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


Groups > linux.kernel > #1502852

Re: [PATCH] bdi flusher should not be throttled here when it fall into buddy slow path

From Mel Gorman <mgorman@techsingularity.net>
Newsgroups linux.kernel
Subject Re: [PATCH] bdi flusher should not be throttled here when it fall into buddy slow path
Date 2016-10-18 12:00 +0200
Message-ID <stzlD-8kr-17@gated-at.bofh.it> (permalink)
References <stx0t-70j-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On Tue, Oct 18, 2016 at 03:12:45PM +0800, zhouxianrong@huawei.com wrote:
> From: z00281421 <z00281421@notesmail.huawei.com>
> 
> bdi flusher may enter page alloc slow path due to writepage and kmalloc. 
> in that case the flusher as a direct reclaimer should not be throttled here
> because it can not to reclaim clean file pages or anaonymous pages
> for next moment; furthermore writeback rate of dirty pages would be
> slow down and other direct reclaimers and kswapd would be affected.
> bdi flusher should be iosceduled by get_request rather than here.
> 
> Signed-off-by: z00281421 <z00281421@notesmail.huawei.com>

What does this patch do that PF_LESS_THROTTLE is not doing already if
there is an underlying BDI?

There have been a few patches like this recently that look like they might
do something useful but are subtle. They really should be accompanied by
a test case and data showing they either fix a functional issue (machine
livelocking due to writeback not making progress) or a performance issue.

-- 
Mel Gorman
SUSE Labs

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


Thread

[PATCH] bdi flusher should not be throttled here when it fall into buddy slow path <zhouxianrong@huawei.com> - 2016-10-18 09:30 +0200
  Re: [PATCH] bdi flusher should not be throttled here when it fall into buddy slow path "Hillf Danton" <hillf.zj@alibaba-inc.com> - 2016-10-18 11:40 +0200
  Re: [PATCH] bdi flusher should not be throttled here when it fall  into buddy slow path Mel Gorman <mgorman@techsingularity.net> - 2016-10-18 12:00 +0200
    Re: [PATCH] bdi flusher should not be throttled here when it fall  into buddy slow path zhouxianrong <zhouxianrong@huawei.com> - 2016-10-18 13:20 +0200
      Re: [PATCH] bdi flusher should not be throttled here when it fall  into buddy slow path Michal Hocko <mhocko@kernel.org> - 2016-10-18 13:50 +0200
  [PATCH] bdi flusher should not be throttled here when it fall into buddy slow path <zhouxianrong@huawei.com> - 2016-10-20 14:50 +0200
    Re: [PATCH] bdi flusher should not be throttled here when it fall  into buddy slow path Michal Hocko <mhocko@kernel.org> - 2016-10-20 15:30 +0200

csiph-web