svn commit: r1181396 - in /hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver: HRegion.java wal/HLog.java

[ns...@apache.org]

Author: nspiegelberg
Date: Tue Oct 11 02:05:05 2011
New Revision: 1181396

URL: http://svn.apache.org/viewvc?rev=1181396&view=rev
Log:
HBASE-3081: Log Splitting & Replay - Distinguish between Network IOE and Parsing IOE

Summary:
Originally, if HBase got an IOE from HDFS while splitting or opening a region,
it would abort the operation. The assumption being that this is a network
failure that will likely disappear at a later time or different partition of the
network. However, if HBase gets parsing exceptions, we want to log the problem
and continue opening/splitting the region anyways, because parsing is an
idempotent problem and retries won't fix this issue.

Test Plan:
mvn clean test

DiffCamp Revision: 165921
Reviewed By: kannan
CC: dhruba, kannan
Revert Plan:
OK

Modified:
    hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/HRegion.java
    hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/wal/HLog.java

Modified: hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/HRegion.java
URL: http://svn.apache.org/viewvc/hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/HRegion.java?rev=1181396&r1=1181395&r2=1181396&view=diff
==============================================================================
--- hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/HRegion.java (original)
+++ hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/HRegion.java Tue Oct 11 02:05:05 2011
@@ -24,6 +24,7 @@ import java.io.IOException;
 import java.io.InterruptedIOException;
 import java.io.UnsupportedEncodingException;
 import java.lang.reflect.Constructor;
+import java.text.ParseException;
 import java.util.AbstractList;
 import java.util.ArrayList;
 import java.util.Arrays;
@@ -2032,11 +2033,15 @@ public class HRegion implements HeapSize
           "log spliting, so we have this data in another edit.  " +
           "Continuing, but renaming " + edits + " as " + p, eof);
     } catch (IOException ioe) {
-      if (ioe.getMessage().startsWith("File is corrupt")) {
+      // If the IOE resulted from bad file format,
+      // then this problem is idempotent and retrying won't help
+      if (ioe.getCause() instanceof ParseException) {
         Path p = HLog.moveAsideBadEditsFile(fs, edits);
         LOG.warn("File corruption encountered!  " +
             "Continuing, but renaming " + edits + " as " + p, ioe);
       } else {
+        // other IO errors may be transient (bad network connection,
+        // checksum exception on one datanode, etc).  throw & retry
         throw ioe;
       }
     }

Modified: hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/wal/HLog.java
URL: http://svn.apache.org/viewvc/hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/wal/HLog.java?rev=1181396&r1=1181395&r2=1181396&view=diff
==============================================================================
--- hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/wal/HLog.java (original)
+++ hbase/branches/0.89/src/main/java/org/apache/hadoop/hbase/regionserver/wal/HLog.java Tue Oct 11 02:05:05 2011
@@ -30,6 +30,7 @@ import java.io.OutputStream;
 import java.io.UnsupportedEncodingException;
 import java.lang.reflect.Method;
 import java.net.URLEncoder;
+import java.text.ParseException;
 import java.util.ArrayList;
 import java.util.Collections;
 import java.util.HashMap;
@@ -1313,13 +1314,20 @@ public class HLog implements Syncable {
             LOG.warn("EOF from hlog " + logPath + ".  continuing");
             processedLogs.add(logPath);
           } catch (IOException e) {
-             if (skipErrors) {
-               LOG.info("Got while parsing hlog " + logPath +
-                 ". Marking as corrupted", e);
-               corruptedLogs.add(logPath);
-             } else {
-               throw e;
-             }
+            // If the IOE resulted from bad file format,
+            // then this problem is idempotent and retrying won't help
+            if (e.getCause() instanceof ParseException) {
+              LOG.warn("ParseException from hlog " + logPath + ".  continuing");
+              processedLogs.add(logPath);
+            } else {
+              if (skipErrors) {
+                LOG.info("Got while parsing hlog " + logPath +
+                  ". Marking as corrupted", e);
+                corruptedLogs.add(logPath);
+              } else {
+                throw e;
+              }
+            }
           }
         }
         writeEditsBatchToRegions(editsByRegion, logWriters, rootDir, fs, conf);