From: Wouter Verhelst <w@uter.be>
To: Josef Bacik <jbacik@fb.com>
Cc: axboe@fb.com, linux-block@vger.kernel.org, kernel-team@fb.com,
nbd-general@lists.sourceforge.net, linux-kernel@vger.kernel.org
Subject: Re: [Nbd] [PATCH][V3] nbd: add multi-connection support
Date: Thu, 29 Sep 2016 18:41:00 +0200 [thread overview]
Message-ID: <20160929164100.akytbkbtvziwaqqj@grep.be> (raw)
In-Reply-To: <87908d95-0b7c-bc3f-f69d-94d006829daf@fb.com>
On Thu, Sep 29, 2016 at 10:03:50AM -0400, Josef Bacik wrote:
> So think of it like normal disks with multiple channels. We don't send flushes
> down all the hwq's to make sure they are clear, we leave that decision up to the
> application (usually a FS of course).
Well, when I asked earlier, Christoph said[1] that blk-mq assumes that
when a FLUSH is sent over one channel, and the reply comes in, that all
commands which have been received, regardless of which channel they were
received over, have reched disk.
[1] Message-ID: <20160915122304.GA15501@infradead.org>
It is impossible for nbd to make such a guarantee, due to head-of-line
blocking on TCP.
[...]
> perhaps we could add a flag later that says send all the flushes down
> all the connections for the paranoid, it should be relatively
> straightforward to do. Thanks,
That's not an unreasonable approach, I guess.
--
< ron> I mean, the main *practical* problem with C++, is there's like a dozen
people in the world who think they really understand all of its rules,
and pretty much all of them are just lying to themselves too.
-- #debian-devel, OFTC, 2016-02-12
next prev parent reply other threads:[~2016-09-29 16:41 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-28 20:01 [PATCH][V3] nbd: add multi-connection support Josef Bacik
2016-09-29 9:52 ` [Nbd] " Wouter Verhelst
2016-09-29 14:03 ` Josef Bacik
2016-09-29 16:41 ` Wouter Verhelst [this message]
2016-09-29 16:59 ` Josef Bacik
2016-10-02 16:17 ` Alex Bligh
2016-10-03 1:47 ` Josef Bacik
2016-10-03 7:20 ` Christoph Hellwig
2016-10-03 7:51 ` Wouter Verhelst
2016-10-03 7:57 ` Christoph Hellwig
2016-10-03 11:34 ` Alex Bligh
2016-10-03 14:32 ` Josef Bacik
2016-10-03 14:46 ` Alex Bligh
2016-10-03 21:07 ` Wouter Verhelst
2016-10-04 9:35 ` Alex Bligh
2016-10-06 9:04 ` Wouter Verhelst
2016-10-06 9:41 ` Alex Bligh
2016-10-06 10:15 ` Wouter Verhelst
2016-10-06 11:04 ` Alex Bligh
2016-10-06 10:31 ` Christoph Hellwig
2016-10-06 13:09 ` Wouter Verhelst
2016-10-06 13:16 ` Christoph Hellwig
2016-10-06 13:55 ` Wouter Verhelst
2016-10-03 7:49 ` Wouter Verhelst
2016-10-11 9:00 ` Sagi Grimberg
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=20160929164100.akytbkbtvziwaqqj@grep.be \
--to=w@uter.be \
--cc=axboe@fb.com \
--cc=jbacik@fb.com \
--cc=kernel-team@fb.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nbd-general@lists.sourceforge.net \
/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).