[HADOOP-19292] BlockDecompressorStream#rawReadInt wastes about 1% of overall CPU cycles creating new EOFException - ASF JIRA

XML

Word

Printable

JSON

Details

Type: Improvement
Status: Patch Available
Priority: Major
Resolution: Unresolved
Affects Version/s: 3.3.6
Fix Version/s: None
Component/s: compress, io
Labels:
None

Description

On our HBase clusters, while looking at CPU profiles, I noticed that about 1% of overall CPU cycles are spent under BlockDecompressorStream#rawReadInt just throwing EOFException. This could be easily avoided.

Attachments

- Sort By Name
- Sort By Date
- Ascending
- Descending

HADOOP-19292-Don-t-create-new-EOFException-in-BlockD.patch
30/Sep/24 14:44
2 kB
Benoit Sigoure

Activity

People

Assignee:: Benoit Sigoure

Reporter:: Benoit Sigoure

Votes:: 0 Vote for this issue

Watchers:: 2 Start watching this issue

Dates

Created:: 30/Sep/24 11:56

Updated:: 01/Oct/24 19:38