From: "Dmitry V. Levin" <ldv@altlinux.org>
To: ALT Devel discussion list <devel@lists.altlinux.org>
Subject: Re: [devel] Ядра 4.19/5.4 и дисковый шедулер
Date: Sun, 22 Mar 2020 02:51:16 +0300
Message-ID: <20200321235116.GA26284@altlinux.org> (raw)
In-Reply-To: <fb6605f3-0b9d-cd3a-50ac-27609b8ce422@rosalinux.ru>
On Sun, Mar 22, 2020 at 02:32:01AM +0300, Mikhail Novosyolov wrote:
> 19.03.2020 23:26, Leonid Krivoshein пишет:
> > 19.03.2020 23:11, alexei@taf.ru пишет:
> >> Добрый день!
> >>
> >> Скажите, кто знает, а вот такая картина на ядрах, начиная с 4.19, нормальная?:
> >>
> >> # cat /sys/block/sda/queue/scheduler
> >> [none] bfq
> >>
> >> при том на 4.9 имеем такую картину:
> >>
> >> # cat /sys/block/sda/queue/scheduler
> >> noop [deadline]
> >
> > А /dev/sda то какой? Для NVME и некоторых SSD вообще лучше noop.
>
> В шляпе и в хуавей решили, что лучше bfq:
>
> https://gitee.com/src-openeuler/systemd/blob/master/0001-udev-use-bfq-as-the-default-scheduler.patch
Тут много познавательного написано на эту тему, почитайте:
https://github.com/systemd/systemd/pull/13321
> А для каких "некоторых" SSD лучше noop и почему?
"It is worth noting that there is little difference in throughput between
the mq-deadline/none/bfq I/O schedulers when using fast multi-queue SSD
configurations or fast NVME devices. In these cases it may be preferable
to use the 'none' I/O scheduler to reduce CPU overhead."
--
ldv
next prev parent reply other threads:[~2020-03-21 23:51 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-19 20:11 alexei
2020-03-19 20:26 ` Leonid Krivoshein
2020-03-19 20:35 ` Andrey Savchenko
2020-03-23 5:57 ` Alexey V. Vissarionov
2020-03-23 9:39 ` Andrey Savchenko
2020-03-23 12:28 ` Alexey V. Vissarionov
2020-03-23 13:18 ` Andrey Savchenko
2020-03-23 13:32 ` Sergey V Turchin
2020-03-23 15:02 ` Alexey V. Vissarionov
2020-03-24 6:30 ` Sergey V Turchin
2020-03-24 8:51 ` Anton Gorlov
2020-03-24 9:16 ` Sergey V Turchin
2020-03-24 17:42 ` Anton Gorlov
2020-03-23 13:40 ` Anton V. Boyarshinov
2020-03-23 13:52 ` Andrey Savchenko
2020-03-23 15:19 ` Alexey V. Vissarionov
2020-03-23 16:43 ` Andrey Savchenko
2020-03-21 23:32 ` Mikhail Novosyolov
2020-03-21 23:51 ` Dmitry V. Levin [this message]
2020-03-19 20:51 ` Konstantin Lepikhov
2020-03-19 20:56 ` Leonid Krivoshein
2020-03-19 21:03 ` alexei
2020-03-19 21:03 ` Leonid Krivoshein
2020-03-20 3:57 ` Anton Farygin
2020-03-20 4:10 ` Alexei Takaseev
2020-03-22 16:07 ` Sergey Y. Afonin
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=20200321235116.GA26284@altlinux.org \
--to=ldv@altlinux.org \
--cc=devel@lists.altlinux.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
ALT Linux Team development discussions
This inbox may be cloned and mirrored by anyone:
git clone --mirror http://lore.altlinux.org/devel/0 devel/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 devel devel/ http://lore.altlinux.org/devel \
devel@altlinux.org devel@altlinux.ru devel@lists.altlinux.org devel@lists.altlinux.ru devel@linux.iplabs.ru mandrake-russian@linuxteam.iplabs.ru sisyphus@linuxteam.iplabs.ru
public-inbox-index devel
Example config snippet for mirrors.
Newsgroup available over NNTP:
nntp://lore.altlinux.org/org.altlinux.lists.devel
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git