shuwenwei commented on code in PR #19198:
URL: https://github.com/apache/iotdb/pull/19198#discussion_r4549531234
##########
iotdb-core/datanode/src/main/java/org/apache/iotdb/db/storageengine/buffer/TimeSeriesMetadataCache.java:
##########
@@ -316,6 +317,177 @@ public TimeseriesMetadata get(
}
}
+ /**
+ * Load the TimeseriesMetadata of {@code allSensors} of a device, reading
the device in a single
+ * batch when the per-measurement cache does not already hold all of them.
This is used by
+ * wide-table scans (a device with many columns) to avoid walking the device
metadata index once
+ * per column / leaf node.
+ *
+ * <p>The returned map always holds copies of the cached (or freshly read)
metadata, so the caller
+ * may apply {@code setModified} and {@code setChunkMetadataLoader} without
corrupting cached
+ * entries — matching {@link #get}.
+ *
+ * @param filePath path of the tsfile
+ * @param tsFileID id of the tsfile
+ * @param device target device
+ * @param allSensors measurements the caller needs, including the time
column keyed by ""
+ * @param queryContext query context used for metrics and to detect external
tsfiles
+ * @param ignoreNotExists whether a device missing from a file that claims a
device-level time
+ * index should be skipped instead of reported as an inconsistency
+ * @return map from measurementId (including the time column, keyed by "")
to TimeseriesMetadata;
+ * entries whose series is empty (count == 0) are mapped to null
+ * @throws IOException if the metadata cannot be read from disk or the
device is unexpectedly
+ * absent
+ */
+ public Map<String, TimeseriesMetadata> getDeviceTimeSeriesMetadata(
+ String filePath,
+ TsFileID tsFileID,
+ IDeviceID device,
+ Set<String> allSensors,
+ QueryContext queryContext,
+ boolean ignoreNotExists)
+ throws IOException {
+ long startTime = System.nanoTime();
+ boolean externalTsFile = queryContext.isExternalTsFileScan();
+ LongConsumer timeSeriesMetadataIoSizeRecorder =
+
queryContext.getQueryStatistics().getLoadTimeSeriesMetadataActualIOSize()::addAndGet;
+ boolean cacheHit = true;
+
+ try {
+ if (CACHE_ENABLE && !externalTsFile) {
+ Map<String, TimeseriesMetadata> cached =
+ getCachedDeviceTimeSeriesMetadata(tsFileID, device, allSensors);
+ if (cached != null) {
+ return cached;
+ }
+ // serialize concurrent reads of the same device+file (same lock key
as get) so threads
+ // don't each deserialize the whole device and race on the shared
reader
+ synchronized (
+ devices.computeIfAbsent(device.toString() + SEPARATOR + filePath,
WeakReference::new)) {
+ cached = getCachedDeviceTimeSeriesMetadata(tsFileID, device,
allSensors);
+ if (cached != null) {
+ return cached;
+ }
+ cacheHit = false;
+ TsFileSequenceReader reader =
+ FileReaderManager.getInstance()
+ .get(filePath, tsFileID, true,
timeSeriesMetadataIoSizeRecorder, false);
+ return readDeviceTimeSeriesMetadata(
+ reader, tsFileID, device, allSensors, true, ignoreNotExists);
+ }
+ }
+ cacheHit = false;
+ TsFileSequenceReader reader =
+ FileReaderManager.getInstance()
+ .get(filePath, tsFileID, true, timeSeriesMetadataIoSizeRecorder,
externalTsFile);
+ return readDeviceTimeSeriesMetadata(
+ reader, tsFileID, device, allSensors, false, ignoreNotExists);
+ } finally {
+ if (cacheHit) {
+ queryContext
+ .getQueryStatistics()
+ .getLoadTimeSeriesMetadataFromCacheCount()
+ .incrementAndGet();
+ queryContext
+ .getQueryStatistics()
+ .getLoadTimeSeriesMetadataFromCacheTime()
+ .getAndAdd(System.nanoTime() - startTime);
+ } else {
+ queryContext
+ .getQueryStatistics()
+ .getLoadTimeSeriesMetadataFromDiskCount()
+ .incrementAndGet();
+ queryContext
+ .getQueryStatistics()
+ .getLoadTimeSeriesMetadataFromDiskTime()
+ .getAndAdd(System.nanoTime() - startTime);
+ }
+ }
+ }
+
+ /**
+ * @return copies of the cached metadata for every measurement in {@code
allSensors}, or null as
+ * soon as one of them is not cached and the device therefore has to be
read from disk
+ */
+ private Map<String, TimeseriesMetadata> getCachedDeviceTimeSeriesMetadata(
+ TsFileID tsFileID, IDeviceID device, Set<String> allSensors) {
+ Map<String, TimeseriesMetadata> result = new HashMap<>(allSensors.size());
+ for (String measurement : allSensors) {
+ TimeseriesMetadata metadata =
+ lruCache.getIfPresent(new TimeSeriesMetadataCacheKey(tsFileID,
device, measurement));
+ if (metadata == null) {
+ return null;
+ }
+ result.put(
+ measurement,
+ metadata == NULL_EXISTS_CACHE_PLACE_HOLDER ? null : new
TimeseriesMetadata(metadata));
+ }
+ return result;
+ }
+
+ private Map<String, TimeseriesMetadata> readDeviceTimeSeriesMetadata(
+ TsFileSequenceReader reader,
+ TsFileID tsFileID,
+ IDeviceID device,
+ Set<String> allSensors,
+ boolean cacheEnabled,
+ boolean ignoreNotExists)
+ throws IOException {
+ // Use the chunk-metadata-including variant: the returned
TimeseriesMetadata are passed to
+ // setModifications and then to DiskAlignedChunkMetadataLoader, which
dereferences the chunk
+ // metadata list, so readDeviceMetadata (which skips chunk metadata) would
NPE at query time.
+ List<TimeseriesMetadata> deviceMetadataList =
reader.getDeviceTimeseriesMetadata(device);
Review Comment:
[P2] Consult BloomFilter before reading device metadata
The batch path calls `reader.getDeviceTimeseriesMetadata(device)` before
asking the BloomFilter whether the device is present. The existing per-column
`get()` checks `BloomFilterCache` first and can skip that index read. For wide
scans over sparse files, each absent device/file pair now incurs an unnecessary
metadata-index read before this branch returns empty, potentially eroding the
optimization. Please perform the cached time-column BloomFilter check before
the full-device read, preserving the current missing-device behavior and
query-stat accounting.
--
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]