) down in timer_create()
timer: Added usleep[_range] timer
timers: Document meaning of deferrable timer
Historically, Linux has tried to make the regular timer tick on the
various CPUs not happen at the same time, to avoid contention on
xtime_lock.
Nowadays, with the tickless kernel, this contention no longer happens
since time keeping and updating are done differently. In addition,
this skew is actually hurting power consumption in a measurable way on
many-core systems.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
LKML-Reference: <20100727210210.58d3118c@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Norbert reported that nohz_ratelimit() causes his laptop to burn about
4W (40%) extra. For now back out the change and see if we can adjust
the power management code to make better decisions.
Reported-by: Norbert Preining <preining@logic.at>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mike Galbraith <efault@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Commit 0224cf4c5e (sched: Intoduce get_cpu_iowait_time_us())
broke things by not making sure preemption was indeed disabled
by the callers of nr_iowait_cpu() which took the iowait value of
the current cpu.
This resulted in a heap of preempt warnings. Cure this by making
nr_iowait_cpu() take a cpu number and fix up the callers to pass
in the right number.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: linux-pm@lists.linux-foundation.org
LKML-Reference: <1277968037.1868.120.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Chris Wedgwood reports that 39c0cbe (sched: Rate-limit nohz) causes a
serial console regression, unresponsiveness, and indeed it does. The
reason is that the nohz code is skipped even when the tick was already
stopped before the nohz_ratelimit(cpu) condition changed.
Move the nohz_ratelimit() check to the other conditions which prevent
long idle sleeps.
Reported-by: Chris Wedgwood <cw@f00f.org>
Tested-by: Brian Bloniarz <bmb@athenacr.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Greg KH <gregkh@suse.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Jef Driesen <jefdriesen@telenet.be>
LKML-Reference: <1276790557.27822.516.camel@twins>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
In the new push model, all idle CPUs indeed go into nohz mode. There is
still the concept of idle load balancer (performing the load balancing
on behalf of all the idle cpu's in the system). Busy CPU kicks the nohz
balancer when any of the nohz CPUs need idle load balancing.
The kickee CPU does the idle load balancing on behalf of all idle CPUs
instead of the normal idle balance.
This addresses the below two problems with the current nohz ilb logic:
* the idle load balancer continued to have periodic ticks during idle and
wokeup frequently, even though it did not have any rebalancing to do on
behalf of any of the idle CPUs.
* On x86 and CPUs that have APIC timer stoppage on idle CPUs, this
periodic wakeup can result in a periodic additional interrupt on a CPU
doing the timer broadcast.
Also currently we are migrating the unpinned timers from an idle to the cpu
doing idle load balancing (when all the cpus in the system are idle,
there is no idle load balancing cpu and timers get added to the same idle cpu
where the request was made. So the existing optimization works only on semi idle
system).
And In semi idle system, we no longer have periodic ticks on the idle load
balancer CPU. Using that cpu will add more delays to the timers than intended
(as that cpu's timer base may not be uptodate wrt jiffies etc). This was
causing mysterious slowdowns during boot etc.
For now, in the semi idle case, use the nearest busy cpu for migrating timers
from an idle cpu. This is good for power-savings anyway.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1274486981.2840.46.camel@sbs-t61.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For the ondemand cpufreq governor, it is desired that the iowait
time is microaccounted in a similar way as idle time is.
This patch introduces the infrastructure to account and expose
this information via the get_cpu_iowait_time_us() function.
[akpm@linux-foundation.org: fix CONFIG_NO_HZ=n build]
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082523.284feab6@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that the only user of ts->idle_lastupdate is
update_ts_time_stats(), the entire field can be eliminated.
In update_ts_time_stats(), idle_lastupdate is first set to
"now", and a few lines later, the only user is an if() statement
that assigns a variable either to "now" or to
ts->idle_lastupdate, which has the value of "now" at that point.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082439.2fab0b4f@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch folds the updating of the last_update_time into the
update_ts_time_stats() function, and updates the callers.
This allows for further cleanups that are done in the next
patch.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082403.60072967@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Right now, get_cpu_idle_time_us() only reports the idle
statistics upto the point the CPU entered last idle; not what is
valid right now.
This patch adds an update of the idle statistics to
get_cpu_idle_time_us(), so that calling this function always
returns statistics that are accurate at the point of the call.
This includes resetting the start of the idle time for
accounting purposes to avoid double accounting.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082323.2d2f1945@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently, two places update the idle statistics (and more to
come later in this series).
This patch creates a helper function for updating these
statistics.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082245.163e67ed@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The exported function get_cpu_idle_time_us() has no comment
describing it; add a kerneldoc comment
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: davej@redhat.com
LKML-Reference: <20100509082208.7cb721f0@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Entering nohz code on every micro-idle is costing ~10% throughput for netperf
TCP_RR when scheduling cross-cpu. Rate limiting entry fixes this, but raises
ticks a bit. On my Q6600, an idle box goes from ~85 interrupts/sec to 128.
The higher the context switch rate, the more nohz entry costs. With this patch
and some cycle recovery patches in my tree, max cross cpu context switch rate is
improved by ~16%, a large portion of which of which is this ratelimiting.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1268301003.6785.28.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
timers, init: Limit the number of per cpu calibration bootup messages
posix-cpu-timers: optimize and document timer_create callback
clockevents: Add missing include to pacify sparse
x86: vmiclock: Fix printk format
x86: Fix printk format due to variable type change
sparc: fix printk for change of variable type
clocksource/events: Fix fallout of generic code changes
nohz: Allow 32-bit machines to sleep for more than 2.15 seconds
nohz: Track last do_timer() cpu
nohz: Prevent clocksource wrapping during idle
nohz: Type cast printk argument
mips: Use generic mult/shift factor calculation for clocks
clocksource: Provide a generic mult/shift factor calculation
clockevents: Use u32 for mult and shift factors
nohz: Introduce arch_needs_cpu
nohz: Reuse ktime in sub-functions of tick_check_idle.
time: Remove xtime_cache
time: Implement logarithmic time accumulation
