The Good, the Blog & the Ugly - Tim Cook's Weblog

Demonstrating ZFS Self-Healing

I'm the kind of guy who likes to tinker. To see under the bonnet. I used to have a go at "fixing" TV's by taking the back off and seeing what could be adjusted (which is kind-of anathema to one of the philosophies of ZFS).

So, when I have been presenting and demonstrating ZFS to customers, the thing I really like to show is what ZFS does when I inject "silent data corruption" into one device in a mirrored storage pool.

This is cool, because ZFS does a couple of things that are not done by any comparable product:

• It detects the corruption by using checksums on all data and metadata.
• It automatically repairs the damage, using data from the other mirror, assuming checksum(s) on that mirror are OK.

This all happens before the data is passed off to the process that asked for it. This is how it looks in slideware:

The key to demonstrating this live is how to inject corruption, without having to apply a magnet or lightning bolt to my disk. Here is my version of such a demonstration:

1. Create a mirrored storage pool, and filesystem

   cleek[bash]# zpool create demo mirror /export/zfs/zd0 /export/zfs/zd1 cleek[bash]# zfs create demo/ccs

2. Load up some data into that filesystem, see how we are doing

   cleek[bash]# cp -pr /usr/ccs/bin /demo/ccs cleek[bash]# zfs list NAME USED AVAIL REFER MOUNTPOINT demo 2.57M 231M 9.00K /demo demo/ccs 2.51M 231M 2.51M /demo/ccs

3. Get a personal checksum of all the data in the files - the "find/cat" will output the contents of all files, then I pipe all that data into "cksum"

   cleek[bash]# cd /demo/ccs cleek[bash]# find . -type f -exec cat {} + | cksum 1891695928 2416605

4. Now for the fun part. I will inject some corruption by writing some zeroes onto the start of one of the mirrors.

   cleek[bash]# dd bs=1024k count=32 conv=notrunc if=/dev/zero of=/export/zfs/zd0 32+0 records in 32+0 records out

5. Now if I re-read the data now, ZFS will not find any problems, and I can verify this at any time using "zpool status"

   cleek[bash]# find . -type f -exec cat {} + | cksum 1891695928 2416605 cleek[bash]# zpool status demo pool: demo state: ONLINE scrub: none requested config: NAME STATE READ WRITE CKSUM demo ONLINE 0 0 0 mirror ONLINE 0 0 0 /export/zfs/zd0 ONLINE 0 0 0 /export/zfs/zd1 ONLINE 0 0 0

   The reason for this is that ZFS still has all the data for this filesystem cached, so it does not need to read anything from the storage pool's devices.

6. To force ZFS' cached data to be flushed, I export and re-import my storage pool

   cleek[bash]# cd / cleek[bash]# zpool export -f demo cleek[bash]# zpool import -d /export/zfs demo cleek[bash]# cd - /demo/ccs

7. At this point, I should find that ZFS has found some corrupt metadata

   cleek[bash]# zpool status demo pool: demo state: ONLINE status: One or more devices has experienced an unrecoverable error. An attempt was made to correct the error. Applications are unaffected. action: Determine if the device needs to be replaced, and clear the errors using 'zpool online' or replace the device with 'zpool replace'. see: http://www.sun.com/msg/ZFS-8000-9P scrub: none requested config: NAME STATE READ WRITE CKSUM demo ONLINE 0 0 0 mirror ONLINE 0 0 0 /export/zfs/zd0 ONLINE 0 0 7 /export/zfs/zd1 ONLINE 0 0 0

8. Cool - Solaris Fault Manager at work. I'll bring that mirror back online, so ZFS will try using it for what I plan to do next...

   cleek[bash]# zpool online demo/export/zfs/zd0 Bringing device /export/zfs/zd0 online

9. Now, I can repeat my read of data to generate my checksum, and check what happens

   cleek[bash]# find . -type f -exec cat {} + | cksum 1891695928 2416605 note that my checksum is the same cleek[bash]# zpool status [...] NAME STATE READ WRITE CKSUM demo ONLINE 0 0 0 mirror ONLINE 0 0 0 /export/zfs/zd0 ONLINE 0 0 63 /export/zfs/zd1 ONLINE 0 0 0

Of course, if I wanted to know the instant things happened, I could also use DTrace (in another window):

cleek[bash]# dtrace -n :zfs:zio_checksum_error:entry
dtrace: description ':zfs:zio_checksum_error:entry' matched 1 probe
CPU     ID                    FUNCTION:NAME
  0  40650         zio_checksum_error:entry
  0  40650         zio_checksum_error:entry
  0  40650         zio_checksum_error:entry
  0  40650         zio_checksum_error:entry
[...]

Technorati Tag: ZFS

Posted at 09:00AM Nov 16, 2005 by timc in Sun  |  Comments[4]