From: Christoph Hellwig <hch@lst.de>
To: Jens Axboe <axboe@kernel.dk>
Cc: Christoph Hellwig <hch@lst.de>,
Jeffle Xu <jefflexu@linux.alibaba.com>,
Ming Lei <ming.lei@redhat.com>,
Damien Le Moal <Damien.LeMoal@wdc.com>,
linux-block@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: Re: switch block layer polling to a bio based model
Date: Mon, 26 Apr 2021 17:06:38 +0200 [thread overview]
Message-ID: <20210426150638.GA24618@lst.de> (raw)
In-Reply-To: <2d229167-f56d-583b-569c-166c97ce2e71@kernel.dk>
On Mon, Apr 26, 2021 at 08:57:31AM -0600, Jens Axboe wrote:
> I was separately curious about this as I have a (as of yet unposted)
> patchset that recycles bio allocations, as we spend quite a bit of time
> doing that for high rate polled IO. It's good for taking the above 2.97M
> IOPS to 3.2-3.3M IOPS, and it'd obviously be a bit more problematic with
> required RCU freeing of bio's. Even without the alloc cache, using RCU
> will ruin any potential cache locality on back-to-back bio free + bio
> alloc.
That sucks indeed. How do you recycle the bios? If we make sure the
bio is only ever recycled as a bio and bi_bdev remaings valid long
enough we might not need the rcu free. Even without your recycling
we could probably do something nasty using SLAB_TYPESAFE_BY_RCU.
next prev parent reply other threads:[~2021-04-26 15:06 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-26 13:48 switch block layer polling to a bio based model Christoph Hellwig
2021-04-26 13:48 ` [PATCH 01/12] direct-io: remove blk_poll support Christoph Hellwig
2021-04-26 13:48 ` [PATCH 02/12] block: don't try to poll multi-bio I/Os in __blkdev_direct_IO Christoph Hellwig
2021-04-26 13:48 ` [PATCH 03/12] iomap: don't try to poll multi-bio I/Os in __iomap_dio_rw Christoph Hellwig
2021-04-26 13:48 ` [PATCH 04/12] blk-mq: factor out a "classic" poll helper Christoph Hellwig
2021-04-26 13:48 ` [PATCH 05/12] blk-mq: factor out a blk_qc_to_hctx helper Christoph Hellwig
2021-04-26 13:48 ` [PATCH 06/12] blk-mq: refactor hybrid polling Christoph Hellwig
2021-04-26 13:48 ` [PATCH 07/12] blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal Christoph Hellwig
2021-04-26 13:48 ` [PATCH 08/12] blk-mq: remove blk_qc_t_valid Christoph Hellwig
2021-04-26 13:48 ` [PATCH 09/12] block: rename REQ_HIPRI to REQ_POLLED Christoph Hellwig
2021-04-26 13:48 ` [PATCH 10/12] block: RCU free polled bios Christoph Hellwig
2021-04-26 13:48 ` [PATCH 11/12] block: define 'struct bvec_iter' as packed Christoph Hellwig
2021-04-26 13:48 ` [PATCH 12/12] block: switch polling to be bio based Christoph Hellwig
2021-04-26 15:27 ` Ming Lei
2021-04-26 14:57 ` switch block layer polling to a bio based model Jens Axboe
2021-04-26 15:06 ` Christoph Hellwig [this message]
2021-04-26 15:12 ` Jens Axboe
2021-04-26 16:15 ` Christoph Hellwig
2021-04-26 16:48 ` Jens Axboe
2021-04-26 17:05 ` Christoph Hellwig
2021-04-26 17:18 ` Jens Axboe
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=20210426150638.GA24618@lst.de \
--to=hch@lst.de \
--cc=Damien.LeMoal@wdc.com \
--cc=axboe@kernel.dk \
--cc=jefflexu@linux.alibaba.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=ming.lei@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).