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


Groups > linux.kernel > #1742037 > unrolled thread

Re: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from idle

Started byQuan Xu <quan.xu0@gmail.com>
First post2017-09-29 12:30 +0200
Last post2017-09-29 12:30 +0200
Articles 1 — 1 participant

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from  idle Quan Xu <quan.xu0@gmail.com> - 2017-09-29 12:30 +0200

#1742037 — Re: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from idle

FromQuan Xu <quan.xu0@gmail.com>
Date2017-09-29 12:30 +0200
SubjectRe: [RFC PATCH v2 7/7] sched/idle: update poll time when wakeup from idle
Message-ID<uv0Ip-4Vn-9@gated-at.bofh.it>

On 2017/8/29 20:46, Peter Zijlstra wrote:
> On Tue, Aug 29, 2017 at 11:46:41AM +0000, Yang Zhang wrote:
>> In ttwu_do_wakeup, it will update avg_idle when wakeup from idle. Here
>> we just reuse this logic to update the poll time. It may be a little
>> late to update the poll in ttwu_do_wakeup, but the test result shows no
>> obvious performance gap compare with updating poll in irq handler.
>>
>> one problem is that idle_stamp only used when using CFS scheduler. But
>> it is ok since it is the default policy for scheduler and only consider
>> it should enough.
>>
>> Signed-off-by: Yang Zhang <yang.zhang.wz@gmail.com>
>> Signed-off-by: Quan Xu <quan.xu0@gmail.com>
> Same broken SoB chain, and not a useful word on why you need to adjust
> this crap to begin with. What you want that poll duration to be related
> to is the cost of a VMEXIT/VMENTER cycle, not however long we happened
> to be idle.
>
> So no.

Peter,

I think you are right..

IIUC, the time we happened to be idle may contain a chain of 
VMEXIT/VMENTER cycles,
which would be mainly (except the last VMEXIT/VMENTER cycles) for just 
idle loops. right?

as you mentioned, poll duration to be related to is the cost of __a__ 
VMEXIT/VMENTER cycle.
howerver it is very difficult to measure a VMEXIT/VMENTER cycle 
accurately from
kvm guest, we could find out an approximate one -- dropping the idle 
loops from the
time we happened to be idle.. make sense?

Quan

[toc] | [standalone]


Back to top | Article view | linux.kernel


csiph-web