comnetwork commented on a change in pull request #638: PHOENIX-5494
URL: https://github.com/apache/phoenix/pull/638#discussion_r348320326
##########
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);
+ }
+
+ Region region = regionCoprocessorEnvironment.getRegion();
+ HashMap<ImmutableBytesPtr, List<Cell>> rowKeyPtrToCells =
+ new HashMap<ImmutableBytesPtr, List<Cell>>();
+ try (RegionScanner scanner = region.getScanner(scan)) {
+ boolean more = true;
+ while(more)
+ {
+ List<Cell> cells = new ArrayList<Cell>();
+ more = scanner.next(cells);
+ if (cells.isEmpty()) {
+ continue;
+ }
+ Cell cell = cells.get(0);
+ byte[] rowKey = CellUtil.cloneRow(cell);
+ rowKeyPtrToCells.put(new ImmutableBytesPtr(rowKey), cells);
+ }
+ }
+
+ return new CachedLocalTable(rowKeyPtrToCells);
+ }
+
+ private static long getMaxTimestamp(Collection<? extends Mutation>
dataTableMutationsWithSameRowKeyAndTimestamp){
+ long maxTimestamp = Long.MIN_VALUE;
+ for(Mutation mutation : dataTableMutationsWithSameRowKeyAndTimestamp) {
+ long timestamp =
mutation.getFamilyCellMap().values().iterator().next().get(0).getTimestamp();
Review comment:
1. Yes , we can guarantee that all cells in a mutation have the the same
timestamp
because the previous IndexManagementUtil.flattenMutationsByTimestamp. I
would add more comments for it.
2. What the logic do you mean? the logic getMaxTimestamp here is not in
CachedLocalTable, do you mean the
mutation.getFamilyCellMap().values().iterator().next().get(0).getTimestamp() ?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
