Georgia Advanced Computing Resource Center

Aug 22 outage

"W" means "don't know When this task will be done"

Soon: /etc/motd on pcluster, zcluster

Sometime Tuesday: message to users

2 PM: VM snapshots

3 PM:
  disable logins pcluster
  disable logins zcluster (except for jkissing, students)

  kick users off pcluster
  kick users off zcluster?

  drain all nodes or queues, pcluster
  disable all queues except somedevq, zcluster

  kill all jobs pcluster
  kill all jobs zcluster

  do GE jobs testing MPI and storage I/O throughput
    CC to use fsr15 for iozone
    ST to use fsr12 for MPI/NAMD
    PB to use fsr7 for dumb I/O

  stop execd on all nodes, zcluster

	      W: shut down racks 8,9,10,11

4 PM:
 modify PanFS blksize on remaining nodes
 shut down VMs
 shut down 3070s
 shut down Panasas 

 morning             W: enable Panasas jumbo frames
 morning             W: VMware updates
 connect ESX IPMI cat5
	       W: "final rsyncs" of /db, /usr/local
              W: Curtis reconfig storage unit NICs/LAGs
              W: PanFS 16K blksize on remaining nodes and zcluster.rcc

---

by 5PM:
we tell NEG "go ahead"


probably between 9 and 12PM, NEG at work.

---

****  AFTER ******
"Midnight" (when NEG is done):
power up 3070s
power up Panasas
power up ESX servers and VMs
start final rsyncs
power up racks 8,9,10,11

"Morning" (starting by 8AM)

panasas OS upgrade
switch and test /db, /usr/local mounts on the zcluster

do GE jobs testing MPI and storage I/O throughput

   W: GE upgrade
   W: yum updates of nodes
   W: yum update of zhead
   W: update FW on Dells
   W: move some rack15 nodes to rack 16?
   W: reinstall rack11?
   W: thumper upgrades
   W: rccstor upgrades 

switch and test NFS mounts on pcluster

   W: upgrade PGI compiler

reenable queues on zcluster
resume queues on pcluster

enable logins pcluster
enable logins zcluster

email users that outage is over
contact Lab Storage users about their mounts