From: Mel Gorman <mgorman@techsingularity.net>
To: howaboutsynergy@protonmail.com
Cc: Andrew Morton <akpm@linux-foundation.org>,
"bugzilla-daemon@bugzilla.kernel.org"
<bugzilla-daemon@bugzilla.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>
Subject: Re: [Bug 204165] New: 100% CPU usage in compact_zone_order
Date: Tue, 16 Jul 2019 08:11:21 +0100 [thread overview]
Message-ID: <20190716071121.GA24383@techsingularity.net> (raw)
In-Reply-To: <EDGpMqBME0-wqL8JuVQeCbXEy1lZkvqS0XMvMj6Z_OFhzyK5J6qXWAgNUCxrcgVLmZVlqMH-eRJrqOCxb1pct39mDyFMcWhIw1ZUTAVXr2o=@protonmail.com>
On Tue, Jul 16, 2019 at 03:57:30AM +0000, howaboutsynergy@protonmail.com wrote:
> > PID: 21120 TASK: ffff8fd7f10ddac0 CPU: 9 COMMAND: "stress"
> > START: __schedule at ffffffff987f5a0c
> > [ffff9cb9a9f57928] isolate_migratepages_block at ffffffff981b35c6
> > [ffff9cb9a9f57950] isolate_migratepages_block at ffffffff981b37bd
> > [ffff9cb9a9f57a10] compact_zone at ffffffff981b4c07
> > [ffff9cb9a9f57ab8] compact_zone_order at ffffffff981b51de
> > [ffff9cb9a9f57b78] try_to_compact_pages at ffffffff981b5a17
> > [ffff9cb9a9f57bd8] __alloc_pages_direct_compact at ffffffff981d95a7
> > [ffff9cb9a9f57c30] __alloc_pages_slowpath at ffffffff981d99ee
> > [ffff9cb9a9f57cd0] release_pages at ffffffff9819aa08
> > [ffff9cb9a9f57d00] __pagevec_lru_add_fn at ffffffff9819ada9
> > [ffff9cb9a9f57d40] __alloc_pages_nodemask at ffffffff981da668
> > [ffff9cb9a9f57da0] do_huge_pmd_anonymous_page at ffffffff98202c01
> > [ffff9cb9a9f57df0] __handle_mm_fault at ffffffff981bfa4c
> > [ffff9cb9a9f57ea0] handle_mm_fault at ffffffff981c01f9
> > [ffff9cb9a9f57ec8] __do_page_fault at ffffffff9803d5c7
> > [ffff9cb9a9f57f28] do_page_fault at ffffffff9803d85d
> > [ffff9cb9a9f57f48] page_fault at ffffffff98800de8
> > [ffff9cb9a9f57f50] page_fault at ffffffff98800dfe
> > RIP: 00005879fc8c4c10 RSP: 00007ffd393aa0d0 RFLAGS: 00010206
> > RAX: 0000000010b8a000 RBX: 0000714104876010 RCX: 0000714358a5a3db
> > RDX: 0000000000000000 RSI: 00000002540bf000 RDI: 0000714104876000
> > RBP: 00005879fc8c5a54 R8: 0000714104876010 R9: 0000000000000000
> > R10: 0000000000000022 R11: 00000002540be400 R12: ffffffffffffffff
> > R13: 0000000000000002 R14: 0000000000001000 R15: 00000002540be400
> > ORIG_RAX: ffffffffffffffff CS: 0033 SS: 002b
> > crash>
High CPU usage in this path is not something I've observed recently.
When it happens and CPU usage is high, can you run the following commands
please?
trace-cmd record -e compaction:* sleep 10
trace-cmd report > trace.log
and send me the resulting trace.log please?
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2019-07-16 7:17 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <bug-204165-27@https.bugzilla.kernel.org/>
2019-07-15 21:25 ` Andrew Morton
2019-07-15 23:28 ` howaboutsynergy
2019-07-16 1:52 ` howaboutsynergy
2019-07-16 3:25 ` howaboutsynergy
2019-07-16 3:57 ` howaboutsynergy
2019-07-16 7:11 ` Mel Gorman [this message]
2019-07-16 19:15 ` howaboutsynergy
2019-07-17 17:53 ` Mel Gorman
2019-07-17 22:00 ` howaboutsynergy
2019-07-18 8:37 ` Mel Gorman
2019-07-16 10:03 ` Mel Gorman
2019-07-16 1:08 ` howaboutsynergy
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=20190716071121.GA24383@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=akpm@linux-foundation.org \
--cc=bugzilla-daemon@bugzilla.kernel.org \
--cc=howaboutsynergy@protonmail.com \
--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