From: Linus Torvalds <torvalds@linux-foundation.org>
To: Michael Larabel <Michael@michaellarabel.com>
Cc: "Ted Ts'o" <tytso@google.com>,
Andreas Dilger <adilger.kernel@dilger.ca>,
Ext4 Developers List <linux-ext4@vger.kernel.org>
Subject: Re: Kernel Benchmarking
Date: Fri, 11 Sep 2020 09:19:57 -0700 [thread overview]
Message-ID: <CAHk-=whP-7Uw9WgWgjRgF1mCg+NnkOPpWjVw+a9M3F9C52DrVg@mail.gmail.com> (raw)
In-Reply-To: <0cbc959e-1b8d-8d7e-1dc6-672cf5b3899a@MichaelLarabel.com>
On Fri, Sep 11, 2020 at 6:42 AM Michael Larabel
<Michael@michaellarabel.com> wrote:
>
> From preliminary testing of the patch on a Threadripper box, the EXT4 locking patch did help with a small improvement at 10 concurrent users for Apache but all the higher counts didn't end up showing any real change with the patch.
Ok, it's probably simply that fairness is really bad for performance
here in general, and that special case is just that - a special case,
not the main issue.
I'll have to think about it. We've certainly seen this before (the
queued spinlocks brought the same fairness issues), but this is much
worse because of how it affects scheduling on a big level.
Some middle ground hybrid model (unfair in the common case, but with
at least _some_ measure of fairness for the worst-case situation to
avoid the worst-case latency spikes) would be best, but I don't see
how to do it.
Linus
Linus
Linus
next prev parent reply other threads:[~2020-09-11 16:20 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CAHk-=wiZnE409WkTOG6fbF_eV1LgrHBvMtyKkpTqM9zT5hpf9A@mail.gmail.com>
[not found] ` <4ced9401-de3d-b7c9-9976-2739e837fafc@MichaelLarabel.com>
[not found] ` <CAHk-=wj+Qj=wXByMrAx3T8jmw=soUetioRrbz6dQaECx+zjMtg@mail.gmail.com>
[not found] ` <CAHk-=wgOPjbJsj-LeLc-JMx9Sz9DjGF66Q+jQFJROt9X9utdBg@mail.gmail.com>
[not found] ` <CAHk-=wjjK7PTnDZNi039yBxSHtAqusFoRrZzgMNTiYkJYdNopw@mail.gmail.com>
[not found] ` <aa90f272-1186-f9e1-8fdb-eefd332fdae8@MichaelLarabel.com>
[not found] ` <CAHk-=wh_31_XBNHbdF7EUJceLpEpwRxVF+_1TONzyBUym6Pw4w@mail.gmail.com>
[not found] ` <e24ef34d-7b1d-dd99-082d-28ca285a79ff@MichaelLarabel.com>
[not found] ` <CAHk-=wgEE4GuNjcRaaAvaS97tW+239-+tjcPjTq2FGhEuM8HYg@mail.gmail.com>
[not found] ` <6e1d8740-2594-c58b-ff02-a04df453d53c@MichaelLarabel.com>
[not found] ` <CAHk-=wgJ3-cEkU-5zXFPvRCHKkCCuKxVauYWGphjePEhJJgtgQ@mail.gmail.com>
[not found] ` <d2023f4c-ef14-b877-b5bb-e4f8af332abc@MichaelLarabel.com>
[not found] ` <CAHk-=wiz=J=8mJ=zRG93nuJ9GtQAm5bSRAbWJbWZuN4Br38+EQ@mail.gmail.com>
2020-09-11 0:05 ` Kernel Benchmarking Linus Torvalds
2020-09-11 0:49 ` Michael Larabel
2020-09-11 2:20 ` Linus Torvalds
[not found] ` <0cbc959e-1b8d-8d7e-1dc6-672cf5b3899a@MichaelLarabel.com>
2020-09-11 16:19 ` Linus Torvalds [this message]
2020-09-11 22:07 ` Linus Torvalds
2020-09-11 22:37 ` Michael Larabel
2020-09-12 7:28 ` Amir Goldstein
2020-09-12 10:32 ` Michael Larabel
2020-09-12 14:37 ` Matthew Wilcox
2020-09-12 14:44 ` Michael Larabel
2020-09-15 3:32 ` Matthew Wilcox
2020-09-15 10:39 ` Jan Kara
2020-09-15 13:52 ` Matthew Wilcox
[not found] ` <658ae026-32d9-0a25-5a59-9c510d6898d5@MichaelLarabel.com>
2020-09-14 17:47 ` Linus Torvalds
2020-09-14 20:21 ` Matthieu Baerts
2020-09-14 20:53 ` Linus Torvalds
2020-09-15 0:42 ` Linus Torvalds
2020-09-15 15:34 ` Matthieu Baerts
2020-09-15 18:27 ` Linus Torvalds
2020-09-15 18:47 ` Linus Torvalds
2020-09-15 19:26 ` Matthieu Baerts
2020-09-15 19:32 ` Linus Torvalds
2020-09-15 19:56 ` Matthieu Baerts
2020-09-15 23:35 ` Linus Torvalds
2020-09-16 10:34 ` Jan Kara
2020-09-16 18:47 ` Linus Torvalds
[not found] ` <9a92bf16-02c5-ba38-33c7-f350588ac874@tessares.net>
2020-09-15 19:24 ` Linus Torvalds
2020-09-15 19:38 ` Matthieu Baerts
2020-09-15 18:31 ` Linus Torvalds
2020-09-15 14:21 ` Michael Larabel
2020-09-15 17:52 ` Linus Torvalds
2020-09-17 17:51 ` Linus Torvalds
2020-09-17 18:23 ` Matthew Wilcox
2020-09-17 18:30 ` Linus Torvalds
2020-09-17 18:50 ` Matthew Wilcox
2020-09-17 19:00 ` Linus Torvalds
2020-09-17 19:27 ` Matthew Wilcox
2020-09-17 19:47 ` Linus Torvalds
2020-09-18 0:39 ` Sedat Dilek
2020-09-18 0:40 ` Sedat Dilek
2020-09-18 20:25 ` Sedat Dilek
2020-09-20 17:06 ` Linus Torvalds
2020-09-20 17:14 ` Sedat Dilek
2020-09-20 17:40 ` Linus Torvalds
2020-09-20 18:00 ` Sedat Dilek
2020-09-20 23:23 ` Dave Chinner
2020-09-20 23:31 ` Linus Torvalds
2020-09-20 23:40 ` Linus Torvalds
2020-09-21 1:20 ` Dave Chinner
2020-09-12 15:53 ` Matthew Wilcox
2020-09-12 17:59 ` Linus Torvalds
2020-09-12 20:32 ` Rogério Brito
2020-09-14 9:33 ` Jan Kara
2020-09-12 20:58 ` Josh Triplett
2020-09-12 20:59 ` James Bottomley
2020-09-12 21:15 ` Linus Torvalds
2020-09-12 22:32 ` Matthew Wilcox
2020-09-13 0:40 ` Dave Chinner
2020-09-13 2:39 ` Linus Torvalds
2020-09-13 3:40 ` Matthew Wilcox
2020-09-13 23:45 ` Dave Chinner
2020-09-14 3:31 ` Matthew Wilcox
2020-09-15 14:28 ` Chris Mason
2020-09-15 9:27 ` Jan Kara
2020-09-13 3:18 ` Matthew Wilcox
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='CAHk-=whP-7Uw9WgWgjRgF1mCg+NnkOPpWjVw+a9M3F9C52DrVg@mail.gmail.com' \
--to=torvalds@linux-foundation.org \
--cc=Michael@michaellarabel.com \
--cc=adilger.kernel@dilger.ca \
--cc=linux-ext4@vger.kernel.org \
--cc=tytso@google.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.