[LU-16761] osd-ldiskfs: cache unaligned page to avoid RMW Created: 23/Apr/23  Updated: 27/Apr/23

Status: Open
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: None

Type: Improvement Priority: Minor
Reporter: Qian Yingjin Assignee: Qian Yingjin
Resolution: Unresolved Votes: 0
Labels: None

Issue Links:
Related
Rank (Obsolete): 9223372036854775807

 Description   

It would better to cache the unaligned page in kernel page cache to avoid the subsequent writes on the same page which may trigger the expensive Read-Modify-Write (RMW).
And when prepare write, if the page is mapping-ed and uptodate, it can avoid read it before write even it is not page-aligned.

 Comments   
Comment by Gerrit Updater [ 23/Apr/23 ]

"Qian Yingjin <qian@ddn.com>" uploaded a new patch: https://review.whamcloud.com/c/fs/lustre-release/+/50717
Subject: LU-16761 osd-ldiskfs: skip Uptodate page to avoid RMW
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 67b4e69ae414432d17178da129ab0a7f28c4b4b2

Generated at Sat Feb 10 03:29:47 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.