Summary PHYSGI Meeting 10/10/94
T. Throwe
Next Meeting:
The next meeting will be Monday, October 17, 11:30 - 12:00, in Rm. 2-160.
Production User Input for PHYSGI01:
- Representatives from E852 and E891 were present at this week's meeting.
- E852 is ready to begin production activity on data collected during the
recent AGS run. They expect the demand for time on PHYSGI01 to continue
into the foreseeable future.
- E891 will be getting beam next week (perhaps as early as the weekend of
the 15th) and expect to be running two jobs on PHYSGI01 after the usual
initial startup problems. They do not expect to have any demands for
time on PHYSGI01 for the present week.
- The representative from E891 (Al Saulys) feels that their present disk
allocation will be adequate.
All experiments which anticipate running more than an single occasional
production job during a given week should attend the
scheduling meeting. If that is not possible they should notify Bruce
Gibbard (gibbard@bnl.gov) and Tom Throwe (throwe@rsgi02.rhic.gov)
of their needs by Email prior to the Monday 11:30 meeting.
Plan for week beginning 10/10/94:
The following are the basic rules established to control the use of
resources on PHYSGI01.
With the conclusion of the AGS run these rules have been simplified
somewhat.
- A production process is defined as a process which would accrue an hour or
more of CPU time in 8 hours of uncontended running.
- Each experiment is currently allowed to run up to 6 concurrent
"production" processes. Only one of these 6 processes may be run at
full priority, (100).
- All "production" processes beyond the first are to be niced to 2 (102).
This allows for the possibility of assigning medium priority jobs, niced
to 1 (101), at some point in the future.
- Extended use of a tape drive is defined as use which extends for more
than 1 hour.
- In the presences of demand by other experiments for tape drives, no
experiment should make extended use of more than 2 tape drives.
- The tape stackers represent a relatively scarce resource. It is hoped
that negotiation between users will result in mutually acceptable
sharing. If users find that not to be the case, rules will be established
to guarantee sharing which is as equitable as possible, consistent with
the overall mission of the PHYSGI computing system.
Other issues:
-
As stated in the 8/8/94 summary, there
were numerous reports of network problems and Charybdis, the router
serving Physics, was scheduled for an upgrade. The upgrade of Charybdis
has occurred. Please report any current network problems to your
network contact person.
-
The interaction of private multi-cast tunnels with MBone (desk top video
conferencing) tunnels has the potential for substantially increasing
network traffic. In the absence of an important need for such tunnels,
their use is discouraged on subnets in the Physics Department.
Users of PHYSGI01 are still strongly encourage to set a
mail forward
from their working account on PHYSGI01 to an account on a machine where
they frequently check their mail so that they can be easily contacted.