Skip to content

fixes #2111 adds unit test for external compaction metadata validation #2309

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
keith-turner merged 11 commits into from
Oct 12, 2021
Merged

fixes #2111 adds unit test for external compaction metadata validation #2309

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
7ff9096
fixes #2111 adds unit test for external compaction metadata validation
keith-turner Oct 7, 2021
430279b
adds missing license header
keith-turner Oct 7, 2021
33bc17b
fixes compile issue
keith-turner Oct 7, 2021
83add26
fixes imports
keith-turner Oct 7, 2021
e00215a
Update server/tserver/src/main/java/org/apache/accumulo/tserver/table…
ctubbsii Oct 11, 2021
5137d9f
Update server/tserver/src/main/java/org/apache/accumulo/tserver/table…
ctubbsii Oct 11, 2021
29ae552
cr update
keith-turner Oct 11, 2021
8441ece
wrap line
keith-turner Oct 11, 2021
72e49b9
CR update
keith-turner Oct 11, 2021
8a101d2
Update core/src/main/java/org/apache/accumulo/core/metadata/schema/Ex…
ctubbsii Oct 12, 2021
bbdab48
Update server/tserver/src/main/java/org/apache/accumulo/tserver/table…
ctubbsii Oct 12, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions core/src/main/java/org/apache/accumulo/core/metadata/schema/ExternalCompactionMetadata.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,12 @@ public ExternalCompactionMetadata(Set<StoredTabletFile> jobFiles, Set<StoredTabl
TabletFile compactTmpName, String compactorId, CompactionKind kind, short priority,
CompactionExecutorId ceid, boolean propagateDeletes, boolean initiallySelectedAll,
Long compactionId) {
if (!initiallySelectedAll && !propagateDeletes
&& (kind == CompactionKind.SELECTOR || kind == CompactionKind.USER)) {
throw new IllegalArgumentException(
"When user or selector compactions do not propagate deletes, it's expected that all "
+ "files were selected initially.");
}
this.jobFiles = Objects.requireNonNull(jobFiles);
this.nextFiles = Objects.requireNonNull(nextFiles);
this.compactTmpName = Objects.requireNonNull(compactTmpName);
Expand Down
120 changes: 68 additions & 52 deletions server/tserver/src/main/java/org/apache/accumulo/tserver/tablet/CompactableImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -602,9 +602,30 @@ public CompactableImpl(Tablet tablet, CompactionManager manager,

Map<ExternalCompactionId,String> extCompactionsToRemove = new HashMap<>();

var extSelInfo = initExternalSelection(extCompactions, tablet, extCompactionsToRemove);
// Memoize the supplier so it only calls tablet.getCompactionID() once, because the impl goes to
// zookeeper. It's a supplier because it may not be needed.
Supplier<Optional<Pair<Long,CompactionConfig>>> tabletCompactionId = Suppliers.memoize(() -> {
try {
return Optional.of(tablet.getCompactionID());
} catch (NoNodeException nne) {
return Optional.empty();
}
});

verifyExternalCompactions(extCompactions, dataFileSizes.keySet(), extCompactionsToRemove);
var extSelInfo =
processExternalMetadata(extCompactions, () -> tabletCompactionId.get().map(Pair::getFirst),
dataFileSizes.keySet(), extCompactionsToRemove);

if (extSelInfo.isPresent()) {
if (extSelInfo.get().selectKind == CompactionKind.USER) {
this.chelper = CompactableUtils.getHelper(extSelInfo.get().selectKind, tablet,
tabletCompactionId.get().get().getFirst(), tabletCompactionId.get().get().getSecond());
this.compactionConfig = tabletCompactionId.get().get().getSecond();
this.compactionId = tabletCompactionId.get().get().getFirst();
} else if (extSelInfo.get().selectKind == CompactionKind.SELECTOR) {
this.chelper = CompactableUtils.getHelper(extSelInfo.get().selectKind, tablet, null, null);
}
}

extCompactionsToRemove.forEach((ecid, reason) -> {
log.warn("Removing external compaction {} for {} because {} meta: {}", ecid,
Expand Down Expand Up @@ -669,30 +690,6 @@ protected long getNanoTime() {
};
}

private void verifyExternalCompactions(
Map<ExternalCompactionId,ExternalCompactionMetadata> extCompactions,
Set<StoredTabletFile> tabletFiles, Map<ExternalCompactionId,String> extCompactionsToRemove) {

Set<StoredTabletFile> seen = new HashSet<>();
boolean overlap = false;

for (var entry : extCompactions.entrySet()) {
ExternalCompactionMetadata ecMeta = entry.getValue();
if (!tabletFiles.containsAll(ecMeta.getJobFiles())) {
extCompactionsToRemove.putIfAbsent(entry.getKey(), "Has files outside of tablet files");
} else if (!Collections.disjoint(seen, ecMeta.getJobFiles())) {
overlap = true;
}
seen.addAll(ecMeta.getJobFiles());
}

if (overlap) {
extCompactions.keySet().forEach(ecid -> {
extCompactionsToRemove.putIfAbsent(ecid, "Some external compaction files overlap");
});
}
}

private synchronized boolean addJob(CompactionJob job) {
if (runningJobs.add(job)) {
compactionRunning = true;
Expand Down Expand Up @@ -815,16 +812,47 @@ private void checkIfUserCompactionCanceled() {
}

/**
* For user compactions a set of files is selected. Those files then get compacted by one or more
* compactions until the set is empty. This method attempts to reconstruct the selected set of
* files when a tablet is loaded with an external user compaction. It avoids repeating work and
* when a user compaction completes, files are verified against the selected set. Since the data
* is coming from persisted storage, lots of checks are done in this method rather than assuming
* the persisted data is correct.
* This method validates metadata about external compactions. It also extracts specific
* information needed for user and selector compactions.
*/
private Optional<SelectedInfo> initExternalSelection(
Map<ExternalCompactionId,ExternalCompactionMetadata> extCompactions, Tablet tablet,
static Optional<SelectedInfo> processExternalMetadata(
Map<ExternalCompactionId,ExternalCompactionMetadata> extCompactions,
Supplier<Optional<Long>> tabletCompactionId, Set<StoredTabletFile> tabletFiles,
Map<ExternalCompactionId,String> externalCompactionsToRemove) {

// Check that external compactions have disjoint sets of files. Also check that each external
// compaction only has files inside a tablet.
Set<StoredTabletFile> seen = new HashSet<>();
boolean overlap = false;

for (var entry : extCompactions.entrySet()) {
ExternalCompactionMetadata ecMeta = entry.getValue();
if (!tabletFiles.containsAll(ecMeta.getJobFiles())) {
externalCompactionsToRemove.putIfAbsent(entry.getKey(),
"Has files outside of tablet files");
} else if (!Collections.disjoint(seen, ecMeta.getJobFiles())) {
overlap = true;
}
seen.addAll(ecMeta.getJobFiles());
}

if (overlap) {
extCompactions.keySet().forEach(ecid -> {
externalCompactionsToRemove.putIfAbsent(ecid, "Some external compaction files overlap");
});
return Optional.empty();
}

/*
* The rest of the code validates user compaction metadata and extracts needed information.
*
* For user compactions a set of files is selected. Those files then get compacted by one or
* more compactions until the set is empty. This method attempts to reconstruct the selected set
* of files when a tablet is loaded with an external user compaction. It avoids repeating work
* and when a user compaction completes, files are verified against the selected set. Since the
* data is coming from persisted storage, lots of checks are done in this method rather than
* assuming the persisted data is correct.
*/
CompactionKind extKind = null;
boolean unexpectedExternal = false;
Set<StoredTabletFile> tmpSelectedFiles = null;
Expand Down Expand Up @@ -902,17 +930,14 @@ private Optional<SelectedInfo> initExternalSelection(
reasons.add("Concurrent compactions not propagatingDeletes");
}

Pair<Long,CompactionConfig> idAndCfg = null;
if (extKind == CompactionKind.USER) {
try {
idAndCfg = tablet.getCompactionID();
if (!idAndCfg.getFirst().equals(cid)) {
unexpectedExternal = true;
reasons.add("Compaction id mismatch with zookeeper");
}
} catch (NoNodeException e) {
Optional<Long> compactionId = tabletCompactionId.get();
if (compactionId.isEmpty()) {
unexpectedExternal = true;
reasons.add("No compaction id in zookeeper");
} else if (!compactionId.get().equals(cid)) {
unexpectedExternal = true;
reasons.add("Compaction id mismatch with zookeeper");
}
}

Expand All @@ -925,17 +950,8 @@ private Optional<SelectedInfo> initExternalSelection(
return Optional.empty();
}

if (extKind != null) {
if (extKind == CompactionKind.USER) {
this.chelper = CompactableUtils.getHelper(extKind, tablet, cid, idAndCfg.getSecond());
this.compactionConfig = idAndCfg.getSecond();
this.compactionId = cid;
} else if (extKind == CompactionKind.SELECTOR) {
this.chelper = CompactableUtils.getHelper(extKind, tablet, null, null);
}

if (extKind != null)
return Optional.of(new SelectedInfo(initiallySelAll, tmpSelectedFiles, extKind));
}

return Optional.empty();
}
Expand Down
4 changes: 2 additions & 2 deletions ...rver/src/test/java/org/apache/accumulo/tserver/tablet/CompactableImplFileManagerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -448,11 +448,11 @@ Set<StoredTabletFile> getCompactingFiles() {

}

private static StoredTabletFile newFile(String f) {
static StoredTabletFile newFile(String f) {
return new StoredTabletFile("hdfs://nn1/accumulo/tables/1/t-0001/" + f);
}

private static Set<StoredTabletFile> newFiles(String... strings) {
static Set<StoredTabletFile> newFiles(String... strings) {
return Arrays.asList(strings).stream().map(s -> newFile(s)).collect(Collectors.toSet());
}

Expand Down
Loading