[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16861746#comment-16861746
]
Adar Dembo commented on KUDU-749:
-
[~ZhangYao]'s patch has been merged and will be part of the 1.10.0
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16856350#comment-16856350
]
ZhangYao commented on KUDU-749:
---
Here is the patch:) [https://gerrit.cloudera.org/#/c/13516/]
> Improve
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16856257#comment-16856257
]
ZhangYao commented on KUDU-749:
---
Oops:(，I mistakenly reversed the result. The average latency decreases by
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16856172#comment-16856172
]
Adar Dembo commented on KUDU-749:
-
[~ZhangYao] did you reverse the results? Or did the average latency
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16855686#comment-16855686
]
ZhangYao commented on KUDU-749:
---
Hi, Todd, :) According to your advice I have implemented "seek before"
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16855265#comment-16855265
]
ZhangYao commented on KUDU-749:
---
Hi, Todd, thanks for your advice :). I will try to implement "seek before"
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16854764#comment-16854764
]
Todd Lipcon commented on KUDU-749:
--
Hi [~ZhangYao]. That makes sense to me -- maybe the POC will expose
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16854190#comment-16854190
]
ZhangYao commented on KUDU-749:
---
Hi, Todd:). In order to accelerate the time spending on
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16850922#comment-16850922
]
Grant Henke commented on KUDU-749:
--
[~wdberkeley_impala_f7d4] you recently talked about more general
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16850574#comment-16850574
]
Xu Yao commented on KUDU-749:
-
This problem also exists in our production environment. The reason for this
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16424240#comment-16424240
]
Paul Brannan commented on KUDU-749:
---
My mistake; it was the apply thread, not the MaintenanceManager.
>
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16418186#comment-16418186
]
Todd Lipcon commented on KUDU-749:
--
[~cout] you sure the MaintenanceManager is spending time in
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16415717#comment-16415717
]
Paul Brannan commented on KUDU-749:
---
We have observed the same behavior for an update-heavy workload;
[
https://issues.apache.org/jira/browse/KUDU-749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16182119#comment-16182119
]
Todd Lipcon commented on KUDU-749:
--
FWIW this is still a pretty bad issue for YCSB workload A (zipfian
14 matches
Mail list logo
