From patchwork Mon Dec 4 22:33:23 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Liu Bo X-Patchwork-Id: 10091749 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 976CC60327 for ; Mon, 4 Dec 2017 23:36:00 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 88D4B28A77 for ; Mon, 4 Dec 2017 23:36:00 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 7DB812902B; Mon, 4 Dec 2017 23:36:00 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id EFE7628A77 for ; Mon, 4 Dec 2017 23:35:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752050AbdLDXfs (ORCPT ); Mon, 4 Dec 2017 18:35:48 -0500 Received: from aserp1040.oracle.com ([141.146.126.69]:25243 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751711AbdLDXfp (ORCPT ); Mon, 4 Dec 2017 18:35:45 -0500 Received: from aserv0022.oracle.com (aserv0022.oracle.com [141.146.126.234]) by aserp1040.oracle.com (Sentrion-MTA-4.3.2/Sentrion-MTA-4.3.2) with ESMTP id vB4NZii0025531 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Mon, 4 Dec 2017 23:35:44 GMT Received: from userv0122.oracle.com (userv0122.oracle.com [156.151.31.75]) by aserv0022.oracle.com (8.14.4/8.14.4) with ESMTP id vB4NZhkS003554 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Mon, 4 Dec 2017 23:35:44 GMT Received: from abhmp0004.oracle.com (abhmp0004.oracle.com [141.146.116.10]) by userv0122.oracle.com (8.14.4/8.14.4) with ESMTP id vB4NZhDF031963; Mon, 4 Dec 2017 23:35:43 GMT Received: from dhcp-10-211-47-181.usdhcp.oraclecorp.com.com (/10.211.47.181) by default (Oracle Beehive Gateway v4.0) with ESMTP ; Mon, 04 Dec 2017 15:35:43 -0800 From: Liu Bo To: fstests@vger.kernel.org Cc: linux-btrfs@vger.kernel.org Subject: [PATCH] fstests: btrfs: reproduce a read failure on raid6 setup Date: Mon, 4 Dec 2017 15:33:23 -0700 Message-Id: <20171204223323.3710-1-bo.li.liu@oracle.com> X-Mailer: git-send-email 2.9.4 X-Source-IP: aserv0022.oracle.com [141.146.126.234] Sender: linux-btrfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-btrfs@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This test case is to reproduce a bug of raid6 reconstruction process. The kernel fix are Btrfs: do not merge rbios if their fail stripe index are not identical Btrfs: make raid6 rebuild retry more Signed-off-by: Liu Bo --- tests/btrfs/155 | 119 ++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/btrfs/155.out | 10 +++++ tests/btrfs/group | 1 + 3 files changed, 130 insertions(+) create mode 100755 tests/btrfs/155 create mode 100644 tests/btrfs/155.out diff --git a/tests/btrfs/155 b/tests/btrfs/155 new file mode 100755 index 0000000..2dec0c3 --- /dev/null +++ b/tests/btrfs/155 @@ -0,0 +1,119 @@ +#! /bin/bash +# FS QA Test 155 +# +# The test case is to reproduce a bug in raid6 reconstruction process that +# would end up with read failure. +# +# if there is data +# corruption on two disks in the same horizontal stripe, e.g. due to bitrot. +# +# The bug happens a) when all disks are good to read, +# b) there is corrupted data on two disks in the same horizontal stripe due to +# something like bitrot, +# c) when rebuilding data after crc fails, btrfs is not able to tell whether +# other copies are good or corrupted because btrfs doesn't have crc for +# unallocated blocks. +# +# The kernel fixes are +# Btrfs: do not merge rbios if their fail stripe index are not identical +# Btrfs: make raid6 rebuild retry more +# +#----------------------------------------------------------------------- +# Copyright (c) 2017 Oracle. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write the Free Software Foundation, +# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA +#----------------------------------------------------------------------- +# + +seq=`basename $0` +seqres=$RESULT_DIR/$seq +echo "QA output created by $seq" + +here=`pwd` +tmp=/tmp/$$ +status=1 # failure is the default! +trap "_cleanup; exit \$status" 0 1 2 3 15 + +_cleanup() +{ + cd / + rm -f $tmp.* +} + +# get standard environment, filters and checks +. ./common/rc +. ./common/filter + +# remove previous $seqres.full before test +rm -f $seqres.full + +# real QA test starts here + +# Modify as appropriate. +_supported_fs btrfs +_supported_os Linux +_require_scratch_dev_pool 4 +_require_btrfs_command inspect-internal dump-tree + +get_physical_stripe0() +{ + $BTRFS_UTIL_PROG inspect-internal dump-tree -t 3 $SCRATCH_DEV | \ + grep " DATA\|RAID6" -A 10 | $AWK_PROG '($1 ~ /stripe/ && $3 ~ /devid/ && $2 ~ /0/) { print $6 }' +} + +get_physical_stripe1() +{ + $BTRFS_UTIL_PROG inspect-internal dump-tree -t 3 $SCRATCH_DEV | \ + grep " DATA\|RAID6" -A 10 | $AWK_PROG '($1 ~ /stripe/ && $3 ~ /devid/ && $2 ~ /1/) { print $6 }' +} + +_scratch_dev_pool_get 4 +# step 1: create a raid6 btrfs and create a 4K file +echo "step 1......mkfs.btrfs" >>$seqres.full + +mkfs_opts="-d raid6 -b 1G" +_scratch_pool_mkfs $mkfs_opts >>$seqres.full 2>&1 + +# -o nospace_cache makes sure data is written to the start position of the data +# chunk +_scratch_mount -o nospace_cache + +# [0,64K) is written to stripe 0 and [64K, 128K) is written to stripe 1 +$XFS_IO_PROG -f -d -c "pwrite -S 0xaa 0 128K" -c "fsync" "$SCRATCH_MNT/foobar" | _filter_xfs_io + +_scratch_unmount + +stripe_0=`get_physical_stripe0` +stripe_1=`get_physical_stripe1` +dev4=`echo $SCRATCH_DEV_POOL | awk '{print $4}'` +dev3=`echo $SCRATCH_DEV_POOL | awk '{print $3}'` + +# step 2: corrupt the 1st and 2nd stripe (stripe 0 and 1) +echo "step 2......simulate bitrot at offset $stripe_0 of device_4($dev4) and offset $stripe_1 of device_3($dev3)" >>$seqres.full + +$XFS_IO_PROG -f -d -c "pwrite -S 0xbb $stripe_0 64K" $dev4 | _filter_xfs_io +$XFS_IO_PROG -f -d -c "pwrite -S 0xbb $stripe_1 64K" $dev3 | _filter_xfs_io + +# step 3: read foobar to repair the bitrot +echo "step 3......repair the bitrot" >> $seqres.full +_scratch_mount -o nospace_cache + +# read the 2nd stripe, i.e. [64K, 128K), to trigger repair +od -x -j 64K $SCRATCH_MNT/foobar + +_scratch_dev_pool_put + +# success, all done +status=0 +exit diff --git a/tests/btrfs/155.out b/tests/btrfs/155.out new file mode 100644 index 0000000..7bac256 --- /dev/null +++ b/tests/btrfs/155.out @@ -0,0 +1,10 @@ +QA output created by 155 +wrote 131072/131072 bytes at offset 0 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 9437184 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 9437184 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +0200000 aaaa aaaa aaaa aaaa aaaa aaaa aaaa aaaa +* +0400000 diff --git a/tests/btrfs/group b/tests/btrfs/group index c98cf82..c84a166 100644 --- a/tests/btrfs/group +++ b/tests/btrfs/group @@ -157,3 +157,4 @@ 152 auto quick metadata qgroup send 153 auto quick qgroup 154 auto quick +155 auto quick repair