[hbase] 01/02: HBASE-26027 The calling of HTable.batch blocked at AsyncRequestFutureImpl.waitUntilDone caused by ArrayStoreException (#3925)

[ap...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

apurtell pushed a commit to branch branch-2.5
in repository https://gitbox.apache.org/repos/asf/hbase.git

commit 49d4c4a4c0f189503b95b7fb4407f6bfd56be37a
Author: bsglz <18...@qq.com>
AuthorDate: Fri Dec 10 14:34:17 2021 +0800

    HBASE-26027 The calling of HTable.batch blocked at AsyncRequestFutureImpl.waitUntilDone caused by ArrayStoreException (#3925)
    
    * HBASE-26027 The calling of HTable.batch blocked at AsyncRequestFutureImpl.waitUntilDone caused by ArrayStoreException
---
 .../hadoop/hbase/client/AsyncRequestFutureImpl.java       | 15 +++++++++++++--
 .../apache/hadoop/hbase/TestClientOperationTimeout.java   |  5 ++---
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/hbase-client/src/main/java/org/apache/hadoop/hbase/client/AsyncRequestFutureImpl.java b/hbase-client/src/main/java/org/apache/hadoop/hbase/client/AsyncRequestFutureImpl.java
index 8cfcf0c..ca6d534 100644
--- a/hbase-client/src/main/java/org/apache/hadoop/hbase/client/AsyncRequestFutureImpl.java
+++ b/hbase-client/src/main/java/org/apache/hadoop/hbase/client/AsyncRequestFutureImpl.java
@@ -21,6 +21,7 @@ package org.apache.hadoop.hbase.client;
 
 import java.io.IOException;
 import java.io.InterruptedIOException;
+import java.net.SocketTimeoutException;
 import java.util.ArrayList;
 import java.util.Collection;
 import java.util.Collections;
@@ -1132,7 +1133,17 @@ class AsyncRequestFutureImpl<CResult> implements AsyncRequestFuture {
   @Override
   public void waitUntilDone() throws InterruptedIOException {
     try {
-      waitUntilDone(Long.MAX_VALUE);
+      if (this.operationTimeout > 0) {
+        // the worker thread maybe over by some exception without decrement the actionsInProgress,
+        // then the guarantee of operationTimeout will be broken, so we should set cutoff to avoid
+        // stuck here forever
+        long cutoff = (EnvironmentEdgeManager.currentTime() + this.operationTimeout) * 1000L;
+        if (!waitUntilDone(cutoff)) {
+          throw new SocketTimeoutException("time out before the actionsInProgress changed to zero");
+        }
+      } else {
+        waitUntilDone(Long.MAX_VALUE);
+      }
     } catch (InterruptedException iex) {
       throw new InterruptedIOException(iex.getMessage());
     } finally {
@@ -1144,7 +1155,7 @@ class AsyncRequestFutureImpl<CResult> implements AsyncRequestFuture {
     }
   }
 
-  private boolean waitUntilDone(long cutoff) throws InterruptedException {
+  private boolean waitUntilDone(long cutoff) throws InterruptedException{
     boolean hasWait = cutoff != Long.MAX_VALUE;
     long lastLog = EnvironmentEdgeManager.currentTime();
     long currentInProgress;
diff --git a/hbase-server/src/test/java/org/apache/hadoop/hbase/TestClientOperationTimeout.java b/hbase-server/src/test/java/org/apache/hadoop/hbase/TestClientOperationTimeout.java
index 09bdf7a..20424c9 100644
--- a/hbase-server/src/test/java/org/apache/hadoop/hbase/TestClientOperationTimeout.java
+++ b/hbase-server/src/test/java/org/apache/hadoop/hbase/TestClientOperationTimeout.java
@@ -29,7 +29,6 @@ import org.apache.hadoop.hbase.client.Get;
 import org.apache.hadoop.hbase.client.Put;
 import org.apache.hadoop.hbase.client.ResultScanner;
 import org.apache.hadoop.hbase.client.RetriesExhaustedException;
-import org.apache.hadoop.hbase.client.RetriesExhaustedWithDetailsException;
 import org.apache.hadoop.hbase.client.Scan;
 import org.apache.hadoop.hbase.client.Table;
 import org.apache.hadoop.hbase.client.TableDescriptorBuilder;
@@ -158,7 +157,7 @@ public class TestClientOperationTimeout {
   }
 
   /**
-   * Tests that a batch mutate on a table throws {@link RetriesExhaustedException} when the
+   * Tests that a batch mutate on a table throws {@link SocketTimeoutException} when the
    * operation takes longer than 'hbase.client.operation.timeout'.
    */
   @Test
@@ -175,7 +174,7 @@ public class TestClientOperationTimeout {
       TABLE.batch(puts, new Object[2]);
       Assert.fail("should not reach here");
     } catch (Exception e) {
-      Assert.assertTrue(e instanceof RetriesExhaustedWithDetailsException);
+      Assert.assertTrue(e instanceof SocketTimeoutException);
     }
   }