[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2015-02-07 Thread Sean Owen (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Sean Owen updated SPARK-3545: - Component/s: Scheduler Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in

[jira] [Updated] (SPARK-3545) Put HadoopRDD.getPartitions forward and put TaskScheduler.start back in SparkContext to reduce DAGScheduler.JobSubmitted processing time and shorten cluster resources occ

2014-09-16 Thread YanTang Zhai (JIRA)
[ https://issues.apache.org/jira/browse/SPARK-3545?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] YanTang Zhai updated SPARK-3545: Description: We have two problems: (1) HadoopRDD.getPartitions is lazyied to process in