From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Pekka Enberg" Subject: Re: [PATCH 00/28] Swap over NFS -v16 Date: Fri, 29 Feb 2008 13:58:52 +0200 Message-ID: <84144f020802290358t2774f7bwd87efe79e7bd4235@mail.gmail.com> References: <20080220144610.548202000@chello.nl> <20080223000620.7fee8ff8.akpm@linux-foundation.org> <18371.43950.150842.429997@notabene.brown> <1204023042.6242.271.camel@lappy> <18372.64081.995262.986841@notabene.brown> <1204099113.6242.353.camel@lappy> <84144f020802270005p3bfbd04ar9da2875218ef98c4@mail.gmail.com> <1204285912.6243.93.camel@lappy> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "Neil Brown" , "Andrew Morton" , "Linus Torvalds" , linux-kernel@vger.kernel.org, linux-mm@kvack.org, netdev@vger.kernel.org, trond.myklebust@fys.uio.no, "Christoph Lameter" To: "Peter Zijlstra" Return-path: Received: from rv-out-0910.google.com ([209.85.198.187]:2142 "EHLO rv-out-0910.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754033AbYB2L6x (ORCPT ); Fri, 29 Feb 2008 06:58:53 -0500 Received: by rv-out-0910.google.com with SMTP id k20so2532592rvb.1 for ; Fri, 29 Feb 2008 03:58:52 -0800 (PST) In-Reply-To: <1204285912.6243.93.camel@lappy> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: Hi Peter, On Fri, Feb 29, 2008 at 1:51 PM, Peter Zijlstra wrote: > I made page->reserve into PG_emergency and made that bit stick for the > lifetime of that page allocation. I then made kmem_is_emergency() look > up the head page backing that allocation's slab and return > PageEmergency(). [snip] On Fri, Feb 29, 2008 at 1:51 PM, Peter Zijlstra wrote: > This is a stricter model than I had before, and has one ramification I'm > not entirely sure I like. > > It means the page remains a reserve page throughout its lifetime, which > means the slab remains a reserve slab throughout its lifetime. Therefore > it may never be used for !reserve allocations. Which in turn generates > complexities for the partial list. Hmm, so why don't we then clear the PG_emergency flag then and allocate a new fresh page to the reserves? On Fri, Feb 29, 2008 at 1:51 PM, Peter Zijlstra wrote: > Does this sound like something I should pursuit? I feel it might > complicate the slab allocators too much.. I can't answer that question until I see the code ;-). But overall, I think it's better to put that code in SLUB rather than trying to work around it elsewhere. The fact is, as soon as you have some sort of reservation for _objects_, you need help from the SLUB allocator. Pekka