RAL-LCG2-Tier-1

From GridPP Wiki
Revision as of 14:11, 25 July 2012 by Stephen jones (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

RAL-LCG2-Tier-1

Topic: HEPSPEC06



RAL Tier-1
Generation config, CPU OS Kernel 32/64 mem gcc Total Per Core Notes
2007 Streamline dual Intel E5410 @ 2.33GHz SL5.4 - 32bit on 64bit OS 16GB gcc version 66.537 8.317
2007 Clustervision dual Intel E5440 @ 2.83GHz SL5.4 - 32bit on 64bit OS 16GB gcc version 75.617 9.452
2008 Streamline dual Intel L5420 @ 2.50GHz SL5.4 - 32bit on 64bit OS 16GB gcc version 69.547 8.693
2008 Viglen dual Intel E5420 @ 2.50GHz SL5.4 - 32bit on 64bit OS 16GB gcc version 70.760 8.845
2009 Viglen dual Intel E5520 @ 2.26GHz SL5.4 - 32bit on 64bit OS 24GB gcc version 92.593 11.574 Average All Units
2009 Streamline dual Intel E5520 @ 2.26GHz SL5.4 - 32bit on 64bit OS 24GB gcc version 92.170 11.521 Average All Units
2010 Clustervision/Dell dual Intel X5650 @ 2.66GHz SL5.4 - 32bit on 64bit OS 48GB gcc version 166.410 13.868 Average All Units
2010 Viglen dual Intel X5650 @ 2.66GHz SL5.4 - 32bit on 64bit OS 48GB gcc version 156.030 13.003 Average All Units
2011 Viglen dual Intel E5645 @ 2.40GHz SL5.4 - 32bit on 64bit OS 48GB gcc version - - Average All Units
2011 Dell dual X5650 @ 2.66GHz SL5.4 - 32bit on 64bit OS 48GB gcc version - - Average All Units



This page is a Key Document, and is the responsibility of Rob Harper. It was last reviewed on 2012-03-15 when it was considered to be 0% complete. It was last judged to be accurate on (never).



Topic: Middleware_transition


gLite3.1/SL4


WMS - 3 nodes v3.1.32-0.slc4

LCG-CE - 1 node v3.1.37-0 (planned to be migrated to glite3.2 CREAM, not scheduled yet)

PROXY - v3.1.29-0

gLite3.2/EMI


APEL - v3.2.5-0.sl5

ARGUS - n/a

BDII_site - 3 nodes v3.2.10-1.sl5

BDII_top - 5 nodes v3.2.10-3.sl5

CE (CREAM/LCG) - 4 CREAM nodes v3.2.10-0.sl5, 1 CREAM node v3.2.6-0.sl5

FTS - v3.2.1-2.sl5 (Oracle backend)

glexec - v3.2.2-2.sl5

LB - 2 nodes v3.2.12-11.sl5

LFC - 7 nodes v3.2.7-2 (Oracle backend)

SE - Castor 2.1.10-0

UI - v3.2.10-1.sl5

VOBOX - v3.2.11-0.sl5

WMS - n/a

WN - v3.2.7-0

Comments


Plan to virtualize further Grid Services deployments using Microsoft Hyper-V

Regarding migration to EMI/UMD, no work yet, but would prefer to have access to some installation and maintenance recipes supported by developers (similar to what does exist for gLite).

Topic: Protected_Site_networking


  • Tier1 is a subnet of the RAL /16 network
  • Two overlaid subnets: 130.246.176.0/21 and 130.246.216/21
  • Third overlaid /22 subnet for Facilities Data Service
  • To be physically split later as traffic increases
  • Monitoring: Cacti with weathermaps
  • Site SJ5 link: 20Gb/s + 20Gb/s failover direct to SJ5 core two routes (Reading, London)
  • T1 <-> OPN link: 10Gb/s + 10Gb/s failover, two routes • T1 <-> Core 10GbE • T1 <-> SJ5 bypass: 10Gb/s • T1 <-> PPD-T2: 10GbE
  • Limited by line speeds and who else needs the bandwidth


File:Tier1-network.jpg


Topic: Resiliency_and_Disaster_Planning




      • This section intentionally left blank


Topic: SL4_Survey_August_2011





      • This section intentionally left blank


Topic: Site_information


Memory

1. Real physical memory per job slot:

All WNs have 2GB/core (1 job slot per core).

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

Dependent on queue : 500M,700M,1000M,2000M,3000M

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

no limit

4. Number of cores per WN:

4 or 8 depending on hardware.

Comments:

Network

1. WAN problems experienced in the last year:

2. Problems/issues seen with site networking:

3. Forward look:

Plan for doubled 10GbE (20Gb/s) for internal links and doubling of existing links as needed.

Comments:

Topic: Site_status_and_plans



SL5 WNs

Current status (date): 19/11/2009 All LHC accessible WNs are SL5,

Planned upgrade: None

Comments:

SRM

Current status (date):

Planned upgrade:

Comments:

SCAS/glexec

Current status (date): 10/05/2011 SCAS deployed, intend to look at ARGUS but delayed due to staff changes.

Planned deployment:

Comments:

CREAM CE

Current status (date): 10/05/2011 CREAM CEs available for all VOs, planning reinstallation of remaining 2 lcg-CEs

Planned deployment:

Comments: