Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1434810

[PATCH v3 0/4] sched,time: fix irq time accounting with nohz_idle

Show all headers | View raw

Currently irq time accounting only works in these cases:
1) purely ticke based accounting
2) nohz_full accounting, but only on housekeeping & nohz_full CPUs
3) architectures with native vtime accounting

On nohz_idle CPUs, which are probably the majority nowadays,
irq time accounting is currently broken. This leads to systems
reporting a dramatically lower amount of irq & softirq time than
is actually spent handling them, with all the time spent while the
system is in the idle task being accounted as idle.

This patch set seems to bring the amount of irq time reported by
top (and /proc/stat) roughly in line with that measured when I do
a "perf record -g -a" run to see what is using all that time.

The amount of irq time used, especially softirq, is shockingly high,
to the point of me thinking this patch set may be wrong, but the
numbers seem to match what perf is giving me...

These patches apply on top of Wanpeng Li's steal time patches.

CONFIG_IRQ_TIME_ACCOUNTING is now a config option that is available
as a separate choice from tick based / nohz_idle / nohz_full mode,
a suggested by Frederic Weisbecker.

Next up: look at the things that are using CPU time on an otherwise
idle system, and see if I can make those a little faster :)

v2: address Peterz's concerns, some more cleanups
v3: rewrite the code along Frederic's suggestions, now cputime_t
    is used everywhere

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

[PATCH v3 0/4] sched,time: fix irq time accounting with nohz_idle riel@redhat.com - 2016-06-30 21:40 +0200
  [PATCH 2/4] nohz,cputime: replace VTIME_GEN irq time code with IRQ_TIME_ACCOUNTING code riel@redhat.com - 2016-06-30 21:40 +0200
  [PATCH 1/4] sched,time: count actually elapsed irq & softirq time riel@redhat.com - 2016-06-30 21:40 +0200
    Re: [PATCH 1/4] sched,time: count actually elapsed irq & softirq time Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-05 14:50 +0200
      Re: [PATCH 1/4] sched,time: count actually elapsed irq & softirq  time Rik van Riel <riel@redhat.com> - 2016-07-05 15:20 +0200
        Re: [PATCH 1/4] sched,time: count actually elapsed irq & softirq time Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-05 16:10 +0200
      [PATCH v3 1/4] sched,time: count actually elapsed irq & softirq  time Rik van Riel <riel@redhat.com> - 2016-07-05 18:50 +0200
        Re: [PATCH v3 1/4] sched,time: count actually elapsed irq & softirq  time Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-06 16:20 +0200
  Re: [PATCH v3 0/4] sched,time: fix irq time accounting with nohz_idle Nikolay Borisov <kernel@kyup.com> - 2016-07-05 15:10 +0200
    Re: [PATCH v3 0/4] sched,time: fix irq time accounting with  nohz_idle Rik van Riel <riel@redhat.com> - 2016-07-05 15:20 +0200

csiph-web