From: Sagi Grimberg <sagi@grimberg.me>
To: Potnuri Bharat Teja <bharat@chelsio.com>
Cc: Steve Wise <swise@opengridcomputing.com>,
target-devel@vger.kernel.org, nab@linux-iscsi.org,
linux-rdma@vger.kernel.org
Subject: Re: SQ overflow seen running isert traffic
Date: Tue, 18 Oct 2016 16:17:53 +0300 [thread overview]
Message-ID: <ed7ebb39-be81-00b3-ef23-3f4c0e3afbb1@grimberg.me> (raw)
In-Reply-To: <20161018112801.GA3117@chelsio.com>
> I tried out this change and it works fine with iwarp. I dont see SQ
> overflow. Apparently we have increased the sq too big to overflow. I am going
> to let it run with higher workloads for longer time, to see if it holds good.
Actually on second thought, this patch is an overkill. Effectively we
now set:
MAX_CMD=266
and max_rdma_ctx=128 so together we take 394 which seems to too much.
If we go by the scheme of 1 rdma + 1 send for each IO we need:
- 128 sends
- 128 rdmas
- 10 miscs
so this gives 266.
Perhaps this is due to the fact that iWARP needs to register memory for
rdma reads as well? (and also rdma writes > 128k for chelsio HW right?)
What is the workload you are running? with immediatedata enabled you
should issue reg+rdma_read+send only for writes > 8k.
Does this happen when you run only reads for example?
I guess its time to get the sq accounting into shape...
next prev parent reply other threads:[~2016-10-18 13:17 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-27 7:01 RQ overflow seen running isert traffic Potnuri Bharat Teja
[not found] ` <20160927070157.GA13140-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
2016-09-29 14:12 ` Steve Wise
2016-10-05 6:14 ` Sagi Grimberg
2016-10-17 11:16 ` Potnuri Bharat Teja
2016-10-17 18:29 ` Steve Wise
2016-10-18 8:04 ` Sagi Grimberg
2016-10-18 11:28 ` SQ " Potnuri Bharat Teja
2016-10-18 13:17 ` Sagi Grimberg [this message]
[not found] ` <ed7ebb39-be81-00b3-ef23-3f4c0e3afbb1-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2016-10-18 14:34 ` Steve Wise
2016-10-18 16:13 ` Jason Gunthorpe
2016-10-18 19:03 ` Steve Wise
2016-10-20 8:34 ` Sagi Grimberg
[not found] ` <f7a4b395-1786-3c7a-7639-195e830db5ad-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-03-20 13:05 ` Potnuri Bharat Teja
2017-03-20 15:04 ` Steve Wise
2016-10-31 3:40 ` Nicholas A. Bellinger
2016-11-02 17:03 ` Steve Wise
[not found] ` <1477885208.27946.8.camel-XoQW25Eq2zviZyQQd+hFbcojREIfoBdhmpATvIKMPHk@public.gmane.org>
2016-11-08 10:06 ` Potnuri Bharat Teja
2017-03-20 10:15 ` Potnuri Bharat Teja
2017-03-21 6:32 ` Nicholas A. Bellinger
2017-03-21 7:51 ` Potnuri Bharat Teja
[not found] ` <20170321075131.GA11565-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
2017-03-21 13:52 ` Sagi Grimberg
[not found] ` <945e2947-f67a-4202-cd27-d4631fe10f68-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-03-21 15:25 ` [SPAMMY (7.002)]Re: " Potnuri Bharat Teja
[not found] ` <20170321152506.GA32655-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
2017-03-21 16:38 ` Sagi Grimberg
[not found] ` <4dab6b43-20d3-86f0-765a-be0851e9f4a0-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org>
2017-03-21 17:50 ` Potnuri Bharat Teja
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=ed7ebb39-be81-00b3-ef23-3f4c0e3afbb1@grimberg.me \
--to=sagi@grimberg.me \
--cc=bharat@chelsio.com \
--cc=linux-rdma@vger.kernel.org \
--cc=nab@linux-iscsi.org \
--cc=swise@opengridcomputing.com \
--cc=target-devel@vger.kernel.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.