[GitHub] [phoenix] kadirozde commented on a change in pull request #638: PHOENIX-5494

[GitBox <gi...@apache.org>]

kadirozde commented on a change in pull request #638: PHOENIX-5494
URL: https://github.com/apache/phoenix/pull/638#discussion_r347547089
 
 

 ##########
 File path: phoenix-core/src/main/java/org/apache/phoenix/hbase/index/builder/IndexBuildManager.java
 ##########
 @@ -88,27 +111,102 @@ public void getIndexUpdates(ListMultimap<HTableInterfaceReference, Pair<Mutation
       IndexMetaData indexMetaData) throws Throwable {
     // notify the delegate that we have started processing a batch
     this.delegate.batchStarted(miniBatchOp, indexMetaData);
-
+    CachedLocalTable cachedLocalTable =
+            preScanAllRequiredRows(
+                    mutations,
+                    (PhoenixIndexMetaData)indexMetaData,
+                    this.regionCoprocessorEnvironment);
     // Avoid the Object overhead of the executor when it's not actually parallelizing anything.
     for (Mutation m : mutations) {
-      Collection<Pair<Mutation, byte[]>> updates = delegate.getIndexUpdate(m, indexMetaData);
+      Collection<Pair<Mutation, byte[]>> updates = delegate.getIndexUpdate(m, indexMetaData, cachedLocalTable);
       for (Pair<Mutation, byte[]> update : updates) {
         indexUpdates.put(new HTableInterfaceReference(new ImmutableBytesPtr(update.getSecond())), new Pair<>(update.getFirst(), m.getRow()));
       }
     }
   }
 
+  @VisibleForTesting
+  public static CachedLocalTable preScanAllRequiredRows(
+          Collection<? extends Mutation> dataTableMutationsWithSameRowKeyAndTimestamp,
+          final PhoenixIndexMetaData indexMetaData,
+          RegionCoprocessorEnvironment regionCoprocessorEnvironment) throws IOException {
+      List<IndexMaintainer> indexTableMaintainers = indexMetaData.getIndexMaintainers();
+      Set<KeyRange> keys = new HashSet<KeyRange>(dataTableMutationsWithSameRowKeyAndTimestamp.size());
+      for (Mutation mutation : dataTableMutationsWithSameRowKeyAndTimestamp) {
+          keys.add(PVarbinary.INSTANCE.getKeyRange(mutation.getRow()));
+      }
+
+      Set<ColumnReference> getterColumnReferences = Sets.newHashSet();
+      for (IndexMaintainer indexTableMaintainer : indexTableMaintainers)
+      {
+          getterColumnReferences.addAll(
+                  indexTableMaintainer.getAllColumns());
+
+      }
+
+      getterColumnReferences.add(new ColumnReference(
+              indexTableMaintainers.get(0).getDataEmptyKeyValueCF(),
+              indexTableMaintainers.get(0).getEmptyKeyValueQualifier()));
+
+      Scan scan = IndexManagementUtil.newLocalStateScan(
+              Collections.singletonList(getterColumnReferences));
+      ScanRanges scanRanges = ScanRanges.createPointLookup(new ArrayList<KeyRange>(keys));
+      scanRanges.initializeScan(scan);
+      scan.setFilter(new SkipScanFilter(scanRanges.getSkipScanFilter(), true));
+
+      if(indexMetaData.getReplayWrite() != null) {
+          long timestamp = getMaxTimestamp(dataTableMutationsWithSameRowKeyAndTimestamp);
+          scan.setTimeRange(0, timestamp);
+      }
+
 
 Review comment:
   We can eliminate unnecessary for raw and all versions scans for regular operations by just adding the following else part :
   else {
             scan.setRaw(false);
             scan.setMaxVersions(1);
         }

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services