On 03/25/2016 07:28 PM, Lindsay Mathieson wrote:> On 25/03/2016 10:33 PM, Krutika Dhananjay wrote:
>> There is one bug that was uncovered recently wherein the same file
>> could possibly get healed twice before marking that it no longer
>> needs a heal.
>> Pranith sent a patch @ http://review.gluster.org/#/c/13766/ to fix
>> this, although IIUC this bug existed in versions < 3.7.9 as well.
>> Also because of this bug, files that need heal may appear in
>> heal-info output longer than they ought to.
>> Did you see this issue in versions < 3.7.9 as well?
>>
>
>
> The slow I/O? No I didn't - and that's my big concern as the
cluster
> is unusable for extended periods while its happening.
I think you need the exact no. of files and size of files that need
healing to make any meaningful comparison of self-heal performance
across versions.
VM workloads with sharding might not be the ideal 'reproducer' since you
really don't know how many shards get modified when a replica is down
and I/O on the VMs happen. I suppose you could try testing the heal
performance of a specific no. of files on a sharded volume and compare
results.
My 2 cents.
-Ravi
>
> I didn't notice double heals happening previously, but I doubt I would
> have if it was happening.
>
>
> thanks,
>