Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1439517
| From | Paolo Bonzini <pbonzini@redhat.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq |
| Date | 2016-07-08 16:40 +0200 |
| Message-ID | <rSF6F-60Q-27@gated-at.bofh.it> (permalink) |
| References | <rPPYB-58Z-9@gated-at.bofh.it> <rPPYB-58Z-11@gated-at.bofh.it> <rSDex-4Mm-5@gated-at.bofh.it> <rSE0V-5l8-13@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
[Multipart message — attachments visible in raw view] - view raw
On 08/07/2016 15:19, Rik van Riel wrote: > On Fri, 2016-07-08 at 14:30 +0200, Frederic Weisbecker wrote: >> On Thu, Jun 30, 2016 at 03:35:50PM -0400, riel@redhat.com wrote: >>> From: Rik van Riel <riel@redhat.com> >>> >>> Drop local_irq_save/restore from irqtime_account_irq. >>> Instead, have softirq and hardirq track their time spent >>> independently, with the softirq code subtracting hardirq >>> time that happened during the duration of the softirq run. >>> >>> The softirq code can be interrupted by hardirq code at >>> any point in time, but it can check whether it got a >>> consistent snapshot of the timekeeping variables it wants, >>> and loop around in the unlikely case that it did not. >>> >>> Signed-off-by: Rik van Riel <riel@redhat.com> >> >> So the purpose is to get rid of local_irq_save/restore()? >> Is it really worth such complication? > > local_irq_save/restore are quite slow, and look like the > largest source of overhead in irq time accounting. I'm looking at an upstream tree, without your patches applied, but it seems to me that irqtime_account_irq is always called with interrupts disabled: irqtime_account_irq -> account_irq_enter_time -> __irq_enter -> HARDIRQ_ENTER [1] -> irq_enter [3] -> __do_softirq [1] -> account_irq_exit_time -> __do_softirq [1] -> __irq_exit -> HARDIRQ_EXIT [1] -> irq_exit [2] [1] = does local_irq_disable/enable [2] = contains WARN_ON_ONCE(!irqs_disabled()) [3] = calls rcu_irq_enter(), which checks irqs_disabled() I don't think your first two patches change this, so perhaps it's enough to remove that local_irq-save/restore? Either this, or ENEEDWEEKEND... Paolo
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq riel@redhat.com - 2016-06-30 21:40 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-08 14:40 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Rik van Riel <riel@redhat.com> - 2016-07-08 15:30 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-08 16:10 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Paolo Bonzini <pbonzini@redhat.com> - 2016-07-08 16:40 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Rik van Riel <riel@redhat.com> - 2016-07-08 18:00 +0200
Re: [PATCH 4/4] irqtime: drop local_irq_save/restore from irqtime_account_irq Frederic Weisbecker <fweisbec@gmail.com> - 2016-07-09 02:00 +0200
csiph-web