Intel Computer Systems Cluster (the "fish machines")

Intel has donated 25 Pentium III Xeon servers to CMU for systems courses. The systems, which run the Red Hat 6.2 distribution of Linux (version 2.2.16), are rack-mounted in the Wean Hall 3rd floor machine room, and are administered by the CS facilities group. They are rebooted every morning at 7am.

Quick Start Login

While logged in to an Andrew machine (telnet linux.andrew) and in the home directory of your Andrew account: The uppercase 'ANDREW.CMU.EDU' is significant.

If you can't login, please read the rest of this document first, and if things still aren't working, send mail to your instructor (agn@cs.cmu.edu).

Getting Help

Information about the CS computing environment is at www.cs.cmu.edu/~help.

If you are having trouble logging in, please send mail to your instructor.

Frequently Asked Questions

Q: How do I get an account?
A: Accounts will be created for you automatically.


If you're not on the list, please request an account from Andreas Nowatzyk (agn@cs.cmu.edu).

Q: What do I need to do before logging in for the very first time?
A: From your Andrew home directory on one of the Andrew Unix cluster machines (linux.andrew.cmu.edu or unix.andrew.cmu.edu), run the following one-time checkin script:

    unix> /afs/cs/academic/class/15213-f04/bin/checkin
Important: Before you run this script, make sure you do not have any subdirectories in your Andrew home directory called 15-213 or 213hw. If you do, rename them before running the checkin script.

Q: What does the checkin script do?
A: It creates two subdirectories in your Andrew home directory: 15-213 and 213hw.
The 15-213 directory contains the .klogin and .login files that will allow you to login from the fish machines. DO NOT DELETE ANYTHING IN THIS SUBDIRECTORY.
The 213hw directory contains secure subdirectories for each of the labs, with the permissions set so that only you can read the contents.

Remember, you only need to run the checkin script once, before your very first login to the fish machines.

Q: How do I log into one of these machines once I have run the checkin script?
A: From your home directory on an Andrew Linux or Unix machine (e.g., linux.andrew or unix.andrew), if your Andrew login is bovik and you want to login to the fish machine called chum.cmcl.cs.cmu.edu, then login as follows:

    unix> ssh -1 -l bovik@ANDREW.CMU.EDU  chum.cmcl.cs.cmu.edu
    [type your Andrew password to the prompt]
Notice that the uppercase 'ANDREW.CMU.EDU' is significant. That's -1 (dash one) followed by a -l (dash el). For some SSH clients you must explicitly specify -1 to request the SSH version 1 protocol. With some clients, you may be able to login without the -1:
    unix> ssh -l bovik@ANDREW.CMU.EDU  chum.cmcl.cs.cmu.edu
    [then type your Andrew password to the prompt]

Q: I did everything you said but I still can't login. Now what?
A: Here are the most common reasons students can't login:

If you still can't login, please send mail to your instructor.

Fish Machines That Are Available to Students

Intel engineers traditionally use the names of North American rivers as internal names for their processor projects. So it seems fitting that we, as denizens of the Intel cluster, name the machines after freshwater fish of North America.

chum.cmcl.cs.cmu.edu flier.cmcl.cs.cmu.edu gobi.cmcl.cs.cmu.edu grayling.cmcl.cs.cmu.edu
inconnu.cmcl.cs.cmu.edu minnow.cmcl.cs.cmu.edu muskie.cmcl.cs.cmu.edu paddlefish.cmcl.cs.cmu.edu
perch.cmcl.cs.cmu.edu pickerel.cmcl.cs.cmu.edu pike.cmcl.cs.cmu.edu pumpkinseed.cmcl.cs.cmu.edu
salmon.cmcl.cs.cmu.edu sauger.cmcl.cs.cmu.edu shad.cmcl.cs.cmu.edu sheepshead.cmcl.cs.cmu.edu
sockeye.cmcl.cs.cmu.edu striper.cmcl.cs.cmu.edu sturgeon.cmcl.cs.cmu.edu walleye.cmcl.cs.cmu.edu
warmouth.cmcl.cs.cmu.edu whitefish.cmcl.cs.cmu.edu

Fish Machines Available to Teaching Staff Only

bass.cmcl.cs.cmu.edu bluegill.cmcl.cs.cmu.edu char.cmcl.cs.cmu.edu

About the Intel Cluster

The machines in the Intel Cluster are connected by a Cisco 3524 switch with 24 full-duplex 100 Mb/s ports and 2 full-duplex 1 Gb/s ports. The switching fabric has a peak bandwidth of 10.8 Gb/s and a maximum aggregate forwarding rate (from port to port) of 5.4 Gb/s.

Each node on the cluster runs Red Hat Linux 6.2 (Linux kernel 2.2.16) and consists of the following hardware:


Last modified: Sun Aug 29 18:04:17 EDT 2004