Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
1 年多 前同步成功

通知 160
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 01 2月, 2017 3 次提交
  3. 14 1月, 2017 3 次提交
  5. 15 11月, 2016 3 次提交
  7. 30 9月, 2016 4 次提交
  9. 18 8月, 2016 3 次提交
    • S
      sched/cputime: Improve scalability by not accounting thread group tasks pending runtime · a1eb1411
      由 Stanislaw Gruszka 提交于 
      Commit:

  d670ec13 ("posix-cpu-timers: Cure SMP wobbles")

started accounting thread group tasks pending runtime in thread_group_cputime().

Another commit:

  6e998916 ("sched/cputime: Fix clock_nanosleep()/clock_gettime() inconsistency")

updated scheduler runtime statistics (call update_curr()) when reading task pending
runtime. Those changes cause bad performance of SYS_times() and
SYS_clock_gettimes(CLOCK_PROCESS_CPUTIME_ID) syscalls, especially on
larger systems with many CPUs.

While we would like to have cpuclock monotonicity kept i.e. have
problems fixed by above commits stay fixed, we also would like to have
good performance.

However when we notice that change from commit d670ec13 is not
longer needed to solve problem addressed by that commit, because of
change from the second commit 6e998916, we can get room for
optimization. Since we update task while reading it's pending runtime
in task_sched_runtime(), clock_gettime(CLOCK_PROCESS_CPUTIME_ID) will
see updated values and on testcase from d670ec13 process cpuclock
will not be smaller than thread cpuclock.

I tested the patch on testcases from commits d670ec13,
6e998916 and some other cpuclock/cputimers testcases and
did not found cpuclock monotonicity problems or other malfunction.

This patch has the drawback that we will not provide thread group cputime
up-to-date to the last moment. For example when arming cputime timer,
we will arm it with possibly a bit outdated values and that timer will
trigger earlier compared to behaviour without the patch. However that
was the behaviour before d670ec13 commit (kernel v3.1) so it's
unlikely to affect applications.

Patch improves related syscall performance, as measured by Giovanni's
benchmarks described in commit:

  6075620b ("sched/cputime: Mitigate performance regression in times()/clock_gettime()")

The benchmark results are:

SYS_clock_gettime():

  threads    4.7-rc7     3.18-rc3              4.7-rc7 + prefetch    4.7-rc7 + patch
                         (pre-6e998916)
  2          3.48        2.23 ( 35.68%)        3.06 ( 11.83%)        1.08 ( 68.81%)
  5          3.33        2.83 ( 14.84%)        3.25 (  2.40%)        0.71 ( 78.55%)
  8          3.37        2.84 ( 15.80%)        3.26 (  3.30%)        0.56 ( 83.49%)
  12         3.32        3.09 (  6.69%)        3.37 ( -1.60%)        0.42 ( 87.28%)
  21         4.01        3.14 ( 21.70%)        3.90 (  2.74%)        0.35 ( 91.35%)
  30         3.63        3.28 (  9.75%)        3.36 (  7.41%)        0.28 ( 92.23%)
  48         3.71        3.02 ( 18.69%)        3.11 ( 16.27%)        0.39 ( 89.39%)
  79         3.75        2.88 ( 23.23%)        3.16 ( 15.74%)        0.46 ( 87.76%)
  110        3.81        2.95 ( 22.62%)        3.25 ( 14.80%)        0.56 ( 85.41%)
  128        3.88        3.05 ( 21.28%)        3.31 ( 14.76%)        0.62 ( 84.10%)

SYS_times():

  threads    4.7-rc7     3.18-rc3              4.7-rc7 + prefetch    4.7-rc7 + patch
                         (pre-6e998916)
  2          3.65        2.27 ( 37.94%)        3.25 ( 11.03%)        1.62 ( 55.71%)
  5          3.45        2.78 ( 19.34%)        3.17 (  7.92%)        2.33 ( 32.28%)
  8          3.52        2.79 ( 20.66%)        3.22 (  8.69%)        2.06 ( 41.44%)
  12         3.29        3.02 (  8.33%)        3.36 ( -2.04%)        2.00 ( 39.18%)
  21         4.07        3.10 ( 23.86%)        3.92 (  3.78%)        2.07 ( 49.18%)
  30         3.87        3.33 ( 13.80%)        3.40 ( 12.17%)        1.89 ( 51.12%)
  48         3.79        2.96 ( 21.94%)        3.16 ( 16.61%)        1.69 ( 55.46%)
  79         3.88        2.88 ( 25.82%)        3.28 ( 15.42%)        1.60 ( 58.81%)
  110        3.90        2.98 ( 23.73%)        3.38 ( 13.35%)        1.73 ( 55.61%)
  128        4.00        3.10 ( 22.40%)        3.38 ( 15.45%)        1.66 ( 58.52%)
Reported-and-tested-by: NGiovanni Gherdovich <ggherdovich@suse.cz>
Signed-off-by: NStanislaw Gruszka <sgruszka@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Galbraith <mgalbraith@suse.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/20160817093043.GA25206@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      a1eb1411
    • W
      sched/cputime: Resync steal time when guest & host lose sync · 03cbc732
      由 Wanpeng Li 提交于 
      Commit:

  57430218 ("sched/cputime: Count actually elapsed irq & softirq time")

... fixed a bug but also triggered a regression:

On an i5 laptop, 4 pCPUs, 4vCPUs for one full dynticks guest, there are four
CPU hog processes(for loop) running in the guest, I hot-unplug the pCPUs
on host one by one until there is only one left, then observe CPU utilization
via 'top' in the guest, it shows:

  100% st for cpu0(housekeeping)
   75% st for other CPUs (nohz full mode)

However, w/o this commit it shows the correct 75% for all four CPUs.

When a guest is interrupted for a longer amount of time, missed clock ticks
are not redelivered later. Because of that, we should not limit the amount
of steal time accounted to the amount of time that the calling functions
think have passed.

However, the interval returned by account_other_time() is NOT rounded down
to the nearest jiffy, while the base interval in get_vtime_delta() it is
subtracted from is, so the max cputime limit is required to avoid underflow.

This patch fixes the regression by limiting the account_other_time() from
get_vtime_delta() to avoid underflow, and lets the other three call sites
(in account_other_time() and steal_account_process_time()) account however
much steal time the host told us elapsed.
Suggested-by: NRik van Riel <riel@redhat.com>
Suggested-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NWanpeng Li <wanpeng.li@hotmail.com>
Reviewed-by: NRik van Riel <riel@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kvm@vger.kernel.org
Link: http://lkml.kernel.org/r/1471399546-4069-1-git-send-email-wanpeng.li@hotmail.com
[ Improved the changelog. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      03cbc732
    • P
      sched/cputime: Fix NO_HZ_FULL getrusage() monotonicity regression · 173be9a1
      由 Peter Zijlstra 提交于 
      Mike reports:

 Roughly 10% of the time, ltp testcase getrusage04 fails:
 getrusage04    0  TINFO  :  Expected timers granularity is 4000 us
 getrusage04    0  TINFO  :  Using 1 as multiply factor for max [us]time increment (1000+4000us)!
 getrusage04    0  TINFO  :  utime:           0us; stime:         179us
 getrusage04    0  TINFO  :  utime:        3751us; stime:           0us
 getrusage04    1  TFAIL  :  getrusage04.c:133: stime increased > 5000us:

And tracked it down to the case where the task simply doesn't get
_any_ [us]time ticks.

Update the code to assume all rtime is utime when we lack information,
thus ensuring a task that elides the tick gets time accounted.
Reported-by: NMike Galbraith <umgwanakikbuti@gmail.com>
Tested-by: NMike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Fredrik Markstrom <fredrik.markstrom@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: stable@vger.kernel.org # 4.3+
Fixes: 9d7fb042 ("sched/cputime: Guarantee stime + utime == rtime")
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      173be9a1
  11. 11 8月, 2016 2 次提交
  13. 14 7月, 2016 4 次提交
    • R
      sched/cputime: Drop local_irq_save/restore from irqtime_account_irq() · 553bf6bb
      由 Rik van Riel 提交于 
      Paolo pointed out that irqs are already blocked when irqtime_account_irq()
is called. That means there is no reason to call local_irq_save/restore()
again.
Suggested-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1468421405-20056-6-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      553bf6bb
    • F
      sched/cputime: Clean up the old vtime gen irqtime accounting completely · 0cfdf9a1
      由 Frederic Weisbecker 提交于 
      Vtime generic irqtime accounting has been removed but there are a few
remnants to clean up:

* The vtime_accounting_cpu_enabled() check in irq entry was only used
  by CONFIG_VIRT_CPU_ACCOUNTING_GEN. We can safely remove it.

* Without the vtime_accounting_cpu_enabled(), we no longer need to
  have a vtime_common_account_irq_enter() indirect function.

* Move vtime_account_irq_enter() implementation under
  CONFIG_VIRT_CPU_ACCOUNTING_NATIVE which is the last user.

* The vtime_account_user() call was only used on irq entry for
  CONFIG_VIRT_CPU_ACCOUNTING_GEN. We can remove that too.
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1468421405-20056-4-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      0cfdf9a1
    • R
      sched/cputime: Replace VTIME_GEN irq time code with IRQ_TIME_ACCOUNTING code · b58c3584
      由 Rik van Riel 提交于 
      The CONFIG_VIRT_CPU_ACCOUNTING_GEN irq time tracking code does not
appear to currently work right.

On CPUs without nohz_full=, only tick based irq time sampling is
done, which breaks down when dealing with a nohz_idle CPU.

On firewalls and similar systems, no ticks may happen on a CPU for a
while, and the irq time spent may never get accounted properly. This
can cause issues with capacity planning and power saving, which use
the CPU statistics as inputs in decision making.

Remove the VTIME_GEN vtime irq time code, and replace it with the
IRQ_TIME_ACCOUNTING code, when selected as a config option by the user.
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1468421405-20056-3-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      b58c3584
    • R
      sched/cputime: Count actually elapsed irq & softirq time · 57430218
      由 Rik van Riel 提交于 
      Currently, if there was any irq or softirq time during 'ticks'
jiffies, the entire period will be accounted as irq or softirq
time.

This is inaccurate if only a subset of the time was actually spent
handling irqs, and could conceivably mis-count all of the ticks during
a period as irq time, when there was some irq and some softirq time.

This can actually happen when irqtime_account_process_tick is called
from account_idle_ticks, which can pass a larger number of ticks down
all at once.

Fix this by changing irqtime_account_hi_update(), irqtime_account_si_update(),
and steal_account_process_ticks() to work with cputime_t time units, and
return the amount of time spent in each mode.

Rename steal_account_process_ticks() to steal_account_process_time(), to
reflect that time is now accounted in cputime_t, instead of ticks.

Additionally, have irqtime_account_process_tick() take into account how
much time was spent in each of steal, irq, and softirq time.

The latter could help improve the accuracy of cputime
accounting when returning from idle on a NO_HZ_IDLE CPU.

Properly accounting how much time was spent in hardirq and
softirq time will also allow the NO_HZ_FULL code to re-use
these same functions for hardirq and softirq accounting.
Signed-off-by: NRik van Riel <riel@redhat.com>
[ Make nsecs_to_cputime64() actually return cputime64_t. ]
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1468421405-20056-2-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      57430218
  15. 06 7月, 2016 1 次提交
  17. 14 6月, 2016 1 次提交
  19. 08 3月, 2016 1 次提交
  21. 29 2月, 2016 1 次提交
    • R
      sched, time: Switch VIRT_CPU_ACCOUNTING_GEN to jiffy granularity · ff9a9b4c
      由 Rik van Riel 提交于 
      When profiling syscall overhead on nohz-full kernels,
after removing __acct_update_integrals() from the profile,
native_sched_clock() remains as the top CPU user. This can be
reduced by moving VIRT_CPU_ACCOUNTING_GEN to jiffy granularity.

This will reduce timing accuracy on nohz_full CPUs to jiffy
based sampling, just like on normal CPUs. It results in
totally removing native_sched_clock from the profile, and
significantly speeding up the syscall entry and exit path,
as well as irq entry and exit, and KVM guest entry & exit.

Additionally, only call the more expensive functions (and
advance the seqlock) when jiffies actually changed.

This code relies on another CPU advancing jiffies when the
system is busy. On a nohz_full system, this is done by a
housekeeping CPU.

A microbenchmark calling an invalid syscall number 10 million
times in a row speeds up an additional 30% over the numbers
with just the previous patches, for a total speedup of about
40% over 4.4 and 4.5-rc1.

Run times for the microbenchmark:

 4.4				3.8 seconds
 4.5-rc1			3.7 seconds
 4.5-rc1 + first patch		3.3 seconds
 4.5-rc1 + first 3 patches	3.1 seconds
 4.5-rc1 + all patches		2.3 seconds

A non-NOHZ_FULL cpu (not the housekeeping CPU):

 all kernels			1.86 seconds
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: clark@redhat.com
Cc: eric.dumazet@gmail.com
Cc: fweisbec@gmail.com
Cc: luto@amacapital.net
Link: http://lkml.kernel.org/r/1455152907-18495-5-git-send-email-riel@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      ff9a9b4c
  23. 21 12月, 2015 1 次提交
    • S
      missing include asm/paravirt.h in cputime.c · 1fe7c4ef
      由 Stefano Stabellini 提交于 
      Add include asm/paravirt.h to cputime.c, as steal_account_process_tick
calls paravirt_steal_clock, which is defined in asm/paravirt.h.

The ifdef CONFIG_PARAVIRT is necessary because not all archs have an
asm/paravirt.h to include.

The reason why currently cputime.c compiles, even though include
<asm/paravirt.h> is missing, is that on x86 asm/paravirt.h is included
by one of the other headers included in kernel/sched/cputime.c:

On arm and arm64, where I am about to introduce asm/paravirt.h and
stolen time support, without #include <asm/paravirt.h> in cputime.c, I
would get an error.
Signed-off-by: NStefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
      1fe7c4ef
  25. 04 12月, 2015 7 次提交
  27. 01 10月, 2015 1 次提交
  29. 03 8月, 2015 1 次提交
  31. 08 5月, 2015 1 次提交
  33. 03 10月, 2014 1 次提交
  35. 19 9月, 2014 1 次提交
  37. 08 9月, 2014 1 次提交
    • R
      sched, time: Atomically increment stime & utime · eb1b4af0
      由 Rik van Riel 提交于 
      The functions task_cputime_adjusted and thread_group_cputime_adjusted()
can be called locklessly, as well as concurrently on many different CPUs.

This can occasionally lead to the utime and stime reported by times(), and
other syscalls like it, going backward. The cause for this appears to be
multiple threads racing in cputime_adjust(), both with values for utime or
stime that is larger than the original, but each with a different value.

Sometimes the larger value gets saved first, only to be immediately
overwritten with a smaller value by another thread.

Using atomic exchange prevents that problem, and ensures time
progresses monotonically.
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: umgwanakikbuti@gmail.com
Cc: fweisbec@gmail.com
Cc: akpm@linux-foundation.org
Cc: srao@redhat.com
Cc: lwoodman@redhat.com
Cc: atheurer@redhat.com
Cc: oleg@redhat.com
Link: http://lkml.kernel.org/r/1408133138-22048-4-git-send-email-riel@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      eb1b4af0