Difference between revisions of "UKI-SOUTHGRID-BRIS-HEP"

From GridPP Wiki
Jump to: navigation, search
 
(No difference)

Latest revision as of 14:25, 25 July 2012

UKI-SOUTHGRID-BRIS-HEP

Topic: HEPSPEC06


UKI-SOUTHGRID-BRIS-HEP
OS+cores,Bits OS Kernel 32/64 mem gcc Total Per Core
Dual Xeon E5405 2.0GHz SL5.3 2.6.18-128.4.1.el5 64 16GB 4.1.2 59.705 7.46
Dual AMD Opteron 2378 2.4GHz SL5.3 2.6.18-164.9.1.el5 64 16GB 4.1.2 74.34 9.2925


Topic: Middleware_transition


  • StoRM v1.3 SE (lcgse02.phy.bris.ac.uk) is still SL4 as is its slave gridftp server gridftp01.phy.bris.ac.uk. StoRM v1.4 & 1.5 are not supported on SL5, and StoRM v1.6 & 1.7 (supported on SL5) are very unstable & not production ready yet (just ask Chris Walker who's had ++painful experience with them). Waiting on stable StoRM for SL5 - soon hopefuly.


  • lcgnetmon (owned+operated by RAL) is still SL4 AFAIK


gLite3.2/EMI


ARGUS : Not yet

BDII_site : gLite 3.2

CE (CREAM/LCG) : 2 x gLite 3.2 CREAM-CE

glexec : Not yet

SE : see above

UI : gLite 3.2

WMS : Ain't got one (content to use others')

WN : gLite 3.2

Comments


Topic: Protected_Site_networking



      • This section intentionally left blank


Topic: Resiliency_and_Disaster_Planning



      • This section intentionally left blank


Topic: SL4_Survey_August_2011

  • lcg-CE (lcgce04.phy.bris.ac.uk ) planning to upgrade to cream-ce very soon.


  • StoRM v1.3 SE (lcgse02.phy.bris.ac.uk) is still SL4 as is its slave gridftp server gridftp01.phy.bris.ac.uk. StoRM v1.4 & 1.5 are not supported on SL5, and StoRM v1.6 & 1.7 (supported on SL5) are very unstable & not production ready yet (just ask Chris Walker who's had ++painful experience with them). Waiting on stable StoRM for SL5 - soon hopefuly.


  • lcgnetmon (owned+operated by RAL) is still SL4 AFAIK


Topic: Site_information


Memory

1. Real physical memory per job slot:

  • PP-managed cluster: Old WN (being phased out ASAP): 512MB/core; New WN: 2GB/core
  • HPC-managed cluster: 2GB/core

2. Real memory limit beyond which a job is killed:

  • None known (Unix default = unlimited) (both clusters)

3. Virtual memory limit beyond which a job is killed:

  • None known (Unix default = unlimited) (both clusters)


4. Number of cores per WN:

  • PP-managed cluster: Old WN (being phased out ASAP) 2 cores; New WN: 8 cores
  • HPC-managed cluster: 4 cores

Comments:

Network

1. WAN problems experienced in the last year:

  • None

2. Problems/issues seen with site networking:

  • None

3. Forward look:

  • Uni link to SWERN either will be or already is upgraded to 2.5Gbps AFAIK


Comments:

Topic: Site_status_and_plans



SL5 WNs

Current status (date): (Dec 2009) VM CE in production with SL5 WN passing all OPS SAM tests. More WN soon.

SRM

Current status (date): 1.6.11-3sec
Planned upgrade: No plans to upgrade, plan to retire DPM in Dec 2009.

StoRM SE must be upgra^H^H^H^H^H rebuilt (there's no upgrade path!) to 1.4 & enable other VO support on it.

ARGUS/glexec

Current status (date): Not yet installed (22.3.11)

Planned deployment: Waiting to hear how it goes elsewhere first.

Comments:

CREAM CE

Current status (date): Installed and working (22.3.11)

Planned deployment:

Comments: