Skip to content

HBASE-28637 asyncwal should attempt to recover lease if close fails (#5962) #6033

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 2 commits into from
Jul 10, 2024
Merged

HBASE-28637 asyncwal should attempt to recover lease if close fails (#5962) #6033

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
015f1d9
HBASE-28637 asyncwal should attempt to recover lease if close fails (…
jojochuang Jun 12, 2024
ef21185
Fix spotless
jojochuang Jun 27, 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
12 changes: 11 additions & 1 deletion hbase-server/src/main/java/org/apache/hadoop/hbase/regionserver/wal/AsyncFSWAL.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@
import org.apache.hadoop.hbase.client.RegionInfo;
import org.apache.hadoop.hbase.io.asyncfs.AsyncFSOutput;
import org.apache.hadoop.hbase.io.asyncfs.monitor.StreamSlowMonitor;
import org.apache.hadoop.hbase.util.RecoverLeaseFSUtils;
import org.apache.hadoop.hbase.wal.AsyncFSWALProvider;
import org.apache.hadoop.hbase.wal.WALEdit;
import org.apache.hadoop.hbase.wal.WALKeyImpl;
Expand Down Expand Up @@ -716,13 +717,22 @@ private void waitForSafePoint() {
}
}

private void recoverLease(FileSystem fs, Path p, Configuration conf) {
try {
RecoverLeaseFSUtils.recoverFileLease(fs, p, conf, null);
} catch (IOException ex) {
LOG.error("Unable to recover lease after several attempts. Give up.", ex);
}
}

private void closeWriter(AsyncWriter writer, Path path) {
inflightWALClosures.put(path.getName(), writer);
closeExecutor.execute(() -> {
try {
writer.close();
} catch (IOException e) {
LOG.warn("close old writer failed", e);
LOG.warn("close old writer failed.", e);
recoverLease(this.fs, path, conf);
} finally {
// call this even if the above close fails, as there is no other chance we can set closed to
// true, it will not cause big problems.
Expand Down
24 changes: 16 additions & 8 deletions hbase-server/src/main/java/org/apache/hadoop/hbase/regionserver/wal/FSHLog.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.util.ClassSize;
import org.apache.hadoop.hbase.util.CommonFSUtils;
import org.apache.hadoop.hbase.util.RecoverLeaseFSUtils;
import org.apache.hadoop.hbase.util.Threads;
import org.apache.hadoop.hbase.wal.FSHLogProvider;
import org.apache.hadoop.hbase.wal.WALEdit;
Expand Down Expand Up @@ -455,15 +456,22 @@ private void closeWriter(Writer writer, Path path, boolean syncCloseCall) throws
writer.close();
span.addEvent("writer closed");
} catch (IOException ioe) {
int errors = closeErrorCount.incrementAndGet();
boolean hasUnflushedEntries = isUnflushedEntries();
if (syncCloseCall && (hasUnflushedEntries || (errors > this.closeErrorsTolerated))) {
LOG.error("Close of WAL " + path + " failed. Cause=\"" + ioe.getMessage() + "\", errors="
+ errors + ", hasUnflushedEntries=" + hasUnflushedEntries);
throw ioe;
LOG.warn("close old writer failed.", ioe);
try {
RecoverLeaseFSUtils.recoverFileLease(fs, path, conf, null);
} catch (IOException ex) {
LOG.error("Unable to recover lease after several attempts. Give up.", ex);

int errors = closeErrorCount.incrementAndGet();
boolean hasUnflushedEntries = isUnflushedEntries();
if (syncCloseCall && (hasUnflushedEntries || (errors > this.closeErrorsTolerated))) {
LOG.error("Close of WAL " + path + " failed. Cause=\"" + ioe.getMessage() + "\", errors="
+ errors + ", hasUnflushedEntries=" + hasUnflushedEntries);
throw ioe;
}
LOG.warn("Riding over failed WAL close of " + path
+ "; THIS FILE WAS NOT CLOSED BUT ALL EDITS SYNCED SO SHOULD BE OK", ioe);
}
LOG.warn("Riding over failed WAL close of " + path
+ "; THIS FILE WAS NOT CLOSED BUT ALL EDITS SYNCED SO SHOULD BE OK", ioe);
}
}

Expand Down