WIP: Avoid kmem_alloc in IO path #667
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
There appears to be some issues with too-frequent allocations in spl-kmem and this is especially noticable due to allocations we do for each read or write IO operation. We embed the vdev_buf into zio struct itself, and since ldi_vnode has to call buf_alloc() we also allow ldi_iokit to allocate a local holder. (It is inconvenient to try to include C++ headers in zio.h). If this does speed up IO, it is only because we now avoid the real problem which is still something we should also address
|
I'm running this now (rebased on master). Will report back how I fare. I've been heaving stabiity and performance problems lately on Mojave, maybe this'll help |
|
didn't see any obvious differences in speed, but maybe my hard drive setup is in general just too slow :D |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There appears to be some issues with too-frequent allocations in spl-kmem
and this is especially noticable due to allocations we do for each
read or write IO operation.
We embed the vdev_buf into zio struct itself, and since ldi_vnode has
to call buf_alloc() we also allow ldi_iokit to allocate a local holder.
(It is inconvenient to try to include C++ headers in zio.h).
If this does speed up IO, it is only because we now avoid the real problem
which is still something we should also address