xiangfu0 commented on code in PR #19795:
URL: https://github.com/apache/pinot/pull/19795#discussion_r4218002781
##########
pinot-segment-local/src/main/java/org/apache/pinot/segment/local/utils/TDigestUtils.java:
##########
@@ -207,331 +181,194 @@ public static TDigest deserialize(byte[] bytes) {
return deserialize(ByteBuffer.wrap(bytes));
}
- /// Validates the structure and declared capacities of a serialized merging
digest.
- public static void validateSerialized(byte[] bytes) {
- validateEncodedDigest(ByteBuffer.wrap(bytes));
+ /// Validates serialized lengths and centroid values without allocating
centroid arrays.
+ public static double validateSerialized(byte[] bytes) {
+ return validateSerialized(ByteBuffer.wrap(bytes));
}
- /// Deserializes a finite-valued digest into a merging digest with the
temporary-buffer footprint used by 3.2.
+ /// Validates one legacy digest without changing `input` and returns its
total centroid weight.
///
- /// Unlike the standard verbose decoder, this method does not retain the
substantially larger default 3.3
- /// temporary arrays. It also repairs legacy weighted boundary centroids
before the first 3.3 merge.
- public static TDigest deserializeFiniteWithLegacyBuffer(byte[] bytes) {
- ByteBuffer input = ByteBuffer.wrap(bytes);
- validateEncodedDigest(input.duplicate());
-
- int encoding = input.getInt();
- double min = input.getDouble();
- double max = input.getDouble();
- double compression;
- int centroidCount;
- boolean verbose;
- if (encoding == VERBOSE_ENCODING) {
- compression = input.getDouble();
- centroidCount = input.getInt();
- verbose = true;
- } else if (encoding == SMALL_ENCODING) {
- compression = input.getFloat();
- input.getShort();
- input.getShort();
- centroidCount = input.getShort();
- verbose = false;
- } else {
- throw new IllegalStateException("Invalid format for serialized
histogram");
- }
-
- if (centroidCount == 0) {
- return createMergingDigestWithLegacyBuffer(compression);
- }
- double[] means = new double[centroidCount + 2];
- double[] weights = new double[centroidCount + 2];
- for (int i = 0; i < centroidCount; i++) {
- double weight = verbose ? input.getDouble() : input.getFloat();
- double mean = verbose ? input.getDouble() : input.getFloat();
- if (!(weight > 0.0) || !Double.isFinite(weight)) {
- throw new IllegalArgumentException("Invalid TDigest centroid weight: "
+ weight);
- }
- if (!Double.isFinite(mean)) {
- throw new IllegalArgumentException("Expected a finite TDigest centroid
mean: " + mean);
- }
- weights[i] = weight;
- means[i] = mean;
- }
-
- int normalizedCount = weights[0] != 1.0 || weights[centroidCount - 1] !=
1.0
- ? normalizeBoundaries(means, weights, centroidCount, min, max) :
centroidCount;
- long addCount = 0L;
- for (int i = 0; i < normalizedCount; i++) {
- double weight = weights[i];
- if (weight != Math.rint(weight) || weight >= 0x1p63) {
- return copyIntoLegacyBuffer(
- deserialize(toVerboseBytes(min, max, compression, means, weights,
normalizedCount)), normalizedCount);
- }
- long integralWeight = (long) weight;
- addCount = Math.addExact(addCount, 1L + (integralWeight - 1L) /
Integer.MAX_VALUE);
- }
-
- int minimumMainCapacity = Math.addExact(Math.toIntExact(addCount), 2);
- TDigest digest = createMergingDigestWithLegacyBuffer(compression,
minimumMainCapacity);
- for (int i = 0; i < normalizedCount; i++) {
- long remainingWeight = (long) weights[i];
- while (remainingWeight > 0L) {
- int weight = (int) Math.min(remainingWeight, Integer.MAX_VALUE);
- digest.add(means[i], weight);
- remainingWeight -= weight;
- }
- }
- return digest;
+ /// Trailing bytes remain available to the caller for intermediate values
containing several objects.
+ public static double validateSerialized(ByteBuffer input) {
+ return validateSerialized(input, true);
}
- /// Deserializes a digest and advances `input` past its encoded bytes.
- public static TDigest deserialize(ByteBuffer input) {
- ByteBuffer encoded = input.slice();
- validateEncodedDigest(encoded.duplicate());
-
- int encoding = encoded.getInt();
- double min = encoded.getDouble();
- double max = encoded.getDouble();
- double compression;
- int mainCapacity;
- int bufferCapacity;
- int centroidCount;
- int centroidSize;
- if (encoding == VERBOSE_ENCODING) {
- compression = encoded.getDouble();
- centroidCount = encoded.getInt();
- mainCapacity = getDefaultCentroidCapacity(compression);
- bufferCapacity = 5 * mainCapacity;
- centroidSize = VERBOSE_CENTROID_SIZE;
- } else if (encoding == SMALL_ENCODING) {
- compression = encoded.getFloat();
- mainCapacity = encoded.getShort();
- bufferCapacity = encoded.getShort();
- centroidCount = encoded.getShort();
- centroidSize = SMALL_CENTROID_SIZE;
- } else {
- // MergingDigest.fromBytes() has already produced the canonical
exception for this case.
- throw new IllegalStateException("Invalid format for serialized
histogram");
- }
- int centroidOffset = encoded.position();
- if (centroidCount == 0) {
- return configureScaleFunction(MergingDigest.fromBytes(input));
- }
-
- double firstWeight = readWeight(encoded, centroidOffset, centroidSize);
- double lastWeight = readWeight(encoded, centroidOffset + (centroidCount -
1) * centroidSize, centroidSize);
- int defaultMainCapacity = getDefaultCentroidCapacity(compression);
- boolean needsBoundaryRepair = firstWeight != 1.0 || lastWeight != 1.0;
- boolean exceedsDefaultVerboseCapacity = encoding == VERBOSE_ENCODING &&
centroidCount > defaultMainCapacity;
- if (!needsBoundaryRepair && !exceedsDefaultVerboseCapacity) {
- return configureScaleFunction(MergingDigest.fromBytes(input));
- }
-
- double[] means = new double[centroidCount + 2];
- double[] weights = new double[centroidCount + 2];
- encoded.position(centroidOffset);
- for (int i = 0; i < centroidCount; i++) {
- if (centroidSize == VERBOSE_CENTROID_SIZE) {
- weights[i] = encoded.getDouble();
- means[i] = encoded.getDouble();
- } else {
- weights[i] = encoded.getFloat();
- means[i] = encoded.getFloat();
- }
- }
- int encodedLength = encoded.position();
- int normalizedCount = needsBoundaryRepair
- ? normalizeBoundaries(means, weights, centroidCount, min, max) :
centroidCount;
- byte[] normalizedBytes = toVerboseBytes(min, max, compression, means,
weights, normalizedCount);
- MergingDigest result;
- if (normalizedCount <= defaultMainCapacity) {
- result = MergingDigest.fromBytes(ByteBuffer.wrap(normalizedBytes));
- } else {
- int resolvedMainCapacity = mainCapacity == -1 ? defaultMainCapacity :
mainCapacity;
- int resolvedBufferCapacity = bufferCapacity == -1
- ? DEFAULT_MERGE_BUFFER_MULTIPLIER * resolvedMainCapacity :
bufferCapacity;
- int smallMainCapacity = Math.max(resolvedMainCapacity, normalizedCount);
- long smallBufferCapacity = Math.max(Math.max((long)
resolvedBufferCapacity, smallMainCapacity + 1L),
- 2L * smallMainCapacity + 1L);
- if ((double) (float) compression == compression && normalizedCount <=
Short.MAX_VALUE
- && smallMainCapacity <= Short.MAX_VALUE && smallBufferCapacity <=
Short.MAX_VALUE
- && areFloatExact(means, weights, normalizedCount)) {
- ByteBuffer normalized = ByteBuffer.allocate(SMALL_HEADER_SIZE +
SMALL_CENTROID_SIZE * normalizedCount);
- normalized.putInt(SMALL_ENCODING);
- normalized.putDouble(min);
- normalized.putDouble(max);
- normalized.putFloat((float) compression);
- normalized.putShort((short) smallMainCapacity);
- normalized.putShort((short) smallBufferCapacity);
- normalized.putShort((short) normalizedCount);
- for (int i = 0; i < normalizedCount; i++) {
- normalized.putFloat((float) weights[i]);
- normalized.putFloat((float) means[i]);
- }
- normalized.flip();
- result = MergingDigest.fromBytes(normalized);
- } else {
- result = MergingDigest.fromBytes(
- ByteBuffer.wrap(reduceVerboseCentroids(normalizedBytes,
defaultMainCapacity)));
- }
- }
- input.position(Math.addExact(input.position(), encodedLength));
- return configureScaleFunction(result);
+ private static double validateSerialized(ByteBuffer input, boolean
checkCapacity) {
+ return inspectSerialized(input, checkCapacity).totalWeight();
}
- private static TDigest configureScaleFunction(MergingDigest digest) {
- digest.setScaleFunction(ScaleFunction.K_1);
- return digest;
- }
-
- private static TDigest copyIntoLegacyBuffer(TDigest source, int
centroidCount) {
- TDigest digest = createMergingDigestWithLegacyBuffer(source.compression(),
Math.addExact(centroidCount, 2));
- digest.add(java.util.List.of(source));
- return digest;
+ /// Header and numerical metadata for one legacy byte payload. The centroid
bytes remain owned by the caller.
+ /// Header-only inspection leaves total weight as NaN until centroid
inspection validates the numerical fields.
+ ///
+ /// Legacy writers can emit poisoned numerical state after overflow or
broken fractional boundary repair.
+ /// Such state is retained with degraded quantiles, rather than being passed
to the sorted K1 kernel.
+ public record SerializedTDigestMetadata(int encoding, double min, double
max, double compression,
+ int centroidCount, int mainCapacity, int bufferCapacity, int
centroidOffset, int centroidSize,
+ int encodedLength, double totalWeight, boolean hasNonFiniteMeans,
boolean needsLegacyFallback,
+ boolean unorderedMeans, boolean fractionalWeights) {
}
- private static boolean areFloatExact(double[] means, double[] weights, int
count) {
- for (int i = 0; i < count; i++) {
- if ((double) (float) weights[i] != weights[i] || (double) (float)
means[i] != means[i]) {
- return false;
- }
- }
- return true;
+ /// Inspects one payload without mutating `input`, scanning the centroid
values once.
+ public static SerializedTDigestMetadata inspectSerialized(ByteBuffer input) {
+ return inspectSerialized(input, true);
}
- private static byte[] toVerboseBytes(double min, double max, double
compression, double[] means, double[] weights,
- int count) {
- ByteBuffer normalized = ByteBuffer.allocate(VERBOSE_HEADER_SIZE +
VERBOSE_CENTROID_SIZE * count);
- normalized.putInt(VERBOSE_ENCODING);
- normalized.putDouble(min);
- normalized.putDouble(max);
- normalized.putDouble(compression);
- normalized.putInt(count);
- for (int i = 0; i < count; i++) {
- normalized.putDouble(weights[i]);
- normalized.putDouble(means[i]);
- }
- return normalized.array();
+ /// Inspects a payload, optionally enforcing the legacy decoder's declared
centroid capacity.
+ public static SerializedTDigestMetadata inspectSerialized(ByteBuffer input,
boolean checkCapacity) {
+ return inspectSerialized(input, readSerializedHeader(input,
checkCapacity), null, null);
}
- private static double readWeight(ByteBuffer encoded, int offset, int
centroidSize) {
- return centroidSize == VERBOSE_CENTROID_SIZE ? encoded.getDouble(offset) :
encoded.getFloat(offset);
+ /// Reads and validates the fixed-size header without scanning or allocating
centroid arrays.
+ public static SerializedTDigestMetadata readSerializedHeader(ByteBuffer
input) {
+ return readSerializedHeader(input, true);
}
- private static void validateEncodedDigest(ByteBuffer input) {
- int encoding = input.getInt();
+ /// Reads a fixed-size header, optionally enforcing the declared centroid
capacity.
+ ///
+ /// Numerical flags and total weight are computed by the subsequent
inspection or decoding pass.
+ public static SerializedTDigestMetadata readSerializedHeader(ByteBuffer
input, boolean checkCapacity) {
+ ByteBuffer encoded = input.slice().order(ByteOrder.BIG_ENDIAN);
+ int encoding = encoded.getInt();
if (encoding != VERBOSE_ENCODING && encoding != SMALL_ENCODING) {
throw new IllegalStateException("Invalid format for serialized
histogram");
}
- input.getDouble();
- input.getDouble();
+ double min = encoded.getDouble();
+ double max = encoded.getDouble();
double compression;
int mainCapacity;
+ int bufferCapacity = 0;
int centroidCount;
int centroidSize;
if (encoding == VERBOSE_ENCODING) {
- compression = input.getDouble();
- mainCapacity = getDefaultCentroidCapacity(compression);
- centroidCount = input.getInt();
+ compression = normalizeCompression(encoded.getDouble());
+ mainCapacity = Math.max(getDefaultCentroidCapacity(compression),
getLegacyDefaultCentroidCapacity(compression));
+ centroidCount = encoded.getInt();
centroidSize = VERBOSE_CENTROID_SIZE;
} else {
- compression = input.getFloat();
- mainCapacity = input.getShort();
- int bufferCapacity = input.getShort();
+ compression = normalizeCompression(encoded.getFloat());
+ mainCapacity = encoded.getShort();
+ bufferCapacity = encoded.getShort();
checkSmallArrayCapacity(mainCapacity);
checkSmallArrayCapacity(bufferCapacity);
if (mainCapacity == -1) {
mainCapacity = getDefaultCentroidCapacity(compression);
}
- centroidCount = input.getShort();
+ centroidCount = encoded.getShort();
centroidSize = SMALL_CENTROID_SIZE;
}
if (centroidCount < 0) {
throw new IllegalArgumentException("Invalid negative TDigest centroid
count: " + centroidCount);
}
- if (centroidCount > input.remaining() / centroidSize) {
+ if (centroidCount > encoded.remaining() / centroidSize) {
throw new BufferUnderflowException();
}
- int readableMainCapacity = mainCapacity;
- if (encoding == VERBOSE_ENCODING && compression > 0.0 &&
Double.isFinite(compression)) {
- readableMainCapacity = Math.max(mainCapacity,
getLegacyDefaultCentroidCapacity(compression));
+ if (checkCapacity && centroidCount > mainCapacity) {
+ throw new IllegalArgumentException("TDigest centroid count exceeds
capacity: " + centroidCount);
}
- if (centroidCount > readableMainCapacity) {
- throw new ArrayIndexOutOfBoundsException(
- "Index " + readableMainCapacity + " out of bounds for length " +
readableMainCapacity);
- }
- }
-
- private static void checkSmallArrayCapacity(int capacity) {
- if (capacity < -1) {
- throw new NegativeArraySizeException(Integer.toString(capacity));
+ if (Double.isNaN(min) || Double.isNaN(max) || (centroidCount > 0 && min >
max)) {
Review Comment:
[code-review] Legacy digests with NaN extrema are now permanently
unreadable: `readSerializedHeader` throws `Invalid TDigest extrema` on
`Double.isNaN(min) || Double.isNaN(max)` before the centroid scan that sets
`needsLegacyFallback`. t-digest 3.3 `MergingDigest` ingesting legal +/-Infinity
values serializes `min=NaN, max=NaN` almost deterministically (merging two
infinite means yields NaN, and `min = Math.min(min, mean[0])` propagates it).
Such stored BYTES columns / star-tree values / intermediates were readable by
the old reader (it skipped min/max) and were supposed to stay readable per this
file's own doc ("Historical poisoned states remain byte-readable with NaN
statistics"). Suggest folding NaN extrema into the legacy-degraded fallback
instead of throwing.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
