Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

KEP-4205: reporting experimental results and concerns on phase 2 #5063

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions keps/sig-node/4205-psi-metric/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,18 @@ risk of early reporting for nodes under pressure. We intend to address this conc
by conducting careful experimentation with PSI threshold values to identify the optimal
default threshold to be used for reporting the nodes under heavy resource pressure.

> [!IMPORTANT]
> After some investigation we understood that
> we cannot directly/solely use PSI metrics at node level to identify nodes under "pressure" and taint them.

Experimental results show that a CPU intensive pod with stringent CPU limit is reporting a really high PSI pressure
even if the pressure is only due to CPU throttling and not by competition with neighbors.
But due to how the PSI interface is defined, this is reported also on the kubelet slice and at node level.
So having a badly configured pod on the node, is enough to get a relevant PSI pressure reported at node level
even if the node is not really suffering.
This raises a significant concern about phase 2
(utilize the node level PSI metric to set node condition and node taints).

## Design Details

#### Phase 1
Expand Down