[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Tsz Wo Nicholas Sze updated HADOOP-12916: - +1 the new patch looks good. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch, HADOOP-12916.07.patch, > HADOOP-12916.08.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.08.patch Attach a new patch v08 to get a clean Jenkins run. Delta of changes: Adding a new unit test ensuring DecayRpcScheduler works without FCQ such as LinkedBlockingQueue. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch, HADOOP-12916.07.patch, > HADOOP-12916.08.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.07.patch The patch applies to my local trunk branch without problem. Not sure why Jenkins failed. Reattach.. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch, HADOOP-12916.07.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.06.patch > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: (was: HADOOP-12916.06.patch) > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: (was: HADOOP-12916.06.patch) > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.06.patch > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.06.patch Thanks [~szetszwo] for the review. I've updated the patch based on your suggestion. Also rebase the patch to trunk with additional unit test added for the scheduler constructor exception handling. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch, HADOOP-12916.06.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.05.patch Thanks [~arpitagarwal] and [~szetszwo] for the review. Update the patch that 1) Fixing exception handling when constructing the scheduler instance. 2) Keep the default decay factor and decay windows size to the same as the original FCQ. 3) Enable decay on the average response time for scheduler decision. I don't change the Configuration#getTimeDurations() to return a List because it incurs extra box/unbox overhead. A long array should be good for many cases. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch, > HADOOP-12916.05.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: (was: HADOOP-12916.04.patch) > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.04.patch > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Tsz Wo Nicholas Sze updated HADOOP-12916: - Hadoop Flags: Reviewed +1 the new patch looks good. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.04.patch Thanks [~szetszwo]! Attach patch 04 to remove the redundant synchronization when accessing atomic arrays. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch, HADOOP-12916.04.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.03.patch Attached a new patch that uses AtomLongArray/AtomicDoubleArray for previous window response time/count. Also include some minor clean up for check style issue. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch, HADOOP-12916.03.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.02.patch Update the patch that cleans up the javac and checkstyle issues. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch, > HADOOP-12916.02.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Status: Patch Available (was: Open) > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.00.patch Attach a patch that 1) Separate the scheduler interface and implementation from FCQ 2) Allow DecayRpcScheduler to collect window based per priority level response time metrics. 3) Allow optional backoff based on per priority level response time target based backoff. 4) Additional unit test for response time target based backoff. 5) Additional unit test to ensure backward compatibility for current FCQ deployment With this refactor, the FCQ is purely a weighted priority call queue and the DecayRpcScheduler is a fairness scheduler based on the callers' call count. The weight priority call queue can be plugged with other priority based scheduler for Qos. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.01.patch Thanks for [~szetszwo] for the review. I've update the patch that addresses your comments and the checkstyle/findbugs issues from Jenkins. bq. "Should priorityLevels be passed in the second try/catch in CallQueueManager#createScheduler?" We already pass the int.class which is the priority level in the second try/catch. > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: (was: HADOOP-12916.01.patch) > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HADOOP-12916: Attachment: HADOOP-12916.01.patch > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > Attachments: HADOOP-12916.00.patch, HADOOP-12916.01.patch > > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HADOOP-12916) Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff
[ https://issues.apache.org/jira/browse/HADOOP-12916?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Tsz Wo Nicholas Sze updated HADOOP-12916: - Component/s: ipc > Allow different Hadoop IPC Call Queue throttling policies with FCQ/BackOff > -- > > Key: HADOOP-12916 > URL: https://issues.apache.org/jira/browse/HADOOP-12916 > Project: Hadoop Common > Issue Type: Improvement > Components: ipc >Reporter: Xiaoyu Yao >Assignee: Xiaoyu Yao > > Currently back off policy from HADOOP-10597 is hard coded to base on whether > call queue is full. This ticket is open to allow flexible back off policies > such as moving average of response time in RPC calls of different priorities. -- This message was sent by Atlassian JIRA (v6.3.4#6332)