From: Zach Brown <zab-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: Kent Overstreet <koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org,
tytso-3s7WtUTddSA@public.gmane.org
Subject: Re: [PATCH 5/5] aio: Refactor aio_read_evt, use cmxchg(), fix bug
Date: Tue, 9 Oct 2012 17:26:34 -0700 [thread overview]
Message-ID: <20121010002634.GX26187@lenny.home.zabbo.net> (raw)
In-Reply-To: <20121010000600.GB26835-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
> The AIO ringbuffer stuff just annoys me more than most
Not more than everyone, though, I can personally promise you that :).
> (it wasn't until
> the other day that I realized it was actually exported to userspace...
> what led to figuring that out was noticing aio_context_t was a ulong,
> and got truncated to 32 bits with a 32 bit program running on a 64 bit
> kernel. I'd been horribly misled by the code comments and the lack of
> documentation.)
Yeah. It's the userspace address of the mmaped ring. This has annoyed
the process migration people who can't recreate the context in a new
kernel because there's no userspace interface to specify creation of a
context at a specific address.
> But if we do have an explicit handle, I don't see why it shouldn't be a
> file descriptor.
Because they're expensive to create and destroy when compared to a
single system call. Imagine that we're using waiting for a single
completion to implement a cheap one-off sync call. Imagine it's a
buffered op which happens to hit the cache and is really quick.
(And they're annoying to manage: libraries and O_CLOEXEC, running into
fd/file limit tunables, bleh.)
If the 'completion context' is no more than a structure in userspace
memory then a lot of stuff just works. Tasks can share it amongst
themselves as they see fit. A trivial one-off sync call can just dump
it on the stack and point to it. It doesn't have to be specifically
torn down on task exit.
> > And perhaps obviously, I'd start with the acall stuff :). It was a lot
> > lighter. We could talk about how to make it extensible without going
> > all the way to the generic packed variable size duplicating or not and
> > returning or not or.. attributes :).
>
> Link? I haven't heard of acall before.
I linked to it after that giant silly comment earlier in the thread,
here it is again:
http://lwn.net/Articles/316806/
There's a mostly embarassing video of a jetlagged me giving that talk at
LCA kicking around.. ah, here:
http://mirror.linux.org.au/pub/linux.conf.au/2009/Thursday/131.ogg
- z
next prev parent reply other threads:[~2012-10-10 0:26 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-09 6:39 [PATCH 1/5] aio: Kill return value of aio_complete() Kent Overstreet
[not found] ` <1349764760-21093-1-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 6:39 ` [PATCH 2/5] aio: kiocb_cancel() Kent Overstreet
[not found] ` <1349764760-21093-2-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 18:26 ` Zach Brown
[not found] ` <20121009182625.GM26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-09 21:37 ` Kent Overstreet
[not found] ` <20121009213700.GF29494-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-10 11:03 ` Theodore Ts'o
[not found] ` <20121010110356.GA11468-AKGzg7BKzIDYtjvyW6yDsg@public.gmane.org>
2012-10-10 21:20 ` Zach Brown
[not found] ` <20121010212051.GD6371-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 23:21 ` Theodore Ts'o
2012-10-11 2:41 ` Kent Overstreet
2012-10-09 6:39 ` [PATCH 5/5] aio: Refactor aio_read_evt, use cmxchg(), fix bug Kent Overstreet
[not found] ` <1349764760-21093-5-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 18:37 ` Zach Brown
[not found] ` <20121009183753.GP26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-09 21:27 ` Kent Overstreet
[not found] ` <20121009212724.GD29494-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 22:47 ` Zach Brown
[not found] ` <20121009224703.GT26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-09 22:55 ` Kent Overstreet
[not found] ` <20121009225509.GA26835-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 23:10 ` Zach Brown
[not found] ` <20121009231059.GV26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 0:06 ` Kent Overstreet
[not found] ` <20121010000600.GB26835-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-10 0:26 ` Zach Brown [this message]
[not found] ` <20121010002634.GX26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 0:47 ` Kent Overstreet
[not found] ` <20121010004746.GF26835-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-10 21:43 ` Zach Brown
[not found] ` <20121010214315.GE6371-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-11 2:51 ` Kent Overstreet
[not found] ` <20121011025102.GE24174-jC9Py7bek1znysI04z7BkA@public.gmane.org>
2012-10-11 16:43 ` Zach Brown
2012-10-09 18:25 ` [PATCH 1/5] aio: Kill return value of aio_complete() Zach Brown
2012-10-09 6:39 ` [PATCH 3/5] aio: Rewrite refcounting Kent Overstreet
[not found] ` <1349764760-21093-3-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 18:27 ` Zach Brown
[not found] ` <20121009182755.GN26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-09 22:21 ` Kent Overstreet
[not found] ` <20121009222153.GG29494-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 22:35 ` Zach Brown
[not found] ` <20121009223504.GS26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 0:17 ` Kent Overstreet
2012-10-09 6:39 ` [PATCH 4/5] aio: vmap ringbuffer Kent Overstreet
[not found] ` <1349764760-21093-4-git-send-email-koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 18:29 ` Zach Brown
2012-10-09 21:31 ` Kent Overstreet
[not found] ` <20121009213111.GE29494-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 22:32 ` Zach Brown
2012-10-09 22:44 ` Kent Overstreet
[not found] ` <20121009224428.GH29494-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-09 22:58 ` Zach Brown
[not found] ` <20121009225836.GU26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 0:16 ` Kent Overstreet
[not found] ` <20121010001630.GC26835-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
2012-10-10 0:36 ` Zach Brown
[not found] ` <20121010003626.GY26187-fypN+1c5dIyjpB87vu3CluTW4wlIGRCZ@public.gmane.org>
2012-10-10 1:09 ` Kent Overstreet
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=20121010002634.GX26187@lenny.home.zabbo.net \
--to=zab-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=tytso-3s7WtUTddSA@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;
as well as URLs for NNTP newsgroup(s).