Changes between Initial Version and Version 1 of TipAndDoc/storage/RAID/failure

Timestamp:

Jun 12, 2009 10:57:55 AM (16 years ago)

Author:

mitty

Comment:

--

TipAndDoc/storage/RAID/failure

@@ +1 @@
+[[PageOutline]]
+
+ = failure test =
+
+ == 初期状態 ==
+ * cat /proc/mdstat
+{{{
+Personalities : [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4] [raid10]
+md1 : active raid1 sda2[0] sdc1[2](S) sdb2[1]
+      1461760 blocks [2/2] [UU]
+
+md0 : active raid0 sda1[0] sdb1[1]
+      192512 blocks 64k chunks
+
+unused devices: <none>
+}}}
+ * sudo mdadm -D /dev/md1
+{{{
+/dev/md1:
+        Version : 00.90.03
+  Creation Time : Thu Jun 11 22:27:07 2009
+     Raid Level : raid1
+     Array Size : 1461760 (1427.74 MiB 1496.84 MB)
+  Used Dev Size : 1461760 (1427.74 MiB 1496.84 MB)
+   Raid Devices : 2
+  Total Devices : 3
+Preferred Minor : 1
+    Persistence : Superblock is persistent
+
+    Update Time : Fri Jun 12 02:21:57 2009
+          State : clean
+ Active Devices : 2
+Working Devices : 3
+ Failed Devices : 0
+  Spare Devices : 1
+
+           UUID : 79c3f25a:e47a02f3:9bb41f43:b191cd1a
+         Events : 0.5
+
+    Number   Major   Minor   RaidDevice State
+       0       8        2        0      active sync   /dev/sda2
+       1       8       18        1      active sync   /dev/sdb2
+
+       2       8       33        -      spare   /dev/sdc1
+}}}
+
+ == hot-remove spare disk ==
+ * sudo mdadm /dev/md1 -r /dev/sdc1
+{{{
+mdadm: hot removed /dev/sdc1
+}}}
+   * sudo mdadm -D /dev/md1
+{{{
+    Number   Major   Minor   RaidDevice State
+       0       8        2        0      active sync   /dev/sda2
+       1       8       18        1      active sync   /dev/sdb2
+}}}
+ * sudo mdadm /dev/md1 -a /dev/sdc1
+{{{
+mdadm: re-added /dev/sdc1
+}}}
+   * sudo mdadm -D /dev/md1
+{{{
+    Number   Major   Minor   RaidDevice State
+       0       8        2        0      active sync   /dev/sda2
+       1       8       18        1      active sync   /dev/sdb2
+
+       2       8       33        -      spare   /dev/sdc1
+}}}
+
+ == fail, remove and re-add ==
+ * man mdadm
+{{{
+MANAGE MODE
+       Usage: mdadm device options... devices...
+
+       This usage will allow individual devices in  an  array  to  be  failed,
+       removed  or  added.  It is possible to perform multiple operations with
+       on command. For example:
+         mdadm /dev/md0 -f /dev/hda1 -r /dev/hda1 -a /dev/hda1
+       will firstly mark /dev/hda1 as faulty in /dev/md0 and will then  remove
+       it  from the array and finally add it back in as a spare.  However only
+       one md array can be affected by a single command.
+}}}
+ 
+ * sudo mdadm /dev/md1 -f /dev/sda2 -r /dev/sda2 -a /dev/sda2
+{{{
+mdadm: set /dev/sda2 faulty in /dev/md1
+mdadm: hot removed /dev/sda2
+mdadm: re-added /dev/sda2
+}}}
+   * cat /proc/mdstat
+{{{
+Personalities : [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4] [raid10]
+md1 : active raid1 sda2[2](S) sdc1[3] sdb2[1]
+      1461760 blocks [2/1] [_U]
+      [>....................]  recovery =  0.5% (8448/1461760) finish=2.8min speed=8448K/sec
+
+md0 : active raid0 sda1[0] sdb1[1]
+      192512 blocks 64k chunks
+
+unused devices: <none>
+}}}
+   * sudo mdadm -D /dev/md1
+{{{
+/dev/md1:
+        Version : 00.90.03
+  Creation Time : Thu Jun 11 22:27:07 2009
+     Raid Level : raid1
+     Array Size : 1461760 (1427.74 MiB 1496.84 MB)
+  Used Dev Size : 1461760 (1427.74 MiB 1496.84 MB)
+   Raid Devices : 2
+  Total Devices : 3
+Preferred Minor : 1
+    Persistence : Superblock is persistent
+
+    Update Time : Fri Jun 12 02:28:20 2009
+          State : clean, degraded, recovering
+ Active Devices : 1
+Working Devices : 3
+ Failed Devices : 0
+  Spare Devices : 2
+
+ Rebuild Status : 8% complete
+
+           UUID : 79c3f25a:e47a02f3:9bb41f43:b191cd1a
+         Events : 0.17
+
+    Number   Major   Minor   RaidDevice State
+       3       8       33        0      spare rebuilding   /dev/sdc1
+       1       8       18        1      active sync   /dev/sdb2
+
+       2       8        2        -      spare   /dev/sda2
+}}}
+
+ === recovering ===
+   * dmesg
+{{{
+[ 6932.978126] raid1: Disk failure on sda2, disabling device.
+[ 6932.978134]  Operation continuing on 1 devices
+[ 6932.994568] RAID1 conf printout:
+[ 6932.994603]  --- wd:1 rd:2
+[ 6932.995107]  disk 0, wo:1, o:0, dev:sda2
+[ 6932.995127]  disk 1, wo:0, o:1, dev:sdb2
+[ 6933.022454] RAID1 conf printout:
+[ 6933.022462]  --- wd:1 rd:2
+[ 6933.022476]  disk 1, wo:0, o:1, dev:sdb2
+[ 6933.056753] RAID1 conf printout:
+[ 6933.056758]  --- wd:1 rd:2
+[ 6933.056762]  disk 0, wo:1, o:1, dev:sdc1
+[ 6933.056764]  disk 1, wo:0, o:1, dev:sdb2
+[ 6933.061349] md: recovery of RAID array md1
+[ 6933.061379] md: minimum _guaranteed_  speed: 1000 KB/sec/disk.
+[ 6933.061403] md: using maximum available idle IO bandwidth (but not more than 200000 KB/sec) for recovery.
+[ 6933.062332] md: using 128k window, over a total of 1461760 blocks.
+[ 6933.173690] md: unbind<sda2>
+[ 6933.173708] md: export_rdev(sda2)
+[ 6933.945635] md: bind<sda2>
+[ 7066.932827] md: md1: recovery done.
+[ 7067.055469] RAID1 conf printout:
+[ 7067.055475]  --- wd:2 rd:2
+[ 7067.055479]  disk 0, wo:0, o:1, dev:sdc1
+[ 7067.055481]  disk 1, wo:0, o:1, dev:sdb2
+}}}
+   * cat /proc/mdstat
+{{{
+Personalities : [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4] [raid10]
+md1 : active raid1 sda2[2](S) sdc1[0] sdb2[1]
+      1461760 blocks [2/2] [UU]
+
+md0 : active raid0 sda1[0] sdb1[1]
+      192512 blocks 64k chunks
+
+unused devices: <none>
+}}}
+   * sudo mdadm -D /dev/md1
+{{{
+/dev/md1:
+        Version : 00.90.03
+  Creation Time : Thu Jun 11 22:27:07 2009
+     Raid Level : raid1
+     Array Size : 1461760 (1427.74 MiB 1496.84 MB)
+  Used Dev Size : 1461760 (1427.74 MiB 1496.84 MB)
+   Raid Devices : 2
+  Total Devices : 3
+Preferred Minor : 1
+    Persistence : Superblock is persistent
+
+    Update Time : Fri Jun 12 02:31:09 2009
+          State : active
+ Active Devices : 2
+Working Devices : 3
+ Failed Devices : 0
+  Spare Devices : 1
+
+           UUID : 79c3f25a:e47a02f3:9bb41f43:b191cd1a
+         Events : 0.45
+
+    Number   Major   Minor   RaidDevice State
+       0       8       33        0      active sync   /dev/sdc1
+       1       8       18        1      active sync   /dev/sdb2
+
+       2       8        2        -      spare   /dev/sda2
+}}}
+
+ == reboot with degraded 1 disk ==
+ * sudo mdadm /dev/md1 -f /dev/sdc1 /dev/sda2
+{{{
+mdadm: set /dev/sdc1 faulty in /dev/md1
+mdadm: set /dev/sda2 faulty in /dev/md1
+}}}
+ * sudo mdadm /dev/md1 -r /dev/sdc1 /dev/sda2
+{{{
+mdadm: hot removed /dev/sdc1
+mdadm: hot removed /dev/sda2
+}}}
+   * sudo mdadm -D /dev/md1
+{{{
+    Number   Major   Minor   RaidDevice State
+       0       0        0        0      removed
+       1       8       18        1      active sync   /dev/sdb2
+}}}
+ * sudo reboot
+   * /dev/sdb2 のみで正常に起動する