Turning on/off nodes on red.
This is a short tutorial on how to turn nodes on and off on red.
First of all, you will need a username and password. Please email mako for this information as I do not want to post it here for obvious reasons.
All of the compute nodes and the headnode can be power cycled through the APC power strips. Please note that apc03 is currently off it's network. I just notified TeamHPC to get a replacement, and hope to get this corrected during our next downtime.
You can see where all of the nodes are located on /etc/apc.map on the headnode. The first column is the name of the APC power strip, the second column is the power port it's on, and the last is the node that is on that port. For instance, "apc01 7 node034" tells me that to control node034, I should telnet to apc01, go to controlling port 7.
Let's take this node034 example and go through how to power cycle the node. The information in green is what you will need to type in.
[root@red etc]# telnet apc01
Trying 172.16.102.1...
Connected to apc01 (172.16.102.1).
Escape character is '^]'.
User Name : getthisfrommako
Password : *************
American Power Conversion Network Management Card AOS v2.2.7
(c) Copyright 2002 All Rights Reserved Rack PDU APP v2.2.0
-------------------------------------------------------------------------------
Name : Unknown Date : 08/04/2006
Contact : Unknown Time : 10:19:25
Location : Unknown User : Administrator
Up Time : 3 Days 23 Hours 14 Minutes Stat : P+ N+ A+
Switched Rack PDU: Communication Established
------- Control Console -------------------------------------------------------
1- Device Manager
2- Network
3- System
4- Logout
<ESC>- Main Menu, <ENTER>- Refresh, <CTRL-L>- Event Log
> 1
------- Device Manager --------------------------------------------------------
1- Phase Monitor/Configuration
2- Outlet Restriction Configuration
3- Outlet Control/Configuration
4- Power Supply Status
<ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> 3
------- Outlet Control/Configuration ------------------------------------------
1- Outlet 01: Outlet 1 ON
2- Outlet 02: Outlet 2 ON
3- Outlet 03: Outlet 3 ON
4- Outlet 04: Outlet 4 ON
5- Outlet 05: Outlet 5 ON
6- Outlet 06: Outlet 6 ON
7- Outlet 07: Outlet 7 ON
8- Outlet 08: Outlet 8 ON
9- Outlet 09: Outlet 9 ON
10- Outlet 10: Outlet 10 ON
11- Outlet 11: Outlet 11 ON
12- Outlet 12: Outlet 12 ON
13- Outlet 13: Outlet 13 ON
14- Outlet 14: Outlet 14 ON
15- Outlet 15: Outlet 15 ON
16- Outlet 16: Outlet 16 ON
17- Outlet 17: Outlet 17 ON
18- Outlet 18: Outlet 18 ON
19- Outlet 19: Outlet 19 ON
20- Outlet 20: Outlet 20 ON
21- Outlet 21: Outlet 21 ON
22- Outlet 22: Outlet 22 ON
23- Outlet 23: Outlet 23 ON
24- Outlet 24: Outlet 24 ON
25- Master Control/Configuration
<ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> 7
------- Outlet 07: Outlet 7 ---------------------------------------------------
Name : Outlet 7
Outlet : 7
State : ON
Phase : 1
1- Control Outlet 7
2- Configure Outlet 7
?- Help, <ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> 1
------- Control Outlet --------------------------------------------------------
Name : Outlet 7
Outlet : 7
State : ON
Phase : 1
1- Immediate On
2- Immediate Off
3- Immediate Reboot
4- Delayed On
5- Delayed Off
6- Delayed Reboot
7- Cancel
?- Help, <ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> 6
-----------------------------------------------------------------------
Delayed Reboot
This command will delay for 0 seconds, shutdown
outlet 7 named 'Outlet 7', delay for 5 seconds,
and then restart.
Enter 'YES' to continue or <ENTER> to cancel : YES
Command successfully issued.
Press <ENTER> to continue...
------- Control Outlet --------------------------------------------------------
Name : Outlet 7
Outlet : 7
State : OFF*
Phase : 1
1- Immediate On
2- Immediate Off
3- Immediate Reboot
4- Delayed On
5- Delayed Off
6- Delayed Reboot
7- Cancel
?- Help, <ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> <ENTER>
------- Control Outlet --------------------------------------------------------
Name : Outlet 7
Outlet : 7
State : ON
Phase : 1
1- Immediate On
2- Immediate Off
3- Immediate Reboot
4- Delayed On
5- Delayed Off
6- Delayed Reboot
7- Cancel
?- Help, <ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> <ESC>
------- Outlet 03: Outlet 3 ---------------------------------------------------
Name : Outlet 3
Outlet : 3
State : ON
Phase : 3
1- Control Outlet 3
2- Configure Outlet 3
?- Help, <ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> <ESC>
------- Outlet Control/Configuration ------------------------------------------
1- Outlet 01: Outlet 1 ON
2- Outlet 02: Outlet 2 ON
3- Outlet 03: Outlet 3 ON
4- Outlet 04: Outlet 4 ON
5- Outlet 05: Outlet 5 ON
6- Outlet 06: Outlet 6 ON
7- Outlet 07: Outlet 7 ON
8- Outlet 08: Outlet 8 ON
9- Outlet 09: Outlet 9 ON
10- Outlet 10: Outlet 10 ON
11- Outlet 11: Outlet 11 ON
12- Outlet 12: Outlet 12 ON
13- Outlet 13: Outlet 13 ON
14- Outlet 14: Outlet 14 ON
15- Outlet 15: Outlet 15 ON
16- Outlet 16: Outlet 16 ON
17- Outlet 17: Outlet 17 ON
18- Outlet 18: Outlet 18 ON
19- Outlet 19: Outlet 19 ON
20- Outlet 20: Outlet 20 ON
21- Outlet 21: Outlet 21 ON
22- Outlet 22: Outlet 22 ON
23- Outlet 23: Outlet 23 ON
24- Outlet 24: Outlet 24 ON
25- Master Control/Configuration
<ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> <ESC>
------- Device Manager --------------------------------------------------------
1- Phase Monitor/Configuration
2- Outlet Restriction Configuration
3- Outlet Control/Configuration
4- Power Supply Status
<ESC>- Back, <ENTER>- Refresh, <CTRL-L>- Event Log
> <ESC>
------- Control Console -------------------------------------------------------
1- Device Manager
2- Network
3- System
4- Logout
<ESC>- Main Menu, <ENTER>- Refresh, <CTRL-L>- Event Log
> 4
Connection Closed - Bye
Connection closed by foreign host.
[root@red etc]#
----------
To reboot the headnode, you will need to turn apc01 port 1 off, then go to apc02 and turn off and on port 24, then turn apc01 port1 back on again. This is due to the redundant power supplies ont he headnode.