Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TEZ-4569: SCATTER_GATHER + BROADCAST hangs on DAG Recovery #361

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
+526 −1
Open

TEZ-4569: SCATTER_GATHER + BROADCAST hangs on DAG Recovery #361

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a34afd7
Add tests
okumin Jun 11, 2024
47a8700
TEZ-4569: SCATTER_GATHER + BROADCAST hangs on DAG Recovery
okumin Jun 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion tez-dag/src/main/java/org/apache/tez/dag/app/dag/impl/VertexImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2817,6 +2817,18 @@ private VertexState setupVertex() {
return VertexState.INITED;
}

private boolean canSkipInitializingParents() {
// Both cases use RootInputVertexManager. RootInputVertexManager can start tasks even though
// any parents are not fully initialized.
if (vertexPlan.hasVertexManagerPlugin()) {
final VertexManagerPluginDescriptor pluginDesc = DagTypeConverters
.convertVertexManagerPluginDescriptorFromDAGPlan(vertexPlan.getVertexManagerPlugin());
return pluginDesc.getClassName().equals(RootInputVertexManager.class.getName());
} else {
return inputsWithInitializers != null;
}
}

private boolean isVertexInitSkippedInParentVertices() {
for (Map.Entry<Vertex, Edge> entry : sourceVertices.entrySet()) {
if(!(((VertexImpl) entry.getKey()).isVertexInitSkipped())) {
Expand All @@ -2843,7 +2855,7 @@ private void assignVertexManager() throws TezException {
if (recoveryData != null && recoveryData.shouldSkipInit()
&& (recoveryData.isVertexTasksStarted() ||
recoveryData.getVertexConfigurationDoneEvent().isSetParallelismCalled())
&& isVertexInitSkippedInParentVertices()) {
&& (canSkipInitializingParents() || isVertexInitSkippedInParentVertices())) {
// Replace the original VertexManager with NoOpVertexManager if the reconfiguration is done in the last AM attempt
VertexConfigurationDoneEvent reconfigureDoneEvent = recoveryData.getVertexConfigurationDoneEvent();
if (LOG.isInfoEnabled()) {
Expand Down
Loading