[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080827165635.GY26610@one.firstfloor.org>
Date: Wed, 27 Aug 2008 18:56:35 +0200
From: Andi Kleen <andi@...stfloor.org>
To: Rick Jones <rick.jones2@...com>
Cc: Andi Kleen <andi@...stfloor.org>,
Evgeniy Polyakov <johnpol@....mipt.ru>,
Eric Dumazet <dada1@...mosbay.com>,
Denys Fedoryshchenko <denys@...p.net.lb>,
netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: loaded router, excessive getnstimeofday in oprofile
On Wed, Aug 27, 2008 at 09:49:10AM -0700, Rick Jones wrote:
> Andi Kleen wrote:
> >>Those banks really want to crank down on latency - to the point they
> >>start disabling interrupt coalescing. I bet they'd toss anything out
> >>they could to shave another microsecond.
> >
> >
> >This change would actually likely lower their latency.
>
> I'm guessing you mean increase their latency? I agree, it could -
> depends entirely on the PPS in production I suspect.
No, moving the time stamps into the socket decreases latency
for all packets that don't need time stamps. And they likely
have some packets which don't need time stamps too.
As a secondary effect if they use a RT kernel it might
be also beneficial to do the (depending on the platform)
costly time stamp in the lower priority socket context
than in the high priority interrupt thread.
-Andi
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists