MarkGaox commented on code in PR #2736:
URL: https://github.com/apache/helix/pull/2736#discussion_r1465493205
##########
helix-rest/src/main/java/org/apache/helix/rest/clusterMaintenanceService/StoppableInstancesSelector.java:
##########
@@ -129,32 +136,53 @@ public ObjectNode
getStoppableInstancesCrossZones(List<String> instances,
if (instanceSet.isEmpty()) {
continue;
}
- populateStoppableInstances(new ArrayList<>(instanceSet),
toBeStoppedInstancesSet, stoppableInstances,
- failedStoppableInstances);
+ populateStoppableInstances(new ArrayList<>(instanceSet),
toBeStoppedInstancesSet,
+ stoppableInstances, failedStoppableInstances,
+ _maxAdditionalOfflineInstances - toBeStoppedInstancesSet.size());
}
processNonexistentInstances(instances, failedStoppableInstances);
return result;
}
private void populateStoppableInstances(List<String> instances, Set<String>
toBeStoppedInstances,
- ArrayNode stoppableInstances, ObjectNode failedStoppableInstances)
throws IOException {
+ ArrayNode stoppableInstances, ObjectNode failedStoppableInstances,
+ int allowedOfflineInstances) throws IOException {
Map<String, StoppableCheck> instancesStoppableChecks =
_maintenanceService.batchGetInstancesStoppableChecks(_clusterId,
instances,
_customizedInput, toBeStoppedInstances);
for (Map.Entry<String, StoppableCheck> instanceStoppableCheck :
instancesStoppableChecks.entrySet()) {
String instance = instanceStoppableCheck.getKey();
StoppableCheck stoppableCheck = instanceStoppableCheck.getValue();
- if (!stoppableCheck.isStoppable()) {
- ArrayNode failedReasonsNode =
failedStoppableInstances.putArray(instance);
- for (String failedReason : stoppableCheck.getFailedChecks()) {
-
failedReasonsNode.add(JsonNodeFactory.instance.textNode(failedReason));
- }
- } else {
+ if (stoppableCheck.isStoppable() && allowedOfflineInstances > 0) {
stoppableInstances.add(instance);
// Update the toBeStoppedInstances set with the currently identified
stoppable instance.
// This ensures that subsequent checks in other zones are aware of
this instance's stoppable status.
toBeStoppedInstances.add(instance);
+ allowedOfflineInstances--;
+ continue;
+ }
+ ArrayNode failedReasonsNode =
failedStoppableInstances.putArray(instance);
+ boolean failedHelixOwnChecks = false;
+ if (allowedOfflineInstances <= 0) {
+
failedReasonsNode.add(JsonNodeFactory.instance.textNode(EXCEED_MAX_OFFLINE_INSTANCES));
+ failedHelixOwnChecks = true;
+ }
+
+ if (!stoppableCheck.isStoppable()) {
+ for (String failedReason : stoppableCheck.getFailedChecks()) {
+ // HELIX_OWN_CHECK can always be added to the failedReasonsNode.
+ if
(failedReason.startsWith(StoppableCheck.Category.HELIX_OWN_CHECK.getPrefix())) {
+
failedReasonsNode.add(JsonNodeFactory.instance.textNode(failedReason));
+ failedHelixOwnChecks = true;
+ continue;
+ }
+ // CUSTOM_INSTANCE_CHECK and CUSTOM_PARTITION_CHECK can only be
added to the failedReasonsNode
+ // if continueOnFailure is true and there is no failed
Helix_OWN_CHECKS.
+ if (_continueOnFailure && !failedHelixOwnChecks) {
Review Comment:
Say our maxAllowedOffline = 3, and there are 5 instances. The problem is
when we do batchGetStoppable for these 5 instances, we would have to process
all 5 in parallel. However, if we process them in parallel, then there is no
easy way for the individual instance to know the stop of itself will violate
the maxAllowedOffline = 3 constraint unless we put a lock on everything.
--
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]
