Re: tbench regression on each kernel release from 2.6.22 -> 2.6.28

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: David Miller
Date: Monday, August 11, 2008 - 2:50 pm

From: Christoph Lameter <cl@linux-foundation.org>
Date: Mon, 11 Aug 2008 16:33:43 -0500


It could be, and any kind of analysis into this would be great.

I had a change that RCU destroyed sockets and this added a
tiny bit of latency, so I never added it even though it would
have allowed a lot of simplification of socket handling (which
I though would make up for RCU's latency, but it didn't).
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
tbench regression on each kernel release from 2.6.22 -&gt; 2 ..., Christoph Lameter, (Mon Aug 11, 11:36 am)
Re: tbench regression on each kernel release from 2.6.22 ..., Christoph Lameter, (Mon Aug 11, 11:56 am)
Re: tbench regression on each kernel release from 2.6.22 - ..., Christoph Lameter, (Mon Aug 11, 2:33 pm)
Re: tbench regression on each kernel release from 2.6.22 - ..., David Miller, (Mon Aug 11, 2:50 pm)
Re: tbench regression on each kernel release from 2.6.22 - ..., Christoph Lameter, (Tue Aug 12, 11:57 am)
Re: tbench regression on each kernel release from 2.6.22 - ..., Christoph Lameter, (Mon Aug 18, 7:07 am)
Re: tbench regression on each kernel release from 2.6.22 - ..., Christoph Lameter, (Mon Aug 18, 7:34 am)