[jira] [Created] (IMPALA-6977) Report CPU usage (user/sys) per fragment

["Tim Armstrong (JIRA)" <ji...@apache.org>]

Tim Armstrong created IMPALA-6977:
-------------------------------------

             Summary: Report CPU usage (user/sys) per fragment
                 Key: IMPALA-6977
                 URL: https://issues.apache.org/jira/browse/IMPALA-6977
             Project: IMPALA
          Issue Type: Improvement
          Components: Backend
            Reporter: Tim Armstrong


The exec summary only shows wallclock time, because that is the only time reported per operator.
{noformat}
Operator       #Hosts  Avg Time  Max Time  #Rows  Est. #Rows   Peak Mem  Est. Peak Mem  Detail                 
---------------------------------------------------------------------------------------------------------------
03:AGGREGATE        1   1.782ms   1.782ms      1           1   28.16 KB       10.00 MB  FINALIZE               
02:EXCHANGE         1  90.073us  90.073us      3           1  104.00 KB              0  UNPARTITIONED          
01:AGGREGATE        3   1s560ms   1s657ms      3           1    1.35 MB       10.00 MB                         
00:SCAN HDFS        3   1s567ms   1s815ms  6.00M       6.00M   59.11 MB      144.00 MB  tpch_seq_gzip.lineitem 
{noformat}

This is fairly useful for understanding query bottlenecks but is misleading whn it comes to determining where CPU was consumed. We have accurate User and Sys time for fragment instances so we could have a CPU usage summary based on profile information
{noformat}
Fragment       #Hosts  Avg UserTime  Max UserTime  Avg SysTime   Max SysTime
------------------------------------------------------------------------------
F01            1       12.000ms      .......       ..........
F00            3       7s245ms       7s624ms       .......       ..........
{noformat}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)