[PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
[PATCH 1/3] mm: provide filemap_range_needs_writeback() helper · Jens Axboe <axboe@kernel.dk> · 2021-02-09
Re: [PATCH 1/3] mm: provide filemap_range_needs_writeback() helper · Christoph Hellwig <hch@infradead.org> · 2021-02-09
Re: [PATCH 1/3] mm: provide filemap_range_needs_writeback() helper · Jens Axboe <axboe@kernel.dk> · 2021-02-09
[PATCH 2/3] mm: use filemap_range_needs_writeback() for O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
Re: [PATCH 2/3] mm: use filemap_range_needs_writeback() for O_DIRECT reads · Christoph Hellwig <hch@infradead.org> · 2021-02-09
Re: [PATCH 2/3] mm: use filemap_range_needs_writeback() for O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
[PATCH 3/3] iomap: use filemap_range_needs_writeback() for O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
Re: [PATCH 3/3] iomap: use filemap_range_needs_writeback() for O_DIRECT reads · Christoph Hellwig <hch@infradead.org> · 2021-02-09
Re: [PATCH 3/3] iomap: use filemap_range_needs_writeback() for O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads · Andrew Morton <akpm@linux-foundation.org> · 2021-02-09
Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-09
Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads · Sedat Dilek <hidden> · 2021-02-10
Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads · Jens Axboe <axboe@kernel.dk> · 2021-02-10

Re: [PATCHSET v2 0/3] Improve IOCB_NOWAIT O_DIRECT reads

From: Andrew Morton <akpm@linux-foundation.org>
Date: 2021-02-09 21:21:45
Also in: linux-fsdevel

On Mon,  8 Feb 2021 19:30:05 -0700 Jens Axboe [off-list ref] wrote:

Hi,

For v1, see:

https://lore.kernel.org/linux-fsdevel/20210208221829.17247-1-axboe@kernel.dk/ (local)

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.

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!

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help