[LU-10916] Improve lfs mirror resync performance Created: 14/Apr/18  Updated: 14/Aug/18  Resolved: 06/Aug/18

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.11.0
Fix Version/s: Lustre 2.12.0

Type: Improvement Priority: Minor
Reporter: Andreas Dilger Assignee: Zhenyu Xu
Resolution: Fixed Votes: 0
Labels: FLR2

Issue Links:
Related
is related to LU-11226 sanity-flr test 200 fails with 'check... Resolved
is related to LU-10191 FLR2: Server Local Client (SLC) Reopened
Rank (Obsolete): 9223372036854775807

 Description   

My understanding is that the current lfs mirror resync implementation will do resync on each stale mirror of a file separately (read+write, read+write, ... each full component), rather than doing the resync in parallel (read+write+write+write ... for all stale components).

This potentially slows down resync significantly, because the same data may need to be read from disk multiple times if the file is very large. It would be better to write all of the stale replicas at the same time.

There may be other performance optimizations possible once the basic FLR functionality and infrastructure is good enough that we can focus on performance.



 Comments   
Comment by Gerrit Updater [ 11/Jul/18 ]

Bobi Jam (bobijam@hotmail.com) uploaded a new patch: https://review.whamcloud.com/32808
Subject: LU-10916 lfs: improve lfs mirror resync
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: d860341928887a5cbfc70320913e3f63dcf97534

Comment by Gerrit Updater [ 06/Aug/18 ]

Oleg Drokin (green@whamcloud.com) merged in patch https://review.whamcloud.com/32808/
Subject: LU-10916 lfs: improve lfs mirror resync
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 0e5c12ac29a9622e8ca05d5e39cd5e2a721ace93

Comment by Peter Jones [ 06/Aug/18 ]

Landed for 2.12

Generated at Sat Feb 10 02:39:19 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.