linux-nvme.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: sagi@grimberg.me (Sagi Grimberg)
Subject: [PATCH] nvme-rdma: Always signal fabrics private commands
Date: Wed, 13 Jul 2016 17:47:21 +0300	[thread overview]
Message-ID: <57865479.1080707@grimberg.me> (raw)
In-Reply-To: <001f01d1dd12$c5fb8500$51f28f00$@opengridcomputing.com>


> Double completion?  When the QP exits RTS with pending unsignaled SQ WRs, cxgb4
> doesn't know if those were actually completed by hardware, so they are completed
> with FLUSH_ERR status.  I _could_ change cxgb4 to just eat those, but I'm a
> little worried about breaking the iWARP Verbs semantics.  Perhaps I shouldn't
> be.  It does seem to be causing lots of pain...

What exactly breaks iWARP semantics here?

Think of a case where we posted unsignaled send, got a successful reply
from the peer, now we drain the qp, and the send which belongs to a
transaction that we already completed is flush with error. Does that
sound like a correct behavior?

  reply	other threads:[~2016-07-13 14:47 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-23 16:08 [PATCH] nvme-rdma: Always signal fabrics private commands Sagi Grimberg
2016-06-23 18:17 ` Steve Wise
2016-06-24  7:07 ` Christoph Hellwig
2016-06-24 14:05   ` Steve Wise
2016-06-26 16:41   ` Sagi Grimberg
2016-06-28  8:41     ` Christoph Hellwig
2016-06-28 14:20       ` Steve Wise
2016-06-29 14:57         ` Steve Wise
2016-06-30  6:36           ` 'Christoph Hellwig'
2016-06-30 13:44             ` Steve Wise
2016-06-30 15:10               ` Steve Wise
2016-07-13 10:08               ` Sagi Grimberg
2016-07-13 10:11                 ` Sagi Grimberg
2016-07-13 14:28                   ` Steve Wise
2016-07-13 14:47                     ` Sagi Grimberg [this message]
2016-07-13 14:51                       ` Steve Wise
2016-07-13 15:02                         ` Sagi Grimberg
2016-07-13 15:12                           ` Steve Wise

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=57865479.1080707@grimberg.me \
    --to=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).