Survey of Computing at Some European HEP Labs
SLAC Trip, December, 1993
R. Les Cottrell, Richard Dubois, Tony Johnson, Randy Melen
EXECUTIVE OVERVIEW
Visits to CERN, DESY and RAL were made during Dec 1993 to continue
discussions with colleagues on current activities and future plans for
support of computing and networking. In particular we focussed on
issues raised by the SLAC Computer Advisory Committee concerning the
distributed environment and client server computing and how to migrate
from today's supported systems to those we will need towards the end of
this century. While in England, Cottrell took the opportunity to
discuss the European Networking scene with ex SLACers at DANTE in
England.
VM
All three Labs are downsizing their IBM mainframe operations. CERN
hopes to phase out the service by end 1996, DESY is moving
production work to Unix, RAL have downsized from an IBM 3090-600 to
a 3090-400 and expect to continue this downsize as users move
elsewhere. CERN has assigned one FTE in the CN division to
coordinate the move from VM. L3 at CERN is looking at developing
some tools to facilitate moving REXX execs to Unix.
VMS
CERN and DESY are "rightsizing" their central VMS clusters allowing
for an increase or decrease in VMS CPU power in future. This is
being accomplished by converting to scalable ALPHA based clusters and
removing their VAX 9000 and associated HSC based peripherals. Both
CERN & DESY expect to continue to support VMS in the medium term and
have no timetable for terminating VMS support. Both labs are
converting to SCSI based disks, and to providing VMS tape access via
a Unix staging system based on code from CERN. All labs appear to
have very advantageous software licensing relationships with DEC,
akin to that of Stanford University and much better than that enjoyed
by SLAC.
UNIX
We received strong confirmation that the move from mainframe
computing to distributed computing is correct. In particular, the
move to Unix is clearly happening elsewhere.
There are no winners yet on sophisticated batch systems for
workstation farms. Other labs are looking to see if SLAC will
provide leadership and repeat the success of the SLAC Batch
Monitor.
CERN and DESY in particular have done some collaborative work on a
consistent UNIX environment and interface. They recognize the need
for site-wide coordinated user accounts and are working towards that
goal. The direction at all labs is towards dedicated servers running
a single service.
The management of software costs in the distributed
environment is becoming a critical issue at all labs, requiring
considerable effort to negotiate reasonable site licenses and
investing in license server technology. With the rapid advances
in technology, all labs recognize the need for more agility
and flexibility in procurements. Vendor partnerships are being
pursued at all labs in order to leverage skills.
Both CERN and DESY have are doing some work with MPP technology
(CERN's Meiko, DESY's APE, Zeuthen's IBM SP-1) for their
theoreticians.
Data Management
There is no clear winner or even contender for a commercial product
for staging software. It is worthwhile to examine CERN's SHIFT
software mounted on a high speed network (FDDI speeds or better) as
a staging service for compute servers at SLAC.
The future of high density tape storage does not have a clear winner
yet but SLAC is uniquely positioned with partnerships and/or
proximity with Storage Tek, IBM, and Ampex.
Further confirmation was received that 8mm tape backup is not
reliable for other than streaming I/O (such as backups). However it
is important for importing and exporting data with other sites. RAL
have had considerable success with DAT technology and strongly
prefers it to 8mm.
Physics Applications
PAW is the analysis tool of choice by CERN and DESY experiments.
There are many complaints about the reliability and speed of the
COMIS macro facility.
GEANT users can expect to see a 2x improvement in speed in version
3.17 from geometry optimization.
Bulk processing is run on UNIX farms. At CERN, analysis is run on
VMS and VM where access to tapes is easier. DESY does not have much
of a VMS presence in the offline analysis environments.
CERN and DESY have become accustomed to data volumes and CPU needs
far in excess of SLD's.
PCs & Macs
CERN is actively developing PC, Mac and Unix environments to enable
them to manage large numbers of users in a cost effective fashion
and provide services that are more attractive than VM. The CERN PC
management environment appears to be the most advanced and is worthy
of serious consideration at SLAC.
All Labs recognize the importance of central support for Macs and PCs
and the necessity to provide coordinate sensible software licensing,
recommend configurations, coordinate maintenance and training, provide
backup services etc. Without this central role, they feel entropy
rapidly increases and the costs of running the environment are hidden
and become unmanageable.
Both CERN & RAL appear to have large support
efforts for PCs and Macs, with over a dozen people at CERN and 6 at RAL.
RAL also put together a task force to address the needs for Office
Systems. They have made considerable progress and their reports are
well worth reviewing for applicability at SLAC.
Networking
All Labs are actively increasing the capacities of their LANs. At
the moment they are using FDDI to meet the backbone and major volume
server needs. Both CERN & DESY have invested in DEC Gigaswitches
for non blocking FDDI access. CERN, who got in on the early
Gigaswitch deployment have found it to be very complex. CERN and
RAL are also moving away from a bridged network to a routed network.
CERN and RAL are working with pilot ATM experiments to understand
the next generation technology that they feel will most likely
be successful in the second half of the 90's.
European wide area networking is less centrally coordinated than the
US, and efforts to coordinate the networks European wide are in
their early stages.