On 11/07/2019 12:02 AM, Guoqing Jiang wrote:
On 11/5/19 10:11 PM, Song Liu wrote:
On Mon, Nov 4, 2019 at 4:33 PM Wols Lists <antlists@xxxxxxxxxxxxxxx>
wrote:
On 04/11/19 20:01, Nigel Croxon wrote:
The MD driver for level-456 should prevent re-reading read errors.
For redundant raid it makes no sense to retry the operation:
When one of the disks in the array hits a read error, that will
cause a stall for the reading process:
- either the read succeeds (e.g. after 4 seconds the HDD error
strategy could read the sector)
- or it fails after HDD imposed timeout (w/TLER, e.g. after 7
seconds (might be even longer)
Okay, I'm being completely naive here, but what is going on? Are you
saying that if we hit a read error, we just carry on, ignore it, and
calculate the missing block from parity?
If so, what happens if we hit two errors on a raid-5, or 3 on a raid-6,
or whatever ... :-)
Based on my understanding (no data on this), the drive will retry read
internally before return error. Therefore, host level retry doesn't
really
help. But I could be wrong.
The read which bypasses the cache could retry too, should it be
changed as well?
Do you mean the align read part? If so, yes, we should handle it too.
Now it calls retry_aligned_read when
there is a read failure for align read. We can set R5_ReadError before
handling the stripe.
Regards
Xiao
