Skip to content
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

CNDB-13027: Fix V5VectorPostingsWriter to handle omitted ordinals correctly #1584

Merged
merged 1 commit into from
Feb 19, 2025
+68 −2
Merged

CNDB-13027: Fix V5VectorPostingsWriter to handle omitted ordinals correctly #1584

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 5 additions & 2 deletions src/java/org/apache/cassandra/index/sai/disk/v5/V5VectorPostingsWriter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,7 +281,7 @@ public void writeGenericOrdinalToRowIdMapping(SequentialWriter writer,
int postingListSize;
if (originalOrdinal == OrdinalMapper.OMITTED)
{
assert remappedPostings.structure == Structure.ONE_TO_MANY;
assert remappedPostings.structure == Structure.ZERO_OR_ONE_TO_MANY;
postingListSize = 0;
}
else
Expand All @@ -298,7 +298,7 @@ public void writeGenericOrdinalToRowIdMapping(SequentialWriter writer,
int originalOrdinal = newToOldMapper.applyAsInt(i);
if (originalOrdinal == OrdinalMapper.OMITTED)
{
assert remappedPostings.structure == Structure.ONE_TO_MANY;
assert remappedPostings.structure == Structure.ZERO_OR_ONE_TO_MANY;
writer.writeInt(0);
continue;
}
Expand All @@ -321,6 +321,9 @@ public void writeGenericRowIdMapping(SequentialWriter writer,
var rowIdToOrdinalMap = new Int2IntHashMap(remappedPostings.maxNewOrdinal, 0.65f, OrdinalMapper.OMITTED);
for (int i = 0; i <= remappedPostings.maxNewOrdinal; i++) {
int ord = remappedPostings.ordinalMapper.newToOld(i);
if (ord == OrdinalMapper.OMITTED)
continue;

var rowIds = postingsMap.get(vectorValues.getVector(ord)).getRowIds();
for (int r = 0; r < rowIds.size(); r++)
{
Expand Down
63 changes: 63 additions & 0 deletions test/unit/org/apache/cassandra/index/sai/cql/VectorCompactionTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,6 +110,69 @@ public void testOneToManyCompactionTooManyHoles()
testOneToManyCompactionHolesInternal(MIN_PQ_ROWS, sstables);
}

@Test
public void testZeroOrOneToManyCompaction()
{
for (int sstables = 2; sstables <= 3; sstables++)
{
testZeroOrOneToManyCompactionInternal(10, sstables);
testZeroOrOneToManyCompactionInternal(MIN_PQ_ROWS, sstables);
}
}

public void testZeroOrOneToManyCompactionInternal(int vectorsPerSstable, int sstables)
{
createTable();
disableCompaction();

insertZeroOrOneToManyRows(vectorsPerSstable, sstables);

validateQueries();
compact();
validateQueries();
}

private void insertZeroOrOneToManyRows(int vectorsPerSstable, int sstables)
{
var R = getRandom();
double duplicateChance = R.nextDouble() * 0.2;
int j = 0;
boolean nullInserted = false;

for (int i = 0; i < sstables; i++)
{
var vectorsInserted = new ArrayList<Vector<Float>>();
var duplicateExists = false;
while (vectorsInserted.size() < vectorsPerSstable || !duplicateExists)
{
if (!nullInserted && vectorsInserted.size() == vectorsPerSstable/2)
{
// Insert one null vector in the middle
execute("INSERT INTO %s (pk, v) VALUES (?, null)", j++);
nullInserted = true;
continue;
}

Vector<Float> v;
if (R.nextDouble() < duplicateChance && !vectorsInserted.isEmpty())
{
// insert a duplicate
v = vectorsInserted.get(R.nextIntBetween(0, vectorsInserted.size() - 1));
duplicateExists = true;
}
else
{
// insert a new random vector
v = randomVectorBoxed(2);
vectorsInserted.add(v);
}
assert v != null;
execute("INSERT INTO %s (pk, v) VALUES (?, ?)", j++, v);
}
flush();
}
}

public void testOneToManyCompactionHolesInternal(int vectorsPerSstable, int sstables)
{
createTable();
Expand Down