tflobbe commented on a change in pull request #1297: SOLR-14253 Replace various
sleep calls with ZK waits
URL: https://github.com/apache/lucene-solr/pull/1297#discussion_r385436094
##########
File path: solr/core/src/java/org/apache/solr/cloud/ZkController.java
##########
@@ -1684,58 +1685,37 @@ private void
doGetShardIdAndNodeNameProcess(CoreDescriptor cd) {
}
private void waitForCoreNodeName(CoreDescriptor descriptor) {
- int retryCount = 320;
- log.debug("look for our core node name");
- while (retryCount-- > 0) {
- final DocCollection docCollection = zkStateReader.getClusterState()
-
.getCollectionOrNull(descriptor.getCloudDescriptor().getCollectionName());
- if (docCollection != null && docCollection.getSlicesMap() != null) {
- final Map<String, Slice> slicesMap = docCollection.getSlicesMap();
- for (Slice slice : slicesMap.values()) {
- for (Replica replica : slice.getReplicas()) {
- // TODO: for really large clusters, we could 'index' on this
-
- String nodeName = replica.getStr(ZkStateReader.NODE_NAME_PROP);
- String core = replica.getStr(ZkStateReader.CORE_NAME_PROP);
-
- String msgNodeName = getNodeName();
- String msgCore = descriptor.getName();
-
- if (msgNodeName.equals(nodeName) && core.equals(msgCore)) {
- descriptor.getCloudDescriptor()
- .setCoreNodeName(replica.getName());
- getCoreContainer().getCoresLocator().persist(getCoreContainer(),
descriptor);
- return;
- }
- }
+ log.debug("waitForCoreNodeName >>> look for our core node name");
+ try {
+ zkStateReader.waitForState(descriptor.getCollectionName(), 320,
TimeUnit.SECONDS, c -> {
+ String name = ClusterStateMutator.getAssignedCoreNodeName(c,
getNodeName(), descriptor.getName());
+ if (name == null) {
+ return false;
}
- }
- try {
- Thread.sleep(1000);
- } catch (InterruptedException e) {
- Thread.currentThread().interrupt();
- }
+ descriptor.getCloudDescriptor().setCoreNodeName(name);
+ return true;
+ });
+ } catch (TimeoutException | InterruptedException e) {
+ throw new SolrException(ErrorCode.SERVER_ERROR, "Timeout waiting for
collection state", e);
}
+ getCoreContainer().getCoresLocator().persist(getCoreContainer(),
descriptor);
}
- private void waitForShardId(CoreDescriptor cd) {
+ private void waitForShardId(final CoreDescriptor cd) {
log.debug("waiting to find shard id in clusterstate for " + cd.getName());
- int retryCount = 320;
- while (retryCount-- > 0) {
- final String shardId =
zkStateReader.getClusterState().getShardId(cd.getCollectionName(),
getNodeName(), cd.getName());
- if (shardId != null) {
- cd.getCloudDescriptor().setShardId(shardId);
- return;
- }
- try {
- Thread.sleep(1000);
- } catch (InterruptedException e) {
- Thread.currentThread().interrupt();
- }
+ try {
+ zkStateReader.waitForState(cd.getCollectionName(), 320,
TimeUnit.SECONDS, c -> {
+ if (c == null) return false;
+ final String shardId = c.getShardId(getNodeName(), cd.getName());
+ if (shardId != null) {
+ cd.getCloudDescriptor().setShardId(shardId);
+ return true;
+ }
+ return false;
+ });
+ } catch (TimeoutException | InterruptedException e) {
+ throw new SolrException(ErrorCode.SERVER_ERROR, "Could not get shard id
for core: " + cd.getName());
Review comment:
Same as before, we should probably re set the interruption. Also, did you
intentionally not wrap the exception?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
