linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christian Marie <christian@ponies.io>
To: linux-mm@kvack.org
Subject: Re: isolate_freepages_block and excessive CPU usage by OSD process
Date: Fri, 5 Dec 2014 16:50:47 +1100	[thread overview]
Message-ID: <20141205055047.GA18326@cucumber.syd4.anchor.net.au> (raw)
In-Reply-To: <5480EE9D.1050503@suse.cz>

[-- Attachment #1: Type: text/plain, Size: 644 bytes --]

On Fri, Dec 05, 2014 at 12:30:37AM +0100, Vlastimil Babka wrote:
> Oh, I would think that if you can't allocate single pages, then there's
> little wonder that compaction also spends all its time looking for single
> free pages. Did that happen just now for the single page allocations,
> or was it always the case?

This has always been the case with the default min_free_pages and given enough
pressure for enough time. I have just been hoping that compaction should
be "smart" enough to lest reclaim do its stuff quickly if single page
allocations are failing.

Raising min_free_kbytes makes these 0 order allocations failures never happen.

[-- Attachment #2: Type: application/pgp-signature, Size: 819 bytes --]

  reply	other threads:[~2014-12-05  5:50 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CABYiri-do2YdfBx=r+u1kwXkEwN4v+yeRSHB-ODXo4gMFgW-Fg.mail.gmail.com>
2014-11-19  1:21 ` Christian Marie
2014-11-19 18:03   ` Andrey Korolyov
2014-11-19 21:20     ` Christian Marie
2014-11-19 23:10       ` Vlastimil Babka
2014-11-19 23:49         ` Andrey Korolyov
2014-11-20  3:30         ` Christian Marie
2014-11-21  2:35         ` Christian Marie
2014-11-23  9:33           ` Christian Marie
2014-11-24 21:48             ` Andrey Korolyov
2014-11-28  8:03               ` Joonsoo Kim
2014-11-28  9:26                 ` Vlastimil Babka
2014-12-01  8:31                   ` Joonsoo Kim
2014-12-02  1:47                     ` Christian Marie
2014-12-02  4:53                       ` Joonsoo Kim
2014-12-02  5:06                         ` Christian Marie
2014-12-03  4:04                           ` Christian Marie
2014-12-03  8:05                             ` Joonsoo Kim
2014-12-04 23:30                             ` Vlastimil Babka
2014-12-05  5:50                               ` Christian Marie [this message]
2014-12-03  7:57                           ` Joonsoo Kim
2014-12-04  7:30                             ` Christian Marie
2014-12-04  7:51                               ` Christian Marie
2014-12-05  1:07                               ` Joonsoo Kim
2014-12-05  5:55                                 ` Christian Marie
2014-12-08  7:19                                   ` Joonsoo Kim
2014-12-10 15:06                                 ` Vlastimil Babka
2014-12-11  3:08                                   ` Joonsoo Kim
2014-12-02 15:46                         ` Vlastimil Babka
2014-12-03  7:49                           ` Joonsoo Kim
2014-12-03 12:43                             ` Vlastimil Babka
2014-12-04  6:53                               ` Joonsoo Kim
2014-11-15 11:48 Andrey Korolyov
2014-11-15 16:32 ` Vlastimil Babka
2014-11-15 17:10   ` Andrey Korolyov
2014-11-15 18:45     ` Vlastimil Babka
2014-11-15 18:52       ` Andrey Korolyov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20141205055047.GA18326@cucumber.syd4.anchor.net.au \
    --to=christian@ponies.io \
    --cc=linux-mm@kvack.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox