'''Hardware bugs''' * #1298 Suspect bad memory * #1299 Verify that MCE is enabled in the BIOS of all wave #2 nodes * #1300 Configure the firewall services module in IPP core * #1301 Figure out why alala can't rebuild it's raid set * #1302 Test bonding on master.ipp * #1303 Figure out why ippdb02 crashes when the array verification runs * #1304 ipp000 has a dead CPU socket * #1305 Security issue: the kernel on all nodes needs to be upgraded to 2.6.30.x * #1306 2nd PDU in cab3 needs to be installed * #1307 Where is ippdb00? * #1308 Fix dead disk bays * #1309 Update kernel + OS image on all MHPCC nodes * #1310 Find fan modules for ipp037 ---- * [wiki:Production_Cluster_Status Production Cluster Status] * [wiki:Production_Cluster Production Cluster Logs] * [wiki:NebulousVolumes Nebulous Volume Logs] * [wiki:ipp_production_cluster Production Cluster Device Map] * [http://ganglia.pan-starrs.ifa.hawaii.edu/?c=IPP%20Production&m=&r=day&s=descending&hc=4 Production Cluster Ganglia (performance monitor)] * [wiki:Development_Cluster_Status Development Cluster Status] * [wiki:Development_Cluster_Logs Development Cluster Logs] * [wiki:Development_Cluster_Device_Map Development Cluster Device Map] * [http://ganglia.pan-starrs.ifa.hawaii.edu/?c=IPP%20Development&m=&r=hour&s=descending&hc=4 Development Cluster Ganglia (performance monitor)] * [wiki:Development_Cluster_Uses Development Cluster Uses] ---- * [wiki:PortForwardedHostTable IPP Host Port Forward Table] : SSH Config entries to simplify access to IPP machines with private IP addresses * [wiki:HowTo_ClearingNFS_HangUps HowTo: Clearing NFS Hang-ups] * [wiki:Wave4TaskList Wave4 Task List] * [wiki:AlalaRAIDMap Alala disk sled -> RAID port map] * [wiki:PomaRAIDMap Poma disk sled -> RAID port map] * [wiki:GentooImageUpdate-profile-10.0 Gentoo Image Update Profile 10.0] * [wiki:GentooImageUpdate Gentoo Image Update] * [wiki:ProductionSpareDiskStockpile Spare Disk Stockpile @ MHPCC] * [wiki:HowToArecaArrayVerification HowTo: Areca Array Verification] * [wiki:HowToInstallConsoleUtil HowTo: Install console utility] * [wiki:RecommendedLinuxSysctls Linux sysctl's for GigE TCP/IP] * [wiki:HowToInstall3Ware9690SAOnLinux2622 Install 3Ware 9690SA RAID card from a Linux 2.6.22 boot cd] * [wiki:GentooStage4Build Gentoo Stage 4 build] * [wiki:IPPGentooPackages The IPP Gentoo portage configuration and overlay] * [wiki:IPPConfigSystem The IPP nodes configuration file management system] * [wiki:NebdiskdAlerts nebdiskd alert emails] * [wiki:CatalystIsos Catalyst ISOs] * [wiki:HowToCheckTheRaid HowTo: Check raid status] ---- Useful docs * 802.3ad (LACP) ethernet link aggregation * [http://www.gentoo.org/doc/en/handbook/handbook-x86.xml?part=4&chap=3] * [http://www.linuxfoundation.org/en/Net:Bonding] * [http://www.cisco.com/en/US/tech/tk389/tk213/technologies_configuration_example09186a008089a821.shtml] * textex -> texlive migration [http://www.gentoo.org/proj/en/tex/texlive-migration-guide.xml] ---- MHPCC Address and Phone Numbers Maui High Performance Computing Center 550 Lipoa Parkway Kihei, Maui, HI 96753 Telephone: (808) 879-5077 Fax: (808) 879-5018 MHPCC Computer Room: (808) 879-5077 ext. 318 {{{ Email: mhpcc-help@mhpcc.hpc.mil * Primary point of contact is Brad Thomas brad.thomas.ctr@mhpcc.hpc.mil * Secondary POC is Eddie Domingo eddie.domingo.ctr@mhpcc.hpc.mil * OLD From 2009-08-1 -> -10, POC is Steve Gima gima@mhpcc.hpc.mil * Manager is Lance Terada lancer@mhpcc.hpc.mil }}} [wiki:WeekendDiskChanges Weekend Disk Changes] ---- Vendors IPP waves #1 and #3: ASA Computers [http://www.asaservers.com/showpages.asp?pid=1268] Point of sales contact is: Alok K Srivastav {{{ ASA Computers Inc. 645 National Ave Mountain View, CA 94043 Phone: 650-230-8000 Toll Free: 1-800-REAL-PCS FAX: 650-230-8090 Sales E-mail: sales@asacomputers.com tech support: tech1@asacomputers.com 6-9 AM PST Tech support number: 650-230-8050 8-5 PM PST Tech support number: 650-230-8020 Customer Service: cs@asacomputers.com }}} IPP Wave #2 YMI/Rackmountpro [http://www.rackmountpro.com/contactus.aspx] Sales point of contact is Patrick Lam . {{{ Sales/Product/Order Inquiry Hours: M-F 8:30AM - 5:30PM PST Tel: (800) 526-8650 Fax: (626) 956-0098 sales@rackmountpro.com Technical Support Hours: M-F 8:30AM - 5:30PM PST Tel: (800) 526-8650 support@rackmountpro.com }}} IPP wave #3 DB machines {{{ Mike Martin - Senior Account Executive Aberdeen LLC 562-699-6998 or 800-552-6868 ext 142 / 562-695-5570 Fax mikem@aberdeeninc.com / http://www.aberdeeninc.com }}} ---- == IPP Production Cluster Hardware == Note: Wave1 of the cluster has been upgraded. The following describes the current configuration. {{{ #!html }}} The IPP Production Cluster currently has 66 storage nodes, 3 database nodes, 69 compute nodes (138 total) with the following configuration: === Storage Nodes === * 18 ASA 5U Chenbro RM5U51924B Chassis (wave1 - refurbished) * Dual Quad-core Intel(R) Xeon(R) CPU E5620 @ 2.40GHz * 12M L3 cache * 24GB DDR3-1333 RAM * 40TB RAID6 ext3 root partition and xfs local storage /export/ippXXX.0 * Areca 1280ML SATAII Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 * 15 YMI 5U Chenbro RM5U51924B Chassis (wave2) * Dual Quad-Core Intel(R) Xeon(R) CPU X5482 @ 3.20GHz * 2 x 6MB L2 cache * 32GB DDR2-800 RAM * 20TB RAID6 ext3 root partition and xfs local storage /export/ippXXX.0 * Areca 1280ML SATAII Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 * 16 ASA 5U Chenbro RM5U51924B Chassis (wave3) * Dual Quad-Core Intel(R) Xeon(R) CPU X5482 @ 3.20GHz * 2 x 6MB L2 cache * 32GB DDR2-800 RAM * 20TB RAID6 ext3 root partition and xfs local storage /export/ippXXX.0 * 3ware 9650SE-24 SATAII Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 * 13 YMI 5U Chenbro RM5U51924B (YM5U52624) (wave4) * Dual Six-core Intel(R) Xeon(R) CPU X5650 @ 2.67GHz * 12M L3 cache * 48GB DDR3-1333 RAM * 40TB RAID6 ext3 root partition and xfs local storage /export/ippXXX.0 * LSI MegaRAID 9280-24i4e SATAIII Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.34.4 * 10 Aspen 2U + 4U JBOD Supermicro (wave6 - STScI) deployment scheduled for June (6th) - (8th), 2012 * Dual Six-core Intel(R) Xeon(R) CPU E5645 @ 2.40GHz * 12M L3 cache * 48GB DDR3-1333 RAM * 4 x 120GB RAID5 (2 + 1) + 1 hot spare ext3 system * 3 x 33TB RAID6 (12 + 2) + 3 hot spares ext4 local storage /export/stsciXX.0, stsciXX.1, stsciXX.2 (total storage: 99TB) * LSI MegaRAID 9260-4i and 9280-8e SATA/SAS Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.34.4 * 4 YMI 8U Chenbro RM8U8074 Chassis (storage archive @ ATRC) * Dual Six-core Intel(R) Xeon(R) CPU X5650 @ 2.67GHz * 12M L3 cache * 24GB DDR3-1333 RAM * 2TB ext3 root partition * 3 x 40TB RAID6 xfs local storage /export/ippdbXX.[0,1,2] * 3ware 9650SE-2LP SATAII Raid Controller * Gentoo Base System release 2.0.1 (IPP 2010.0 release) * Linux 2.6.34.4 === Database Nodes === * 3 Aberdeen 3U Chenbro RM3U Chassis (wave3) * Dual Quad-Core Intel(R) Xeon(R) CPU X5482 @ 3.20GHz * 2 x 6MB L2 cache * 32GB DDR2-800 RAM * 1.9TB RAID6 ext3 root partition and xfs local storage /export/ippdbXX.0 * 3ware 9690SA-8I SAS/SATAII Raid Controller * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 === Compute Nodes === * 20 ASA 1U Chenbro RM1U1426 Chassis (wave3) * Dual Quad-Core Intel(R) Xeon(R) CPU X5482 @ 3.20GHz * 2 x 6MB L2 cache * 32GB DDR2-800 RAM * 500GB SW RAID1 ext3 root partition and local storage /export/ippcXX.0 * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 * 15 YMI 1U Chenbro RM1U1426 Chassis (wave4) * Dual Six-core Intel(R) Xeon(R) CPU X5650 @ 2.67GHz * 12M L3 cache * 24GB DDR3-1333 RAM * 1TB RAID1 ext3 root partition and local storage /export/ippcXX.0 * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384 * 34 YMI 1U Chenbro RM1U1426 Chassis (wave5) * Dual Six-core Intel(R) Xeon(R) CPU X5650 @ 2.67GHz * 12M L3 cache * 48GB DDR3-1333 RAM * 4 x 3TB HDD's * 2 x 3TB RAID1 ext3 root partition and local storage /export/ippcXX.0 * 2 x 3TB RAID0 ext3 (additional) local storage /export/ippcXX.1 * Gentoo Base System release 1.12.11.1 (IPP 2008.0 release) * Linux 2.6.28-rc7-00105-gfeaf384