Skip to content

HADOOP-17995. Stale record should be remove when DataNodePeerMetrics#dumpSendPacketDownstreamAvgInfoAsJson #3708

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
Nov 25, 2021
Merged

HADOOP-17995. Stale record should be remove when DataNodePeerMetrics#dumpSendPacketDownstreamAvgInfoAsJson #3708

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
9 changes: 6 additions & 3 deletions ...ct/hadoop-common/src/main/java/org/apache/hadoop/metrics2/lib/MutableRollingAverages.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,7 +167,7 @@ synchronized void replaceScheduledTask(int windows, long interval,
}

@Override
public void snapshot(MetricsRecordBuilder builder, boolean all) {
public synchronized void snapshot(MetricsRecordBuilder builder, boolean all) {
if (all || changed()) {
for (final Entry<String, LinkedBlockingDeque<SumAndCount>> entry
: averages.entrySet()) {
Expand All @@ -179,8 +179,11 @@ public void snapshot(MetricsRecordBuilder builder, boolean all) {
long totalCount = 0;

for (final SumAndCount sumAndCount : entry.getValue()) {
totalCount += sumAndCount.getCount();
totalSum += sumAndCount.getSum();
if (Time.monotonicNow() - sumAndCount.getSnapshotTimeStamp()
< recordValidityMs) {
totalCount += sumAndCount.getCount();
totalSum += sumAndCount.getSum();
}
}

if (totalCount != 0) {
Expand Down
10 changes: 10 additions & 0 deletions ...op-hdfs/src/test/java/org/apache/hadoop/hdfs/server/datanode/TestDataNodePeerMetrics.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,16 @@ public void testRemoveStaleRecord() throws Exception {
GenericTestUtils.waitFor(
() -> rollingAverages.getStats(numSamples).size() > 0, 500, 5000);
assertEquals(3, rollingAverages.getStats(numSamples).size());
String json = peerMetrics.dumpSendPacketDownstreamAvgInfoAsJson();
for (String peerAddr : peerAddrList) {
assertThat(json, containsString(peerAddr));
}
/* wait for stale report to be removed */
GenericTestUtils.waitFor(
() -> rollingAverages.getStats(numSamples).isEmpty(), 500, 10000);
assertEquals(0, rollingAverages.getStats(numSamples).size());
json = peerMetrics.dumpSendPacketDownstreamAvgInfoAsJson();
assertEquals("{}", json);

/* dn can report peer metrics normally when it added back to cluster */
for (String peerAddr : peerAddrList) {
Expand All @@ -138,6 +144,10 @@ public void testRemoveStaleRecord() throws Exception {
GenericTestUtils.waitFor(
() -> rollingAverages.getStats(numSamples).size() > 0, 500, 10000);
assertEquals(3, rollingAverages.getStats(numSamples).size());
json = peerMetrics.dumpSendPacketDownstreamAvgInfoAsJson();
for (String peerAddr : peerAddrList) {
assertThat(json, containsString(peerAddr));
}
}

/**
Expand Down