From: Christoph Hellwig <hch@lst.de>
To: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Keith Busch <keith.busch@intel.com>,
James Smart <james.smart@broadcom.com>,
Hannes Reinecke <hare@suse.de>, Ewan Milne <emilne@redhat.com>,
Max Gurtovoy <maxg@mellanox.com>,
Linux NVMe Mailinglist <linux-nvme@lists.infradead.org>,
Linux Kernel Mailinglist <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/4] Rework NVMe abort handling
Date: Thu, 19 Jul 2018 16:23:55 +0200 [thread overview]
Message-ID: <20180719142355.GA18800@lst.de> (raw)
In-Reply-To: <20180719141025.yveza2svhvc2r4lw@linux-x5ow.site>
On Thu, Jul 19, 2018 at 04:10:25PM +0200, Johannes Thumshirn wrote:
> The problem I'm trying to solve here is really just single commands
> timing out because of i.e. a bad switch in between which causes frame
> loss somewhere.
And that is exactly the case where NVMe abort does not actually work
in any sensible way.
Remember that while NVMe guarantes ordered delivery inside a given
queue it does not guarantee anything between multiple queues.
So now you have your buggy FC setup where an I/O command times out
because your switch delayed it for two hours due to a firmware bug.
After 30 seconds we send an abort over the admin queue, which happens
to pass through just fine. The controller will tell you: no command
found as it has never seen it.
No with the the code following what we have in PCIe that just means
we'll eventually controller reset after the I/O command times out
the second time as we still won't have seen a completion for it.
If you incorrectly just continue and resend the command we'll actually
get the command sent twice and thus a potential bug once the original
command just gets sent along.
next prev parent reply other threads:[~2018-07-19 14:21 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-19 13:28 [PATCH 0/4] Rework NVMe abort handling Johannes Thumshirn
2018-07-19 13:28 ` [PATCH 1/4] nvme: factor out pci abort handling into core Johannes Thumshirn
2018-07-19 16:29 ` kbuild test robot
2018-07-19 13:28 ` [PATCH 2/4] nvme: rdma: abort commands before resetting controller Johannes Thumshirn
2018-07-19 13:28 ` [PATCH 3/4] nvmet: loop: " Johannes Thumshirn
2018-07-19 13:28 ` [PATCH 4/4] nvme: fc: " Johannes Thumshirn
2018-07-19 13:42 ` [PATCH 0/4] Rework NVMe abort handling Christoph Hellwig
2018-07-19 14:10 ` Johannes Thumshirn
2018-07-19 14:23 ` Christoph Hellwig [this message]
2018-07-19 14:35 ` Johannes Thumshirn
2018-07-19 14:50 ` Christoph Hellwig
2018-07-19 14:54 ` Johannes Thumshirn
2018-07-19 15:04 ` James Smart
2018-07-20 6:36 ` Johannes Thumshirn
2018-07-19 15:00 ` James Smart
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=20180719142355.GA18800@lst.de \
--to=hch@lst.de \
--cc=emilne@redhat.com \
--cc=hare@suse.de \
--cc=james.smart@broadcom.com \
--cc=jthumshirn@suse.de \
--cc=keith.busch@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-nvme@lists.infradead.org \
--cc=maxg@mellanox.com \
--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 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).