HBASE-2985 HRegionServer.multi() no longer calls HRegion.put(List) when possible

git-svn-id: https://svn.apache.org/repos/asf/hbase/trunk@1024074 13f79535-47bb-0310-9956-ffa450edef68

CHANGES.txt

@@ -596,6 +596,8 @@ Release 0.21.0 - Unreleased
    HBASE-3121  [rest] Do not perform cache control when returning results
    HBASE-2669  HCM.shutdownHook causes data loss with
                hbase.client.write.buffer != 0
+   HBASE-2985  HRegionServer.multi() no longer calls HRegion.put(List) when 
+   	       possible
 
   IMPROVEMENTS
    HBASE-1760  Cleanup TODOs in HTable

src/main/java/org/apache/hadoop/hbase/client/HConnectionManager.java

@@ -1176,7 +1176,7 @@ public class HConnectionManager {
                 List<Pair<Integer, Result>> regionResults = e.getValue();
                 for (Pair<Integer, Result> regionResult : regionResults) {
                   if (regionResult == null) {
-                    // failed
+                    // if the first/only record is 'null' the entire region failed.
                     LOG.debug("Failures for region: " + Bytes.toStringBinary(regionName) + ", removing from cache");
                   } else {
                     // success

src/main/java/org/apache/hadoop/hbase/client/HTable.java

@@ -551,7 +551,10 @@ public class HTable implements HTableInterface {
   }
 
   /**
-   * Method that does a batch call on Deletes, Gets and Puts.
+   * Method that does a batch call on Deletes, Gets and Puts.  The ordering of
+   * execution of the actions is not defined. Meaning if you do a Put and a
+   * Get in the same {@link #batch} call, you will not necessarily be
+   * guaranteed that the Get returns what the Put had put.
    *
    * @param actions list of Get, Put, Delete objects
    * @param results Empty Result[], same size as actions. Provides access to partial

src/main/java/org/apache/hadoop/hbase/client/MultiResponse.java

@@ -42,8 +42,8 @@ public class MultiResponse implements Writable {
 
   // map of regionName to list of (Results paired to the original index for that
   // Result)
-  private Map<byte[], List<Pair<Integer, Result>>> results = new TreeMap<byte[], List<Pair<Integer, Result>>>(
+  private Map<byte[], List<Pair<Integer, Result>>> results =
-      Bytes.BYTES_COMPARATOR);
+      new TreeMap<byte[], List<Pair<Integer, Result>>>(Bytes.BYTES_COMPARATOR);
 
   public MultiResponse() {
   }

src/main/java/org/apache/hadoop/hbase/regionserver/HRegionServer.java

@@ -2330,9 +2330,11 @@ public class HRegionServer implements HRegionInterface, HBaseRPCErrorHandler,
       // actions in the list.
       Collections.sort(actionsForRegion);
       Row action = null;
+      List<Action> puts = new ArrayList<Action>();
       try {
         for (Action a : actionsForRegion) {
           action = a.getAction();
+          // TODO catch exceptions so we can report them on a per-item basis.
           if (action instanceof Delete) {
             delete(regionName, (Delete) action);
             response.add(regionName, new Pair<Integer, Result>(
@@ -2341,14 +2343,50 @@ public class HRegionServer implements HRegionInterface, HBaseRPCErrorHandler,
             response.add(regionName, new Pair<Integer, Result>(
                 a.getOriginalIndex(), get(regionName, (Get) action)));
           } else if (action instanceof Put) {
-            put(regionName, (Put) action);
+            puts.add(a);
-            response.add(regionName, new Pair<Integer, Result>(
-                a.getOriginalIndex(), new Result()));
           } else {
             LOG.debug("Error: invalid Action, row must be a Get, Delete or Put.");
             throw new IllegalArgumentException("Invalid Action, row must be a Get, Delete or Put.");
           }
         }
+
+        // We do the puts with result.put so we can get the batching efficiency
+        // we so need. All this data munging doesn't seem great, but at least
+        // we arent copying bytes or anything.
+        if (!puts.isEmpty()) {
+          HRegion region = getRegion(regionName);
+          if (!region.getRegionInfo().isMetaTable()) {
+            this.cacheFlusher.reclaimMemStoreMemory();
+          }
+
+          Pair<Put,Integer> [] putsWithLocks = new Pair[puts.size()];
+          int i = 0;
+          for (Action a : puts) {
+            Put p = (Put) a.getAction();
+
+            Integer lock = getLockFromId(p.getLockId());
+            putsWithLocks[i++] = new Pair<Put, Integer>(p, lock);
+          }
+
+          this.requestCount.addAndGet(puts.size());
+
+          OperationStatusCode[] codes = region.put(putsWithLocks);
+          for( i = 0 ; i < codes.length ; i++) {
+            OperationStatusCode code = codes[i];
+
+            Action theAction = puts.get(i);
+            Result result = null;
+
+            if (code == OperationStatusCode.SUCCESS) {
+              result = new Result();
+            }
+            // TODO turning the alternate exception into a different result
+
+            response.add(regionName,
+                new Pair<Integer, Result>(
+                    theAction.getOriginalIndex(), result));
+          }
+        }
       } catch (IOException ioe) {
         if (multi.size() == 1) throw ioe;
         LOG.debug("Exception processing " +

src/test/java/org/apache/hadoop/hbase/client/TestMultiParallel.java

@@ -354,17 +354,11 @@ public class TestMultiParallel {
     get.addColumn(BYTES_FAMILY, QUALIFIER);
     actions.add(get);
 
-    // 5 get of the put in #2 (entire family)
+    // There used to be a 'get' of a previous put here, but removed
-    get = new Get(KEYS[10]);
+    // since this API really cannot guarantee order in terms of mixed
-    get.addFamily(BYTES_FAMILY);
+    // get/puts.
-    actions.add(get);
 
-    // 6 get of the delete from #3
+    // 5 put of new column
-    get = new Get(KEYS[20]);
-    get.addColumn(BYTES_FAMILY, QUALIFIER);
-    actions.add(get);
-
-    // 7 put of new column
     put = new Put(KEYS[40]);
     put.add(BYTES_FAMILY, qual2, val2);
     actions.add(put);
@@ -378,10 +372,7 @@ public class TestMultiParallel {
     validateEmpty(results[2]);
     validateEmpty(results[3]);
     validateResult(results[4]);
-    validateResult(results[5]);
+    validateEmpty(results[5]);
-    validateResult(results[5], qual2, val2); // testing second column in #5
-    validateEmpty(results[6]); // deleted
-    validateEmpty(results[7]);
 
     // validate last put, externally from the batch
     get = new Get(KEYS[40]);