Date: Thursday, July 17, 2014 (09:00-12:00)

Who is affected:
Potentially, all users of CS Department infrastructure systems, to include
e-mail, web service, and penguins login machines.

What is happening:
During this window, the storage underlying the department\’s VMware
infrastructure will undergo minor repairs.

NO OUTAGE IS EXPECTED during this time, but this message is being sent in
the interest of disclosure in the unlikely event something goes wrong which
causes an outage.

Why is it happening:
One of the storage nodes underlying the department\’s VMware infrastructure
has a bad DIMM. So far, it is only generating correctable errors, but needs
to be replaced in order to avoid the potential for further problems.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this maintenance will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.
Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

It appears that the CS network is not reachable from the outside. We are en route to campus to troubleshoot the problem.

Update (23:05): It seems that the fiber link between the department and the main campus (and onward to the internet) is not working. Technicians are working to sort out the issue ASAP.

Update (01:35 7/13): A damaged fiber has been located and replaced. Network service to the CS Department should now be restored.

Date: Thursday, July 10, 2014 (05:00-08:00)

Who is affected:
All users of the CS department computing

What is happening:
We will be troubleshooting our file system, which will require for CS
storage to be rebooted. All services that depend upon access to storage
will be unavailable, including – cycle servers, ionic cluster, web content,
home directories, CIFS, etc.

Why is it happening:
This is necessary in order to fix a bug on our file system, which can cause
major NFS failures.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this downtime will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.

Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

Date: Thursday, July 3, 2014 (06:00-08:00)

Who is affected:
All users of the CS department computing

What is happening:
We will be patching our file system, which will require for CS storage to
be rebooted. All services that depend upon access to storage will be
unavailable, including – cycle servers, ionic cluster, web content, home
directories, CIFS, etc.

Why is it happening:
This is necessary in order to fix a bug on our file system, which can cause
major NFS failures.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this downtime will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.

Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

Date: Wednesday, July 2, 2014 (06:00-07:30)

Who is affected:
All users of CS Department networks, including systems in the CS Building;
221 Nassau; CITP; and the CS section of the HPCRC.

What is happening:
During this window, OIT Hardware Support will be replacing critical links
in the fiber paths that connect our network to other parts of the campus.
During these replacements, segments of our network will become unavailable
for brief periods.

Why is it happening:
OIT is in the process of relocating a major fiber hub site on campus. As
our building is one of those served by this hub site, our connections must
be rerouted as a result.

We do not expect extended outages resulting from this work, but you can
expect to see outages of a few minutes at a time for various segments of
the network.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this downtime will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.

Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

Date: Thursday, June 12, 2014 (08:00-13:00)

Who is affected:
All users of the CS department computing.

What is happening:
We are upgrading our storage firmware, which requires for CS storage to be
rebooted. We expect that some of the SMB/CIFS clients will have to
reconnect, but NFS service will be continuous. The rest of CS services
should not be affected.

Why is it happening:
This is necessary in order to install a backup accelerator, which will
allow for us to have better support for critical applications and
workloads.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this downtime will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.

Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

Update (10:17): A problem with the upgrade has resulted in an NFS outage. We apologize for the trouble and are working to restore service as quickly as possible.

Update (10:26): All service should now be restored.

Date: Thursday, June 5, 2014 (05:00-08:00)

Who is affected:
All users of the CS department computing

What is happening:
We are upgrading our file system, which requires for CS storage to be
shutdown. All services that depend upon access to storage will be
unavailable, including – cycle servers, ionic cluster, web content, home
directories, CIFS, etc.

Why is it happening:
This is necessary in order to install a backup accelerator, which will
allow for us to have a better support for critical applications and
workloads.

We will post updates to the status page: http://www.csstaff.org
as necessary.

If this downtime will cause you undue hardship, please contact
csstaff@cs.princeton.edu immediately, so we can discuss options to reduce
any negative impact. Your patience is appreciated.

Sincerely,
CS Staff
_______________________________________________
downtime mailing list
downtime@lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/downtime

Who is affected:
All users of the CS department computing and network infrastructure

What is happening:
We are physically moving our gateway router and core switch between racks within the second floor construction area and transitioning to new fiber uplinks. During this time, both wired and wireless networking will be unavailable in the CS building. All CS-based services will be unavailable including cycle servers, ionic cluster, e-mail, web content, DNS, DHCP, CIFS, etc. CS portions of the wired network will be unavailable in Sherrerd Hall (CITP), 221 Nassau (PlanetLab), and the Friend Center (010 Suite).

Why is it happening:
This is part of the renovation work.

Who is affected:
Most users in the CS Building

What is happening:
We will be temporarily disconnecting and then reconnecting many wired network ports over a wide swath of the CS Building. This specifically includes offices that have had their connections recently moved from one box to another. It also includes the uplink to room 002.

Why is it happening:
This is part of the network relocation that is part of the ongoing CS Building renovations.

As part of the network relocation work, we will need to bring down the
wireless network in the CS Building. This work will take place
6:00am-9:00am tomorrow morning (1/31/2014).