Linux-NVME Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: sagi@lightbits.io (Sagi Grimberg)
Subject: nvme-fabrics: crash at nvme connect-all
Date: Thu, 9 Jun 2016 16:48:20 +0300	[thread overview]
Message-ID: <575973A4.9080001@lightbits.io> (raw)
In-Reply-To: <005701d1c253$f9590550$ec0b0ff0$@opengridcomputing.com>


>>> Steve, did you see this before? I'm wandering if we need some sort
>>> of logic handling with resource limitation in iWARP (global mrs pool...)
>>
>> Haven't seen this.  Does 'cat /sys/kernel/debug/iw_cxgb4/blah/stats' show
>> anything interesting?  Where/why is it crashing?
>>
>
> So this is the failure:
>
> [  703.239462] rdma_rw_init_mrs: failed to allocated 128 MRs
> [  703.239498] failed to init MR pool ret= -12
> [  703.239541] nvmet_rdma: failed to create_qp ret= -12
> [  703.239582] nvmet_rdma: nvmet_rdma_alloc_queue: creating RDMA queue failed
> (-12).
>
> Not sure why it would fail.  I would think my setup would be allocating more
> given I have 16 cores on the host and target.  The debugfs "stats" file I
> mentioned above should show us something if we're running out of adapter
> resources for MR or PBL records.

Note that Marta ran both the host and the target on the same machine.
So, 8 (cores) x 128 (queue entries) x 2 (host and target) gives 2048
MRs...

What is the T5 limitation?

  reply	other threads:[~2016-06-09 13:48 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-09  9:18 nvme-fabrics: crash at nvme connect-all Marta Rybczynska
2016-06-09  9:29 ` Sagi Grimberg
2016-06-09 10:07   ` Marta Rybczynska
2016-06-09 11:09     ` Sagi Grimberg
2016-06-09 12:12       ` Marta Rybczynska
2016-06-09 12:30         ` Sagi Grimberg
2016-06-09 13:27           ` Steve Wise
2016-06-09 13:36             ` Steve Wise
2016-06-09 13:48               ` Sagi Grimberg [this message]
2016-06-09 14:09                 ` Steve Wise
2016-06-09 14:22                   ` Steve Wise
2016-06-09 14:29                     ` Steve Wise
2016-06-09 15:04                       ` Marta Rybczynska
2016-06-09 15:40                         ` Steve Wise
2016-06-09 15:48                           ` Steve Wise
2016-06-10  9:03                             ` Marta Rybczynska
2016-06-10 13:40                               ` Steve Wise
2016-06-10 13:42                                 ` Marta Rybczynska
2016-06-10 13:49                                   ` Steve Wise
2016-06-09 13:25   ` Christoph Hellwig
2016-06-09 13:24 ` Christoph Hellwig
2016-06-09 15:37   ` Marta Rybczynska
2016-06-09 20:25     ` Steve Wise
2016-06-09 20:35       ` Ming Lin
2016-06-09 21:06         ` Steve Wise
2016-06-09 22:26           ` Ming Lin
2016-06-09 22:40             ` Steve Wise
     [not found]             ` <055801d1c29f$e164c000$a42e4000$@opengridcomputing.com>
2016-06-10 15:11               ` Steve Wise
2016-06-10 16:22                 ` Steve Wise
2016-06-10 18:43                   ` Ming Lin
2016-06-10 19:17                     ` Steve Wise
2016-06-10 20:00                       ` Ming Lin
2016-06-10 20:15                         ` Steve Wise
2016-06-10 20:18                           ` Ming Lin
2016-06-10 21:14                             ` Steve Wise
2016-06-10 21:20                               ` Ming Lin
2016-06-10 21:25                                 ` 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=575973A4.9080001@lightbits.io \
    --to=sagi@lightbits.io \
    /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