janhoy commented on a change in pull request #1387: SOLR-14210: Include replica
health in healtcheck handler
URL: https://github.com/apache/lucene-solr/pull/1387#discussion_r403719563
##########
File path:
solr/core/src/java/org/apache/solr/handler/admin/HealthCheckHandler.java
##########
@@ -88,15 +98,45 @@ public void handleRequestBody(SolrQueryRequest req,
SolrQueryResponse rsp) throw
return;
}
- // Set status to true if this node is in live_nodes
- if
(clusterState.getLiveNodes().contains(cores.getZkController().getNodeName())) {
- rsp.add(STATUS, OK);
- } else {
+ // Fail if not in live_nodes
+ if
(!clusterState.getLiveNodes().contains(cores.getZkController().getNodeName())) {
rsp.add(STATUS, FAILURE);
rsp.setException(new
SolrException(SolrException.ErrorCode.SERVICE_UNAVAILABLE, "Host Unavailable:
Not in live nodes as per zk"));
+ return;
}
- rsp.setHttpCaching(false);
+ // Optionally require that all cores on this node are active if param
'requireHealthyCores=true'
+ if (req.getParams().getBool(PARAM_REQUIRE_HEALTHY_CORES, false)) {
+ Collection<CloudDescriptor> coreDescriptors = cores.getCores().stream()
+ .map(c ->
c.getCoreDescriptor().getCloudDescriptor()).collect(Collectors.toList());
+ List<String> unhealthyCores = findUnhealthyCores(coreDescriptors,
clusterState);
+ if (unhealthyCores.size() > 0) {
+ rsp.add(STATUS, FAILURE);
+ rsp.setException(new
SolrException(SolrException.ErrorCode.SERVICE_UNAVAILABLE,
+ "Replica(s) " + unhealthyCores + " are currently
initializing or recovering"));
+ return;
+ }
+ rsp.add("message", "All cores are healthy");
+ }
+
+ // All lights green, report healthy
+ rsp.add(STATUS, OK);
+ }
+
+ /**
+ * Find replicas DOWN or RECOVERING, or replicas in clusterstate that do not
exist on local node.
+ * We first find local cores which are either not registered or unhealthy,
and check each of these against
+ * the clusterstate, and return a list of unhealthy replicas that are part
of an active shard for an existing collection
+ * @param cores list of core descriptors to iterate
+ * @param clusterState clusterstate from ZK
+ * @return list of core names that are either DOWN ore RECOVERING on
'nodeName'
+ */
+ static List<String> findUnhealthyCores(Collection<CloudDescriptor> cores,
ClusterState clusterState) {
Review comment:
So I changed logic to report number of unhealthy cores instead of list of
names.
I agree that the corner case of wiping disk is not within scope of this
issue.
----------------------------------------------------------------
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
