[HADOOP-312] Connections should not be cached - ASF JIRA

XML

Word

Printable

JSON

Details

Type: Improvement
Status: Closed
Priority: Major
Resolution: Fixed
Affects Version/s: None
Fix Version/s: 0.6.0
Component/s: ipc
Labels:
None

Description

Servers and clients (client include datanodes, tasktrackers, DFSClients & tasks) should not cache connections or maybe cache them for very short periods of time. Clients should set up & tear down connections to the servers everytime they need to contact the servers (including the heartbeats). If connection is cached, then reuse the existing connection for a few subsequent transactions until the connection expires. The heartbeat interval should be more so that many more clients (order of tens of thousands) can be accomodated within 1 heartbeat interval.

Attachments

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

control_conn_caching.patch
06/Sep/06 20:25
13 kB
Devaraj Das
no_conn_caching.patch
01/Sep/06 19:08
13 kB
Devaraj Das
no_conn_caching.patch
29/Aug/06 20:05
7 kB
Devaraj Das
no_conn_caching.patch
29/Aug/06 20:00
7 kB
Devaraj Das
no_conn_caching.patch
22/Aug/06 12:45
12 kB
Devaraj Das
no_conn_caching.patch
19/Aug/06 18:15
12 kB
Devaraj Das
no_conn_caching.patch
18/Aug/06 05:45
11 kB
Devaraj Das
no_connection_caching.patch
07/Aug/06 18:40
10 kB
Devaraj Das
no_connection_caching.patch
26/Jul/06 09:30
9 kB
Devaraj Das

Issue Links

is blocked by

HADOOP-362 tasks can get lost when reporting task completion to the JobTracker has an error

Closed

Activity

People

Assignee:: Devaraj Das

Reporter:: Devaraj Das

Votes:: 0 Vote for this issue

Watchers:: 0 Start watching this issue

Dates

Created:: 22/Jun/06 01:55

Updated:: 08/Sep/06 21:19

Resolved:: 06/Sep/06 22:49