From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758937AbXJaKYz (ORCPT ); Wed, 31 Oct 2007 06:24:55 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756632AbXJaKYr (ORCPT ); Wed, 31 Oct 2007 06:24:47 -0400 Received: from smtp108.mail.mud.yahoo.com ([209.191.85.218]:35882 "HELO smtp108.mail.mud.yahoo.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1755680AbXJaKYq (ORCPT ); Wed, 31 Oct 2007 06:24:46 -0400 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com.au; h=Received:X-YMail-OSG:From:To:Subject:Date:User-Agent:Cc:References:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding:Content-Disposition:Message-Id; b=wWQAuwwFU3+ChMX0QtixUsgt/y6z6clxHNO9hMbjMzQ+VWRNfI6rENgkVVNNV/FcaGHMprCaYBfgXvlpuYXpKoE4i/DxKShQ+hNqdVFYLoSoS1L/FfLt+FfCK+0TprOokAtP/0woJrBY0oZvXyNODiBWUN7NcOEmnN1OxumKHxE= ; X-YMail-OSG: OWyHNnUVM1kvBMmPpf0mZVj5chDclHow4idmVsSLBxrw75VHjxrRNDxOcpw_RQCzkzP8w2ejrw-- From: Nick Piggin To: Balbir Singh Subject: Re: [PATCH] Swap delay accounting, include lock_page() delays Date: Wed, 31 Oct 2007 20:10:33 +1100 User-Agent: KMail/1.9.5 Cc: Andrew Morton , Linux MM Mailing List , Linux Kernel Mailing List References: <20071031075243.22225.53636.sendpatchset@balbir-laptop> <200710311841.53671.nickpiggin@yahoo.com.au> In-Reply-To: <200710311841.53671.nickpiggin@yahoo.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200710312010.33833.nickpiggin@yahoo.com.au> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Wednesday 31 October 2007 18:41, Nick Piggin wrote: > On Wednesday 31 October 2007 18:52, Balbir Singh wrote: > > Reported-by: Nick Piggin > > > > The delay incurred in lock_page() should also be accounted in swap delay > > accounting > > > > Signed-off-by: Balbir Singh > > Ah right, I forgot to resend this one, sorry. Thanks for remembering. Although, I think I had a bit more detail in the changelog which I think should be kept. Basically, swap delay accounting seems quite broken as of now, because what it is counting is the time required to allocate a new page and submit the IO, but not actually the time to perform the IO at all (which I'd expect will be significant, although possibly in some workloads the actual page allocation will dominate). > > > --- > > > > mm/memory.c | 2 +- > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > diff -puN mm/swapfile.c~fix-delay-accounting-swap-accounting > > mm/swapfile.c diff -puN mm/memory.c~fix-delay-accounting-swap-accounting > > mm/memory.c --- > > linux-2.6-latest/mm/memory.c~fix-delay-accounting-swap-accounting 2007-10 > >-3 1 12:58:05.000000000 +0530 +++ > > linux-2.6-latest-balbir/mm/memory.c 2007-10-31 13:02:50.000000000 +0530 > > @@ -2084,9 +2084,9 @@ static int do_swap_page(struct mm_struct > > count_vm_event(PGMAJFAULT); > > } > > > > - delayacct_clear_flag(DELAYACCT_PF_SWAPIN); > > mark_page_accessed(page); > > lock_page(page); > > + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); > > > > /* > > * Back out if somebody else already faulted in this pte. > > _