Brian Johnson created PHOENIX-2083:
--------------------------------------
Summary: Pig maps splits are very unevent
Key: PHOENIX-2083
URL: https://issues.apache.org/jira/browse/PHOENIX-2083
Project: Phoenix
Issue Type: Bug
Affects Versions: 4.1.0
Reporter: Brian Johnson
When running a pig job on MR with the Phoenix loader we got about 75 maps
tasks, but there was huge amount of skew in how the records were allocated and
the vast majority of them went to about 20 mappers and 5 got nothing at all.
Task
Value
task_1433431098673_66646_m_000042 0
task_1433431098673_66646_m_000057 0
task_1433431098673_66646_m_000061 0
task_1433431098673_66646_m_000067 0
task_1433431098673_66646_r_000000 0
task_1433431098673_66646_m_000031 127242
task_1433431098673_66646_m_000026 130669
task_1433431098673_66646_m_000017 179685
task_1433431098673_66646_m_000068 190741
task_1433431098673_66646_m_000040 191062
task_1433431098673_66646_m_000056 191509
task_1433431098673_66646_m_000053 191518
task_1433431098673_66646_m_000060 191560
task_1433431098673_66646_m_000048 191579
task_1433431098673_66646_m_000041 191623
task_1433431098673_66646_m_000047 191686
task_1433431098673_66646_m_000065 191720
task_1433431098673_66646_m_000064 191726
task_1433431098673_66646_m_000054 191763
task_1433431098673_66646_m_000066 191871
task_1433431098673_66646_m_000052 191875
task_1433431098673_66646_m_000045 191908
task_1433431098673_66646_m_000049 191914
task_1433431098673_66646_m_000063 192124
task_1433431098673_66646_m_000058 192352
task_1433431098673_66646_m_000069 192352
task_1433431098673_66646_m_000044 192519
task_1433431098673_66646_m_000007 529769
task_1433431098673_66646_m_000018 584940
task_1433431098673_66646_m_000005 585864
task_1433431098673_66646_m_000003 697683
task_1433431098673_66646_m_000016 709321
task_1433431098673_66646_m_000008 710190
task_1433431098673_66646_m_000004 710774
task_1433431098673_66646_m_000011 711818
task_1433431098673_66646_m_000038 713862
task_1433431098673_66646_m_000037 714577
task_1433431098673_66646_m_000022 716796
task_1433431098673_66646_m_000014 717478
task_1433431098673_66646_m_000025 722809
task_1433431098673_66646_m_000030 723182
task_1433431098673_66646_m_000024 723378
task_1433431098673_66646_m_000013 731836
task_1433431098673_66646_m_000010 732525
task_1433431098673_66646_m_000001 734611
task_1433431098673_66646_m_000036 739874
task_1433431098673_66646_m_000072 1810925
task_1433431098673_66646_m_000039 1923212
task_1433431098673_66646_m_000059 2014210
task_1433431098673_66646_m_000055 2287499
task_1433431098673_66646_m_000074 2887750
task_1433431098673_66646_m_000073 3049942
task_1433431098673_66646_m_000029 3156535
task_1433431098673_66646_m_000071 3841375
task_1433431098673_66646_m_000027 4001882
task_1433431098673_66646_m_000051 4343619
task_1433431098673_66646_m_000034 5363718
task_1433431098673_66646_m_000050 7734798
task_1433431098673_66646_m_000020 9543930
task_1433431098673_66646_m_000070 10058382
task_1433431098673_66646_m_000046 10143291
task_1433431098673_66646_m_000062 10263757
task_1433431098673_66646_m_000032 10908072
task_1433431098673_66646_m_000015 11182800
task_1433431098673_66646_m_000000 11300385
task_1433431098673_66646_m_000043 11359327
task_1433431098673_66646_m_000021 12632598
task_1433431098673_66646_m_000009 14598258
task_1433431098673_66646_m_000028 14698359
task_1433431098673_66646_m_000033 16407474
task_1433431098673_66646_m_000012 17944269
task_1433431098673_66646_m_000023 20568188
task_1433431098673_66646_m_000035 21656353
task_1433431098673_66646_m_000002 27413291
task_1433431098673_66646_m_000006 35573698
task_1433431098673_66646_m_000019 35717128
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)