All of
 help / color / mirror / Atom feed
From: Jens Axboe <>
Cc: Andrew Morton <>,,,
Subject: Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads
Date: Wed, 10 Feb 2021 07:47:49 -0700	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

On 2/10/21 1:07 AM, Sedat Dilek wrote:
> On Tue, Feb 9, 2021 at 10:25 PM Jens Axboe <> wrote:
>> On 2/9/21 12:55 PM, Andrew Morton wrote:
>>> On Mon,  8 Feb 2021 19:30:05 -0700 Jens Axboe <> wrote:
>>>> Hi,
>>>> For v1, see:
>>>> tldr; don't -EAGAIN IOCB_NOWAIT dio reads just because we have page cache
>>>> entries for the given range. This causes unnecessary work from the callers
>>>> side, when the IO could have been issued totally fine without blocking on
>>>> writeback when there is none.
>>> Seems a good idea.  Obviously we'll do more work in the case where some
>>> writeback needs doing, but we'll be doing synchronous writeout in that
>>> case anyway so who cares.
>> Right, I think that'll be a round two on top of this, so we can make the
>> write side happier too. That's a bit more involved...
>>> Please remind me what prevents pages from becoming dirty during or
>>> immediately after the filemap_range_needs_writeback() check?  Perhaps
>>> filemap_range_needs_writeback() could have a comment explaining what it
>>> is that keeps its return value true after it has returned it!
>> It's inherently racy, just like it is now. There's really no difference
>> there, and I don't think there's a way to close that. Even if you
>> modified filemap_write_and_wait_range() to be non-block friendly,
>> there's nothing stopping anyone from adding dirty page cache right after
>> that call.
> Jens, do you have some numbers before and after your patchset is applied?

I don't, the load was pretty light for the test case - it was just doing
33-34K of O_DIRECT 4k random reads in a pretty small range of the device.
When you end up having page cache in that range, that means you end up
punting a LOT of requests to the async worker. So it wasn't as much a
performance win for this particular case, but an efficiency win. You get
rid of a worker using 40% CPU, and reduce the latencies.

> And kindly a test "profile" for FIO :-)?

To reproduce this, have a small range dio rand reads and then have
something else that does a few buffered reads from the same range.

Jens Axboe

      reply	other threads:[~2021-02-10 14:48 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-09  2:30 Jens Axboe
2021-02-09  2:30 ` [PATCH 1/3] mm: provide filemap_range_needs_writeback() helper Jens Axboe
2021-02-09  7:47   ` Christoph Hellwig
2021-02-09 14:30     ` Jens Axboe
2021-02-09  2:30 ` [PATCH 2/3] mm: use filemap_range_needs_writeback() for O_DIRECT reads Jens Axboe
2021-02-09  7:48   ` Christoph Hellwig
2021-02-09 14:27     ` Jens Axboe
2021-02-09  2:30 ` [PATCH 3/3] iomap: " Jens Axboe
2021-02-09  7:51   ` Christoph Hellwig
2021-02-09 14:29     ` Jens Axboe
2021-02-09 19:55 ` [PATCHSET v2 0/3] Improve IOCB_NOWAIT " Andrew Morton
2021-02-09 20:11   ` Jens Axboe
2021-02-10  8:07     ` Sedat Dilek
2021-02-10  8:07       ` Sedat Dilek
2021-02-10 14:47       ` Jens Axboe [this message]

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \ \ \ \
    --subject='Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads' \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

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.