Apache
/
hadoop
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

HADOOP-17657: implement StreamCapabilities in SequenceFile.Writer and fall back to flush, if hflush is not supported (#2949) 

Co-authored-by: Kishen Das <kishen@cloudera.com>
Reviewed-by: Steve Loughran <stevel@apache.org>
This commit is contained in:
kishendas 2021-05-04 01:20:56 -07:00 committed by GitHub
parent 62bcc79a2c
commit e571025f5b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 44 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/SequenceFile.java
View File

@ -27,6 +27,7 @@
import org.apache.hadoop.thirdparty.com.google.common.annotations.VisibleForTesting;
import org.apache.hadoop.util.Options;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.fs.StreamCapabilities;
import org.apache.hadoop.fs.Options.CreateOpts;
import org.apache.hadoop.io.compress.CodecPool;
import org.apache.hadoop.io.compress.CompressionCodec;
@ -834,7 +835,8 @@ public String toString() {
}
/** Write key/value pairs to a sequence-format file. */
public static class Writer implements java.io.Closeable, Syncable {
public static class Writer implements java.io.Closeable, Syncable,
Flushable, StreamCapabilities {
private Configuration conf;
FSDataOutputStream out;
boolean ownOutputStream = true;
@ -1367,6 +1369,21 @@ public void hflush() throws IOException {
out.hflush();
}
}
@Override
public void flush() throws IOException {
if (out != null) {
out.flush();
}
}
@Override
public boolean hasCapability(String capability) {
if (out !=null && capability != null) {
return out.hasCapability(capability);
}
return false;
}
/** Returns the configuration of this file. */
Configuration getConf() { return conf; }

26
hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/io/TestSequenceFile.java
View File

@ -30,6 +30,7 @@
import org.apache.hadoop.test.GenericTestUtils;
import org.apache.hadoop.util.ReflectionUtils;
import org.apache.hadoop.conf.*;
import org.assertj.core.api.Assertions;
import org.junit.Test;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertTrue;
@ -730,6 +731,31 @@ public void testSerializationAvailability() throws IOException {
}
}
@Test
public void testSequenceFileWriter() throws Exception {
Configuration conf = new Configuration();
// This test only works with Raw File System and not Local File System
FileSystem fs = FileSystem.getLocal(conf).getRaw();
Path p = new Path(GenericTestUtils
.getTempPath("testSequenceFileWriter.seq"));
try(SequenceFile.Writer writer = SequenceFile.createWriter(
fs, conf, p, LongWritable.class, Text.class)) {
Assertions.assertThat(writer.hasCapability
(StreamCapabilities.HSYNC)).isEqualTo(true);
Assertions.assertThat(writer.hasCapability(
StreamCapabilities.HFLUSH)).isEqualTo(true);
LongWritable key = new LongWritable();
key.set(1);
Text value = new Text();
value.set("somevalue");
writer.append(key, value);
writer.flush();
writer.hflush();
writer.hsync();
Assertions.assertThat(fs.getFileStatus(p).getLen()).isGreaterThan(0);
}
}
/** For debugging and testing. */
public static void main(String[] args) throws Exception {
int count = 1024 * 1024;