mon: reduce CPU and memory manager pressure of pg health check #7482
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
When we don't need details about which PGs are stuck, we can just iterate once over pg_stat map and increase appropriate counters, no need to repeatedly spam memory manager with stuck_pgs map population (we'll only use its size). Even if we need details, first check if we actually have any PGs in any of requested states, so in most cases we won't iterate needlessly five times over all PG stat map. This at least halves the time needed by pg health gathering (~3ms, down from ~6-7ms) on cluster with 31832 PGs and Intel Xeon E5-2640 CPU. Signed-off-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com>
liewegas
added a commit
that referenced
this pull request
Feb 4, 2016
mon: reduce CPU and memory manager pressure of pg health check Reviewed-by: Sage Weil <sage@redhat.com>
ghost
added
the
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Outdated suggestions cannot be applied.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.
When we don't need details about which PGs are stuck, we can just iterate
once over pg_stat map and increase appropriate counters, no need to
repeatedly spam memory manager with stuck_pgs map population (we'll only
use its size). Even if we need details, first check if we actually have any
PGs in any of requested states, so in most cases we won't iterate needlessly
five times over all PG stat map.
This at least halves the time needed by pg health gathering (~3ms,
down from ~6-7ms) on cluster with 31832 PGs and Intel Xeon E5-2640
CPU on monitor node.
Signed-off-by: Piotr Dałek piotr.dalek@ts.fujitsu.com