Edison Returns to Service
July 26, 2017 by Rebecca Hartman-Baker
We appreciate your patience during the upgrade of Edison to the latest operating system. I am pleased to report that we are returning Edison to users five days earlier than scheduled. At 4:00 pm Pacific time today, we will release the machine to users. Before you log in and begin working on Edison again, here are a few important things you should know.
Access to Edison -- New SSH Host Keys
Edison's SSH host keys have changed. You will see a warning and may be prohibited from logging on due to your ssh security settings. Under normal circumstances, we would encourage users to report this security warning to us. However, due to the change in host keys, this warning is expected and does not need to be reported.
Because the host key has changed, when you try to log in to edison.nersc.gov, which gets resolved to a particular IP address, your SSH client detects that the host key is not the same as the host key for Edison in the known_hosts file. It may abort with output warning you of the problem, leaving it up to the user to determine if this really is Edison, with a new identifier, or if you're being hacked.
On a Mac or Linux machine, the warning says "WARNING: REMOTE HOST IDENTIFICATION HAS CHANGED!" along with a reference to a man-in-the-middle attack and some other language designed to scare you.
In this case, because NERSC has informed you that the host keys for Edison have changed, you can safely go into your local computer's ~/.ssh/known_hosts file and delete any lines referencing edison, edisonXY (where X and Y are integers), or edison.nersc.gov (the warning message will tell you the offending line number). When you next log in to Edison, it will be as if you're logging in for the first time, and you'll be asked to confirm the host key (by typing "yes"). You'll also need to delete lines starting with "edimom" in your .ssh/known_hosts file in your NERSC global home directory (for interactive jobs).
On a Windows machine using PuTTY, a window with "WARNING - POTENTIAL SECURITY BREACH!" will appear, and inform you of the differing keys. You can choose to carry on connecting and update the key by selecting "Yes", carry on connecting without updating by selecting "No", or abandon the connection by selecting "Cancel". While under normal circumstances we would recommend selecting "Cancel" and informing NERSC, since NERSC has informed you of the new Edison host keys, you can safely select "Yes".
For more information, please see: https://www.nersc.gov/users/accounts/user-accounts/computer-security/ssh-key-fingerprints/
Edison Software -- You Must Recompile Your Codes
Edison has been upgraded to a completely new version of the OS. The implications of this change are as follows:
- You must recompile and relink all user codes. Old binaries will fail at startup with an initialization error.
- The default CDT on Edison has changed, meaning that the Cray library defaults have been updated to the latest versions. In addition, the Cray-provided fftw library is now called cray-fftw. Please see https://www.nersc.gov/users/computational-systems/edison/updates-and-status/timeline-and-updates/cdt-17-06-was-set-to-default-during-on-7212017/ for more details.
- Not all NERSC-provided libraries/software are available yet. We must recompile all libraries, and there has not been sufficient time for us to complete this task. We thought it was better to return the system to users now rather than wait for all software to be available. At the top of our to-do list are the binaries we supply to users, such as VASP.
- If there is a module available for the software in question, then we have completed its reinstallation, but may not have fully tested it. If you encounter an error in the available software or there is something that you require that is not available yet, please send in a ticket.
- User cron jobs are not yet available. Please send in a ticket if you wish to have a cron job restored.
- Lustre performance is currently poor. Cray engineers have been informed and are working to find the source of the problem.
- For the latest updates, please see http://www.nersc.gov/users/computational-systems/edison/updates-and-status/open-issues/remaining-issues-from-edison-cle-6-upgrade/
Python and Matlab on Edison -- Defaults Have Changed
- Old NERSC builds of Python on Edison (python/2.7.9) are obsolete. The default Python module on Edison is now python/2.7-anaconda-4.4. Python 3.6 is now available through python/3.6-anaconda-4.4. Older Anaconda-based installations of Python are still available (2.7-anaconda and 3.5-anaconda).
- The default version of MATLAB has been changed to R2016b. Version R2015b is still available by loading the R2015b module.
Running Jobs on Edison -- Update Your Job Scripts
- The SLURM affinity configuration settings have been changed, so most job scripts will need to be updated. The Jobscript Generator, available at https://my.nersc.gov/script_generator.php , has been updated to reflect the new affinity configuration settings, so we recommend using it to aid in updating your scripts.
- In addition, the large job discount ends just after midnight on Tuesday, August 1.
System Availability -- Reboots Possible Through the Weekend
- During the initial period of availability, it is possible that we will encounter some issues that will require us to kill all running jobs and reboot the machine. To accommodate for the potential instability, we will not charge user repos for the time through 11:59 pm, July 31 as we sort out any issues.