[Beowulf] number of admins

[Alan Louis Scheinine]

Other people can give information about failure rates.
Generally speaking with a 1000 nodes will may often be
replacing the hard disks if each node has a low-cost HD.

The amount of time depends alot on learning tricks to
reduce the amount of work, such as making sure users
do not keep data on the nodes of the cluster because
if a node breaks you may spend alot of time recovering
data by putting the disk on another machine (for example)
if a user says the data is essential.  So it must be
clear that local disks are purely scratch.  Once you've
found ways to reduce the cluster maintenance workload
the amount of time depends on the quality of service that
you need to provide.

If some users know very little of using a shell, will the
system administrator be expected to explain simple things?
It can take a large amount of time to explain how to setup
a .profile file when there are many optional software packages
and the users does not know basic ideas such as what is an
environmental variable.  Will the sysadmin be permitted to
say, "ask your colleague who uses the same programs"?

Also, for some software the setup of the license can be
very time consuming as far as communicating with the vendor.
In theory simple, in practice sometimes days of phone calls
and email.

The sysadmin should document what he or she does when installing
specific software, setting up a backup script or solving problems
that might arise more than once.  But writing the docs can
be time-consuming.

Alan
-- 

  Centro di Ricerca, Sviluppo e Studi Superiori in Sardegna
  Center for Advanced Studies, Research, and Development in Sardinia

  Postal Address:               |  Physical Address for FedEx, UPS, DHL:
  ---------------               |  -------------------------------------
  Alan Scheinine                |  Alan Scheinine
  c/o CRS4                      |  c/o CRS4
  C.P. n. 25                    |  Loc. Pixina Manna Edificio 1
  09010 Pula (Cagliari), Italy  |  09010 Pula (Cagliari), Italy

  Email: scheinin at crs4.it

  Phone: 070 9250 238  [+39 070 9250 238]
  Fax:   070 9250 216 or 220  [+39 070 9250 216 or +39 070 9250 220]
  Operator at reception: 070 9250 1  [+39 070 9250 1]
  Mobile phone: 347 7990472  [+39 347 7990472]