You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Vincent zhao (JIRA)" <ji...@apache.org> on 2016/06/28 06:39:57 UTC
[jira] [Commented] (SPARK-16218) 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.
[ 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: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org