From: Hannes Reinecke <hare@suse.de>
To: dm-devel@redhat.com
Subject: Re: RFC for multipath queue_if_no_path timeout.
Date: Fri, 27 Sep 2013 08:07:44 +0200 [thread overview]
Message-ID: <524520B0.6010003@suse.de> (raw)
In-Reply-To: <20130926234957.GA3658@redhat.com>
On 09/27/2013 01:49 AM, Mike Snitzer wrote:
> On Thu, Sep 26 2013 at 7:22pm -0400,
> Alasdair G Kergon <agk@redhat.com> wrote:
>
>> On Thu, Sep 26, 2013 at 10:47:13AM -0700, Frank Mayhar wrote:
>>> Launching it from ramdisk won't help, particularly, since it still goes
>>> through the block layer. The other stuff won't help if a (potentially
>>> unrelated) bug in the daemon happens to be being tickled at the same
>>> time, or if some dependency happens to be broken and _that's_ what's
>>> preventing the daemon from making progress.
>>
>> Then put more effort into debugging your daemon so it doesn't have
>> bugs that make it die? Implement the timeout in a robust independent
>> daemon if it's other code there that's unreliable?
>>
>>> And as far as lvm2 and multipath-tools, yeah, they cope okay in the kind
>>> of environments most people have, but that's not the kind of environment
>>> (or scale) we have to deal with.
>>
>> In what way are your requirements so different that a locked-into-memory
>> monitoring daemon cannot implement this timeout?
>
> Frank, I had a look at your patch. It leaves a lot to be desired, I was
> starting to clean it up but ultimately found myself agreeing with
> Alasdair's original point: that this policy should be implemented in the
> userspace daemon.
>
_Actually_ there is a way how this could be implemented properly:
implement a blk_timeout function.
Thing is, every request_queue might have a timeout function
implemented, whose goal is to abort requests which are beyond that
timeout. EG SCSI uses that for the dev_loss_tmo mechanism.
Multipath what with it being request-based could easily implement
the same mechanism, namely have to blk_timeout function which would
just re-arm the timeout in the default case, but abort any queued
I/O (after a timeout) if all paths are down.
Hmm. I see to draft up a PoC.
Cheers,
Hannes
--
Dr. Hannes Reinecke zSeries & Storage
hare@suse.de +49 911 74053 688
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: J. Hawn, J. Guild, F. Imendörffer, HRB 16746 (AG Nürnberg)
next prev parent reply other threads:[~2013-09-27 6:07 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-09-26 17:14 RFC for multipath queue_if_no_path timeout Frank Mayhar
2013-09-26 17:24 ` Alasdair G Kergon
2013-09-26 17:31 ` Frank Mayhar
2013-09-26 17:38 ` Alasdair G Kergon
2013-09-26 17:47 ` Frank Mayhar
2013-09-26 17:52 ` Mike Snitzer
2013-09-26 20:36 ` [PATCH 1/1] dm mpath: Add timeout mechanism for queue_if_no_path Frank Mayhar
2013-09-26 23:22 ` RFC for multipath queue_if_no_path timeout Alasdair G Kergon
2013-09-26 23:49 ` Mike Snitzer
2013-09-27 6:07 ` Hannes Reinecke [this message]
2013-09-27 8:06 ` Hannes Reinecke
2013-09-27 8:37 ` Alasdair G Kergon
2013-09-27 13:52 ` Hannes Reinecke
2013-09-27 16:37 ` Frank Mayhar
2013-09-27 16:32 ` Frank Mayhar
2013-09-27 16:29 ` Frank Mayhar
2013-10-17 19:03 ` Frank Mayhar
2013-10-17 19:15 ` Mike Snitzer
2013-10-17 20:45 ` Frank Mayhar
2013-10-17 21:13 ` Mike Snitzer
2013-10-18 20:51 ` Frank Mayhar
2013-10-18 21:47 ` Alasdair G Kergon
2013-10-18 22:53 ` [RFC PATCH v2] dm mpath: add a " Mike Snitzer
2013-10-30 1:02 ` Mike Snitzer
2013-10-30 15:08 ` Frank Mayhar
2013-10-30 15:43 ` Mike Snitzer
2013-10-30 18:09 ` Frank Mayhar
2013-10-31 9:36 ` Junichi Nomura
2013-10-31 14:16 ` Frank Mayhar
2013-10-31 14:31 ` Alasdair G Kergon
2013-10-31 17:17 ` Frank Mayhar
2013-11-01 1:23 ` Junichi Nomura
2013-11-01 1:58 ` Junichi Nomura
2013-11-01 4:17 ` Junichi Nomura
2013-11-05 15:18 ` Frank Mayhar
2013-11-05 16:02 ` [RFC PATCH v3] " Frank Mayhar
2013-11-05 16:53 ` Mike Snitzer
2013-11-06 6:54 ` Hannes Reinecke
2013-11-06 15:43 ` Frank Mayhar
2013-11-06 19:21 ` Mike Snitzer
2013-11-07 1:03 ` Junichi Nomura
2013-10-31 14:59 ` [RFC PATCH v2] " Hannes Reinecke
2013-10-21 16:05 ` RFC for multipath " Benjamin Marzinski
2013-10-21 16:17 ` Frank Mayhar
2013-10-23 13:39 ` Benjamin Marzinski
2013-09-27 16:27 ` Frank Mayhar
2013-09-26 17:41 ` Mike Snitzer
2013-09-26 17:55 ` Frank Mayhar
2013-09-26 18:41 ` Mike Snitzer
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=524520B0.6010003@suse.de \
--to=hare@suse.de \
--cc=dm-devel@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.