/**
* Perform time consuming opening of the daughter regions.
*
* @param server Hosting server instance. Can be null when testing
* @param services Used to online/offline regions.
* @param a first daughter region
* @param a second daughter region
* @throws IOException If thrown, transaction failed. Call {@link #rollback(Server,
* RegionServerServices)}
*/
@VisibleForTesting
void openDaughters(final Server server, final RegionServerServices services, Region a, Region b)
throws IOException {
boolean stopped = server != null && server.isStopped();
boolean stopping = services != null && services.isStopping();
// TODO: Is this check needed here?
if (stopped || stopping) {
LOG.info(
"Not opening daughters "
+ b.getRegionInfo().getRegionNameAsString()
+ " and "
+ a.getRegionInfo().getRegionNameAsString()
+ " because stopping="
+ stopping
+ ", stopped="
+ stopped);
} else {
// Open daughters in parallel.
DaughterOpener aOpener = new DaughterOpener(server, a);
DaughterOpener bOpener = new DaughterOpener(server, b);
aOpener.start();
bOpener.start();
try {
aOpener.join();
if (aOpener.getException() == null) {
transition(SplitTransactionPhase.OPENED_REGION_A);
}
bOpener.join();
if (bOpener.getException() == null) {
transition(SplitTransactionPhase.OPENED_REGION_B);
}
} catch (InterruptedException e) {
throw (InterruptedIOException) new InterruptedIOException().initCause(e);
}
if (aOpener.getException() != null) {
throw new IOException("Failed " + aOpener.getName(), aOpener.getException());
}
if (bOpener.getException() != null) {
throw new IOException("Failed " + bOpener.getName(), bOpener.getException());
}
if (services != null) {
if (!services.reportRegionStateTransition(
TransitionCode.SPLIT, parent.getRegionInfo(), hri_a, hri_b)) {
throw new IOException(
"Failed to report split region to master: "
+ parent.getRegionInfo().getShortNameToLog());
}
// Should add it to OnlineRegions
services.addToOnlineRegions(b);
services.addToOnlineRegions(a);
}
}
}
@Override
public boolean prepare() throws IOException {
if (!this.parent.isSplittable()) return false;
// Split key can be null if this region is unsplittable; i.e. has refs.
if (this.splitrow == null) return false;
HRegionInfo hri = this.parent.getRegionInfo();
parent.prepareToSplit();
// Check splitrow.
byte[] startKey = hri.getStartKey();
byte[] endKey = hri.getEndKey();
if (Bytes.equals(startKey, splitrow) || !this.parent.getRegionInfo().containsRow(splitrow)) {
LOG.info(
"Split row is not inside region key range or is equal to "
+ "startkey: "
+ Bytes.toStringBinary(this.splitrow));
return false;
}
long rid = getDaughterRegionIdTimestamp(hri);
this.hri_a = new HRegionInfo(hri.getTable(), startKey, this.splitrow, false, rid);
this.hri_b = new HRegionInfo(hri.getTable(), this.splitrow, endKey, false, rid);
transition(SplitTransactionPhase.PREPARED);
return true;
}
@Override
public PairOfSameType<Region> execute(
final Server server, final RegionServerServices services, User user) throws IOException {
this.server = server;
this.rsServices = services;
PairOfSameType<Region> regions = createDaughters(server, services, user);
stepsAfterPONR(server, services, regions, user);
transition(SplitTransactionPhase.COMPLETED);
return regions;
}
@VisibleForTesting
void stepsAfterPONR(
final Server server,
final RegionServerServices services,
final PairOfSameType<Region> regions,
User user)
throws IOException {
if (this.parent.getCoprocessorHost() != null) {
parent.getCoprocessorHost().preSplitAfterPONR(user);
}
openDaughters(server, services, regions.getFirst(), regions.getSecond());
transition(SplitTransactionPhase.BEFORE_POST_SPLIT_HOOK);
// Coprocessor callback
if (parent.getCoprocessorHost() != null) {
this.parent.getCoprocessorHost().postSplit(regions.getFirst(), regions.getSecond(), user);
}
transition(SplitTransactionPhase.AFTER_POST_SPLIT_HOOK);
}
@Override
public boolean rollback(final Server server, final RegionServerServices services, User user)
throws IOException {
this.server = server;
this.rsServices = services;
// Coprocessor callback
if (this.parent.getCoprocessorHost() != null) {
this.parent.getCoprocessorHost().preRollBackSplit(user);
}
boolean result = true;
ListIterator<JournalEntry> iterator = this.journal.listIterator(this.journal.size());
// Iterate in reverse.
while (iterator.hasPrevious()) {
JournalEntry je = iterator.previous();
transition(je.getPhase(), true);
switch (je.getPhase()) {
case SET_SPLITTING:
if (services != null
&& !services.reportRegionStateTransition(
TransitionCode.SPLIT_REVERTED, parent.getRegionInfo(), hri_a, hri_b)) {
return false;
}
break;
case CREATE_SPLIT_DIR:
this.parent.writestate.writesEnabled = true;
this.parent.getRegionFileSystem().cleanupSplitsDir();
break;
case CLOSED_PARENT_REGION:
try {
// So, this returns a seqid but if we just closed and then reopened, we
// should be ok. On close, we flushed using sequenceid obtained from
// hosting regionserver so no need to propagate the sequenceid returned
// out of initialize below up into regionserver as we normally do.
// TODO: Verify.
this.parent.initialize();
} catch (IOException e) {
LOG.error(
"Failed rollbacking CLOSED_PARENT_REGION of region "
+ parent.getRegionInfo().getRegionNameAsString(),
e);
throw new RuntimeException(e);
}
break;
case STARTED_REGION_A_CREATION:
this.parent.getRegionFileSystem().cleanupDaughterRegion(this.hri_a);
break;
case STARTED_REGION_B_CREATION:
this.parent.getRegionFileSystem().cleanupDaughterRegion(this.hri_b);
break;
case OFFLINED_PARENT:
if (services != null) services.addToOnlineRegions(this.parent);
break;
case PONR:
// We got to the point-of-no-return so we need to just abort. Return
// immediately. Do not clean up created daughter regions. They need
// to be in place so we don't delete the parent region mistakenly.
// See HBASE-3872.
return false;
// Informational only cases
case STARTED:
case PREPARED:
case BEFORE_PRE_SPLIT_HOOK:
case AFTER_PRE_SPLIT_HOOK:
case BEFORE_POST_SPLIT_HOOK:
case AFTER_POST_SPLIT_HOOK:
case OPENED_REGION_A:
case OPENED_REGION_B:
case COMPLETED:
break;
default:
throw new RuntimeException("Unhandled journal entry: " + je);
}
}
// Coprocessor callback
if (this.parent.getCoprocessorHost() != null) {
this.parent.getCoprocessorHost().postRollBackSplit(user);
}
return result;
}
@VisibleForTesting
public PairOfSameType<Region> stepsBeforePONR(
final Server server, final RegionServerServices services, boolean testing)
throws IOException {
if (services != null
&& !services.reportRegionStateTransition(
TransitionCode.READY_TO_SPLIT, parent.getRegionInfo(), hri_a, hri_b)) {
throw new IOException(
"Failed to get ok from master to split "
+ parent.getRegionInfo().getRegionNameAsString());
}
transition(SplitTransactionPhase.SET_SPLITTING);
this.parent.getRegionFileSystem().createSplitsDir();
transition(SplitTransactionPhase.CREATE_SPLIT_DIR);
Map<byte[], List<StoreFile>> hstoreFilesToSplit = null;
Exception exceptionToThrow = null;
try {
hstoreFilesToSplit = this.parent.close(false);
} catch (Exception e) {
exceptionToThrow = e;
}
if (exceptionToThrow == null && hstoreFilesToSplit == null) {
// The region was closed by a concurrent thread. We can't continue
// with the split, instead we must just abandon the split. If we
// reopen or split this could cause problems because the region has
// probably already been moved to a different server, or is in the
// process of moving to a different server.
exceptionToThrow = closedByOtherException;
}
if (exceptionToThrow != closedByOtherException) {
transition(SplitTransactionPhase.CLOSED_PARENT_REGION);
}
if (exceptionToThrow != null) {
if (exceptionToThrow instanceof IOException) throw (IOException) exceptionToThrow;
throw new IOException(exceptionToThrow);
}
if (!testing) {
services.removeFromOnlineRegions(this.parent, null);
}
transition(SplitTransactionPhase.OFFLINED_PARENT);
// TODO: If splitStoreFiles were multithreaded would we complete steps in
// less elapsed time? St.Ack 20100920
//
// splitStoreFiles creates daughter region dirs under the parent splits dir
// Nothing to unroll here if failure -- clean up of CREATE_SPLIT_DIR will
// clean this up.
Pair<Integer, Integer> expectedReferences = splitStoreFiles(hstoreFilesToSplit);
// Log to the journal that we are creating region A, the first daughter
// region. We could fail halfway through. If we do, we could have left
// stuff in fs that needs cleanup -- a storefile or two. Thats why we
// add entry to journal BEFORE rather than AFTER the change.
transition(SplitTransactionPhase.STARTED_REGION_A_CREATION);
assertReferenceFileCount(
expectedReferences.getFirst(), this.parent.getRegionFileSystem().getSplitsDir(this.hri_a));
HRegion a = this.parent.createDaughterRegionFromSplits(this.hri_a);
assertReferenceFileCount(
expectedReferences.getFirst(),
new Path(this.parent.getRegionFileSystem().getTableDir(), this.hri_a.getEncodedName()));
// Ditto
transition(SplitTransactionPhase.STARTED_REGION_B_CREATION);
assertReferenceFileCount(
expectedReferences.getSecond(), this.parent.getRegionFileSystem().getSplitsDir(this.hri_b));
HRegion b = this.parent.createDaughterRegionFromSplits(this.hri_b);
assertReferenceFileCount(
expectedReferences.getSecond(),
new Path(this.parent.getRegionFileSystem().getTableDir(), this.hri_b.getEncodedName()));
return new PairOfSameType<Region>(a, b);
}
/**
* Prepare the regions and region files.
*
* @param server Hosting server instance. Can be null when testing (won't try and update in zk if
* a null server)
* @param services Used to online/offline regions.
* @param user
* @throws IOException If thrown, transaction failed. Call {@link #rollback(Server,
* RegionServerServices)}
* @return Regions created
*/
@VisibleForTesting
PairOfSameType<Region> createDaughters(
final Server server, final RegionServerServices services, User user) throws IOException {
LOG.info("Starting split of region " + this.parent);
if ((server != null && server.isStopped()) || (services != null && services.isStopping())) {
throw new IOException("Server is stopped or stopping");
}
assert !this.parent.lock.writeLock().isHeldByCurrentThread()
: "Unsafe to hold write lock while performing RPCs";
transition(SplitTransactionPhase.BEFORE_PRE_SPLIT_HOOK);
// Coprocessor callback
if (this.parent.getCoprocessorHost() != null) {
// TODO: Remove one of these
parent.getCoprocessorHost().preSplit(user);
parent.getCoprocessorHost().preSplit(splitrow, user);
}
transition(SplitTransactionPhase.AFTER_PRE_SPLIT_HOOK);
// If true, no cluster to write meta edits to or to update znodes in.
boolean testing =
server == null
? true
: server.getConfiguration().getBoolean("hbase.testing.nocluster", false);
this.fileSplitTimeout =
testing
? this.fileSplitTimeout
: server
.getConfiguration()
.getLong("hbase.regionserver.fileSplitTimeout", this.fileSplitTimeout);
PairOfSameType<Region> daughterRegions = stepsBeforePONR(server, services, testing);
final List<Mutation> metaEntries = new ArrayList<Mutation>();
boolean ret = false;
if (this.parent.getCoprocessorHost() != null) {
ret = parent.getCoprocessorHost().preSplitBeforePONR(splitrow, metaEntries, user);
if (ret) {
throw new IOException(
"Coprocessor bypassing region "
+ parent.getRegionInfo().getRegionNameAsString()
+ " split.");
}
try {
for (Mutation p : metaEntries) {
HRegionInfo.parseRegionName(p.getRow());
}
} catch (IOException e) {
LOG.error(
"Row key of mutation from coprossor is not parsable as region name."
+ "Mutations from coprocessor should only for hbase:meta table.");
throw e;
}
}
// This is the point of no return. Adding subsequent edits to .META. as we
// do below when we do the daughter opens adding each to .META. can fail in
// various interesting ways the most interesting of which is a timeout
// BUT the edits all go through (See HBASE-3872). IF we reach the PONR
// then subsequent failures need to crash out this regionserver; the
// server shutdown processing should be able to fix-up the incomplete split.
// The offlined parent will have the daughters as extra columns. If
// we leave the daughter regions in place and do not remove them when we
// crash out, then they will have their references to the parent in place
// still and the server shutdown fixup of .META. will point to these
// regions.
// We should add PONR JournalEntry before offlineParentInMeta,so even if
// OfflineParentInMeta timeout,this will cause regionserver exit,and then
// master ServerShutdownHandler will fix daughter & avoid data loss. (See
// HBase-4562).
transition(SplitTransactionPhase.PONR);
// Edit parent in meta. Offlines parent region and adds splita and splitb
// as an atomic update. See HBASE-7721. This update to META makes the region
// will determine whether the region is split or not in case of failures.
// If it is successful, master will roll-forward, if not, master will rollback
// and assign the parent region.
if (services != null
&& !services.reportRegionStateTransition(
TransitionCode.SPLIT_PONR, parent.getRegionInfo(), hri_a, hri_b)) {
// Passed PONR, let SSH clean it up
throw new IOException(
"Failed to notify master that split passed PONR: "
+ parent.getRegionInfo().getRegionNameAsString());
}
return daughterRegions;
}
private void transition(SplitTransactionPhase nextPhase) throws IOException {
transition(nextPhase, false);
}