Skip to content

[History Server] Tune CPU, memory, and event logging for cold loads #5095

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.

Sign up for GitHub

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

Merged
andrewsykim merged 9 commits into from
Aug 11, 2026
+25 −4
Merged

[History Server] Tune CPU, memory, and event logging for cold loads #5095

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
281ba9a
[History Server] Fix cold-load CPU starvation and per-event logging
Future-Outlier Aug 6, 2026
b3b2064
Merge remote-tracking branch 'origin/master' into historyserver-cold-…
Future-Outlier Aug 6, 2026
e4a26d1
historyserver: leave CPU limit configurable
Future-Outlier Aug 9, 2026
7b4833e
historyserver: size sample memory for session cache
Future-Outlier Aug 10, 2026
a2fb759
Merge upstream master into historyserver-cold-load-cpu
Future-Outlier Aug 10, 2026
6e533d6
historyserver: repair tests after cache changes
Future-Outlier Aug 10, 2026
0e1b497
historyserver: size example cache memory
Future-Outlier Aug 10, 2026
b4e934f
historyserver: document example memory sizing
Future-Outlier Aug 10, 2026
dd1dd68
Merge remote-tracking branch 'upstream/master' into historyserver-col…
Future-Outlier Aug 11, 2026
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
9 changes: 8 additions & 1 deletion historyserver/config/historyserver-azureblob.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,13 @@ spec:
- --ray-root-dir=log
ports:
- containerPort: 8080
# Cache is soft-bounded at 8 GiB; 12 GiB leaves decode headroom.
# The 2 GiB request keeps examples schedulable; size production requests to residency.
args:
- --session-cache-max-bytes=8589934592

@andrewsykim andrewsykim Aug 11, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@JiangJiaWei1103 can we consider renaming this flag to --session-cache-max-memory and have it accept a string like 8GiB?

resources:
limits:
requests:
cpu: "500m"
memory: "2Gi"
limits:
memory: "12Gi"
9 changes: 8 additions & 1 deletion historyserver/config/historyserver-gcs.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,13 @@ spec:
imagePullPolicy: IfNotPresent
ports:
- containerPort: 8080
# Cache is soft-bounded at 8 GiB; 12 GiB leaves decode headroom.
# The 2 GiB request keeps examples schedulable; size production requests to residency.
args:
- --session-cache-max-bytes=8589934592
resources:
limits:
requests:
cpu: "500m"
memory: "2Gi"
limits:
memory: "12Gi"
9 changes: 8 additions & 1 deletion historyserver/config/historyserver.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,13 @@ spec:
# - --use-auth-token-mode=true
ports:
- containerPort: 8080
# Cache is soft-bounded at 8 GiB; 12 GiB leaves decode headroom.
# The 2 GiB request keeps examples schedulable; size production requests to residency.
args:
- --session-cache-max-bytes=8589934592
resources:
limits:
requests:
Comment thread
Future-Outlier marked this conversation as resolved.
cpu: "500m"
memory: "2Gi"
limits:
memory: "12Gi"
2 changes: 1 addition & 1 deletion historyserver/pkg/eventserver/eventserver.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,7 +133,7 @@ func (h *EventHandler) storeEvent(clusterSessionKey string, eventMap map[string]
}
eventType := types.EventType(eventTypeStr)

logrus.Infof("current eventType: %v", eventType)
logrus.Debugf("current eventType: %v", eventType)
switch eventType {
case types.TASK_DEFINITION_EVENT:
return h.handleTaskDefinitionEvent(eventMap, clusterSessionKey, false)
Expand Down
Loading