Skip to content

[FLINK-36645] [flink-autoscaler] Gracefully handle null execution pla… #930

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

Merged
merged 1 commit into from
Jan 13, 2025
Merged

[FLINK-36645] [flink-autoscaler] Gracefully handle null execution pla… #930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 4 additions & 0 deletions flink-autoscaler/src/main/java/org/apache/flink/autoscaler/exceptions/NotReadyException.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,4 +23,8 @@ public class NotReadyException extends RuntimeException {
public NotReadyException(Exception cause) {
super(cause);
}

public NotReadyException(String message) {
super(message);
}
}
5 changes: 5 additions & 0 deletions flink-autoscaler/src/main/java/org/apache/flink/autoscaler/topology/JobTopology.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

package org.apache.flink.autoscaler.topology;

import org.apache.flink.autoscaler.exceptions.NotReadyException;
import org.apache.flink.runtime.instance.SlotSharingGroupId;
import org.apache.flink.runtime.jobgraph.JobVertexID;

Expand Down Expand Up @@ -150,6 +151,10 @@ public static JobTopology fromJsonPlan(
ObjectNode plan = objectMapper.readValue(jsonPlan, ObjectNode.class);
ArrayNode nodes = (ArrayNode) plan.get("nodes");

if (nodes == null || nodes.isEmpty()) {
throw new NotReadyException("No nodes found in the plan, job is not ready yet");
}

var vertexInfo = new HashSet<VertexInfo>();

for (JsonNode node : nodes) {
Expand Down
126 changes: 126 additions & 0 deletions flink-autoscaler/src/test/java/org/apache/flink/autoscaler/ScalingMetricCollectorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

import org.apache.flink.api.common.JobID;
import org.apache.flink.api.common.JobStatus;
import org.apache.flink.autoscaler.exceptions.NotReadyException;
import org.apache.flink.autoscaler.metrics.FlinkMetric;
import org.apache.flink.autoscaler.metrics.MetricNotFoundException;
import org.apache.flink.autoscaler.topology.IOMetrics;
Expand Down Expand Up @@ -228,6 +229,131 @@ public void testJobTopologyParsingFromJobDetails() throws Exception {
new JobTopology(source, sink), metricsCollector.getJobTopology(jobDetailsInfo));
}

@Test
public void testJobTopologyParsingThrowsNotReadyException() throws Exception {
String s =
"{\n"
+ " \"jid\": \"bb8f15efbb37f2ce519f55cdc0e049bf\",\n"
+ " \"name\": \"State machine job\",\n"
+ " \"isStoppable\": false,\n"
+ " \"state\": \"RUNNING\",\n"
+ " \"start-time\": 1707893512027,\n"
+ " \"end-time\": -1,\n"
+ " \"duration\": 214716,\n"
+ " \"maxParallelism\": -1,\n"
+ " \"now\": 1707893726743,\n"
+ " \"timestamps\": {\n"
+ " \"SUSPENDED\": 0,\n"
+ " \"CREATED\": 1707893512139,\n"
+ " \"FAILING\": 0,\n"
+ " \"FAILED\": 0,\n"
+ " \"INITIALIZING\": 1707893512027,\n"
+ " \"RECONCILING\": 0,\n"
+ " \"RUNNING\": 1707893512217,\n"
+ " \"RESTARTING\": 0,\n"
+ " \"CANCELLING\": 0,\n"
+ " \"FINISHED\": 0,\n"
+ " \"CANCELED\": 0\n"
+ " },\n"
+ " \"vertices\": [\n"
+ " {\n"
+ " \"id\": \"bc764cd8ddf7a0cff126f51c16239658\",\n"
+ " \"name\": \"Source: Custom Source\",\n"
+ " \"maxParallelism\": 128,\n"
+ " \"parallelism\": 2,\n"
+ " \"status\": \"FINISHED\",\n"
+ " \"start-time\": 1707893517277,\n"
+ " \"end-time\": -1,\n"
+ " \"duration\": 209466,\n"
+ " \"tasks\": {\n"
+ " \"DEPLOYING\": 0,\n"
+ " \"INITIALIZING\": 0,\n"
+ " \"SCHEDULED\": 0,\n"
+ " \"CANCELING\": 0,\n"
+ " \"CANCELED\": 0,\n"
+ " \"RECONCILING\": 0,\n"
+ " \"RUNNING\": 2,\n"
+ " \"FAILED\": 0,\n"
+ " \"CREATED\": 0,\n"
+ " \"FINISHED\": 0\n"
+ " },\n"
+ " \"metrics\": {\n"
+ " \"read-bytes\": 0,\n"
+ " \"read-bytes-complete\": true,\n"
+ " \"write-bytes\": 4036982,\n"
+ " \"write-bytes-complete\": true,\n"
+ " \"read-records\": 0,\n"
+ " \"read-records-complete\": true,\n"
+ " \"write-records\": 291629,\n"
+ " \"write-records-complete\": true,\n"
+ " \"accumulated-backpressured-time\": 0,\n"
+ " \"accumulated-idle-time\": 0,\n"
+ " \"accumulated-busy-time\": \"NaN\"\n"
+ " }\n"
+ " },\n"
+ " {\n"
+ " \"id\": \"20ba6b65f97481d5570070de90e4e791\",\n"
+ " \"name\": \"Flat Map -> Sink: Print to Std. Out\",\n"
+ " \"maxParallelism\": 128,\n"
+ " \"parallelism\": 2,\n"
+ " \"status\": \"RUNNING\",\n"
+ " \"start-time\": 1707893517280,\n"
+ " \"end-time\": -1,\n"
+ " \"duration\": 209463,\n"
+ " \"tasks\": {\n"
+ " \"DEPLOYING\": 0,\n"
+ " \"INITIALIZING\": 0,\n"
+ " \"SCHEDULED\": 0,\n"
+ " \"CANCELING\": 0,\n"
+ " \"CANCELED\": 0,\n"
+ " \"RECONCILING\": 0,\n"
+ " \"RUNNING\": 2,\n"
+ " \"FAILED\": 0,\n"
+ " \"CREATED\": 0,\n"
+ " \"FINISHED\": 0\n"
+ " },\n"
+ " \"metrics\": {\n"
+ " \"read-bytes\": 4078629,\n"
+ " \"read-bytes-complete\": true,\n"
+ " \"write-bytes\": 0,\n"
+ " \"write-bytes-complete\": true,\n"
+ " \"read-records\": 291532,\n"
+ " \"read-records-complete\": true,\n"
+ " \"write-records\": 1,\n"
+ " \"write-records-complete\": true,\n"
+ " \"accumulated-backpressured-time\": 0,\n"
+ " \"accumulated-idle-time\": 407702,\n"
+ " \"accumulated-busy-time\": 2\n"
+ " }\n"
+ " }\n"
+ " ],\n"
+ " \"status-counts\": {\n"
+ " \"DEPLOYING\": 0,\n"
+ " \"INITIALIZING\": 0,\n"
+ " \"SCHEDULED\": 0,\n"
+ " \"CANCELING\": 0,\n"
+ " \"CANCELED\": 0,\n"
+ " \"RECONCILING\": 0,\n"
+ " \"RUNNING\": 2,\n"
+ " \"FAILED\": 0,\n"
+ " \"CREATED\": 0,\n"
+ " \"FINISHED\": 0\n"
+ " },\n"
+ " \"plan\": {\n"
+ " \"jid\": \"bb8f15efbb37f2ce519f55cdc0e049bf\",\n"
+ " \"name\": \"State machine job\",\n"
+ " \"type\": \"STREAMING\",\n"
+ " \"nodes\": [\n"
+ " ]\n"
+ " }\n"
+ "}";
JobDetailsInfo jobDetailsInfo = new ObjectMapper().readValue(s, JobDetailsInfo.class);

var metricsCollector = new RestApiMetricsCollector<>();
assertThrows(
NotReadyException.class, () -> metricsCollector.getJobTopology(jobDetailsInfo));
}

@Test
public void testJobTopologyParsingFromJobDetailsWithSlotSharingGroup() throws Exception {
String s =
Expand Down
Loading