From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
To: Chuck Lever <chuck.lever@oracle.com>
Cc: sagi@grimberg.me, linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: Re: [PATCH RFC 0/5] xprtrdma Send completion batching
Date: Tue, 5 Sep 2017 14:06:08 -0600 [thread overview]
Message-ID: <20170905200608.GA4055@obsidianresearch.com> (raw)
In-Reply-To: <20170905164347.11106.27140.stgit@manet.1015granger.net>
On Tue, Sep 05, 2017 at 01:00:10PM -0400, Chuck Lever wrote:
> - Send completions are batched to reduce interrupts, but still
> provide a periodic heartbeat signal for SQ housekeeping
I would scrub this commentary, it is very misleading.
The idea of a periodic completion does not match how verbs works at
all, it was an incomplete root cause analysis from a HCA that uses
different rules for freeing space in the SQ.
Instead, I would say this series creates strong SQ accounting and
properly guarentees the SQ can never overflow by only releasing SQ's
back into the pool when the HCA has confirmed they are completed via a
CQ.
Jason
next prev parent reply other threads:[~2017-09-05 20:06 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-05 17:00 [PATCH RFC 0/5] xprtrdma Send completion batching Chuck Lever
2017-09-05 17:00 ` [PATCH RFC 1/5] xprtrdma: Clean up SGE accounting in rpcrdma_prepare_msg_sges() Chuck Lever
2017-09-05 17:00 ` [PATCH RFC 2/5] xprtrdma: Change return value of rpcrdma_prepare_send_sges() Chuck Lever
2017-09-05 17:00 ` [PATCH RFC 3/5] xprtrdma: Add data structure to manage RDMA Send arguments Chuck Lever
2017-09-05 17:00 ` [PATCH RFC 4/5] xprtrdma: Manage RDMA Send arguments via lock-free circular queue Chuck Lever
2017-09-05 21:50 ` Chuck Lever
2017-09-05 17:00 ` [PATCH RFC 5/5] xprtrdma: Remove atomic send completion counting Chuck Lever
2017-09-05 20:06 ` Jason Gunthorpe [this message]
2017-09-05 21:22 ` [PATCH RFC 0/5] xprtrdma Send completion batching Chuck Lever
2017-09-05 22:03 ` Jason Gunthorpe
2017-09-06 14:17 ` Chuck Lever
2017-09-06 1:28 ` Tom Talpey
2017-09-06 11:54 ` Sagi Grimberg
2017-09-06 14:15 ` Chuck Lever
2017-09-06 14:29 ` Sagi Grimberg
2017-09-06 15:11 ` Chuck Lever
2017-09-06 15:23 ` Sagi Grimberg
2017-09-06 18:33 ` Chuck Lever
2017-09-06 19:39 ` Jason Gunthorpe
2017-09-06 20:02 ` Chuck Lever
2017-09-06 20:09 ` Jason Gunthorpe
2017-09-06 21:00 ` Chuck Lever
2017-09-06 21:11 ` Jason Gunthorpe
2017-09-07 13:17 ` Tom Talpey
2017-09-07 15:08 ` Jason Gunthorpe
2017-09-07 16:15 ` Tom Talpey
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=20170905200608.GA4055@obsidianresearch.com \
--to=jgunthorpe@obsidianresearch.com \
--cc=chuck.lever@oracle.com \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
--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).