[
https://issues.apache.org/jira/browse/HDFS-10326?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15367287#comment-15367287
]
Mingliang Liu edited comment on HDFS-10326 at 7/8/16 6:19 AM:
--------------------------------------------------------------
If the conclusion is to enable auto TCP tuning by default while preserving the
configurability, the following code change can be considered. Sorry I can't
attach patch file.
{code}
diff --git
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
index a6e2452..fead88f 100644
---
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
+++
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
@@ -78,8 +78,7 @@
String DFS_CLIENT_SOCKET_TIMEOUT_KEY = "dfs.client.socket-timeout";
String DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_KEY =
"dfs.client.socket.send.buffer.size";
- int DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ int DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT = 0;
String DFS_CLIENT_SOCKET_CACHE_CAPACITY_KEY =
"dfs.client.socketcache.capacity";
int DFS_CLIENT_SOCKET_CACHE_CAPACITY_DEFAULT = 16;
diff --git
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
index 8df2d54..06956c8 100644
---
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
+++
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
@@ -48,8 +48,6 @@
public static final byte COLD_STORAGE_POLICY_ID = 2;
public static final String COLD_STORAGE_POLICY_NAME = "COLD";
- // TODO should be conf injected?
- public static final int DEFAULT_DATA_SOCKET_SIZE = 128 * 1024;
/**
* A special path component contained in the path for a snapshot file/dir
*/
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
index 08365cd..3e3ea42 100644
---
a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
+++
b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
@@ -920,15 +920,13 @@
DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_KEY =
"dfs.datanode.transfer.socket.send.buffer.size";
public static final int
- DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_DEFAULT = 0;
public static final String
DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_KEY =
"dfs.datanode.transfer.socket.recv.buffer.size";
public static final int
- DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_DEFAULT = 0;
public static final String
DFS_DATA_TRANSFER_SERVER_TCPNODELAY =
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
index a198b71..ea46f5d 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
@@ -2422,13 +2422,14 @@
<property>
<name>dfs.client.socket.send.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket send buffer size for a write pipeline in DFSClient side.
This may affect TCP connection throughput.
If it is set to zero or negative value,
no buffer size will be set explicitly,
thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
@@ -2833,23 +2834,25 @@
<property>
<name>dfs.datanode.transfer.socket.send.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket send buffer size for DataXceiver (mirroring packets to downstream
in pipeline). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
<property>
<name>dfs.datanode.transfer.socket.recv.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket receive buffer size for DataXceiver (receiving packets from client
during block writing). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
index 2376576..8b417a0 100644
---
a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
+++
b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
@@ -47,14 +47,6 @@
private MiniDFSCluster cluster;
private Socket socket;
- @Test
- public void testDefaultSendBufferSize() throws IOException {
- socket = createSocket();
- assertEquals("Send buffer size should be the default value.",
- DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT,
- socket.getSendBufferSize());
- }
-
@Test
public void testSpecifiedSendBufferSize() throws IOException {
final int mySendBufferSize = 64 * 1024; // 64 KB
@@ -65,7 +57,7 @@ public void testSpecifiedSendBufferSize() throws IOException {
}
@Test
- public void testAutoTuningSendBufferSize() throws IOException {
+ public void testDefaultSendBufferSize() throws IOException {
conf.setInt(DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_KEY, 0);
socket = createSocket();
LOG.info("The auto tuned send buffer size is: {}",
{code}
was (Author: liuml07):
If the conclusion is to enable auto TCP tuning by default while preserving the
configurability, the following change can considered. Sorry I can't attach
patch file.
{code}
diff --git
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
index a6e2452..fead88f 100644
---
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
+++
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/client/HdfsClientConfigKeys.java
@@ -78,8 +78,7 @@
String DFS_CLIENT_SOCKET_TIMEOUT_KEY = "dfs.client.socket-timeout";
String DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_KEY =
"dfs.client.socket.send.buffer.size";
- int DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ int DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT = 0;
String DFS_CLIENT_SOCKET_CACHE_CAPACITY_KEY =
"dfs.client.socketcache.capacity";
int DFS_CLIENT_SOCKET_CACHE_CAPACITY_DEFAULT = 16;
diff --git
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
index 8df2d54..06956c8 100644
---
a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
+++
b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/protocol/HdfsConstants.java
@@ -48,8 +48,6 @@
public static final byte COLD_STORAGE_POLICY_ID = 2;
public static final String COLD_STORAGE_POLICY_NAME = "COLD";
- // TODO should be conf injected?
- public static final int DEFAULT_DATA_SOCKET_SIZE = 128 * 1024;
/**
* A special path component contained in the path for a snapshot file/dir
*/
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
index 08365cd..3e3ea42 100644
---
a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
+++
b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/DFSConfigKeys.java
@@ -920,15 +920,13 @@
DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_KEY =
"dfs.datanode.transfer.socket.send.buffer.size";
public static final int
- DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ DFS_DATANODE_TRANSFER_SOCKET_SEND_BUFFER_SIZE_DEFAULT = 0;
public static final String
DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_KEY =
"dfs.datanode.transfer.socket.recv.buffer.size";
public static final int
- DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_DEFAULT =
- HdfsConstants.DEFAULT_DATA_SOCKET_SIZE;
+ DFS_DATANODE_TRANSFER_SOCKET_RECV_BUFFER_SIZE_DEFAULT = 0;
public static final String
DFS_DATA_TRANSFER_SERVER_TCPNODELAY =
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
index a198b71..ea46f5d 100644
--- a/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
+++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/resources/hdfs-default.xml
@@ -2422,13 +2422,14 @@
<property>
<name>dfs.client.socket.send.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket send buffer size for a write pipeline in DFSClient side.
This may affect TCP connection throughput.
If it is set to zero or negative value,
no buffer size will be set explicitly,
thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
@@ -2833,23 +2834,25 @@
<property>
<name>dfs.datanode.transfer.socket.send.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket send buffer size for DataXceiver (mirroring packets to downstream
in pipeline). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
<property>
<name>dfs.datanode.transfer.socket.recv.buffer.size</name>
- <value>131072</value>
+ <value>0</value>
<description>
Socket receive buffer size for DataXceiver (receiving packets from client
during block writing). This may affect TCP connection throughput.
If it is set to zero or negative value, no buffer size will be set
explicitly, thus enable tcp auto-tuning on some system.
+ The default value is 0.
</description>
</property>
diff --git
a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
index 2376576..8b417a0 100644
---
a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
+++
b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestDFSClientSocketSize.java
@@ -47,14 +47,6 @@
private MiniDFSCluster cluster;
private Socket socket;
- @Test
- public void testDefaultSendBufferSize() throws IOException {
- socket = createSocket();
- assertEquals("Send buffer size should be the default value.",
- DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_DEFAULT,
- socket.getSendBufferSize());
- }
-
@Test
public void testSpecifiedSendBufferSize() throws IOException {
final int mySendBufferSize = 64 * 1024; // 64 KB
@@ -65,7 +57,7 @@ public void testSpecifiedSendBufferSize() throws IOException {
}
@Test
- public void testAutoTuningSendBufferSize() throws IOException {
+ public void testDefaultSendBufferSize() throws IOException {
conf.setInt(DFS_CLIENT_SOCKET_SEND_BUFFER_SIZE_KEY, 0);
socket = createSocket();
LOG.info("The auto tuned send buffer size is: {}",
{code}
> Disable setting tcp socket send/receive buffers for write pipelines
> -------------------------------------------------------------------
>
> Key: HDFS-10326
> URL: https://issues.apache.org/jira/browse/HDFS-10326
> Project: Hadoop HDFS
> Issue Type: Bug
> Components: datanode, hdfs
> Affects Versions: 2.6.0
> Reporter: Daryn Sharp
> Assignee: Daryn Sharp
>
> The DataStreamer and the Datanode use a hardcoded
> DEFAULT_DATA_SOCKET_SIZE=128K for the send and receive buffers of a write
> pipeline. Explicitly setting tcp buffer sizes disables tcp stack
> auto-tuning.
> The hardcoded value will saturate a 1Gb with 1ms RTT. 105Mbs at 10ms.
> Paltry 11Mbs over a 100ms long haul. 10Gb networks are underutilized.
> There should either be a configuration to completely disable setting the
> buffers, or the the setReceiveBuffer and setSendBuffer should be removed
> entirely.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
