[HADOOP-6713] The RPC server Listener thread is a scalability bottleneck - ASF JIRA

XML

Word

Printable

JSON

Details

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

Hadoop Flags:

Reviewed

Description

The Hadoop RPC Server implementation has a single Listener thread that reads data from the socket and puts them into a call queue. This means that this single thread can pull RPC requests off the network only as fast as a single CPU can execute. This is a scalability bottlneck in our cluster.

Attachments

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

HADOOP-6713.2.patch
26/Apr/10 21:25
11 kB
Dmytro Molkov
HADOOP-6713.patch
21/Apr/10 22:19
10 kB
Dmytro Molkov
HADOOP-6713-rel20.2.patch
02/Jul/10 23:37
12 kB
Bharath Mundlapudi
HADOOP-6713-rel20.3.patch
03/Jul/10 00:09
13 kB
Bharath Mundlapudi
HADOOP-6713-rel20.patch
02/Jul/10 20:53
13 kB
Bharath Mundlapudi

Issue Links

is related to

HDFS-1051 Umbrella Jira for Scaling the HDFS Name Service

Open

Activity

People

Assignee:: Dmytro Molkov

Reporter:: Dhruba Borthakur

Votes:: 0 Vote for this issue

Watchers:: 20 Start watching this issue

Dates

Created:: 19/Apr/10 05:54

Updated:: 24/Aug/10 20:42

Resolved:: 27/Apr/10 18:15