[
https://issues.apache.org/jira/browse/HADOOP-18231?focusedWorklogId=771382&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-771382
]
ASF GitHub Bot logged work on HADOOP-18231:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 17/May/22 14:22
Start Date: 17/May/22 14:22
Worklog Time Spent: 10m
Work Description: ahmarsuhail commented on code in PR #4305:
URL: https://github.com/apache/hadoop/pull/4305#discussion_r874874814
##########
hadoop-tools/hadoop-aws/src/test/java/org/apache/hadoop/fs/s3a/ITestS3PrefetchingInputStream.java:
##########
@@ -0,0 +1,139 @@
+/*
+ * 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.hadoop.fs.s3a;
+
+import java.io.IOException;
+
+import org.junit.Test;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.fs.contract.ContractTestUtils;
+import org.apache.hadoop.fs.s3a.performance.AbstractS3ACostTest;
+import org.apache.hadoop.fs.statistics.IOStatistics;
+import org.apache.hadoop.fs.statistics.StoreStatisticNames;
+import org.apache.hadoop.fs.statistics.StreamStatisticNames;
+
+import static org.apache.hadoop.fs.s3a.Constants.PREFETCH_BLOCK_DEFAULT_SIZE;
+import static org.apache.hadoop.fs.s3a.Constants.PREFETCH_BLOCK_SIZE_KEY;
+import static org.apache.hadoop.fs.s3a.Constants.PREFETCH_ENABLED_KEY;
+import static
org.apache.hadoop.fs.statistics.IOStatisticAssertions.verifyStatisticCounterValue;
+
+public class ITestS3PrefetchingInputStream extends AbstractS3ACostTest {
+
+ public ITestS3PrefetchingInputStream() {
+ super(true);
+ }
+
+ private static final int _1K = 1024;
+ // Path for file which should have length > block size so
S3CachingInputStream is used
+ private Path largeFile;
+ private FileSystem fs;
+ private int numBlocks;
+ private int blockSize;
+ private long largeFileSize;
+ // Size should be < block size so S3InMemoryInputStream is used
+ private static final int smallFileSize = _1K * 16;
+
+ @Override
+ public void setup() throws Exception {
+ super.setup();
+
+ Configuration conf = getConfiguration();
+ conf.setBoolean(PREFETCH_ENABLED_KEY, true);
+ }
+
+ private void openFS() throws IOException {
+ Configuration conf = getConfiguration();
+
+ largeFile = new Path(DEFAULT_CSVTEST_FILE);
+ blockSize = conf.getInt(PREFETCH_BLOCK_SIZE_KEY,
PREFETCH_BLOCK_DEFAULT_SIZE);
+ fs = largeFile.getFileSystem(getConfiguration());
+ FileStatus fileStatus = fs.getFileStatus(largeFile);
+ largeFileSize = fileStatus.getLen();
Review Comment:
It is currently using the landsat file `landsat-pds/scene_list.gz` which has
a size of 42MB
Issue Time Tracking
-------------------
Worklog Id: (was: 771382)
Time Spent: 1.5h (was: 1h 20m)
> tests in ITestS3AInputStreamPerformance are failing
> ----------------------------------------------------
>
> Key: HADOOP-18231
> URL: https://issues.apache.org/jira/browse/HADOOP-18231
> Project: Hadoop Common
> Issue Type: Sub-task
> Reporter: Ahmar Suhail
> Assignee: Ahmar Suhail
> Priority: Minor
> Labels: pull-request-available
> Time Spent: 1.5h
> Remaining Estimate: 0h
>
> The following tests are failing when prefetching is enabled:
> testRandomIORandomPolicy - expects stream to be opened 4 times (once for
> every random read), but prefetching will only open twice.
> testDecompressionSequential128K - expects stream to be opened once, but
> prefetching will open once for each block the file has. landsat file used in
> the test has size 42MB, prefetching block size = 8MB, expected open count is
> 6.
> testReadWithNormalPolicy - same as above.
> testRandomIONormalPolicy - executes random IO, but with a normal policy.
> S3AInputStream will abort the stream and change the policy, prefetching
> handles random IO by caching blocks so doesn't do any of that.
> testRandomReadOverBuffer - multiple assertions failing here, also depends a
> lot on readAhead values, not very relevant for prefetching
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
