public inbox for linux-scsi@vger.kernel.org
 help / color / mirror / Atom feed
From: "Martin K. Petersen" <martin.petersen-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
To: Chris Leech <cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	open-iscsi-/JYPxA39Uh5TLH3MbocFFw@public.gmane.org,
	lduncan-IBi9RG/b67k@public.gmane.org,
	martin.petersen-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org,
	jejb-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org
Subject: Re: [PATCH] libiscsi: add lock around task lists to fix list corruption regression
Date: Thu, 23 Feb 2017 17:11:58 -0500	[thread overview]
Message-ID: <yq1fuj45zgx.fsf@oracle.com> (raw)
In-Reply-To: <20170221173536.32024-1-cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> (Chris Leech's message of "Tue, 21 Feb 2017 09:35:36 -0800")

>>>>> "Chris" == Chris Leech <cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> writes:

Chris> There's a rather long standing regression from commit 659743b
Chris> [SCSI] libiscsi: Reduce locking contention in fast path

Chris> Depending on iSCSI target behavior, it's possible to hit the case
Chris> in iscsi_complete_task where the task is still on a pending list
Chris> (!list_empty(&task->running)).  When that happens the task is
Chris> removed from the list while holding the session back_lock, but
Chris> other task list modification occur under the frwd_lock.  That
Chris> leads to linked list corruption and eventually a panicked system.

Chris> Rather than back out the session lock split entirely, in order to
Chris> try and keep some of the performance gains this patch adds
Chris> another lock to maintain the task lists integrity.

Chris> Major enterprise supported kernels have been backing out the lock
Chris> split for while now, thanks to the efforts at IBM where a lab
Chris> setup has the most reliable reproducer I've seen on this issue.
Chris> This patch has been tested there successfully.

Reviews, please!

-- 
Martin K. Petersen	Oracle Linux Engineering

-- 
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To unsubscribe from this group and stop receiving emails from it, send an email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
Visit this group at https://groups.google.com/group/open-iscsi.
For more options, visit https://groups.google.com/d/optout.

  parent reply	other threads:[~2017-02-23 22:11 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-02-21 17:35 [PATCH] libiscsi: add lock around task lists to fix list corruption regression Chris Leech
     [not found] ` <20170221173536.32024-1-cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2017-02-23 22:11   ` Martin K. Petersen [this message]
2017-02-23 22:25   ` Chris Leech
2017-02-24 15:09     ` Guilherme G. Piccoli
     [not found]       ` <4304a9c0-6427-c0a2-e18a-51292d62022b-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2017-02-24 19:48         ` Ilkka Sovanto
     [not found]     ` <250619225.63072551.1487888748696.JavaMail.zimbra-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2017-03-05 20:49       ` Ilkka Sovanto
     [not found]         ` <CAKYn0tiyWNEjFZHaPDHNjam5=3WCR_V2svNiJmvWeYhpv3=8Ag-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-05-09 22:27           ` Ilkka Sovanto
     [not found]             ` <CAKYn0tjF46gxwj3MtjLL_ic+veXjTZ9n_BGKjz6-fW+Cse2w9w-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2018-12-18 21:07               ` Alan Adamson
2017-02-28  0:58   ` [PATCH v2] " Chris Leech
     [not found]     ` <20170228005836.12444-1-cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2017-02-28 16:46       ` Guilherme G. Piccoli
2017-03-01  3:06       ` Martin K. Petersen

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=yq1fuj45zgx.fsf@oracle.com \
    --to=martin.petersen-qhclzuegtsvqt0dzr+alfa@public.gmane.org \
    --cc=cleech-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=jejb-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org \
    --cc=lduncan-IBi9RG/b67k@public.gmane.org \
    --cc=linux-scsi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=open-iscsi-/JYPxA39Uh5TLH3MbocFFw@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