From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from userp1040.oracle.com ([156.151.31.81]:36545 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753259AbcCQWN7 (ORCPT ); Thu, 17 Mar 2016 18:13:59 -0400 Received: from userv0021.oracle.com (userv0021.oracle.com [156.151.31.71]) by userp1040.oracle.com (Sentrion-MTA-4.3.2/Sentrion-MTA-4.3.2) with ESMTP id u2HMDwnN025956 (version=TLSv1 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Thu, 17 Mar 2016 22:13:58 GMT Received: from userv0122.oracle.com (userv0122.oracle.com [156.151.31.75]) by userv0021.oracle.com (8.13.8/8.13.8) with ESMTP id u2HMDwKL032623 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL) for ; Thu, 17 Mar 2016 22:13:58 GMT Received: from abhmp0010.oracle.com (abhmp0010.oracle.com [141.146.116.16]) by userv0122.oracle.com (8.14.4/8.14.4) with ESMTP id u2HMDvRL009877 for ; Thu, 17 Mar 2016 22:13:57 GMT From: Liu Bo To: linux-btrfs@vger.kernel.org Subject: [PATCH] Btrfs: fix performance regression of writing to prealloc/nocow file Date: Thu, 17 Mar 2016 15:16:15 -0700 Message-Id: <1458252975-1349-1-git-send-email-bo.li.liu@oracle.com> Sender: linux-btrfs-owner@vger.kernel.org List-ID: For nocow/prealloc files, we try our best to not allocate space, however, this ends up a huge performance regression since it's expensive to check if data is shared. Let's go back to only go check shared data once we're not able to allocate space. The test was made against a tmpfs backed loop device: xfs_io -f -c "falloc 0 400M" foobar xfs_io -c "pwrite -W -b 4096 0 400M" foobar Vanilla: wrote 419430400/419430400 bytes at offset 0 400 MiB, 102400 ops; 0:00:01.00 (200.015 MiB/sec and 51203.8403 ops/sec) Patched kernel: wrote 419430400/419430400 bytes at offset 0 400 MiB, 102400 ops; 0:00:01.00 (346.137 MiB/sec and 88610.9796 ops/sec) Signed-off-by: Liu Bo --- fs/btrfs/file.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 098bb8f..f66c1bc 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1525,16 +1525,12 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = num_pages << PAGE_CACHE_SHIFT; - if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | - BTRFS_INODE_PREALLOC)) { + ret = btrfs_check_data_free_space(inode, pos, write_bytes); + if (ret == -ENOSPC && + BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) { ret = check_can_nocow(inode, pos, &write_bytes); - if (ret < 0) - break; if (ret > 0) { - /* - * For nodata cow case, no need to reserve - * data space. - */ only_release_metadata = true; /* * our prealloc extent may be smaller than @@ -1543,10 +1539,13 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_CACHE_SIZE); reserve_bytes = num_pages << PAGE_CACHE_SHIFT; + + ret = 0; goto reserve_metadata; + } else { + ret = -ENOSPC; } } - ret = btrfs_check_data_free_space(inode, pos, write_bytes); if (ret < 0) break; -- 2.5.0