yongzhi.shao created HIVE-27901:
-----------------------------------
Summary: Hive's performance for querying the Iceberg table is very
poor.
Key: HIVE-27901
URL: https://issues.apache.org/jira/browse/HIVE-27901
Project: Hive
Issue Type: Bug
Components: Iceberg integration
Affects Versions: 4.0.0-beta-1
Reporter: yongzhi.shao
Attachments: image-2023-11-22-18-32-28-344.png,
image-2023-11-22-18-33-01-885.png, image-2023-11-22-18-33-32-915.png
I am using HIVE-4.0.0-BETA for testing.
BTW,I found that the performance of HIVE reading ICEBERG table is still very
slow.
How should I deal with this problem?
I count a 7 billion table and compare the performance difference between HIVE
reading ICEBERG-ORC and ORC table respectively.
We use ICEBERG 1.4.2, ICEBERG-ORC with ZSTD compression enabled.
ORC with SNAPPY compression.
HADOOP version 3.1.1 (native zstd not supported).
!image-2023-11-22-18-32-28-344.png!
!image-2023-11-22-18-33-01-885.png!
Also, I have another question. The Submit Plan statistic is clearly incorrect.
Is this something that needs to be fixed?
!image-2023-11-22-18-33-32-915.png!
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
