qqu0127 commented on code in PR #2344:
URL: https://github.com/apache/helix/pull/2344#discussion_r1084318326
##########
helix-core/src/main/java/org/apache/helix/monitoring/mbeans/ClusterStatusMonitor.java:
##########
@@ -55,6 +55,54 @@
import org.slf4j.LoggerFactory;
public class ClusterStatusMonitor implements ClusterStatusMonitorMBean {
+ private class AsyncMissingTopStateMonitor extends Thread {
+ private final Map<String, Map<String, Long>> _missingTopStateResourceMap;
Review Comment:
Does the map have to be a concurrent map? Any risk of concurrent
modification?
##########
helix-core/src/main/java/org/apache/helix/monitoring/mbeans/ClusterStatusMonitor.java:
##########
@@ -55,6 +55,54 @@
import org.slf4j.LoggerFactory;
public class ClusterStatusMonitor implements ClusterStatusMonitorMBean {
+ private class AsyncMissingTopStateMonitor extends Thread {
+ private final Map<String, Map<String, Long>> _missingTopStateResourceMap;
+ private long _missingTopStateDurationThreshold = Long.MAX_VALUE;;
+
+ public AsyncMissingTopStateMonitor(Map<String, Map<String, Long>>
missingTopStateResourceMap) {
+ _missingTopStateResourceMap = missingTopStateResourceMap;
+ }
+
+ public void setMissingTopStateDurationThreshold(long
missingTopStateDurationThreshold) {
+ _missingTopStateDurationThreshold = missingTopStateDurationThreshold;
+ }
+
+ @Override
+ public void run() {
+ try {
+ synchronized (this) {
+ while (true) {
+ while (_missingTopStateResourceMap.size() == 0) {
+ this.wait();
+ }
+ for (Iterator<Map.Entry<String, Map<String, Long>>>
resourcePartitionIt =
+ _missingTopStateResourceMap.entrySet().iterator();
resourcePartitionIt.hasNext(); ) {
+ Map.Entry<String, Map<String, Long>> resourcePartitionEntry =
resourcePartitionIt.next();
+ // Iterate over all partitions and if any partition has missing
top state greater than threshold then report
+ // it.
+ ResourceMonitor resourceMonitor =
getOrCreateResourceMonitor(resourcePartitionEntry.getKey());
+ // If all partitions of resource has top state recovered then
reset the counter
+ if (resourcePartitionEntry.getValue().isEmpty()) {
+
resourceMonitor.resetOneOrManyPartitionsMissingTopStateRealTimeGuage();
+ resourcePartitionIt.remove();
+ } else {
Review Comment:
For me I'm not a fan of this iterate and modify pattern. It's not wrong, but
any chance we can make it a pure function?
##########
helix-core/src/main/java/org/apache/helix/monitoring/mbeans/ClusterStatusMonitor.java:
##########
@@ -583,6 +643,33 @@ public void updateMissingTopStateDurationStats(String
resourceName, long totalDu
}
}
+ public void updateMissingTopStateDurationThreshold(long
missingTopStateDurationThreshold) {
+
_asyncMissingTopStateMonitor.setMissingTopStateDurationThreshold(missingTopStateDurationThreshold);
+ }
+
+ public void updateMissingTopStateResourceMap(String resourceName,String
partitionName, boolean isTopStateMissing, long startTime) {
+ // Top state started missing
+ if (isTopStateMissing) {
+ // Wake up asyncMissingTopStateMonitor thread on first resource being
added to map
+ if (_missingTopStateResourceMap.isEmpty()) {
+ synchronized (_asyncMissingTopStateMonitor) {
+ _asyncMissingTopStateMonitor.notify();
+ }
+ }
+ if (!_missingTopStateResourceMap.containsKey(resourceName)) {
+ _missingTopStateResourceMap.put(resourceName, new HashMap<String,
Long>());
+ }
Review Comment:
This can be reduced to computeIfAbsent ?
##########
helix-core/src/main/java/org/apache/helix/monitoring/mbeans/ClusterStatusMonitor.java:
##########
@@ -109,9 +157,21 @@ public class ClusterStatusMonitor implements
ClusterStatusMonitorMBean {
private final Map<String, JobMonitor> _perTypeJobMonitorMap = new
ConcurrentHashMap<>();
+ /**
+ * Missing top state resource map:
resourceName-><PartitionName->startTimeOfMissingTopState>
+ */
+ private final Map<String, Map<String, Long>> _missingTopStateResourceMap =
new ConcurrentHashMap<>();
+ private final AsyncMissingTopStateMonitor _asyncMissingTopStateMonitor = new
AsyncMissingTopStateMonitor(_missingTopStateResourceMap);
Review Comment:
Now I see it's indeed a ConcurrentHashMap.
One nit, let's make this type explicit in the signature.
##########
helix-core/src/main/java/org/apache/helix/monitoring/mbeans/ClusterStatusMonitor.java:
##########
@@ -583,6 +643,33 @@ public void updateMissingTopStateDurationStats(String
resourceName, long totalDu
}
}
+ public void updateMissingTopStateDurationThreshold(long
missingTopStateDurationThreshold) {
+
_asyncMissingTopStateMonitor.setMissingTopStateDurationThreshold(missingTopStateDurationThreshold);
+ }
+
+ public void updateMissingTopStateResourceMap(String resourceName,String
partitionName, boolean isTopStateMissing, long startTime) {
+ // Top state started missing
+ if (isTopStateMissing) {
+ // Wake up asyncMissingTopStateMonitor thread on first resource being
added to map
+ if (_missingTopStateResourceMap.isEmpty()) {
+ synchronized (_asyncMissingTopStateMonitor) {
+ _asyncMissingTopStateMonitor.notify();
+ }
+ }
+ if (!_missingTopStateResourceMap.containsKey(resourceName)) {
+ _missingTopStateResourceMap.put(resourceName, new HashMap<String,
Long>());
+ }
+ _missingTopStateResourceMap.get(resourceName).put(partitionName,
startTime);
+ } else { // top state recovered
+ // remove partitions from resourceMap whose top state has been
recovered, this will put
+ // asyncMissingTopStateMonitor thread to sleep when no resources left to
monitor.
+ Map<String, Long> entry = _missingTopStateResourceMap.get(resourceName);
+ if (entry != null) {
+ entry.remove(partitionName);
+ }
Review Comment:
Related to the above comment on iterator. Can we do all the GC-like map
cleanup here?
--
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]
