[
https://issues.apache.org/jira/browse/HDDS-1496?focusedWorklogId=253460&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-253460
]
ASF GitHub Bot logged work on HDDS-1496:
----------------------------------------
Author: ASF GitHub Bot
Created on: 03/Jun/19 23:18
Start Date: 03/Jun/19 23:18
Worklog Time Spent: 10m
Work Description: hanishakoneru commented on pull request #804:
HDDS-1496. Support partial chunk reads and checksum verification
URL: https://github.com/apache/hadoop/pull/804#discussion_r290074328
##########
File path:
hadoop-hdds/client/src/test/java/org/apache/hadoop/hdds/scm/storage/TestChunkInputStream.java
##########
@@ -0,0 +1,198 @@
+package org.apache.hadoop.hdds.scm.storage;
+
+import org.apache.hadoop.hdds.client.BlockID;
+import org.apache.hadoop.hdds.protocol.DatanodeDetails;
+import
org.apache.hadoop.hdds.protocol.datanode.proto.ContainerProtos.ChecksumType;
+import
org.apache.hadoop.hdds.protocol.datanode.proto.ContainerProtos.ChunkInfo;
+import org.apache.hadoop.hdds.scm.XceiverClientSpi;
+import org.apache.hadoop.ozone.OzoneConfigKeys;
+import org.apache.hadoop.ozone.common.Checksum;
+import org.apache.hadoop.test.GenericTestUtils;
+import org.apache.ratis.thirdparty.com.google.protobuf.ByteString;
+import org.junit.Assert;
+import org.junit.Before;
+import org.junit.Test;
+
+import java.io.EOFException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Random;
+
+public class TestChunkInputStream {
+
+ private static final int CHUNK_SIZE = 100;
+ private static final int BYTES_PER_CHECKSUM = 20;
+ private static final String CHUNK_NAME = "dummyChunk";
+ private static final Random RANDOM = new Random();
+ private static Checksum checksum;
+
+ private DummyChunkInputStream chunkStream;
+ private ChunkInfo chunkInfo;
+ private byte[] chunkData;
+
+ @Before
+ public void setup() throws Exception {
+ checksum = new Checksum(ChecksumType.valueOf(
+ OzoneConfigKeys.OZONE_CLIENT_CHECKSUM_TYPE_DEFAULT),
+ BYTES_PER_CHECKSUM);
+
+ chunkData = generateRandomData(CHUNK_SIZE);
+
+ chunkInfo = ChunkInfo.newBuilder()
+ .setChunkName(CHUNK_NAME)
+ .setOffset(0)
+ .setLen(CHUNK_SIZE)
+ .setChecksumData(checksum.computeChecksum(
+ chunkData, 0, CHUNK_SIZE).getProtoBufMessage())
+ .build();
+
+ chunkStream = new DummyChunkInputStream(chunkInfo, null, null, null, true);
+ }
+
+ static byte[] generateRandomData(int length) {
+ byte[] bytes = new byte[length];
+ RANDOM.nextBytes(bytes);
+ return bytes;
+ }
+
+ /**
+ * A dummy ChunkInputStream to mock read chunk calls to DN.
+ */
+ public class DummyChunkInputStream extends ChunkInputStream {
+
+ // Stores the read chunk data in each readChunk call
+ List<ByteString> readByteBuffers = new ArrayList<>();
+
+ DummyChunkInputStream(ChunkInfo chunkInfo,
+ BlockID blockId,
+ String traceId,
+ XceiverClientSpi xceiverClient,
+ boolean verifyChecksum) {
+ super(chunkInfo, blockId, traceId, xceiverClient, verifyChecksum);
+ }
+
+ public DummyChunkInputStream(ChunkInfo chunkInfo,
+ BlockID blockId,
+ String traceId,
+ XceiverClientSpi xceiverClient,
+ boolean verifyChecksum,
+ byte[] data) {
+ super(chunkInfo, blockId, traceId, xceiverClient, verifyChecksum);
+ chunkData = data;
+ }
+
+ @Override
+ protected ByteString readChunk(ChunkInfo readChunkInfo,
+ List<DatanodeDetails> excludeDns,
+ List<DatanodeDetails> dnListFromReply) {
+ ByteString byteString = ByteString.copyFrom(chunkData,
+ (int) readChunkInfo.getOffset(),
+ (int) readChunkInfo.getLen());
+ readByteBuffers.add(byteString);
+ return byteString;
+ }
+
+ @Override
+ protected List<DatanodeDetails> getDatanodeList() {
+ // return an empty dummy list of size 10
+ return new ArrayList<>(5);
+ }
+
+ @Override
+ protected void checkOpen() {
+ // No action needed
+ }
+ }
+
+ /**
+ * Match readData with the chunkData byte-wise.
+ * @param readData Data read through ChunkInputStream
+ * @param inputDataStartIndex first index (inclusive) in chunkData to compare
+ * with read data
+ * @param inputDataEndIndex last index (exclusive) in chunkData to compare
Review comment:
Fixed
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 253460)
Time Spent: 6h 20m (was: 6h 10m)
> Support partial chunk reads and checksum verification
> -----------------------------------------------------
>
> Key: HDDS-1496
> URL: https://issues.apache.org/jira/browse/HDDS-1496
> Project: Hadoop Distributed Data Store
> Issue Type: Improvement
> Reporter: Hanisha Koneru
> Assignee: Hanisha Koneru
> Priority: Major
> Labels: pull-request-available
> Time Spent: 6h 20m
> Remaining Estimate: 0h
>
> BlockInputStream#readChunkFromContainer() reads the whole chunk from disk
> even if we need to read only a part of the chunk.
> This Jira aims to improve readChunkFromContainer so that only that part of
> the chunk file is read which is needed by client plus the part of chunk file
> which is required to verify the checksum.
> For example, lets say the client is reading from index 120 to 450 in the
> chunk. And let's say checksum is stored for every 100 bytes in the chunk i.e.
> the first checksum is for bytes from index 0 to 99, the next for bytes from
> index 100 to 199 and so on. To verify bytes from 120 to 450, we would need to
> read from bytes 100 to 499 so that checksum verification can be done.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
