Github user roshannaik commented on a diff in the pull request:
https://github.com/apache/storm/pull/2241#discussion_r129447781
--- Diff: storm-client/src/jvm/org/apache/storm/daemon/Task.java ---
@@ -122,28 +130,33 @@ public Task(Executor executor, Integer taskId) throws
IOException {
return new ArrayList<>(0);
}
+
public List<Integer> getOutgoingTasks(String stream, List<Object>
values) {
if (debug) {
LOG.info("Emitting Tuple: taskId={} componentId={} stream={}
values={}", taskId, componentId, stream, values);
}
- List<Integer> outTasks = new ArrayList<>();
- if (!streamComponentToGrouper.containsKey(stream)) {
- throw new IllegalArgumentException("Unknown stream ID: " +
stream);
- }
- if (null != streamComponentToGrouper.get(stream)) {
- // null value for __system
- for (LoadAwareCustomStreamGrouping grouper :
streamComponentToGrouper.get(stream).values()) {
+ ArrayList<Integer> outTasks = new ArrayList<>();
+
+ // TODO: PERF: expensive hashtable lookup in critical path
--- End diff --
Yes hashmap lookups showed up as an important throughput bottleneck during
profiling. Had to spend a bunch of time eliminating hashmap usage in critical
path. a few still remain unfortunately.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
