Star Poon created HDDS-12195:
--------------------------------
Summary: Missing skip() Method Causes Performance Issues in
OzoneFSInputStream
Key: HDDS-12195
URL: https://issues.apache.org/jira/browse/HDDS-12195
Project: Apache Ozone
Issue Type: Bug
Affects Versions: 1.4.1
Reporter: Star Poon
The skip() method is not implemented in `OzoneFSInputStream`. As a result, it
defaults to `java.io.InputStream#skip`, which uses `read()` and slows down
performance.
Here is a stack trace showing the issue:
{code:java}
...
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.sendCommandAsync(XceiverClientGrpc.java:538)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.sendCommandWithRetry(XceiverClientGrpc.java:430)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.lambda$sendCommandWithTraceIDAndRetry$0(XceiverClientGrpc.java:373)
at
org.apache.hadoop.hdds.tracing.TracingUtil.executeInSpan(TracingUtil.java:169)
at
org.apache.hadoop.hdds.tracing.TracingUtil.executeInNewSpan(TracingUtil.java:149)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.sendCommandWithTraceIDAndRetry(XceiverClientGrpc.java:365)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.sendCommand(XceiverClientGrpc.java:346)
at
org.apache.hadoop.hdds.scm.storage.ContainerProtocolCalls.readChunk(ContainerProtocolCalls.java:359)
at
org.apache.hadoop.hdds.scm.storage.ContainerProtocolCalls.lambda$readChunk$2(ContainerProtocolCalls.java:346)
at
org.apache.hadoop.hdds.scm.storage.ContainerProtocolCalls.tryEachDatanode(ContainerProtocolCalls.java:146)
at
org.apache.hadoop.hdds.scm.storage.ContainerProtocolCalls.readChunk(ContainerProtocolCalls.java:345)
at
org.apache.hadoop.hdds.scm.storage.ChunkInputStream.readChunk(ChunkInputStream.java:442)
at
org.apache.hadoop.hdds.scm.storage.ChunkInputStream.readChunkDataIntoBuffers(ChunkInputStream.java:419)
at
org.apache.hadoop.hdds.scm.storage.ChunkInputStream.readChunkFromContainer(ChunkInputStream.java:404)
at
org.apache.hadoop.hdds.scm.storage.ChunkInputStream.prepareRead(ChunkInputStream.java:336)
at
org.apache.hadoop.hdds.scm.storage.ChunkInputStream.read(ChunkInputStream.java:176)
at
org.apache.hadoop.hdds.scm.storage.ByteArrayReader.readFromBlock(ByteArrayReader.java:54)
at
org.apache.hadoop.hdds.scm.storage.BlockInputStream.readWithStrategy(BlockInputStream.java:362)
at
org.apache.hadoop.hdds.scm.storage.ExtendedInputStream.read(ExtendedInputStream.java:56)
at
org.apache.hadoop.hdds.scm.storage.ByteArrayReader.readFromBlock(ByteArrayReader.java:54)
at
org.apache.hadoop.hdds.scm.storage.MultipartInputStream.readWithStrategy(MultipartInputStream.java:96)
at
org.apache.hadoop.hdds.scm.storage.ExtendedInputStream.read(ExtendedInputStream.java:56)
at
org.apache.hadoop.fs.ozone.OzoneFSInputStream.read(OzoneFSInputStream.java:64)
at java.base/java.io.InputStream.skip(InputStream.java:547) at
java.base/java.io.FilterInputStream.skip(FilterInputStream.java:149) at
java.base/java.io.FilterInputStream.skip(FilterInputStream.java:149) at
io.trino.filesystem.hdfs.HdfsTrinoInputStream.skip(HdfsTrinoInputStream.java:116)
...{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
