ChenSammi commented on code in PR #8843:
URL: https://github.com/apache/ozone/pull/8843#discussion_r2915854722
##########
hadoop-hdds/container-service/src/main/java/org/apache/hadoop/ozone/container/common/volume/StorageVolume.java:
##########
@@ -717,39 +718,25 @@ public synchronized VolumeCheckResult check(@Nullable
Boolean unused)
// We can check again if disk is full. If it is full,
// in this case keep volume as healthy so that READ can still be served
if (!diskChecksPassed && getCurrentUsage().getAvailable() <
minimumDiskSpace) {
- ioTestSlidingWindow.add(true);
return VolumeCheckResult.HEALTHY;
}
- // Move the sliding window of IO test results forward 1 by adding the
- // latest entry and removing the oldest entry from the window.
- // Update the failure counter for the new window.
- ioTestSlidingWindow.add(diskChecksPassed);
if (!diskChecksPassed) {
- currentIOFailureCount.incrementAndGet();
- }
- if (ioTestSlidingWindow.size() > ioTestCount &&
- Objects.equals(ioTestSlidingWindow.poll(), Boolean.FALSE)) {
- currentIOFailureCount.decrementAndGet();
+ ioTestSlidingWindow.add();
}
- // If the failure threshold has been crossed, fail the volume without
- // further scans.
+ // If the failure threshold has been crossed, fail the volume without
further scans.
// Once the volume is failed, it will not be checked anymore.
// The failure counts can be left as is.
- if (currentIOFailureCount.get() > ioFailureTolerance) {
- LOG.error("Failed IO test for volume {}: the last {} runs " +
- "encountered {} out of {} tolerated failures.", this,
- ioTestSlidingWindow.size(), currentIOFailureCount,
- ioFailureTolerance);
+ if (ioTestSlidingWindow.isExceeded()) {
+ LOG.error("Failed IO test for volume {}: encountered more than the {}
tolerated failures within the past {} ms.",
+ this, ioTestSlidingWindow.getWindowSize(),
ioTestSlidingWindow.getExpiryDurationMillis());
return VolumeCheckResult.FAILED;
- } else if (LOG.isDebugEnabled()) {
- LOG.debug("IO test results for volume {}: the last {} runs encountered "
+
- "{} out of {} tolerated failures", this,
- ioTestSlidingWindow.size(),
- currentIOFailureCount, ioFailureTolerance);
}
+ LOG.debug("IO test results for volume {}: encountered {} out of {}
tolerated failures",
+ this, ioTestSlidingWindow.getNumEventsInWindow(),
ioTestSlidingWindow.getWindowSize());
Review Comment:
Shall we call getNumEvents() here, instead of getNumEventsInWindow()?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
