[HADOOP-5784] The length of the heartbeat cycle should be configurable. - ASF JIRA

XML

Word

Printable

JSON

Details

Type: Improvement
Status: Closed
Priority: Major
Resolution: Fixed
Affects Version/s: None
Fix Version/s: 0.21.0
Component/s: None
Labels:
None

Release Note:

Hide
Introduced a configuration parameter, mapred.heartbeats.in.second, as an expert option, that defines how many heartbeats a jobtracker can process in a second. Administrators can set this to an appropriate value based on cluster size and expected processing time on the jobtracker to achieve a balance between jobtracker scalability and latency of jobs.

Show
Introduced a configuration parameter, mapred.heartbeats.in.second, as an expert option, that defines how many heartbeats a jobtracker can process in a second. Administrators can set this to an appropriate value based on cluster size and expected processing time on the jobtracker to achieve a balance between jobtracker scalability and latency of jobs.

Description

Currently, the hearbeat cycle is set to (# nodes / 100) in seconds. This can be too long for clusters that need to run low latency jobs. We should make the number of heartbeats that should arrive a second configurable.

Attachments

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

HADOOP-5784_yhadoop20.patch
22/Sep/09 05:00
6 kB
Arun Murthy
patch-5784-1.txt
27/May/09 09:52
6 kB
Amareshwari Sriramadasu
patch-5784.txt
25/May/09 10:56
3 kB
Amareshwari Sriramadasu

Activity

People

Assignee:: Amareshwari Sriramadasu

Reporter:: Owen O'Malley

Votes:: 1 Vote for this issue

Watchers:: 5 Start watching this issue

Dates

Created:: 08/May/09 07:11

Updated:: 24/Aug/10 20:37

Resolved:: 02/Jun/09 06:52