All of lore.kernel.org
 help / color / mirror / Atom feed
From: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: "Marciniszyn,
	Mike" <mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	"linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: Problem running rping over Intel adapters
Date: Wed, 03 Oct 2012 17:40:57 -0400	[thread overview]
Message-ID: <506CB0E9.90201@redhat.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 2096 bytes --]

We ran into this problem when testing rping over Intel/QLogic hardware:

[root@rdmaperf3 ~]# rping -s -a 172.31.2.103 -v
wait for CONNECTED state 10
connect error -1
cma event RDMA_CM_EVENT_REJECTED, error 28
[root@rdmaperf3 ~]#


[root@rdmaperf8 ~]# rping -c -a 172.31.2.103 -v -C 5
cma event RDMA_CM_EVENT_CONNECT_ERROR, error -1
wait for CONNECTED state 4
connect error -1
[root@rdmaperf8 ~]#

Turns out this is because of a couple things:

1) rping, on the client side, clears the conn_params for the newly to be
attempted connection, then sets:

	conn_param.responder_resources = 1;
	conn_param.initiator_depth = 1;
	conn_param.retry_count = 10;

On the accept side, rping clears the conn_params and then sets just the
responder_resources and initiator_depth, without even checking the
incoming requested conn_param values from the incoming cm_id.  So, OK,
you can get away with that since this is a simple test program, but
still not "best programming practices".  However, the important part
here is the retry_count of 10.  That won't work on Intel/QLogic hardware.

2) the qib driver enforces a maximum of 7 for retry_count.  I don't see
anything in the spec that specifies a maximum for this entry, and in
particular I know it doesn't call out for 7 to mean infinite retries
like it does for rnr_retry_count.

I don't think the spec really cares how we solve this, and I don't think
there is a hard limit of 7 for the retry_count like the qib driver
enforces.  On the other hand, the spec doesn't call out a limit on the
retry_count but I would assume each driver has the option to implement
their own "reasonable, implementation defined" limit in a case like this.

So, do we make qib more liberal in its acceptance of retry_count or do
we fix rping to use a smaller number?  Matters not to me...

-- 
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
              GPG KeyID: 0E572FDD
	      http://people.redhat.com/dledford

Infiniband specific RPMs available at
	      http://people.redhat.com/dledford/Infiniband


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 895 bytes --]

             reply	other threads:[~2012-10-03 21:40 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-03 21:40 Doug Ledford [this message]
     [not found] ` <506CB0E9.90201-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-10-03 21:50   ` Problem running rping over Intel adapters Hefty, Sean
     [not found]     ` <1828884A29C6694DAF28B7E6B8A8237346A98E58-Q3cL8pyY+6ukrb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2012-10-03 21:57       ` Doug Ledford
     [not found]         ` <506CB4D8.4010604-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-10-03 22:02           ` Hefty, Sean
     [not found]             ` <1828884A29C6694DAF28B7E6B8A8237346A98E8E-Q3cL8pyY+6ukrb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2012-10-03 22:05               ` Doug Ledford
2012-10-04  1:47               ` Steve Wise
     [not found]                 ` <506CEAC1.9070808-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2012-10-04  5:41                   ` Or Gerlitz
     [not found]                     ` <506D2174.10601-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2012-10-04 14:27                       ` Steve Wise
     [not found]                         ` <506D9CD2.20606-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
2012-10-04 15:01                           ` Hefty, Sean
     [not found]                             ` <1828884A29C6694DAF28B7E6B8A8237346A99126-Q3cL8pyY+6ukrb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2012-10-04 15:08                               ` Steve Wise
2012-10-03 22:38   ` Hefty, Sean
     [not found]     ` <1828884A29C6694DAF28B7E6B8A8237346A98ECB-Q3cL8pyY+6ukrb+BlOpmy7fspsVTdybXVpNB7YpNyf8@public.gmane.org>
2012-10-04 13:55       ` Marciniszyn, Mike

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=506CB0E9.90201@redhat.com \
    --to=dledford-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=mike.marciniszyn-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org \
    --cc=sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.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.