[
https://issues.apache.org/jira/browse/SPARK-16218?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15352463#comment-15352463
]
Vincent zhao commented on SPARK-16218:
--------------------------------------
now I see , thank you
> spark 1.4.1 "Storage Fraction Cached" was greater than 120%.And I recache
> the talbe in memory and find querying faster than before,May be its a bug.
> -----------------------------------------------------------------------------------------------------------------------------------------------------
>
> Key: SPARK-16218
> URL: https://issues.apache.org/jira/browse/SPARK-16218
> Project: Spark
> Issue Type: Bug
> Components: Block Manager, SQL
> Affects Versions: 1.4.1
> Environment: Java Version 1.7.0_71 (Oracle Corporation)
> Scala Version version 2.10.4
> Reporter: Vincent zhao
> Priority: Minor
> Original Estimate: 48h
> Remaining Estimate: 48h
>
> We have cached a Hive Table in memory using CACHE TABLE tablename.And in the
> early time ,we query the data at a very high speed.But, after many times,we
> found the speed begin very slowly, but the SQL is the same as the early one.
> So we check the reason In the JOBS tab of the Spark Web UI. And we found the
> cost times of some task is very long but the size of the task input is not
> large.But in the Storage tab of the Spark Web UI of spark 1.4.1, we saw a
> case where the "Fraction Cached" was greater than 120%.So
> I recache the talbe in memory and find querying faster than before .May it be
> a bug in this version , if so ,we also can make a monitor for it.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
