kadirozde commented on a change in pull request #701: PHOENIX-5709 Simplify index update generation code for consistent glo… URL: https://github.com/apache/phoenix/pull/701#discussion_r376891928
########## File path: phoenix-core/src/main/java/org/apache/phoenix/hbase/index/IndexRegionObserver.java ########## @@ -409,91 +413,220 @@ private void populatePendingRows(BatchMutateContext context) { } } - private Collection<? extends Mutation> groupMutations(MiniBatchOperationInProgress<Mutation> miniBatchOp, - long now, ReplayWrite replayWrite) throws IOException { - Map<ImmutableBytesPtr, MultiMutation> mutationsMap = new HashMap<>(); - boolean copyMutations = false; - for (int i = 0; i < miniBatchOp.size(); i++) { + public static void setTimestamp(Mutation m, long ts) throws IOException { + for (List<Cell> cells : m.getFamilyCellMap().values()) { + for (Cell cell : cells) { + CellUtil.setTimestamp(cell, ts); + } + } + } + + public static long getTimestamp(Mutation m) throws IOException { + for (List<Cell> cells : m.getFamilyCellMap().values()) { + for (Cell cell : cells) { + return cell.getTimestamp(); + } + } + return 0; + } + + private static void removeColumn(Put put, Cell deleteCell) { + byte[] family = CellUtil.cloneFamily(deleteCell); + List<Cell> cellList = put.getFamilyCellMap().get(family); + if (cellList == null) { + return; + } + Iterator<Cell> cellIterator = cellList.iterator(); + while (cellIterator.hasNext()) { + Cell cell = cellIterator.next(); + if (Bytes.compareTo(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength(), + deleteCell.getQualifierArray(), deleteCell.getQualifierOffset(), deleteCell.getQualifierLength()) == 0) { + cellIterator.remove(); + if (cellList.isEmpty()) { + put.getFamilyCellMap().remove(family); + } + return; + } + } + } + + + private void merge(Put current, Put previous) throws IOException { + for (List<Cell> cells : previous.getFamilyCellMap().values()) { + for (Cell cell : cells) { + if (!current.has(CellUtil.cloneFamily(cell), CellUtil.cloneQualifier(cell))) { + current.add(cell); + } + } + } + } + + private Put mergeNew(Put current, Put previous) throws IOException { + Put next = new Put(current); + for (List<Cell> cells : previous.getFamilyCellMap().values()) { + for (Cell cell : cells) { + if (!current.has(CellUtil.cloneFamily(cell), CellUtil.cloneQualifier(cell))) { + next.add(cell); + } + } + } + return next; + } + + /** + * When there are multiple put mutations on the data same row within the same batch, this method merged them into + * one mutation. + */ + private void mergePendingPutMutations(MiniBatchOperationInProgress<Mutation> miniBatchOp, + Map<ImmutableBytesPtr, Integer> pendingPuts, + long now) throws IOException { + for (Integer i = 0; i < miniBatchOp.size(); i++) { if (miniBatchOp.getOperationStatus(i) == IGNORE) { continue; } Mutation m = miniBatchOp.getOperation(i); + // skip this mutation if we aren't enabling indexing if (this.builder.isEnabled(m)) { - // Track whether or not we need to - ImmutableBytesPtr row = new ImmutableBytesPtr(m.getRow()); - if (mutationsMap.containsKey(row)) { - copyMutations = true; - } else { - mutationsMap.put(row, null); + // Unless we're replaying edits to rebuild the index, we update the time stamp + // of the data table to prevent overlapping time stamps (which prevents index + // inconsistencies as this case isn't handled correctly currently). + setTimestamp(m, now); + if (m instanceof Put) { + ImmutableBytesPtr rowKeyPtr = new ImmutableBytesPtr(m.getRow()); + Integer opIndex = pendingPuts.get(rowKeyPtr); + pendingPuts.put(rowKeyPtr, i); Review comment: It is not safer to wait as this is done under row lock. However, it is more readable if it is done after the merge. So, I will change the order. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services