From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754037AbbGOX7O (ORCPT ); Wed, 15 Jul 2015 19:59:14 -0400 Received: from mail-pd0-f172.google.com ([209.85.192.172]:35940 "EHLO mail-pd0-f172.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753916AbbGOX7N (ORCPT ); Wed, 15 Jul 2015 19:59:13 -0400 Date: Thu, 16 Jul 2015 08:59:44 +0900 From: Sergey Senozhatsky To: Minchan Kim Cc: Sergey Senozhatsky , Andrew Morton , linux-mm@kvack.org, linux-kernel@vger.kernel.org, Sergey Senozhatsky Subject: Re: [PATCH 3/3] zsmalloc: do not take class lock in zs_pages_to_compact() Message-ID: <20150715235944.GA3970@swordfish> References: <1436607932-7116-1-git-send-email-sergey.senozhatsky@gmail.com> <1436607932-7116-4-git-send-email-sergey.senozhatsky@gmail.com> <20150715040703.GA545@swordfish> <20150715233834.GA988@bgram> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20150715233834.GA988@bgram> User-Agent: Mutt/1.5.23+102 (2ca89bed6448) (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, On (07/16/15 08:38), Minchan Kim wrote: > > > diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c > > > index b10a228..824c182 100644 > > > --- a/mm/zsmalloc.c > > > +++ b/mm/zsmalloc.c > > > @@ -1811,9 +1811,7 @@ unsigned long zs_pages_to_compact(struct zs_pool *pool) > > > if (class->index != i) > > > continue; > > > > > > - spin_lock(&class->lock); > > > pages_to_free += zs_can_compact(class); > > > - spin_unlock(&class->lock); > > > } > > > > > > return pages_to_free; > > > > This patch still makes sense. Agree? > > There is already race window between shrink_count and shrink_slab so > it would be okay if we return stale stat with removing the lock if > the difference is not huge. > > Even, now we don't obey nr_to_scan of shrinker in zs_shrinker_scan > so the such accuracy would be pointless. Yeah, automatic shrinker may work concurrently with the user triggered one, so it may be hard (time consuming) to release the exact amount of pages that we returned from _count(). We can look at `sc->nr_to_reclaim' to avoid releasing more pages than shrinker wants us to release, but I'd probably prefer to keep the existing behaviour if we were called by the shrinker. OK, will resend later today. -ss