core: fix node reservation scoring #7730
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
schmichael
force-pushed
the
b-reserved-scoring
branch
from
f02c834 to
e86059b
Compare
The BinPackIter accounted for node reservations twice when scoring nodes which could bias scores toward nodes with reservations. Pseudo-code for previous algorithm: ``` proposed = reservedResources + sum(allocsResources) available = nodeResources - reservedResources score = 1 - (proposed / available) ``` The node's reserved resources are added to the total resources used by allocations, and then the node's reserved resources are later substracted from the node's overall resources. The new algorithm is: ``` proposed = sum(allocResources) available = nodeResources - reservedResources score = 1 - (proposed / available) ``` The node's reserved resources are no longer added to the total resources used by allocations. My guess as to how this bug happened is that the resource utilization variable (`util`) is calculated and returned by the `AllocsFit` function which needs to take reserved resources into account as a basic feasibility check. To avoid re-calculating alloc resource usage (because there may be a large number of allocs), we reused `util` in the `ScoreFit` function. `ScoreFit` properly accounts for reserved resources by subtracting them from the node's overall resources. However since `util` _also_ took reserved resources into account the score would be incorrect. Prior to the fix the added test output: ``` Node: reserved Score: 1.0000 Node: reserved2 Score: 1.0000 Node: no-reserved Score: 0.9741 ``` The scores being 1.0 for *both* nodes with reserved resources is a good hint something is wrong as they should receive different scores. Upon further inspection the double accounting of reserved resources caused their scores to be >1.0 and clamped. After the fix the added test outputs: ``` Node: no-reserved Score: 0.9741 Node: reserved Score: 0.9480 Node: reserved2 Score: 0.8717 ```
schmichael
force-pushed
the
b-reserved-scoring
branch
from
7fdbb8a to
68aca51
Compare
dadgar
approved these changes
Apr 16, 2020
notnoop
approved these changes
Apr 20, 2020
dadgar
reviewed
Apr 24, 2020
Co-authored-by: Alex Dadgar <[email protected]>
|
I'm going to lock this pull request because it has been closed for 120 days ⏳. This helps our maintainers find and focus on the active contributions. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
The BinPackIter accounted for node reservations twice when scoring nodes
which could bias scores toward nodes with reservations.
Pseudo-code for previous algorithm:
The node's reserved resources are added to the total resources used by
allocations, and then the node's reserved resources are later
substracted from the node's overall resources.
The new algorithm is:
The node's reserved resources are no longer added to the total resources
used by allocations.
My guess as to how this bug happened is that the resource utilization
variable (
util) is calculated and returned by theAllocsFitfunctionwhich needs to take reserved resources into account as a basic
feasibility check.
To avoid re-calculating alloc resource usage (because there may be a
large number of allocs), we reused
utilin theScoreFitfunction.ScoreFitproperly accounts for reserved resources by subtracting themfrom the node's overall resources. However since
utilalso tookreserved resources into account the score would be incorrect.
Prior to the fix the added test output:
The scores being 1.0 for both nodes with reserved resources is a good
hint something is wrong as they should receive different scores (and neither
is a perfect fit). Upon further inspection the double accounting of reserved
resources caused their scores to be >1.0 and clamped.
After the fix the added test outputs: