From: Christoph Hellwig <hch@lst.de>
To: Chao Leng <lengchao@huawei.com>
Cc: Sagi Grimberg <sagi@grimberg.me>, Keith Busch <kbusch@kernel.org>,
linux-nvme@lists.infradead.org, Christoph Hellwig <hch@lst.de>,
Chaitanya Kulkarni <Chaitanya.Kulkarni@wdc.com>
Subject: Re: [PATCH 0/3 rfc] Fix nvme-tcp and nvme-rdma controller reset hangs
Date: Wed, 17 Mar 2021 07:59:10 +0100 [thread overview]
Message-ID: <20210317065910.GC14498@lst.de> (raw)
In-Reply-To: <17b15849-f0f3-af61-113f-0eb717e96f0f@huawei.com>
On Wed, Mar 17, 2021 at 10:55:57AM +0800, Chao Leng wrote:
>>> Will it work if nvme mpath used request NOWAIT flag for its submit_bio()
>>> call, and add the bio to the requeue_list if blk_queue_enter() fails? I
>>> think that looks like another way to resolve the deadlock, but we need
>>> the block layer to return a failed status to the original caller.
Yes, I think BLK_MQ_REQ_NOWAIT makes total sense here. dm-mpath also
uses it for its request allocation for similar reasons.
>>
>> But who would kick the requeue list? and that would make near-tag-exhaust performance stink...
The multipath code would have to kick the list. We could also try to
split into two flags, one that affects blk_queue_enter and one that
affects the tag allocation.
> moving nvme_start_freeze from nvme_rdma_teardown_io_queues to nvme_rdma_configure_io_queues can fix it.
> It can also avoid I/O hang long time if reconnection failed.
Can you explain how we'd still ensure that no new commands get queued
during teardown using that scheme?
_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2021-03-17 6:59 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-15 22:27 [PATCH 0/3 rfc] Fix nvme-tcp and nvme-rdma controller reset hangs Sagi Grimberg
2021-03-15 22:27 ` [PATCH 1/3] nvme: introduce nvme_ctrl_is_mpath helper Sagi Grimberg
2021-03-15 22:27 ` [PATCH 2/3] nvme-tcp: fix possible hang when trying to set a live path during I/O Sagi Grimberg
2021-03-15 22:27 ` [PATCH 3/3] nvme-rdma: " Sagi Grimberg
2021-03-16 3:24 ` [PATCH 0/3 rfc] Fix nvme-tcp and nvme-rdma controller reset hangs Chao Leng
2021-03-16 5:04 ` Sagi Grimberg
2021-03-16 6:18 ` Chao Leng
2021-03-16 6:25 ` Sagi Grimberg
2021-03-16 20:07 ` Sagi Grimberg
2021-03-16 20:42 ` Keith Busch
2021-03-16 23:51 ` Sagi Grimberg
2021-03-17 2:55 ` Chao Leng
2021-03-17 6:59 ` Christoph Hellwig [this message]
2021-03-17 7:59 ` Chao Leng
2021-03-17 18:43 ` Sagi Grimberg
2021-03-18 1:51 ` Chao Leng
2021-03-18 4:45 ` Christoph Hellwig
2021-03-18 18:46 ` Sagi Grimberg
2021-03-18 19:16 ` Keith Busch
2021-03-18 19:31 ` Sagi Grimberg
2021-03-18 21:52 ` Keith Busch
2021-03-18 22:45 ` Sagi Grimberg
2021-03-19 14:05 ` Christoph Hellwig
2021-03-19 17:28 ` Christoph Hellwig
2021-03-19 19:07 ` Keith Busch
2021-03-19 19:34 ` Sagi Grimberg
2021-03-20 6:11 ` Christoph Hellwig
2021-03-21 6:49 ` Sagi Grimberg
2021-03-22 6:34 ` Christoph Hellwig
2021-03-17 8:16 ` 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=20210317065910.GC14498@lst.de \
--to=hch@lst.de \
--cc=Chaitanya.Kulkarni@wdc.com \
--cc=kbusch@kernel.org \
--cc=lengchao@huawei.com \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
/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.