# Re: 4.11.2: reshape raid5 -\> raid6 atop bcache deadlocks at start on md\_attr\_store / raid5\_make\_request

- From: Nix \<hidden\>
- Date: 2017-05-24 19:42:48 
- List: linux-raid
- Page: https://ratatoskr.run/linux-raid/2017/05/6635738
- Thread: https://ratatoskr.run/linux-raid/2017/05/6635738/t.md

```text
On 24 May 2017, NeilBrown said:
> Alternately, this might do it.

Bingo! Ticking away nicely:

[  147.538274] md/raid:md125: device sda3 operational as raid disk 0
[  147.574356] md/raid:md125: device sdd3 operational as raid disk 3
[  147.586482] md/raid:md125: device sdc3 operational as raid disk 2
[  147.598571] md/raid:md125: device sdb3 operational as raid disk 1
[  147.613949] md/raid:md125: raid level 6 active with 4 out of 5 devices, algorithm 18
[  147.776155] md: reshape of RAID array md125

md125 : active raid6 sda3[0] sdf3[5] sdd3[4] sdc3[2] sdb3[1]
      15391689216 blocks super 1.2 level 6, 512k chunk, algorithm 18 [5/4] [UUUU_]
      [>....................]  reshape =  0.0% (2669056/5130563072) finish=1363.5min speed=62678K/sec

(wow, this is a lot faster: only 1363 min / 70MiB/s, versus the
--backup-file one, for an array half the size, that was >2500 min,
12MiB/s. I mean, yes, it was at the slow end of the disk, but they don't
differ in speed *that* much.)

Machine still perfectly responsive, as if on reshape was happening at
all. (But then, I've got used to that. The last time I saw any md resync-
induced delays was long ago when I had a sym53c75 in the loop with an
I/O rate of 10MiB/s. I think delays are unavoidable with something
that slow in there.)
```