public inbox for netdev@vger.kernel.org 
 help / color / mirror / Atom feed
From: Hadar Hen Zion <hadarh@mellanox•com>
To: Richard Cochran <richardcochran@gmail•com>
Cc: Shawn Bohrer <shawn.bohrer@gmail•com>,
	"David S. Miller" <davem@davemloft•net>,
	Or Gerlitz <ogerlitz@mellanox•com>,
	Amir Vadai <amirv@mellanox•com>, <netdev@vger•kernel.org>,
	<tomk@rgmadvisors•com>, Shawn Bohrer <sbohrer@rgmadvisors•com>
Subject: Re: [PATCH net-next 1/2] mlx4_en: Add PTP hardware clock
Date: Tue, 24 Dec 2013 15:58:06 +0200	[thread overview]
Message-ID: <52B992EE.5030401@mellanox.com> (raw)
In-Reply-To: <20131223184845.GA4922@netboy>

On 12/23/2013 8:48 PM, Richard Cochran wrote:
> On Sun, Dec 22, 2013 at 03:13:12PM +0200, Hadar Hen Zion wrote:
>
>> 2. Adding spin lock in the data path reduce performance by 15% when
>> HW timestamping is enabled. I did some testing and replacing
>> spin_lock_irqsave with read/write_lock_irqsave prevents the
>> performance decrease.
>
> Why do the spin locks cause such a bottleneck?
>
> Is there really that much lock contention in your test?
>
> Your figure of 15% seems awfully high. How did you arrive at that
> figure?
>
> Thanks,
> Richard
>

The spin locks case such a bottleneck since I'm using multiple streams 
in my performance test. RSS mechanism scattered the streams between 
multiple RX rings while each RX ring is bound to a different cup.
The describe scenario cause lock contention between the different RX rings.

Performance drops from 37.8 Gbits/sec to 32.1 Gbits/sec when spin locks 
are added and goes back to 37.8 Gbits/sec when using read/write locks.

Thanks,
Hadar

  reply	other threads:[~2013-12-24 13:58 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-17 20:32 [PATCH net-next 0/2] mlx4_en: Add PTP support Shawn Bohrer
2013-12-17 20:32 ` [PATCH net-next 1/2] mlx4_en: Add PTP hardware clock Shawn Bohrer
2013-12-17 21:04   ` Or Gerlitz
2013-12-17 21:46     ` Shawn Bohrer
2013-12-18  7:59       ` Or Gerlitz
2013-12-18 15:03         ` Shawn Bohrer
2013-12-22 13:13   ` Hadar Hen Zion
2013-12-23 16:29     ` Shawn Bohrer
2013-12-23 16:59       ` Shawn Bohrer
2013-12-24 15:38         ` Hadar Hen Zion
2013-12-25 11:49           ` Richard Cochran
2013-12-23 18:48     ` Richard Cochran
2013-12-24 13:58       ` Hadar Hen Zion [this message]
2013-12-25 11:53         ` Richard Cochran
     [not found]           ` <CAKBbMu33zXkG4+S1kP6zB+4iKMNNoy=XVBtoqZZEkqurRsgvQw@mail.gmail.com>
2013-12-25 17:02             ` Richard Cochran
2013-12-26  8:26           ` Hadar Hen Zion
2013-12-26  8:33             ` Hadar Hen Zion
2013-12-26  9:17               ` Richard Cochran
2013-12-26 14:41                 ` Hadar Hen-Zion
2013-12-26 14:49                   ` Richard Cochran
2013-12-17 20:32 ` [PATCH net-next 2/2] mlx4_en: Only cycle port if HW timestamp config changes Shawn Bohrer

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=52B992EE.5030401@mellanox.com \
    --to=hadarh@mellanox$(echo .)com \
    --cc=amirv@mellanox$(echo .)com \
    --cc=davem@davemloft$(echo .)net \
    --cc=netdev@vger$(echo .)kernel.org \
    --cc=ogerlitz@mellanox$(echo .)com \
    --cc=richardcochran@gmail$(echo .)com \
    --cc=sbohrer@rgmadvisors$(echo .)com \
    --cc=shawn.bohrer@gmail$(echo .)com \
    --cc=tomk@rgmadvisors$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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