Details
-
Improvement
-
Resolution: Unresolved
-
Minor
-
None
-
None
-
None
-
9223372036854775807
Description
Allow small/unaligned writes to be placed directly into pagecache on the OST without starting IO. This should help IOPS for small writes where we are not limited by pagecache performance as is the case for large writes (where patch https://review.whamcloud.com/34422 "LU-12071 osd-ldiskfs: bypass pagecache if requested" is trying to do the opposite and avoid page cache for large writes).
A reasonable starting point would be 64KiB writes, since this is the upper limit for short writes (data embedded into the BRW RPC request), and beyond this we get good performance for larger writes already (per testing of flash at different io sizes, page 8).
Attachments
Issue Links
- is related to
-
LU-13786 Take server-side locks for direct i/o
- Closed