From: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com>
To: Dave Chinner <david@fromorbit.com>
Cc: "linux-xfs@vger.kernel.org" <linux-xfs@vger.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>
Subject: Re: freezing system for several second on high I/O [kernel 4.15]
Date: Fri, 16 Feb 2018 00:02:28 +0500 [thread overview]
Message-ID: <CABXGCsOpJU4WU2w5DYBA+Q1nquh14zN0oCW6OfCbhTOFYLwO5w@mail.gmail.com> (raw)
In-Reply-To: <20180215054436.GN7000@dastard>
On 15 February 2018 at 10:44, Dave Chinner <david@fromorbit.com> wrote:
> I've already explained that we can't annotate these memory
> allocations to turn off the false positives because that will also
> turning off all detection of real deadlock conditions. Lockdep has
> many, many limitations, and this happens to be one of them.
>
> FWIW, is there any specific reason you running lockdep on your
> desktop system?
Because I wanna make open source better (help fixing all freezing)
>
> I think I've already explained that, too. The graphics subsystem -
> which is responsible for updating the cursor - requires memory
> allocation. The machine is running low on memory, so it runs memory
> reclaim, which recurses back into the filesystem and blocks waiting
> for IO to be completed (either writing dirty data pages or flushing
> dirty metadata) so it can free memory.
Which means machine is running low on memory?
How many memory needed?
$ free -h
total used free shared buff/cache available
Mem: 30G 17G 2,1G 1,4G 10G 12G
Swap: 59G 0B 59G
As can we see machine have 12G available memory. Is this means low memory?
> IOWs, your problems all stem from long IO latencies caused by the
> overloaded storage subsystem - they are propagate to all
> aspects of the OS via direct memory reclaim blocking on IO....
I'm surprised that no QOS analog for disk I/O.
This is reminiscent of the situation in past where a torrent client
clogs the entire channel on the cheap router and it causes problems
with opening web pages. In nowadays it never happens with modern
routers even with overloaded network channel are possible video calls
.
In 2018 my personaly expectation that user can run any set of
applications on computer and this never shoudn't harm system.
--
Best Regards,
Mike Gavrilov.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2018-02-15 19:02 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-30 18:40 mikhail
2018-01-31 2:22 ` Dave Chinner
2018-02-05 3:25 ` mikhail
2018-02-06 3:47 ` mikhail
2018-02-06 6:08 ` Dave Chinner
2018-02-06 7:12 ` Mikhail Gavrilov
2018-02-07 3:40 ` mikhail
2018-02-07 6:55 ` Dave Chinner
2018-02-10 9:34 ` mikhail
2018-02-10 9:35 ` mikhail
2018-02-11 22:56 ` Dave Chinner
2018-02-14 21:27 ` mikhail
2018-02-14 21:52 ` Dave Chinner
2018-02-15 3:40 ` mikhail
2018-02-15 3:42 ` mikhail
2018-02-15 3:46 ` Matthew Wilcox
2018-02-15 5:44 ` Dave Chinner
2018-02-15 19:02 ` Mikhail Gavrilov [this message]
2018-02-15 21:48 ` Dave Chinner
2018-02-18 14:02 ` Mikhail Gavrilov
2018-02-19 5:02 ` Dave Chinner
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=CABXGCsOpJU4WU2w5DYBA+Q1nquh14zN0oCW6OfCbhTOFYLwO5w@mail.gmail.com \
--to=mikhail.v.gavrilov@gmail.com \
--cc=david@fromorbit.com \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.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