public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Jens Axboe <axboe@kernel.dk>
Cc: Chaitanya Kulkarni <chaitanyak@nvidia.com>,
	Saeed Mirzamohammadi <saeed.mirzamohammadi@oracle.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
	Ramanan Govindarajan <ramanan.govindarajan@oracle.com>,
	Sagi Grimberg <sagi@grimberg.me>,
	Paul Webb <paul.x.webb@oracle.com>,
	Christoph Hellwig <hch@lst.de>, Keith Busch <kbusch@kernel.org>
Subject: Re: [bug-report] 5-9% FIO randomwrite ext4 perf regression on 6.12.y kernel
Date: Thu, 21 Nov 2024 05:57:14 +0100	[thread overview]
Message-ID: <20241121045714.GA20680@lst.de> (raw)
In-Reply-To: <d6049cd0-5755-48ee-87af-eb928016f95b@kernel.dk>

On Wed, Nov 20, 2024 at 06:20:12PM -0700, Jens Axboe wrote:
> There's no way that commit is involved, the test as quoted doesn't even
> touch write zeroes. Hence if there really is a regression here, then
> it's either not easily bisectable, some error was injected while
> bisecting, or the test itself is bimodal.

ext4 actually has some weird lazy init code using write zeroes.  So
if the test actually wasn't a steady state one but only run for a short
time after init, and the mentioned commit dropped the intel hack for
deallocate as write zeroes it might actually make a difference.

To check for that do a :

/sys/block/nvmeXn1/queue/write_zeroes_max_bytes

with and without that commit.
 

  reply	other threads:[~2024-11-21  4:57 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-20 21:35 [bug-report] 5-9% FIO randomwrite ext4 perf regression on 6.12.y kernel Saeed Mirzamohammadi
2024-11-21  0:00 ` Chaitanya Kulkarni
2024-11-21  1:20   ` Jens Axboe
2024-11-21  4:57     ` Christoph Hellwig [this message]
2024-11-21 14:48       ` Jens Axboe
2024-11-21 11:30     ` Phil Auld
2024-11-21 14:49       ` Jens Axboe
     [not found]         ` <181bcb70-e0bf-4024-80b7-e79276d6eaf7@oracle.com>
2024-11-21 21:19           ` [External] : " Phil Auld
2024-11-22 12:13           ` Christoph Hellwig
2024-11-22 17:18             ` Paul Webb
2024-11-22 18:26               ` Saeed Mirzamohammadi
2024-11-22 21:09                 ` Keith Busch
2024-11-25  6:46                   ` Christoph Hellwig
2024-11-25 18:28                   ` Saeed Mirzamohammadi
2024-11-26  4:55                     ` Christoph Hellwig
2024-11-26 18:06                       ` Saeed Mirzamohammadi
2024-11-26 18:09                         ` Christoph Hellwig
2024-11-26 18:13                           ` Saeed Mirzamohammadi
2024-11-22 17:13         ` Paul Webb

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=20241121045714.GA20680@lst.de \
    --to=hch@lst.de \
    --cc=axboe@kernel.dk \
    --cc=chaitanyak@nvidia.com \
    --cc=kbusch@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=paul.x.webb@oracle.com \
    --cc=ramanan.govindarajan@oracle.com \
    --cc=saeed.mirzamohammadi@oracle.com \
    --cc=sagi@grimberg.me \
    /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