r9 - 21 Jul 2010 - 07:18:09 - MichaelErnstYou are here: TWiki >  Admins Web > FabricUpgradeP13


  • Introduction
  • Place here anticipated hardware upgrade activities anticipated during this quarter (FY10Q3, April 1 - June 30, 2010).
  • Update SiteCertificationP13 with progress, as appropriate.
  • At the end of the quarter we will update the US ATLAS Facility spreadsheet with newly deployed storage and compute resources (c.f. CapacitySummary).


  • 247 compute servers (1976 cores), Dell R410, 2.8 GHz, 24 GB memory, 2 TB disk
  • 1 DDN S2A? 9900, 1200*2TB disks (~2 PB usable space), 4 frontend data servers Dell R710 w/ 2*10 GE each


  • Two storage servers, Dell R710
    • Each storage server will have 4 MD1200, each with 12 2TB disks configured as RAID-6 via H800 controllers


  • Compute node upgrade for MWT2_IU - planning phase during this quarter, procurement next quarter.


  • Add 1 rack 336TB of storage to GPFS (to be repeated twice more, in the quarter if possible).


  • OU: We just got two new storage servers, Dell R710, and 31 new compute nodes, Dell R410
    • The storage servers have 175 TB (usable) of Lustre storage attached, and the compute nodes have 24 GB of RAM and a 1 TB SATA drive each


  • Ordered 7 R710 (each with 48GB and 10Gb), 42 MD1000s (each will be configured as Raid-6 with 1 hot spare).

-- RobertGardner - 04 May 2010

About This Site

Please note that this site is a content mirror of the BNL US ATLAS TWiki. To edit the content of this page, click the Edit this page button at the top of the page and log in with your US ATLAS computing account name and password.


Powered by TWiki
This site is powered by the TWiki collaboration platformCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback