[LU-11449] osc: send RPCs with random i/o Created: 30/Sep/18 Updated: 17/Feb/21 Resolved: 04/Sep/19 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | None |
| Fix Version/s: | None |
| Type: | Bug | Priority: | Major |
| Reporter: | Patrick Farrell (Inactive) | Assignee: | Patrick Farrell (Inactive) |
| Resolution: | Not a Bug | Votes: | 0 |
| Labels: | patch | ||
| Issue Links: |
|
||||||||||||
| Severity: | 3 | ||||||||||||
| Rank (Obsolete): | 9223372036854775807 | ||||||||||||
| Description |
|
However, it introduced a different issue with small random writes, particularly when sparse. Because small random writes will (in the large file/sparse case) not make complete, contiguous extents, no RPCs will be sent until the max_dirty_mb or grant limit is hit. This means that in the small-random-sparse write case not enough RPCs will be sent. The solution is to add an additional check for greater than max_pages_per_rpc pages. Details in patch. |
| Comments |
| Comment by Gerrit Updater [ 30/Sep/18 ] |
|
Patrick Farrell (paf@cray.com) uploaded a new patch: https://review.whamcloud.com/33255 |
| Comment by Patrick Farrell (Inactive) [ 04/Sep/19 ] |
|
Note from Gerrit, where patch is to be abandoned: The theory of i/o performance I had in mind when I created this appears to be wrong... Basically, it's reasonable to wait for the cache limit to be hit, and it doesn't take long. This seems to be an unnecessary optimization. |
| Comment by Patrick Farrell (Inactive) [ 04/Sep/19 ] |
|
Existing behavior turns out to be OK. |