From: Arnd Bergmann <arnd-r2nGTMty4D4@public.gmane.org>
To: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Cc: Sagi Grimberg
<sagig-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>,
viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org,
axboe-b10kYP2dOMg@public.gmane.org,
milosz-B5zB6C1i6pkAvxtiuMwx3w@public.gmane.org,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: selective block polling and preadv2/pwritev2 revisited V3
Date: Thu, 03 Mar 2016 16:52:55 +0100 [thread overview]
Message-ID: <2369295.6CpmrvqZVS@wuerfel> (raw)
In-Reply-To: <20160303151116.GA24614-jcswGhMUV9g@public.gmane.org>
On Thursday 03 March 2016 16:11:16 Christoph Hellwig wrote:
>
> This series allows to selectively enable/disable polling for completions
> in the block layer on a per-I/O basis. For this it resurrects the
> preadv2/pwritev2 syscalls that Milosz prepared a while ago (and which
> are much simpler now due to VFS changes that happened in the meantime).
> That approach also had a man page update prepared, which I will resubmit
> with the current flags once this series makes it in.
>
> Polling for block I/O is important to reduce the latency on flash and
> post-flash storage technologies. On the fastest NVMe controller I have
> access to it almost halves latencies from over 7 microseconds to about 4
> microseonds. But it only is usesful if we actually care for the latency
> of this particular I/O, and generally is a waste if enabled for all I/O
> to a given device. This series uses the per-I/O flags in preadv2/pwritev2
> to control this behavior. The alternative would be a new O_* flag set
> at open time or using fcntl, but this is still to corse-grained for some
> applications and we're starting to run out out of open flags.
>
> Note that there are plenty of other use cases for preadv2/pwritev2 as well,
> but I'd like to concentrate on this one for now. Example are: non-blocking
> reads (the original purpose), per-I/O O_SYNC, user space support for T10
> DIF/DIX applications tags and probably some more.
If we decide to revise the asm-generic/unistd.h system call list
for future architecture ports, can the syscalls replace all of
read/write/readv/writev/pread64/write64/preadv/pwritev, or would
it be better to keep all of them around indefinitely?
When we introduced the generic syscall table, I tried to limit
it to the syscalls that are actually needed and avoid all duplications,
but since then we have added a couple of calls that can replace old
ones, and we might want to do that when risc-v gets merged.
Arnd
next prev parent reply other threads:[~2016-03-03 15:52 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-03-03 15:03 generic RDMA READ/WRITE API V2 Christoph Hellwig
2016-03-03 15:03 ` [PATCH 2/6] vfs: vfs: Define new syscalls preadv2,pwritev2 Christoph Hellwig
2016-03-10 18:15 ` Michael Kerrisk (man-pages)
[not found] ` <56E1B9A8.3070904-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2016-03-11 9:53 ` Christoph Hellwig
[not found] ` <20160311095357.GA29350-jcswGhMUV9g@public.gmane.org>
2016-04-18 13:51 ` Michael Kerrisk (man-pages)
[not found] ` <5714E676.4090007-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2016-04-25 8:47 ` Christoph Hellwig
[not found] ` <20160425084715.GA29255-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2016-04-25 17:35 ` Michael Kerrisk (man-pages)
2016-05-08 9:29 ` Christoph Hellwig
[not found] ` <1457017443-17662-1-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2016-03-03 15:03 ` [PATCH 1/6] vfs: pass a flags argument to vfs_readv/vfs_writev Christoph Hellwig
2016-03-03 15:04 ` [PATCH 3/6] x86: wire up preadv2 and pwritev2 Christoph Hellwig
2016-03-03 15:04 ` [PATCH 4/6] vfs: add the RWF_HIPRI flag for preadv2/pwritev2 Christoph Hellwig
[not found] ` <1457017443-17662-5-git-send-email-hch-jcswGhMUV9g@public.gmane.org>
2016-05-08 21:47 ` NeilBrown
[not found] ` <874ma8usrr.fsf-wvvUuzkyo1HefUI2i7LXDhCRmIWqnp/j@public.gmane.org>
2016-05-11 8:55 ` Christoph Hellwig
2016-03-03 15:04 ` [PATCH 5/6] direct-io: only use block polling if explicitly requested Christoph Hellwig
2016-03-03 15:04 ` [PATCH 6/6] blk-mq: enable polling support by default Christoph Hellwig
2016-03-03 15:09 ` generic RDMA READ/WRITE API V2 Sagi Grimberg
2016-03-03 15:11 ` selective block polling and preadv2/pwritev2 revisited V3 Christoph Hellwig
2016-03-03 15:16 ` Jens Axboe
[not found] ` <20160303151116.GA24614-jcswGhMUV9g@public.gmane.org>
2016-03-03 15:52 ` Arnd Bergmann [this message]
2016-03-03 16:11 ` Christoph Hellwig
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=2369295.6CpmrvqZVS@wuerfel \
--to=arnd-r2ngtmty4d4@public.gmane.org \
--cc=axboe-b10kYP2dOMg@public.gmane.org \
--cc=hch-jcswGhMUV9g@public.gmane.org \
--cc=linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=milosz-B5zB6C1i6pkAvxtiuMwx3w@public.gmane.org \
--cc=sagig-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org \
--cc=viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org \
/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