Difference between revisions of "UKI-NORTHGRID-MAN-HEP"

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

Latest revision as of 14:23, 25 July 2012

UKI-NORTHGRID-MAN-HEP

Topic: HEPSPEC06


UKI-NORTHGRID-MAN-HEP
OS+cores,Bits OS Kernel 32/64 mem gcc HT on/off Total Per Core Per HW Thread
Dual CPU, Intel Xeon @ 2.80GHz SL 4.4 2.6.9-42.0.3.ELsmp 32bit 4GB 3.4.6 off 10.85 5.43 5.43
Dual CPU, Intel Xeon @ 2.80GHz SL 5.3 2.6.18-128.7.1.el5 64bit 4GB 4.1.2 off 12.54 6.27 6.27
Dual 6 cores, Intel X5650 @ 2.67GHz SL5.3 2.6.18-194.17.4.el5 64bit 48GB 4.1.2 off 164.40 13.70 13.70
Dual 6 cores x 2 HTs, Intel X5650 @ 2.67GHz SL5.3 2.6.18-194.17.4.el5 64bit 48GB 4.1.2 on 211.62 17.64 8.82


Topic: Middleware_transition


All services are x86_64, SL5 and glite3.2

gLite3.2/EMI


ARGUS glite-ARGUS-3.2.4-2


BDII_site glite-BDII_site-3.2.11-1.sl5


BDII_top  glite-BDII_top-3.2.11-1.sl5


CE (CREAM) glite-CREAM-3.2.10-0.sl5 (ce01), glite-CREAM-3.2.11-2.sl5 (ce02)


glexec glite-security-glexec-0.7.0-2.sl5 (ce02)


SE glite-SE_dpm_mysql-3.2.7-2.sl5 (head node), glite-SE_dpm_disk-1.8.0-1.sl5 (data servers)


UI glite-UI-version-3.2.8-0.sl5


WN  glite-WN-version-3.2.10-0.sl5


Comments


Same as Liverpool.

Topic: Protected_Site_networking


7th June ops meeting: Own network, skips univeristy. Have a few subnets. Uses number of tools - weathermap, RRD graphs on each switch.

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: 2 GB

2. Real memory limit beyond which a job is killed: None

3. Virtual memory limit beyond which a job is killed: None

4. Number of cores per WN: 2

Comments:

Network

1. WAN problems experienced in the last year: None

2. Problems/issues seen with site networking: None

3. Forward look:

Comments:

Topic: Site_status_and_plans



SL5 WNs

Current status (date): SL5 (21/10/09)

Planned upgrade: Upgrade to SL5 on all the nodes completed on 15/10/09

Comments:

SRM

Current status (date): DPM 1.7.2 (21/10/09)

Planned upgrade: Upgrade to DPM 1.7.2 on both SEs completed on the 16/10/09

Comments: currently proceeding to unify the two DPM instances as requested by atlas. Head node and pools all SL4.

ARGUS/glexec

Current status (21 Jun 11): ARGUS server installed and tested

Planned deployment: glexec is installed and currently partially configured on WNs

Comments:

CREAM CE

Current status (3 May 11): Both CEs are CREAM CE.

Planned deployment:

Comments: