VladRodionov commented on a change in pull request #623: HBASE-22749:
Distributed MOB compactions
URL: https://github.com/apache/hbase/pull/623#discussion_r338312866
##########
File path:
hbase-server/src/main/java/org/apache/hadoop/hbase/mob/DefaultMobStoreCompactor.java
##########
@@ -183,105 +270,166 @@ protected boolean performCompaction(FileDetails fd,
InternalScanner scanner, Cel
boolean hasMore;
Path path = MobUtils.getMobFamilyPath(conf, store.getTableName(),
store.getColumnFamilyName());
byte[] fileName = null;
- StoreFileWriter mobFileWriter = null, delFileWriter = null;
- long mobCells = 0, deleteMarkersCount = 0;
+ StoreFileWriter mobFileWriter = null;
+ long mobCells = 0;
long cellsCountCompactedToMob = 0, cellsCountCompactedFromMob = 0;
long cellsSizeCompactedToMob = 0, cellsSizeCompactedFromMob = 0;
boolean finished = false;
+
ScannerContext scannerContext =
ScannerContext.newBuilder().setBatchLimit(compactionKVMax).build();
throughputController.start(compactionName);
- KeyValueScanner kvs = (scanner instanceof KeyValueScanner)?
(KeyValueScanner)scanner : null;
- long shippedCallSizeLimit = (long) numofFilesToCompact *
this.store.getColumnFamilyDescriptor().getBlocksize();
+ KeyValueScanner kvs = (scanner instanceof KeyValueScanner) ?
(KeyValueScanner) scanner : null;
+ long shippedCallSizeLimit =
+ (long) numofFilesToCompact *
this.store.getColumnFamilyDescriptor().getBlocksize();
+
+ MobCell mobCell = null;
try {
try {
// If the mob file writer could not be created, directly write the
cell to the store file.
mobFileWriter = mobStore.createWriterInTmp(new Date(fd.latestPutTs),
fd.maxKeyCount,
compactionCompression, store.getRegionInfo().getStartKey(), true);
fileName = Bytes.toBytes(mobFileWriter.getPath().getName());
} catch (IOException e) {
- LOG.warn("Failed to create mob writer, "
- + "we will continue the compaction by writing MOB cells
directly in store files", e);
+ // Bailing out
+ LOG.error("Failed to create mob writer, ", e);
+ throw e;
}
- if (major) {
- try {
- delFileWriter = mobStore.createDelFileWriterInTmp(new
Date(fd.latestPutTs),
- fd.maxKeyCount, compactionCompression,
store.getRegionInfo().getStartKey());
- } catch (IOException e) {
- LOG.warn(
- "Failed to create del writer, "
- + "we will continue the compaction by writing delete markers
directly in store files",
- e);
- }
+ if (compactMOBs) {
+ // Add the only reference we get for compact MOB case
+ // because new store file will have only one MOB reference
+ // in this case - of newly compacted MOB file
+ mobRefSet.get().add(mobFileWriter.getPath().getName());
}
do {
hasMore = scanner.next(cells, scannerContext);
if (LOG.isDebugEnabled()) {
now = EnvironmentEdgeManager.currentTime();
}
for (Cell c : cells) {
- if (major && CellUtil.isDelete(c)) {
- if (MobUtils.isMobReferenceCell(c) || delFileWriter == null) {
- // Directly write it to a store file
- writer.append(c);
+
+ if (compactMOBs) {
+ if (MobUtils.isMobReferenceCell(c)) {
+ String fName = MobUtils.getMobFileName(c);
+ Path pp = new Path(new Path(fs.getUri()), new Path(path, fName));
+
+ // Added to support migration
+ try {
+ mobCell = mobStore.resolve(c, true, false);
+ } catch (FileNotFoundException fnfe) {
+ if (discardMobMiss) {
+ LOG.error("Missing MOB cell: file=" + pp + " not found");
+ continue;
+ } else {
+ throw fnfe;
+ }
+ }
+
+ if (discardMobMiss && mobCell.getCell().getValueLength() == 0) {
+ LOG.error("Missing MOB cell value: file=" + pp + " cell=" +
mobCell);
+ continue;
+ }
+
+ if (mobCell.getCell().getValueLength() > mobSizeThreshold) {
+ // put the mob data back to the store file
+ PrivateCellUtil.setSequenceId(mobCell.getCell(),
c.getSequenceId());
+ if (generationalMob) {
+ //TODO: verify fName
+ StoreFileWriter stw =
mobWriters.getOutputWriterForInputFile(fName);
+ if (stw != null) {
+ stw.append(mobCell.getCell());
+ mobWriters.incrementMobCountForOutputWriter(stw, 1);
+ } else {
+ // leave mob cell in a MOB file which is not in compaction
selections
+ }
+ } else {
+ mobFileWriter.append(mobCell.getCell());
+ mobCells++;
+ }
+ writer.append(MobUtils.createMobRefCell(mobCell.getCell(),
fileName,
+ this.mobStore.getRefCellTags()));
+ cellsCountCompactedFromMob++;
+ cellsSizeCompactedFromMob +=
mobCell.getCell().getValueLength();
+ } else {
+
+ // If MOB value is less than threshold, append it directly to
a store file
+ PrivateCellUtil.setSequenceId(mobCell.getCell(),
c.getSequenceId());
+ writer.append(mobCell.getCell());
+ }
+
} else {
- // Add a ref tag to this cell and write it to a store file.
- writer.append(MobUtils.createMobRefDeleteMarker(c));
- // Write the cell to a del file
- delFileWriter.append(c);
- deleteMarkersCount++;
+ // Not a MOB reference cell
+ int size = c.getValueLength();
+ if (size > mobSizeThreshold) {
+ // This MOB cell comes from a regular store file
+ // therefore we store it in original mob output
+ mobFileWriter.append(c);
+ writer
+ .append(MobUtils.createMobRefCell(c, fileName,
this.mobStore.getRefCellTags()));
+ mobCells++;
+ } else {
+ writer.append(c);
+ }
}
- } else if (mobFileWriter == null || c.getTypeByte() !=
KeyValue.Type.Put.getCode()) {
- // If the mob file writer is null or the kv type is not put,
directly write the cell
+ } else if (c.getTypeByte() != KeyValue.Type.Put.getCode()) {
+ // Not a major compaction or major with MOB disabled
+ // If the kv type is not put, directly write the cell
// to the store file.
writer.append(c);
} else if (MobUtils.isMobReferenceCell(c)) {
+ // Not a major MOB compaction, Put MOB reference
if (MobUtils.hasValidMobRefCellValue(c)) {
int size = MobUtils.getMobValueLength(c);
if (size > mobSizeThreshold) {
// If the value size is larger than the threshold, it's
regarded as a mob. Since
// its value is already in the mob file, directly write this
cell to the store file
writer.append(c);
+ // Add MOB reference to a set
+ mobRefSet.get().add(MobUtils.getMobFileName(c));
} else {
// If the value is not larger than the threshold, it's not
regarded a mob. Retrieve
- // the mob cell from the mob file, and write it back to the
store file. Must
- // close the mob scanner once the life cycle finished.
- try (MobCell mobCell = mobStore.resolve(c, false)) {
- if (mobCell.getCell().getValueLength() != 0) {
- // put the mob data back to the store file
- PrivateCellUtil.setSequenceId(mobCell.getCell(),
c.getSequenceId());
- writer.append(mobCell.getCell());
- cellsCountCompactedFromMob++;
- cellsSizeCompactedFromMob +=
mobCell.getCell().getValueLength();
- } else {
- // If the value of a file is empty, there might be issues
when retrieving,
- // directly write the cell to the store file, and leave it
to be handled by the
- // next compaction.
- writer.append(c);
- }
+ // the mob cell from the mob file, and write it back to the
store file.
Review comment:
1. MOB threshold could be changed and we will need to move MOB cell to/from
MOB file
2. Store file could have value which is larger than MOB threshold and we
will need to take care of that as well.
3. It works.
----------------------------------------------------------------
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
