From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754997AbZEEXld (ORCPT ); Tue, 5 May 2009 19:41:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753242AbZEEXlY (ORCPT ); Tue, 5 May 2009 19:41:24 -0400 Received: from mga14.intel.com ([143.182.124.37]:49626 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752021AbZEEXlX (ORCPT ); Tue, 5 May 2009 19:41:23 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.40,299,1239001200"; d="scan'208";a="139567026" Date: Wed, 6 May 2009 07:40:56 +0800 From: Wu Fengguang To: "Rafael J. Wysocki" Cc: "linux-pm@lists.linux-foundation.org" , Andrew Morton , "pavel@ucw.cz" , "torvalds@linux-foundation.org" , "jens.axboe@oracle.com" , "alan-jenkins@tuffmail.co.uk" , "linux-kernel@vger.kernel.org" , "kernel-testers@vger.kernel.org" Subject: Re: [PATCH 5/5] PM/Hibernate: Do not release preallocated memory unnecessarily (rev. 2) Message-ID: <20090505234056.GA6778@localhost> References: <20090505022427.GA10880@localhost> <20090505024646.GA14621@localhost> <200905060107.45345.rjw@sisk.pl> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200905060107.45345.rjw@sisk.pl> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, May 06, 2009 at 07:07:44AM +0800, Rafael J. Wysocki wrote: > On Tuesday 05 May 2009, Wu Fengguang wrote: > > On Tue, May 05, 2009 at 10:24:27AM +0800, Wu Fengguang wrote: > > > On Mon, May 04, 2009 at 08:22:38AM +0800, Rafael J. Wysocki wrote: > > > > From: Rafael J. Wysocki > > > > > > > > Since the hibernation code is now going to use allocations of memory > > > > to create enough room for the image, it can also use the page frames > > > > allocated at this stage as image page frames. The low-level > > > > hibernation code needs to be rearranged for this purpose, but it > > > > allows us to avoid freeing a great number of pages and allocating > > > > these same pages once again later, so it generally is worth doing. > > > > > > > > [rev. 2: Change the strategy of preallocating memory to allocate as > > > > many pages as needed to get the right image size in one shot (the > > > > excessive allocated pages are released afterwards).] > > > > > > Rafael, I tried out your patches and found doubled memory shrink speed! > > > > > > [ 579.641781] PM: Preallocating image memory ... done (allocated 383900 pages, 128000 image pages kept) > > > [ 583.087875] PM: Allocated 1535600 kbytes in 3.43 seconds (447.69 MB/s) > > > > > For you reference, here is the free memory before/after > > > hibernate_preallocate_memory(): > > > > > > # free > > > total used free shared buffers cached > > > Mem: 1933 1917 15 0 0 1845 > > > -/+ buffers/cache: 72 1861 > > > Swap: 0 0 0 > > > > > > # free > > > total used free shared buffers cached > > > Mem: 1933 920 1012 0 0 356 > > > -/+ buffers/cache: 563 1369 > > > Swap: 0 0 0 > > > > > > It seems that the preallocated memory is not freed on -ENOMEM. > > > > Ah, this was my fault. > > > > I used to do this debugging trick: > > > > @@ -1207,7 +1207,7 @@ int hibernate_preallocate_memory(void) > > pages, size); > > swsusp_show_speed(&start, &stop, pages, "Allocated"); > > > > - return 0; > > + return -ENOMEM; > > > > err_out: > > printk(KERN_CONT "\n"); > > > > That "return -ENOMEM" should be "error = -ENOMEM" :-) > > > > Here is one more run: > > > > [ 194.016991] PM: Preallocating image memory ... done (allocated 383897 pages, 128000 image pages kept) > > [ 196.505999] PM: Allocated 1535588 kbytes in 2.47 seconds (621.69 MB/s) > > > > Now the free report is back to normal: > > > > # free > > total used free shared buffers cached > > Mem: 1933 74 1858 0 0 15 The above 'free' still exposed something wrong: only 74M memory are left, instead of image_size=500M memory. I'm prepared to test your updated patches :-) From mboxrd@z Thu Jan 1 00:00:00 1970 From: Wu Fengguang Subject: Re: [PATCH 5/5] PM/Hibernate: Do not release preallocated memory unnecessarily (rev. 2) Date: Wed, 6 May 2009 07:40:56 +0800 Message-ID: <20090505234056.GA6778@localhost> References: <20090505022427.GA10880@localhost> <20090505024646.GA14621@localhost> <200905060107.45345.rjw@sisk.pl> Mime-Version: 1.0 Return-path: Content-Disposition: inline In-Reply-To: <200905060107.45345.rjw-KKrjLPT3xs0@public.gmane.org> Sender: kernel-testers-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: "Rafael J. Wysocki" Cc: "linux-pm-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org" , Andrew Morton , "pavel-+ZI9xUNit7I@public.gmane.org" , "torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org" , "jens.axboe-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org" , "alan-jenkins-cCz0Lq7MMjm9FHfhHBbuYA@public.gmane.org" , "linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , "kernel-testers-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" On Wed, May 06, 2009 at 07:07:44AM +0800, Rafael J. Wysocki wrote: > On Tuesday 05 May 2009, Wu Fengguang wrote: > > On Tue, May 05, 2009 at 10:24:27AM +0800, Wu Fengguang wrote: > > > On Mon, May 04, 2009 at 08:22:38AM +0800, Rafael J. Wysocki wrote: > > > > From: Rafael J. Wysocki > > > > > > > > Since the hibernation code is now going to use allocations of memory > > > > to create enough room for the image, it can also use the page frames > > > > allocated at this stage as image page frames. The low-level > > > > hibernation code needs to be rearranged for this purpose, but it > > > > allows us to avoid freeing a great number of pages and allocating > > > > these same pages once again later, so it generally is worth doing. > > > > > > > > [rev. 2: Change the strategy of preallocating memory to allocate as > > > > many pages as needed to get the right image size in one shot (the > > > > excessive allocated pages are released afterwards).] > > > > > > Rafael, I tried out your patches and found doubled memory shrink speed! > > > > > > [ 579.641781] PM: Preallocating image memory ... done (allocated 383900 pages, 128000 image pages kept) > > > [ 583.087875] PM: Allocated 1535600 kbytes in 3.43 seconds (447.69 MB/s) > > > > > For you reference, here is the free memory before/after > > > hibernate_preallocate_memory(): > > > > > > # free > > > total used free shared buffers cached > > > Mem: 1933 1917 15 0 0 1845 > > > -/+ buffers/cache: 72 1861 > > > Swap: 0 0 0 > > > > > > # free > > > total used free shared buffers cached > > > Mem: 1933 920 1012 0 0 356 > > > -/+ buffers/cache: 563 1369 > > > Swap: 0 0 0 > > > > > > It seems that the preallocated memory is not freed on -ENOMEM. > > > > Ah, this was my fault. > > > > I used to do this debugging trick: > > > > @@ -1207,7 +1207,7 @@ int hibernate_preallocate_memory(void) > > pages, size); > > swsusp_show_speed(&start, &stop, pages, "Allocated"); > > > > - return 0; > > + return -ENOMEM; > > > > err_out: > > printk(KERN_CONT "\n"); > > > > That "return -ENOMEM" should be "error = -ENOMEM" :-) > > > > Here is one more run: > > > > [ 194.016991] PM: Preallocating image memory ... done (allocated 383897 pages, 128000 image pages kept) > > [ 196.505999] PM: Allocated 1535588 kbytes in 2.47 seconds (621.69 MB/s) > > > > Now the free report is back to normal: > > > > # free > > total used free shared buffers cached > > Mem: 1933 74 1858 0 0 15 The above 'free' still exposed something wrong: only 74M memory are left, instead of image_size=500M memory. I'm prepared to test your updated patches :-)