From mboxrd@z Thu Jan 1 00:00:00 1970 From: tytso@mit.edu Subject: Re: [PATCH (RESEND)] don't scan/accumulate more pages than mballoc will allocate Date: Mon, 5 Apr 2010 09:11:05 -0400 Message-ID: <20100405131105.GB22104@thunk.org> References: <4BB0C761.50204@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: ext4 development To: Eric Sandeen Return-path: Received: from thunk.org ([69.25.196.29]:37573 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754465Ab0DENLH (ORCPT ); Mon, 5 Apr 2010 09:11:07 -0400 Content-Disposition: inline In-Reply-To: <4BB0C761.50204@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Mon, Mar 29, 2010 at 10:29:37AM -0500, Eric Sandeen wrote: > This patch makes mpage_add_bh_to_extent stop the loop after we've > accumulated 2048 pages, by setting mpd->io_done = 1; which ultimately > causes the write_cache_pages loop to break. > > Repeating the test with a dirty_ratio of 80 (to leave something for > fsync to do), I don't see huge IO performance gains, but the reduction > in cpu usage is striking: 80% usage with stock, and 2% with the > below patch. Instrumenting the loop in write_cache_pages clearly > shows that we are wasting time here. > > It'd be better to not have a magic number of 2048 in here, so I'll > look for a cleaner way to get this info out of mballoc; I still need > to look at what Aneesh has in the patch queue, that might help. > This is something we could probably put in for now, though; the 2048 > is already enshrined in a comment in inode.c, at least. I wonder if a better way of fixing this is to changing mpage_da_map_pages() to call ext4_get_blocks() multiple times. This should be a lot easier after we integrate mpage_da_submit_io() into mpage_da_map_pages(). That way we can way more efficient; in a loop, we accumulate the pages, call ext4_get_blocks(), then submit the IO (as a single block I/O submission, instead of 4k at a time through ext4_writepages()), and then call ext4_get_blocks() again, etc. I'm willing to include this patch as an interim stopgap, but eventually, I think we need to refactor and reorganize mpage_da_map_pages() and and mpage_da_submit_IO(), and let them call mballoc (via ext4_get_blocks) multiple times in a loop. Thoughts, suggestions? - Ted