parthchandra commented on code in PR #1187:
URL: https://github.com/apache/parquet-mr/pull/1187#discussion_r1392981151
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ColumnChunkPageReadStore.java:
##########
@@ -199,7 +206,7 @@ public DataPage visit(DataPageV1 dataPageV1) {
@Override
public DataPage visit(DataPageV2 dataPageV2) {
- if (!dataPageV2.isCompressed() && offsetIndex == null && null ==
blockDecryptor) {
+ if (!dataPageV2.isCompressed() && offsetIndex == null && null ==
blockDecryptor) {
Review Comment:
Done
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetMetricsCallback.java:
##########
@@ -0,0 +1,31 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.parquet.hadoop;
+
+/**
+ * a simple interface to pass bask metric values by name to any
implementation. Typically an
Review Comment:
Thanks. My spellink could be better.
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ColumnChunkPageReadStore.java:
##########
@@ -237,21 +246,22 @@ public DataPage visit(DataPageV2 dataPageV2) {
}
} else {
if (null != blockDecryptor) {
- pageBytes = BytesInput.from(
- blockDecryptor.decrypt(pageBytes.toByteArray(),
dataPageAAD));
+ pageBytes = BytesInput.from(
Review Comment:
Done
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ParquetFileReader.java:
##########
@@ -1870,6 +1886,23 @@ public void readAll(SeekableInputStream f,
ChunkListBuilder builder) throws IOEx
}
}
+ private void setReadMetrics(long startNs) {
+ if (metricsCallback != null) {
+ long totalFileReadTimeNs = System.nanoTime() - startNs;
+ double sizeInMb = ((double) length) / (1024 * 1024);
+ double timeInSec = ((double) totalFileReadTimeNs) / 1000_0000_0000L;
+ double throughput = sizeInMb / timeInSec;
+ LOG.debug(
+ "Parquet: File Read stats: Length: {} MB, Time: {} secs,
throughput: {} MB/sec ",
+ sizeInMb,
+ timeInSec,
+ throughput);
Review Comment:
Done
##########
parquet-hadoop/src/main/java/org/apache/parquet/hadoop/ColumnChunkPageReadStore.java:
##########
@@ -237,21 +246,22 @@ public DataPage visit(DataPageV2 dataPageV2) {
}
} else {
if (null != blockDecryptor) {
- pageBytes = BytesInput.from(
- blockDecryptor.decrypt(pageBytes.toByteArray(),
dataPageAAD));
+ pageBytes = BytesInput.from(
+ blockDecryptor.decrypt(pageBytes.toByteArray(),
dataPageAAD));
}
if (dataPageV2.isCompressed()) {
int uncompressedSize = Math.toIntExact(
dataPageV2.getUncompressedSize()
- dataPageV2.getDefinitionLevels().size()
- dataPageV2.getRepetitionLevels().size());
+ long start = System.nanoTime();
pageBytes = decompressor.decompress(pageBytes,
uncompressedSize);
+ setDecompressMetrics(pageBytes, start);
Review Comment:
Yeah, I should have included that. It usually is not an important factor but
for completeness we should include it. Added.
--
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: dev-unsubscr...@parquet.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
