Add udev rule to select I/O scheduler #224
Merged
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
|
What happens on systems with a Linux kernel not supporting BFQ? The rule is just ignored? Is there an error? |
|
It is silently ignored. The ugly messages are only emitted if queue/scheduler does not exist, not when udevd writes something invalid into it. |
Change all block devices which can have a scheduler to BFQ. Test for existing scheduler (which might be "none") to avoid an ugly message in the journal log when we try to set a scheduler to a block device which can't have one (e.g. a partition).
donald
force-pushed
the
add-ioschedulers
branch
from
73cb4b0
to
52efff5
Compare
Sign in
to join this conversation on GitHub.
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Outdated suggestions cannot be applied.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.
Change all block devices which can have a scheduler to BFQ.
I've quick-tested spinning disks, ssd, nvme and virtio block devices and BFQ was always equal or better than any other scheduler ("none", "mq-deadline", "kyber"). No fancy test, just Kernel compile times.
Anyway, we do want to have the BFQ features (cgroups weight based IO throttling) . So until we find a clear performance disadvantage, switch all devices to BFQ for now. If we later find a situation, where BFQ doesn't seem to be the best fit, we can switch the running system to any other scheduler and update the rules file.
I need a reason NOT to use BFQ, not a reason to use it.