kernel-patches: introduce kernel patch for fscache ondemand IO path o… #717
Conversation
…ptimize Signed-off-by: Xin Yin <[email protected]>
kevinXYin
requested review from
bergwolf,
jiangliu,
luodw,
changweige and
hsiangkao
|
@kevinXYin , a new test job has been submitted. Please wait in patience. The test job url: https://tone.openanolis.cn/ws/nrh4nnio/test_result/20656 |
|
@kevinXYin , The CI test is completed, please check result:
Congratulations, your test job passed! |
||||||||||||||||||||||||
|
Yeah, that is a practical way for downstream users. |
| + break; | ||
| + | ||
| + if (!PageUptodate(page)) { | ||
| + error = -EFAULT; |
There was a problem hiding this comment.
This will not cause EIO , if we can not find all data in pagecache , will fallback to dio for the rest iter
There was a problem hiding this comment.
okay, anyway, the error code is somewhat confusing to me... ;)
There was a problem hiding this comment.
yeah , this is a bit confusing since we don't return result codes here , how about just set this like err = -1 ?
There was a problem hiding this comment.
let's leave as it for now...
| + break; | ||
| + | ||
| + if (!PageUptodate(page)) { | ||
| + error = -EFAULT; |
There was a problem hiding this comment.
okay, anyway, the error code is somewhat confusing to me... ;)
This is kernel patch for #714
before we figure out a formal solution for upstream, we should fix this performance issue , that may affect the user experience first.