[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Resolution: Fixed Fix Version/s: 0.98.2 Hadoop Flags: Reviewed Status: Resolved (was: Patch Available) Integrated into trunk and 0.98. Thanks Ted for the review. Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Affects Versions: 0.98.0 Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Critical Fix For: 0.99.0, 0.98.2 Attachments: hbase-10949.patch, master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Status: Patch Available (was: Open) Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Affects Versions: 0.98.0 Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Critical Fix For: 0.99.0 Attachments: hbase-10949.patch, master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Attachment: hbase-10949.patch Attached a patch that uses the comparator of hfile (reader). ITBLL works fine with this patch. Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Affects Versions: 0.98.0 Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Critical Fix For: 0.99.0 Attachments: hbase-10949.patch, master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Priority: Critical (was: Blocker) Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Critical Fix For: 0.99.0 Attachments: master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Summary: Reversed scan could hang (was: Meta scan could hang) Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Blocker Fix For: 0.99.0 Attachments: master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)
[jira] [Updated] (HBASE-10949) Reversed scan could hang
[ https://issues.apache.org/jira/browse/HBASE-10949?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Jimmy Xiang updated HBASE-10949: Affects Version/s: 0.98.0 Reversed scan could hang Key: HBASE-10949 URL: https://issues.apache.org/jira/browse/HBASE-10949 Project: HBase Issue Type: Bug Affects Versions: 0.98.0 Reporter: Jimmy Xiang Assignee: Jimmy Xiang Priority: Critical Fix For: 0.99.0 Attachments: master-jstack.log When I play with ITBLL (from trunk tip), sometimes, meta scan hangs when the cluster is rolling restarted. When this happens, the master takes about 1000% of CPU. It looks like there is an infinite loop somewhere. The logs show nothing interesting except some meta scanner RPC calls timed out. Jstask shows the 10 high QoS RPC handlers are busy with meta scanning. However, if I run it again without HBASE-10018, things are fine. I suspect there is something to do with the small/reverse scan. By the way, I see this problem even with log replay off and hfile version = 2. -- This message was sent by Atlassian JIRA (v6.2#6252)