Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-11226

Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY

    Details

    • Type: Improvement
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: 2.6.0
    • Fix Version/s: 2.8.0, 3.0.0-alpha1
    • Component/s: ipc
    • Labels:
    • Target Version/s:
    • Hadoop Flags:
      Reviewed
    • Release Note:
      Use low latency TCP connections for hadoop IPC

      Description

      During heavy shuffle, packet loss for IPC packets was observed from a machine.

      Avoid packet-loss and speed up transfer by using 0x14 QOS bits for the packets.

      1. HADOOP-11226.5.patch
        6 kB
        Gopal V
      2. HADOOP-11226.4.patch
        5 kB
        Gopal V
      3. HADOOP-11226.3.patch
        4 kB
        Gopal V
      4. HADOOP-11226.2.patch
        1 kB
        Gopal V
      5. HADOOP-11226.1.patch
        1.0 kB
        Gopal V

        Activity

        Hide
        gopalv Gopal V added a comment -

        Patch is not complete, as it takes care of only RFC 1349 compat mode.

        Needs to implement RFC 2474 protocol changes as well.

        http://docs.oracle.com/javase/1.5.0/docs/api/java/net/Socket.html#setPerformancePreferences%28int,%20int,%20int%29

        Show
        gopalv Gopal V added a comment - Patch is not complete, as it takes care of only RFC 1349 compat mode. Needs to implement RFC 2474 protocol changes as well. http://docs.oracle.com/javase/1.5.0/docs/api/java/net/Socket.html#setPerformancePreferences%28int,%20int,%20int%29
        Hide
        hadoopqa Hadoop QA added a comment -

        -1 overall. Here are the results of testing the latest attachment
        http://issues.apache.org/jira/secure/attachment/12677666/HADOOP-11226.2.patch
        against trunk revision fc20129.

        +1 @author. The patch does not contain any @author tags.

        -1 tests included. The patch doesn't appear to include any new or modified tests.
        Please justify why no new tests are needed for this patch.
        Also please list what manual steps were performed to verify this patch.

        +1 javac. The applied patch does not increase the total number of javac compiler warnings.

        +1 javadoc. There were no new javadoc warning messages.

        +1 eclipse:eclipse. The patch built with eclipse:eclipse.

        +1 findbugs. The patch does not introduce any new Findbugs (version 2.0.3) warnings.

        +1 release audit. The applied patch does not increase the total number of release audit warnings.

        -1 core tests. The patch failed these unit tests in hadoop-common-project/hadoop-common:

        org.apache.hadoop.ha.TestZKFailoverController

        Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5440//testReport/
        Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5440//console

        This message is automatically generated.

        Show
        hadoopqa Hadoop QA added a comment - -1 overall . Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12677666/HADOOP-11226.2.patch against trunk revision fc20129. +1 @author . The patch does not contain any @author tags. -1 tests included . The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. +1 javac . The applied patch does not increase the total number of javac compiler warnings. +1 javadoc . There were no new javadoc warning messages. +1 eclipse:eclipse . The patch built with eclipse:eclipse. +1 findbugs . The patch does not introduce any new Findbugs (version 2.0.3) warnings. +1 release audit . The applied patch does not increase the total number of release audit warnings. -1 core tests . The patch failed these unit tests in hadoop-common-project/hadoop-common: org.apache.hadoop.ha.TestZKFailoverController Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5440//testReport/ Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5440//console This message is automatically generated.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Gopal V thanks for your contribution. How about making the socket options configurable via methods like setTrafficClassLowDelay or setTrafficClassLowReliability? I think some users will enable this feature, but the others won't.

        Show
        ozawa Tsuyoshi Ozawa added a comment - Gopal V thanks for your contribution. How about making the socket options configurable via methods like setTrafficClassLowDelay or setTrafficClassLowReliability? I think some users will enable this feature, but the others won't.
        Hide
        gopalv Gopal V added a comment -

        I was following the line which had TCP keepalive set as a hard-parameter.

        That was a sane default and on without options. Similarly, I didn't imagine any case where people want slow IPC with dropped packets.

        Show
        gopalv Gopal V added a comment - I was following the line which had TCP keepalive set as a hard-parameter. That was a sane default and on without options. Similarly, I didn't imagine any case where people want slow IPC with dropped packets.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Hmm, it sounds reasonable to me to make this hard-parameter.

        Chris Nauroth, do you have additional opinions about this change?

        Show
        ozawa Tsuyoshi Ozawa added a comment - Hmm, it sounds reasonable to me to make this hard-parameter. Chris Nauroth , do you have additional opinions about this change?
        Hide
        cnauroth Chris Nauroth added a comment -

        I think it's reasonable to favor low-latency handling on IPC connections. As I understand it, this would have pushed the packet loss burden into shuffle traffic or data transfer protocol traffic during the scenario Gopal originally reported. That's probably a good trade-off, because there tends to be a higher expectation of responsiveness from IPC for things like user commands sent to the NameNode or ResourceManager, or even just heartbeats.

        A potential concern is that Hadoop runs in a wide variety of network architectures, which makes it difficult to test changes like this comprehensively. I see this has been labeled "Infiniband", so that's one scenario covered. I'd advise waiting a few more days to see if anyone else wants to review.

        Community members, if you think you're running Hadoop in a unique network architecture, please help by reviewing this patch.

        Show
        cnauroth Chris Nauroth added a comment - I think it's reasonable to favor low-latency handling on IPC connections. As I understand it, this would have pushed the packet loss burden into shuffle traffic or data transfer protocol traffic during the scenario Gopal originally reported. That's probably a good trade-off, because there tends to be a higher expectation of responsiveness from IPC for things like user commands sent to the NameNode or ResourceManager, or even just heartbeats. A potential concern is that Hadoop runs in a wide variety of network architectures, which makes it difficult to test changes like this comprehensively. I see this has been labeled "Infiniband", so that's one scenario covered. I'd advise waiting a few more days to see if anyone else wants to review. Community members, if you think you're running Hadoop in a unique network architecture, please help by reviewing this patch.
        Hide
        gopalv Gopal V added a comment -

        Thanks Chris Nauroth. I think this needs testing beyond what I've done - my test-setup is a single rack with has 10G ethernet - using both H-TCP & Cubic congestion controls.

        This definitely needs more testing, should be even better when encountering cross-rack packet loss.

        In particular, I'd love to see this patch tested with JDK7 Infiniband native support.

        Hadoop IPC/DataStreamer/Shuffle can already use Infiniband zero-copy mode by adding JVM opt args configuration options -Dcom.sun.sdp.conf=/etc/sdp.conf -Dcom.sun.sdp.debug=/tmp/sdp-debug.log, provided the OS/Hardware has support.

        Show
        gopalv Gopal V added a comment - Thanks Chris Nauroth . I think this needs testing beyond what I've done - my test-setup is a single rack with has 10G ethernet - using both H-TCP & Cubic congestion controls. This definitely needs more testing, should be even better when encountering cross-rack packet loss. In particular, I'd love to see this patch tested with JDK7 Infiniband native support. Hadoop IPC/DataStreamer/Shuffle can already use Infiniband zero-copy mode by adding JVM opt args configuration options -Dcom.sun.sdp.conf=/etc/sdp.conf -Dcom.sun.sdp.debug=/tmp/sdp-debug.log , provided the OS/Hardware has support.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Hmm, When should we commit this? After testing by Gopal?

        Show
        ozawa Tsuyoshi Ozawa added a comment - Hmm, When should we commit this? After testing by Gopal?
        Hide
        cmccabe Colin P. McCabe added a comment -

        It seems like we should make this configurable (and not on by default) since we don't know exactly what it will do on most networks. I also think a lot of people would disagree that latency is more important than throughput for HDFS RPC.

        Show
        cmccabe Colin P. McCabe added a comment - It seems like we should make this configurable (and not on by default) since we don't know exactly what it will do on most networks. I also think a lot of people would disagree that latency is more important than throughput for HDFS RPC.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        How about making it configurable via boolean value in core-site.xml? The default value can be "true" for many use cases. Colin P. McCabe Gopal V, what do you think?

        Show
        ozawa Tsuyoshi Ozawa added a comment - How about making it configurable via boolean value in core-site.xml? The default value can be "true" for many use cases. Colin P. McCabe Gopal V , what do you think?
        Hide
        cnauroth Chris Nauroth added a comment -

        I also think a lot of people would disagree that latency is more important than throughput for HDFS RPC.

        I think it's notable that the change is only on RPC and not on data transfer protocol, where I'd expect most people would favor throughput.

        It seems like we should make this configurable (and not on by default) since we don't know exactly what it will do on most networks.

        I generally think we have too many configuration flags in Hadoop already, but on this one, I have to agree. If it works out well in real-world practice, then we could make it the default at some point later, perhaps on a major version boundary.

        Show
        cnauroth Chris Nauroth added a comment - I also think a lot of people would disagree that latency is more important than throughput for HDFS RPC. I think it's notable that the change is only on RPC and not on data transfer protocol, where I'd expect most people would favor throughput. It seems like we should make this configurable (and not on by default) since we don't know exactly what it will do on most networks. I generally think we have too many configuration flags in Hadoop already, but on this one, I have to agree. If it works out well in real-world practice, then we could make it the default at some point later, perhaps on a major version boundary.
        Hide
        cmccabe Colin P. McCabe added a comment - - edited

        I think a configuration boolean is fine. It should default to the current behavior until we've had a chance to analyze its performance on typical ethernet networks. I would also be fine with this defaulting to true only for infiniband, although I don't know if we have a good way of doing that. (edit: as per Gopal's comments, this option might not make sense on infiniband)

        Show
        cmccabe Colin P. McCabe added a comment - - edited I think a configuration boolean is fine. It should default to the current behavior until we've had a chance to analyze its performance on typical ethernet networks. I would also be fine with this defaulting to true only for infiniband, although I don't know if we have a good way of doing that. (edit: as per Gopal's comments, this option might not make sense on infiniband)
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Thanks Chris and Colin for your comments. Make sense to default to the current behaviour for now.

        Gopal V do you mind updating a patch?

        Show
        ozawa Tsuyoshi Ozawa added a comment - Thanks Chris and Colin for your comments. Make sense to default to the current behaviour for now. Gopal V do you mind updating a patch?
        Hide
        gopalv Gopal V added a comment -

        Sure, I will update the patch in a couple of days with a config option.

        To correct Colin, this patch was built for 10GigE (ixgbe drivers). I tested this with both H-TCP and Cubic congestion control (2.6 and 3.1 kernels).

        The RFCs listed in the patch apply only toTCP/IP not Infiniband RDMA (unless JDK7+ translates the hints via SDP, which is something I'd love to be tested by the community).

        Show
        gopalv Gopal V added a comment - Sure, I will update the patch in a couple of days with a config option. To correct Colin, this patch was built for 10GigE (ixgbe drivers). I tested this with both H-TCP and Cubic congestion control (2.6 and 3.1 kernels). The RFCs listed in the patch apply only toTCP/IP not Infiniband RDMA (unless JDK7+ translates the hints via SDP, which is something I'd love to be tested by the community).
        Hide
        cmccabe Colin P. McCabe added a comment -

        Thanks for the correction, Gopal V. You are right... "pure" infiniband would not use TCP, and this is a TCP socket option.

        Sure, I will update the patch in a couple of days with a config option.

        Thanks.

        Show
        cmccabe Colin P. McCabe added a comment - Thanks for the correction, Gopal V . You are right... "pure" infiniband would not use TCP, and this is a TCP socket option. Sure, I will update the patch in a couple of days with a config option. Thanks.
        Hide
        gopalv Gopal V added a comment -

        Added ipc.client.low-latency with default=false

        Show
        gopalv Gopal V added a comment - Added ipc.client.low-latency with default=false
        Hide
        gopalv Gopal V added a comment -

        No added tests, since this has no easy way to test without a correctly configured system & a tcpdump.

        Show
        gopalv Gopal V added a comment - No added tests, since this has no easy way to test without a correctly configured system & a tcpdump.
        Hide
        hadoopqa Hadoop QA added a comment -

        -1 overall. Here are the results of testing the latest attachment
        http://issues.apache.org/jira/secure/attachment/12701487/HADOOP-11226.3.patch
        against trunk revision cf51ff2.

        +1 @author. The patch does not contain any @author tags.

        -1 tests included. The patch doesn't appear to include any new or modified tests.
        Please justify why no new tests are needed for this patch.
        Also please list what manual steps were performed to verify this patch.

        -1 javac. The patch appears to cause the build to fail.

        Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5795//console

        This message is automatically generated.

        Show
        hadoopqa Hadoop QA added a comment - -1 overall . Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12701487/HADOOP-11226.3.patch against trunk revision cf51ff2. +1 @author . The patch does not contain any @author tags. -1 tests included . The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. -1 javac . The patch appears to cause the build to fail. Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5795//console This message is automatically generated.
        Hide
        hadoopqa Hadoop QA added a comment -

        -1 overall. Here are the results of testing the latest attachment
        http://issues.apache.org/jira/secure/attachment/12701499/HADOOP-11226.4.patch
        against trunk revision edceced.

        +1 @author. The patch does not contain any @author tags.

        -1 tests included. The patch doesn't appear to include any new or modified tests.
        Please justify why no new tests are needed for this patch.
        Also please list what manual steps were performed to verify this patch.

        +1 javac. The applied patch does not increase the total number of javac compiler warnings.

        +1 javadoc. There were no new javadoc warning messages.

        +1 eclipse:eclipse. The patch built with eclipse:eclipse.

        +1 findbugs. The patch does not introduce any new Findbugs (version 2.0.3) warnings.

        +1 release audit. The applied patch does not increase the total number of release audit warnings.

        +1 core tests. The patch passed unit tests in hadoop-common-project/hadoop-common.

        Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5796//testReport/
        Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5796//console

        This message is automatically generated.

        Show
        hadoopqa Hadoop QA added a comment - -1 overall . Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12701499/HADOOP-11226.4.patch against trunk revision edceced. +1 @author . The patch does not contain any @author tags. -1 tests included . The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. +1 javac . The applied patch does not increase the total number of javac compiler warnings. +1 javadoc . There were no new javadoc warning messages. +1 eclipse:eclipse . The patch built with eclipse:eclipse. +1 findbugs . The patch does not introduce any new Findbugs (version 2.0.3) warnings. +1 release audit . The applied patch does not increase the total number of release audit warnings. +1 core tests . The patch passed unit tests in hadoop-common-project/hadoop-common. Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5796//testReport/ Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5796//console This message is automatically generated.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Gopal V thank you for updating a patch! Looks good to me overall. Could you update core-default.xml to describe the new options?

        Show
        ozawa Tsuyoshi Ozawa added a comment - Gopal V thank you for updating a patch! Looks good to me overall. Could you update core-default.xml to describe the new options?
        Hide
        gopalv Gopal V added a comment -

        Sure, I will add - I grepped to see where tcp.nodelay is mentioned, didn't see any docs.

        Show
        gopalv Gopal V added a comment - Sure, I will add - I grepped to see where tcp.nodelay is mentioned, didn't see any docs.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Good catch. It's better to update the point on this JIRA too.

        Show
        ozawa Tsuyoshi Ozawa added a comment - Good catch. It's better to update the point on this JIRA too.
        Hide
        gopalv Gopal V added a comment -

        Updated patch with documentation

        Show
        gopalv Gopal V added a comment - Updated patch with documentation
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        +1, pending for Jenkins.

        Show
        ozawa Tsuyoshi Ozawa added a comment - +1, pending for Jenkins.
        Hide
        hadoopqa Hadoop QA added a comment -

        -1 overall. Here are the results of testing the latest attachment
        http://issues.apache.org/jira/secure/attachment/12703565/HADOOP-11226.5.patch
        against trunk revision d6e05c5.

        +1 @author. The patch does not contain any @author tags.

        -1 tests included. The patch doesn't appear to include any new or modified tests.
        Please justify why no new tests are needed for this patch.
        Also please list what manual steps were performed to verify this patch.

        +1 javac. The applied patch does not increase the total number of javac compiler warnings.

        +1 javadoc. There were no new javadoc warning messages.

        +1 eclipse:eclipse. The patch built with eclipse:eclipse.

        +1 findbugs. The patch does not introduce any new Findbugs (version 2.0.3) warnings.

        +1 release audit. The applied patch does not increase the total number of release audit warnings.

        +1 core tests. The patch passed unit tests in hadoop-common-project/hadoop-common.

        Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5898//testReport/
        Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5898//console

        This message is automatically generated.

        Show
        hadoopqa Hadoop QA added a comment - -1 overall . Here are the results of testing the latest attachment http://issues.apache.org/jira/secure/attachment/12703565/HADOOP-11226.5.patch against trunk revision d6e05c5. +1 @author . The patch does not contain any @author tags. -1 tests included . The patch doesn't appear to include any new or modified tests. Please justify why no new tests are needed for this patch. Also please list what manual steps were performed to verify this patch. +1 javac . The applied patch does not increase the total number of javac compiler warnings. +1 javadoc . There were no new javadoc warning messages. +1 eclipse:eclipse . The patch built with eclipse:eclipse. +1 findbugs . The patch does not introduce any new Findbugs (version 2.0.3) warnings. +1 release audit . The applied patch does not increase the total number of release audit warnings. +1 core tests . The patch passed unit tests in hadoop-common-project/hadoop-common. Test results: https://builds.apache.org/job/PreCommit-HADOOP-Build/5898//testReport/ Console output: https://builds.apache.org/job/PreCommit-HADOOP-Build/5898//console This message is automatically generated.
        Hide
        ozawa Tsuyoshi Ozawa added a comment -

        Committed this to trunk and branch-2. Thanks Gopal V for your contribution and thanks Chris and Colin for your reviews!

        Show
        ozawa Tsuyoshi Ozawa added a comment - Committed this to trunk and branch-2. Thanks Gopal V for your contribution and thanks Chris and Colin for your reviews!
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-trunk-Commit #7294 (See https://builds.apache.org/job/Hadoop-trunk-Commit/7294/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-trunk-Commit #7294 (See https://builds.apache.org/job/Hadoop-trunk-Commit/7294/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/resources/core-default.xml hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Yarn-trunk-Java8 #128 (See https://builds.apache.org/job/Hadoop-Yarn-trunk-Java8/128/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Yarn-trunk-Java8 #128 (See https://builds.apache.org/job/Hadoop-Yarn-trunk-Java8/128/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/src/main/resources/core-default.xml hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Yarn-trunk #862 (See https://builds.apache.org/job/Hadoop-Yarn-trunk/862/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Yarn-trunk #862 (See https://builds.apache.org/job/Hadoop-Yarn-trunk/862/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Hdfs-trunk #2060 (See https://builds.apache.org/job/Hadoop-Hdfs-trunk/2060/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/CHANGES.txt
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Hdfs-trunk #2060 (See https://builds.apache.org/job/Hadoop-Hdfs-trunk/2060/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java hadoop-common-project/hadoop-common/src/main/resources/core-default.xml hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/CHANGES.txt
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Hdfs-trunk-Java8 #119 (See https://builds.apache.org/job/Hadoop-Hdfs-trunk-Java8/119/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Hdfs-trunk-Java8 #119 (See https://builds.apache.org/job/Hadoop-Hdfs-trunk-Java8/119/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Mapreduce-trunk-Java8 #128 (See https://builds.apache.org/job/Hadoop-Mapreduce-trunk-Java8/128/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Mapreduce-trunk-Java8 #128 (See https://builds.apache.org/job/Hadoop-Mapreduce-trunk-Java8/128/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        Hide
        hudson Hudson added a comment -

        FAILURE: Integrated in Hadoop-Mapreduce-trunk #2078 (See https://builds.apache.org/job/Hadoop-Mapreduce-trunk/2078/)
        HADOOP-11226. Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07)

        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java
        • hadoop-common-project/hadoop-common/CHANGES.txt
        • hadoop-common-project/hadoop-common/src/main/resources/core-default.xml
        • hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Show
        hudson Hudson added a comment - FAILURE: Integrated in Hadoop-Mapreduce-trunk #2078 (See https://builds.apache.org/job/Hadoop-Mapreduce-trunk/2078/ ) HADOOP-11226 . Add a configuration to set ipc.Client's traffic class with IPTOS_LOWDELAY|IPTOS_RELIABILITY. Contributed by Gopal V. (ozawa: rev 54639c7d7a34f4a46e8df50d57c79bab34b1ac07) hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/ipc/Client.java hadoop-common-project/hadoop-common/CHANGES.txt hadoop-common-project/hadoop-common/src/main/resources/core-default.xml hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/CommonConfigurationKeysPublic.java
        Hide
        bikassaha Bikas Saha added a comment -

        Comments would help this line.

        +            this.socket.setPerformancePreferences(1, 2, 0);
        Show
        bikassaha Bikas Saha added a comment - Comments would help this line. + this .socket.setPerformancePreferences(1, 2, 0);

          People

          • Assignee:
            gopalv Gopal V
            Reporter:
            gopalv Gopal V
          • Votes:
            0 Vote for this issue
            Watchers:
            10 Start watching this issue

            Dates

            • Created:
              Updated:
              Resolved:

              Development