ahmarsuhail commented on code in PR #7763:
URL: https://github.com/apache/hadoop/pull/7763#discussion_r2177583679
##########
hadoop-tools/hadoop-aws/src/test/java/org/apache/hadoop/fs/s3a/ITestS3AAnalyticsAcceleratorStreamReading.java:
##########
@@ -194,4 +215,127 @@ public void testInvalidConfigurationThrows() throws
Exception {
() ->
S3SeekableInputStreamConfiguration.fromConfiguration(connectorConfiguration));
}
+ @Test
+ public void testLargeFileMultipleGets() throws Throwable {
+ describe("Large file should trigger multiple GET requests");
+
+ Path dest = writeThenReadFile("large-test-file.txt", 10 * 1024 * 1024); //
10MB
+
+
+ try (FSDataInputStream inputStream = getFileSystem().open(dest)) {
+ IOStatistics ioStats = inputStream.getIOStatistics();
+ inputStream.readFully(new byte[(int)
getFileSystem().getFileStatus(dest).getLen()]);
+
+ verifyStatisticCounterValue(ioStats, STREAM_READ_ANALYTICS_GET_REQUESTS,
2);
+ }
+ }
+
+ @Test
+ public void testSmallFileSingleGet() throws Throwable {
+ describe("Small file should trigger only one GET request");
+
+ Path dest = writeThenReadFile("small-test-file.txt", 1 * 1024 * 1024); //
1KB
+
+ try (FSDataInputStream inputStream = getFileSystem().open(dest)) {
+ IOStatistics ioStats = inputStream.getIOStatistics();
+ inputStream.readFully(new byte[(int)
getFileSystem().getFileStatus(dest).getLen()]);
+
+ verifyStatisticCounterValue(ioStats, STREAM_READ_ANALYTICS_GET_REQUESTS,
1);
+ }
+ }
+
+
+ @Test
+ public void testRandomSeekPatternGets() throws Throwable {
+ describe("Random seek pattern should optimize GET requests");
+
+ Path dest = writeThenReadFile("seek-test.txt", 100 * 1024);
Review Comment:
make the file bigger, like ~5MB. make the seeks bigger than the read ahead
values, so greater than 64KB.
eg;
in.read(1MB)
in.seek(2MB)
in.read(512KB)
in.seek(3MB)
--
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: common-issues-unsubscr...@hadoop.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
