Skip to content

Reduce repeated warning logs from AdaptiveAllocationsScalerService #115089

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
merged 1 commit into from
Oct 21, 2024
Merged

Reduce repeated warning logs from AdaptiveAllocationsScalerService #115089

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
32 changes: 18 additions & 14 deletions ...lasticsearch/xpack/ml/inference/adaptiveallocations/AdaptiveAllocationsScalerService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.ConcurrentSkipListSet;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.function.Function;
Expand Down Expand Up @@ -205,13 +206,11 @@ Collection<DoubleWithAttributes> observeDouble(Function<AdaptiveAllocationsScale
private Long lastInferenceStatsTimestampMillis;
private final Map<String, AdaptiveAllocationsScaler> scalers;
private final Map<String, Long> lastScaleUpTimesMillis;

private volatile Scheduler.Cancellable cancellable;
private final AtomicBoolean busy;

private final long scaleToZeroAfterNoRequestsSeconds;

private final Set<String> deploymentIdsWithInFlightScaleFromZeroRequests = new ConcurrentSkipListSet<>();
private final Map<String, String> lastWarningMessages = new ConcurrentHashMap<>();

public AdaptiveAllocationsScalerService(
ThreadPool threadPool,
Expand Down Expand Up @@ -475,7 +474,8 @@ private ActionListener<CreateTrainedModelAssignmentAction.Response> updateAssigm
int numberOfAllocations
) {
return ActionListener.wrap(updateResponse -> {
logger.debug("adaptive allocations scaler: scaled [{}] to [{}] allocations.", deploymentId, numberOfAllocations);
lastWarningMessages.remove(deploymentId);
logger.info("adaptive allocations scaler: scaled [{}] to [{}] allocations.", deploymentId, numberOfAllocations);
threadPool.executor(MachineLearning.UTILITY_THREAD_POOL_NAME)
.execute(
() -> inferenceAuditor.info(
Expand All @@ -484,20 +484,24 @@ private ActionListener<CreateTrainedModelAssignmentAction.Response> updateAssigm
)
);
}, e -> {
logger.atLevel(Level.WARN)
Level level = e.getMessage().equals(lastWarningMessages.get(deploymentId)) ? Level.DEBUG : Level.WARN;
lastWarningMessages.put(deploymentId, e.getMessage());
logger.atLevel(level)
.withThrowable(e)
.log("adaptive allocations scaler: scaling [{}] to [{}] allocations failed.", deploymentId, numberOfAllocations);
threadPool.executor(MachineLearning.UTILITY_THREAD_POOL_NAME)
.execute(
() -> inferenceAuditor.warning(
deploymentId,
Strings.format(
"adaptive allocations scaler: scaling [%s] to [%s] allocations failed.",
if (level == Level.WARN) {
threadPool.executor(MachineLearning.UTILITY_THREAD_POOL_NAME)
.execute(
() -> inferenceAuditor.warning(
deploymentId,
numberOfAllocations
Strings.format(
"adaptive allocations scaler: scaling [%s] to [%s] allocations failed.",
deploymentId,
numberOfAllocations
)
)
)
);
);
}
});
}
}
Loading