[HADOOP-141] Disk thrashing / task timeouts during map output copy phase

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.3.0

Environment

linux

• Assignee: Owen O'Malley
• Reporter: Peter Sutter
• Created: 18/Apr/06 05:21
• Updated: 08/Jul/09 16:51
• Resolved: 14/Oct/06 03:30

Description

MapOutputProtocol connections cause timeouts because of system thrashing and transferring the same file over and over again, ultimately leading to making no forward progress(medium sized job, 500GB input file, map output about as large as the input, 10 node cluster).

There are several bugs behind this, but the following two changes improved matters considerably.

(1)

The buffersize in MapOutputFile is currently hardcoded to 8192 bytes (for both reads and writes). By changing this buffer size to 256KB, the number of disk seeks are reduced and the problem went away.

Ideally there would be a buffer size parameter for this that is separate from the DFS io buffer size.

(2)

I also added the following code to the socket configuration in both Server.java and Client.java. No linger is a minor good idea in an enivronment with some packet loss (and you will have that when all the nodes get busy at once), but 256KB buffers is probably excessive, especially on a LAN, but it takes me two hours to test changes so I havent experimented.

socket.setSendBufferSize(256*1024);
socket.setReceiveBufferSize(256*1024);
socket.setSoLinger(false, 0);
socket.setKeepAlive(true);