From: Bart Van Assche <Bart.VanAssche@wdc.com>
To: "ming.lei@redhat.com" <ming.lei@redhat.com>
Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
"jthumshirn@suse.de" <jthumshirn@suse.de>,
"linux-raid@vger.kernel.org" <linux-raid@vger.kernel.org>,
"hch@lst.de" <hch@lst.de>,
"martin.petersen@oracle.com" <martin.petersen@oracle.com>,
"axboe@kernel.dk" <axboe@kernel.dk>,
"oleksandr@natalenko.name" <oleksandr@natalenko.name>,
"hare@suse.com" <hare@suse.com>,
"shli@kernel.org" <shli@kernel.org>
Subject: Re: [PATCH v4 1/7] md: Make md resync and reshape threads freezable
Date: Mon, 2 Oct 2017 15:39:35 +0000 [thread overview]
Message-ID: <1506958773.3368.12.camel@wdc.com> (raw)
In-Reply-To: <20170927110006.GB1994@ming.t460p>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=
WARNING: multiple messages have this Message-ID (diff)
From: Bart Van Assche <Bart.VanAssche@wdc.com>
To: "ming.lei@redhat.com" <ming.lei@redhat.com>
Cc: "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
"jthumshirn@suse.de" <jthumshirn@suse.de>,
"linux-raid@vger.kernel.org" <linux-raid@vger.kernel.org>,
"hch@lst.de" <hch@lst.de>,
"martin.petersen@oracle.com" <martin.petersen@oracle.com>,
"axboe@kernel.dk" <axboe@kernel.dk>,
"oleksandr@natalenko.name" <oleksandr@natalenko.name>,
"hare@suse.com" <hare@suse.com>,
"shli@kernel.org" <shli@kernel.org>
Subject: Re: [PATCH v4 1/7] md: Make md resync and reshape threads freezable
Date: Mon, 2 Oct 2017 15:39:35 +0000 [thread overview]
Message-ID: <1506958773.3368.12.camel@wdc.com> (raw)
In-Reply-To: <20170927110006.GB1994@ming.t460p>
On Wed, 2017-09-27 at 19:00 +0800, Ming Lei wrote:
> With current linus tree, SCSI I/O is prevented from being dispatch to
> device during suspend by SCSI quiesce, and will be dispatched again
> in resume. With Safe SCSI quiesce[1], any underlying IO request will
> stop at blk_queue_enter() during suspend, and restart from there during
> resume.
>
> For other non-SCSI driver, their .suspend/.resume often
> handles I/O in similar way, for example, NVMe queue will
> be frozen in .suspend, and unfreeze in .resume.
>
> So could you explain a bit which kind of bug this patch fixes?
It seems like you do not fully understand the motivation behind quiescing and
resuming I/O from inside the SCSI and NVMe freeze and thaw power management
callbacks. Hibernation can only work reliably if no I/O is submitted after
creation of the hibernation image has been started. If any I/O is submitted
that is not related to the hibernation process itself by any driver after
user space processes and kernel threads have been frozen then that's a *bug*
in the component that submitted the I/O. The freezing and suspending of I/O
from inside the SCSI and NVMe drivers is a *workaround* for these bugs but is
not a full solution. Before the hibernation image is written to disk I/O is
resumed and the I/O requests that got deferred will be executed at that time.
In other words, suspending and resuming I/O from inside the SCSI and NVMe
drivers is a workaround and not a full solution. The following quote from
Documentation/power/swsusp.txt illustrates this:
* BIG FAT WARNING *********************************************************
*
* If you touch anything on disk between suspend and resume...
* ...kiss your data goodbye.
Bart.
next prev parent reply other threads:[~2017-10-02 15:39 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-25 20:29 [PATCH v4 0/7] Make suspend and resume safe for md-on-SCSI Bart Van Assche
2017-09-25 20:29 ` [PATCH v4 1/7] md: Make md resync and reshape threads freezable Bart Van Assche
2017-09-25 23:04 ` Ming Lei
2017-09-25 23:09 ` Bart Van Assche
2017-09-25 23:09 ` Bart Van Assche
2017-09-26 4:01 ` Ming Lei
2017-09-26 8:13 ` Ming Lei
2017-09-26 14:40 ` Bart Van Assche
2017-09-26 14:40 ` Bart Van Assche
2017-09-26 15:02 ` Ming Lei
2017-09-26 6:06 ` Hannes Reinecke
2017-09-26 11:17 ` Ming Lei
2017-09-26 14:42 ` Bart Van Assche
2017-09-26 14:42 ` Bart Van Assche
2017-09-26 14:59 ` Ming Lei
2017-09-27 3:12 ` Bart Van Assche
2017-09-27 3:12 ` Bart Van Assche
2017-09-27 11:00 ` Ming Lei
2017-10-02 15:39 ` Bart Van Assche [this message]
2017-10-02 15:39 ` Bart Van Assche
2017-10-02 13:26 ` Christoph Hellwig
2017-09-25 20:29 ` [PATCH v4 2/7] block: Make q_usage_counter also track legacy requests Bart Van Assche
2017-09-26 6:05 ` Hannes Reinecke
2017-09-26 8:34 ` Ming Lei
2017-10-02 13:29 ` Christoph Hellwig
2017-09-25 20:29 ` [PATCH v4 3/7] block: Convert RQF_PREEMPT into REQ_PREEMPT Bart Van Assche
2017-10-02 13:42 ` Christoph Hellwig
2017-10-02 13:43 ` Christoph Hellwig
2017-09-25 20:29 ` [PATCH v4 4/7] block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag Bart Van Assche
2017-10-02 13:47 ` Christoph Hellwig
2017-10-02 15:56 ` Bart Van Assche
2017-10-02 16:14 ` hch
2017-09-25 20:29 ` [PATCH v4 5/7] scsi: Reduce suspend latency Bart Van Assche
2017-09-26 22:23 ` Ming Lei
2017-09-27 3:43 ` Bart Van Assche
2017-09-27 5:37 ` Ming Lei
2017-09-25 20:29 ` [PATCH v4 6/7] scsi: Set QUEUE_FLAG_PREEMPT_ONLY while quiesced Bart Van Assche
2017-10-02 13:53 ` Christoph Hellwig
2017-09-25 20:29 ` [PATCH v4 7/7] block: Make SCSI device suspend and resume work reliably Bart Van Assche
2017-09-25 22:59 ` Ming Lei
2017-09-25 23:13 ` Bart Van Assche
2017-09-26 8:32 ` Ming Lei
2017-09-26 14:44 ` Bart Van Assche
2017-09-26 9:15 ` [PATCH v4 0/7] Make suspend and resume safe for md-on-SCSI Ming Lei
2017-09-26 14:29 ` Bart Van Assche
2017-09-26 14:54 ` Ming Lei
2017-09-26 20:17 ` Bart Van Assche
2017-09-26 22:47 ` Ming Lei
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=1506958773.3368.12.camel@wdc.com \
--to=bart.vanassche@wdc.com \
--cc=axboe@kernel.dk \
--cc=hare@suse.com \
--cc=hch@lst.de \
--cc=jthumshirn@suse.de \
--cc=linux-block@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ming.lei@redhat.com \
--cc=oleksandr@natalenko.name \
--cc=shli@kernel.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 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.