From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0b-00082601.pphosted.com ([67.231.153.30]:64882 "EHLO mx0b-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754120AbcCYR0d (ORCPT ); Fri, 25 Mar 2016 13:26:33 -0400 Received: from pps.filterd (m0089730.ppops.net [127.0.0.1]) by m0089730.ppops.net (8.16.0.11/8.16.0.11) with SMTP id u2PHKjbp021158 for ; Fri, 25 Mar 2016 10:26:32 -0700 Received: from mail.thefacebook.com ([199.201.64.23]) by m0089730.ppops.net with ESMTP id 21vva22wjj-1 (version=TLSv1 cipher=AES128-SHA bits=128 verify=NOT) for ; Fri, 25 Mar 2016 10:26:32 -0700 From: Josef Bacik To: Subject: [PATCH 14/14] Btrfs: don't do nocow check unless we have to Date: Fri, 25 Mar 2016 13:26:00 -0400 Message-ID: <1458926760-17563-15-git-send-email-jbacik@fb.com> In-Reply-To: <1458926760-17563-1-git-send-email-jbacik@fb.com> References: <1458926760-17563-1-git-send-email-jbacik@fb.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-btrfs-owner@vger.kernel.org List-ID: Before we write into prealloc/nocow space we have to make sure that there are no references to the extents we are writing into, which means checking the extent tree and csum tree in the case of nocow. So we don't want to do the nocow dance unless we can't reserve data space, since it's a serious drag on performance. With the following sequence fallocate -l10737418240 /mnt/btrfs-test/file cp --reflink /mnt/btrfs-test/file /mnt/btrfs-test/link fio --name=randwrite --rw=randwrite --bs=4k --filename=/mnt/btrfs-test/file \ --end_fsync=1 we get the worst case scenario where we have to fall back on to doing the check anyway. Without this patch lat (usec): min=5, max=111598, avg=27.65, stdev=124.51 write: io=10240MB, bw=126876KB/s, iops=31718, runt= 82646msec With this patch lat (usec): min=3, max=91210, avg=14.09, stdev=110.62 write: io=10240MB, bw=212753KB/s, iops=53188, runt= 49286msec We get twice the throughput, half of the runtime, and half of the average latency. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/file.c | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0ce4bb3..7c80208 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = round_up(write_bytes + sector_offset, root->sectorsize); - if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) && - check_can_nocow(inode, pos, &write_bytes) > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ - only_release_metadata = true; - /* - * our prealloc extent may be smaller than - * write_bytes, so scale down. - */ - num_pages = DIV_ROUND_UP(write_bytes + offset, - PAGE_CACHE_SIZE); - reserve_bytes = round_up(write_bytes + sector_offset, - root->sectorsize); - goto reserve_metadata; - } - ret = btrfs_check_data_free_space(inode, pos, write_bytes); - if (ret < 0) - break; + if (ret < 0) { + if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) && + check_can_nocow(inode, pos, &write_bytes) > 0) { + /* + * For nodata cow case, no need to reserve + * data space. + */ + only_release_metadata = true; + /* + * our prealloc extent may be smaller than + * write_bytes, so scale down. + */ + num_pages = DIV_ROUND_UP(write_bytes + offset, + PAGE_CACHE_SIZE); + reserve_bytes = round_up(write_bytes + + sector_offset, + root->sectorsize); + } else { + break; + } + } -reserve_metadata: ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes); if (ret) { if (!only_release_metadata) -- 2.5.0