From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 21 Mar 2007 15:29:30 GMT
Subject: Re: Be more careful about zlib return values
Message-ID: <Pine.LNX.4.64.0703210827591.6730@woody.linux-foundation.org>
In-Reply-To: <7vodmn2eya.fsf@assigned-by-dhcp.cox.net>



On Wed, 21 Mar 2007, Junio C Hamano wrote:
> 
> I am observing a very curious performance regression with this
> patch.  I do not see anything obviously wrong correctness-wise
> nor performance-wise with it.

Ok, the test you are doing won't call the write function at all, so the 
performance effect you see is almost certainly due to [un]lucky I$ 
placement. It happens..

		Linus