[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaoyu Yao updated HDFS-8855: - Resolution: Fixed Hadoop Flags: Reviewed Status: Resolved (was: Patch Available) Thanks [~xiaobingo] and [~cnauroth] for the contribution and all for the reviews. I've committed the patch to trunk and branch-2. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Fix For: 2.8.0 > > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.008.patch, HDFS-8855.009.patch, > HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.009.patch Posted a new patch v009 to remove white spaces. The UT failures are not related. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Fix For: 2.8.0 > > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.008.patch, HDFS-8855.009.patch, > HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Status: Patch Available (was: Reopened) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Fix For: 2.8.0 > > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.008.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.008.patch Patch v008 to merge follow-up work, kindly review. Thanks. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Fix For: 2.8.0 > > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.008.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jitendra Nath Pandey updated HDFS-8855: --- Resolution: Fixed Fix Version/s: 2.8.0 Status: Resolved (was: Patch Available) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Fix For: 2.8.0 > > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS-8855.4.patch, HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.007.patch > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.007.patch, HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS-8855.4.patch, HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.006.patch 006 patch used computed hash code as cache key. Thanks [~owen.omalley] and [~bobthansen] for review. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.006.patch, > HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: (was: HDFS-8855.006.patch) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.006.patch > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.005.patch > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: (was: HDFS-8855.005.patch) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS-8855.4.patch, HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Status: Patch Available (was: Open) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Status: Open (was: Patch Available) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.005.patch > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.005.patch, HDFS-8855.1.patch, > HDFS-8855.2.patch, HDFS-8855.3.patch, HDFS-8855.4.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.4.patch Patch V4. Added some UTs. Can anyone review it? Thanks. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS-8855.4.patch, HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Environment: (was: HDP 2.2) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.3.patch [~bobthansen] Thanks for review. Although that's called by bootstrap only, it should be thread safe. See patch V3. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs > Environment: HDP 2.2 >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS-8855.2.patch, HDFS-8855.3.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.2.patch Made patch V2. The proposed fix is to cache UGI in webhdfs to avoid creating brand new UGI for every web request. 1. In insecure case, remote-user+proxy-user is the key for cache. 2. In secure case, token is the key. UGI is constructed based on token. It’s necessary to ensure different UGI instance, and thus different connection, given token is changed. Connection cache is designed to be keyed on UGI instances. Actually, the connection cache is keyed on the 'UGI#Subject' instance instead of the UGI instance, which seems to be the right choice because subject contains the security credentials of the users, and we should allow connection re-use in the same authentication context only. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs > Environment: HDP 2.2 >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS-8855.2.patch, > HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Bob Hansen updated HDFS-8855: - Attachment: HDFS_8855.prototype.patch This patch (which compiles, but hasn't actually been "tested" or "validated" or "run") outlines the integration points that seemed like good places to poke at. It caches the client in the Netty context, doesn't close it for op=OPEN calls, and explicitly closes it when the session ends. It might be useful as the basis for further work, or simply as a strawman to discuss. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs > Environment: HDP 2.2 >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch, HDFS_8855.prototype.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Status: Patch Available (was: Open) > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs > Environment: HDP 2.2 >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (HDFS-8855) Webhdfs client leaks active NameNode connections
[ https://issues.apache.org/jira/browse/HDFS-8855?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Xiaobing Zhou updated HDFS-8855: Attachment: HDFS-8855.1.patch Made a patch for review. Idea's been to avoid creating brand new DFSClient per webhdfs request, which will create a new NN connection. > Webhdfs client leaks active NameNode connections > > > Key: HDFS-8855 > URL: https://issues.apache.org/jira/browse/HDFS-8855 > Project: Hadoop HDFS > Issue Type: Bug > Components: webhdfs > Environment: HDP 2.2 >Reporter: Bob Hansen >Assignee: Xiaobing Zhou > Attachments: HDFS-8855.1.patch > > > The attached script simulates a process opening ~50 files via webhdfs and > performing random reads. Note that there are at most 50 concurrent reads, > and all webhdfs sessions are kept open. Each read is ~64k at a random > position. > The script periodically (once per second) shells into the NameNode and > produces a summary of the socket states. For my test cluster with 5 nodes, > it took ~30 seconds for the NameNode to have ~25000 active connections and > fails. > It appears that each request to the webhdfs client is opening a new > connection to the NameNode and keeping it open after the request is complete. > If the process continues to run, eventually (~30-60 seconds), all of the > open connections are closed and the NameNode recovers. > This smells like SoftReference reaping. Are we using SoftReferences in the > webhdfs client to cache NameNode connections but never re-using them? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
