public inbox for linux-rdma@vger.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
To: Matan Barak <matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Majd Dibbiny <majd-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH for-next 0/2] IB/mlx5: Use tasklet to decrease completions processing time in interrupts
Date: Mon, 18 Apr 2016 06:04:56 -0700	[thread overview]
Message-ID: <20160418130456.GA11508@infradead.org> (raw)
In-Reply-To: <1460902121-5567-1-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

On Sun, Apr 17, 2016 at 05:08:39PM +0300, Matan Barak wrote:
> Hi Doug,
> 
> The mlx5 driver handles completion callbacks inside interrupts.
> These callbacks could be lengthy and thus cause hard lockups.
> In order to avoid these lockups, we introduce a tasklet mechanism.
> The mlx5_ib driver uses this mechanism in order to defer its
> completion callbacks processing to the tasklet.
> 
> This follows the same mechanism we implemented for mlx4 that
> successfully decreased the processing time in interrupts.

Just curious:  how much of this time is spent inside the mlx5 driver,
and how much is spent in the callbacks from the consumers?  We've now
more than half done with switch the kernel ULPs to the new CQ API
which will always offload the callbacks to softirq or workqueue context,
so if we can avoid a previous offload the completions would be a lot
more efficient.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  parent reply	other threads:[~2016-04-18 13:04 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-17 14:08 [PATCH for-next 0/2] IB/mlx5: Use tasklet to decrease completions processing time in interrupts Matan Barak
     [not found] ` <1460902121-5567-1-git-send-email-matanb-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2016-04-17 14:08   ` [PATCH for-next 1/2] net/mlx5_core: Use tasklet for user-space CQ completion events Matan Barak
2016-04-17 14:08   ` [PATCH for-next 2/2] IB/mlx5: Fire the CQ completion handler from tasklet Matan Barak
2016-04-18 13:04   ` Christoph Hellwig [this message]
     [not found]     ` <20160418130456.GA11508-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
2016-04-18 13:21       ` [PATCH for-next 0/2] IB/mlx5: Use tasklet to decrease completions processing time in interrupts Matan Barak (External)
     [not found]         ` <5714DF68.6040509-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2016-04-18 14:33           ` Sagi Grimberg
2016-05-13 20:16           ` Doug Ledford
     [not found]             ` <a93b20ca-42bf-ca2b-2995-aa2837a1bafe-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2016-05-15  7:31               ` Matan Barak
     [not found]                 ` <868e5bcf-18c5-30f4-fe3f-b361c0ce43ec-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2016-05-18 14:48                   ` Doug Ledford

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=20160418130456.GA11508@infradead.org \
    --to=hch-wegcikhe2lqwvfeawa7xhq@public.gmane.org \
    --cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=majd-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=matanb-VPRAkNaXOzVWk0Htik3J/w@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox