The HaxbyLab@Dartmouth

Hardware

«  Hydra Cluster Configuration and Maintenance   ::   Home   ::   Software  »

Hardware

Original Purchase

  • Purchase order: No: 1054201
  • Master Number: 11,393
  • Cost: 34,720.00
  • Shipment received: 10/21/2009, FedEx Freight
  • Assembly completed: 10/22/2009

Extensions

Storage

head1

  • 24750

head2

  • 24751

head7

  • 26754
  • MWY quote: MWYQ1499701
  • Purchase order: No: 1106745
  • DC System ID: 100791
  • Invoice: 139515
  • Master Number:
  • Cost: $7,873.00
  • Paid with: startup
  • Shipment received:
  • Assembly completed: 10/28/2011

head8

  • Purchase order: No:
  • Master Number:
  • Cost:
  • Shipment received:
  • Assembly completed:

Components

Router

  • Model Netgear GS748TS-100NAS

  • MAC address: 00:22:3F:ED:D3:57

  • User manuals sup/Netgear-GS748TS/

  • Static assigned IP became 10.0.2.1 (DHCP assigned address was 10.0.0.11)

  • Port assignments

    • Leftmost block (1-12): left-positioned nodes

      • 1,2 – head4
        • 3,4 – head6
    • 2nd block (13-24): misc service

      • 13 – lego ???
      • 19 – APC UPS ???
    • 3rd block (25-36): main + right-positioned nodes

      • 25,26 – head1
      • 27,28 – head2
      • 29,30 – head3
      • 31,32 – head5
      • 33,34 – head7
    • 4th block (37-44): IPMI

      • 37-42 – head1-head6 IPMI
  • SNTP got configured

  • Temporarily LAG for head1-head3 were configured, see _sec_bonding.

  • Logging is forwarded to head1 at Informational level.

Head 3

  • IPMI
    • Net - channel [01]
    • IP [03]: 10.0.1.3
    • MAC [05] : 00:30:48:DC:31:55
    • Subnet [06]: 255.255.0.0
  • Ethernet bond0: bonded eth0+eth1 00:30:48:bc:07:10

Head 2

  • IPMI

    • Net - channel [XX]
    • IP [03]: 10.0.1.2
    • MAC [05] : XXXX 00:30:48:DC:31:55
    • Subnet [06]: 255.255.0.0
  • Ethernet bond0: bonded eth0+eth1 XXX 00:30:48:bc:07:10

  • Storage

    • Some time ago it got expansion with 1TB drives pulled out from the

      head1 and placed into head2, RAID6 was expanded in-place using 3ware internal mechanisms

    • 2013/03/22: p20 has been complaining about SMART problems, so

      replacement drive (slightly different, updated model HUA722010CLA330 fw JP4OA3EA instead of the original HDE721010SLA330 fw ST6OA3AA). (Note – next time use “tw_cli /c0/pXX export” before pulling out the drive ;) )

root@head2:~# tw_cli /c0 show

Unit  UnitType  Status         %RCmpl  %V/I/M  Stripe  Size(GB)  Cache  AVrfy
------------------------------------------------------------------------------
u0    RAID-6    REBUILDING     4%(A)   -       256K    19557.6   W      ON     

Port   Status           Unit   Size        Blocks        Serial
---------------------------------------------------------------
p0     OK               u0     931.51 GB   1953525168    STN6M5MS0G0T4K      
p1     OK               u0     931.51 GB   1953525168    STN6M5MS0G2H9K      
p2     OK               u0     931.51 GB   1953525168    STN6M5MS0G9SMK      
p3     OK               u0     931.51 GB   1953525168    STN6M5MS0G5RTK      
p4     OK               u0     931.51 GB   1953525168    STN6M5MS0G5R8K      
p5     OK               u0     931.51 GB   1953525168    STN6M5MS0EXN1K      
p6     OK               u0     931.51 GB   1953525168    STN6M5MS0G0K7K      
p7     OK               u0     931.51 GB   1953525168    STN610MS0SRZ5K      
p8     OK               u0     931.51 GB   1953525168    STN6M5MS0G41HK      
p9     OK               u0     931.51 GB   1953525168    STN607MS12WGZK      
p10    OK               u0     931.51 GB   1953525168    STN607MS12PYPK      
p11    OK               u0     931.51 GB   1953525168    STN607MS11S6DK      
p12    OK               u0     931.51 GB   1953525168    STN6M5MS0G0KGK      
p13    OK               u0     931.51 GB   1953525168    STN6M5MS0EXNHK      
p14    OK               u0     931.51 GB   1953525168    STN6M5MS0G2WXK      
p15    OK               u0     931.51 GB   1953525168    STN6M5MS0G2JWK      
p16    OK               u0     931.51 GB   1953525168    STN6M5MS0G5LNK      
p17    OK               u0     931.51 GB   1953525168    STN6M5MS0G6LPK      
p18    OK               u0     931.51 GB   1953525168    STN6M5MS0G9S2K      
p19    OK               u0     931.51 GB   1953525168    STN6M5MS0G3ZKK      
p20    OK               -      931.51 GB   1953525168    JPW9K0N0244DYL      
p21    OK               u0     931.51 GB   1953525168    STN6M5MS0G0J0K      
p22    OK               u0     931.51 GB   1953525168    STN6M5MS0G5XJK      
p23    DEGRADED         u0     931.51 GB   1953525168    STN6M5MS0G9PPK      

Name  OnlineState  BBUReady  Status    Volt     Temp     Hours  LastCapTest
---------------------------------------------------------------------------
^[[Abbu   On           Yes       OK        OK       OK       0      xx-xxx-xxxx  

root@head2:~# tw_cli /c0/u0 show

Unit     UnitType  Status         %RCmpl  %V/I/M  Port  Stripe  Size(GB)
------------------------------------------------------------------------
u0       RAID-6    REBUILDING     4%(A)   -       -     256K    19557.6   
u0-0     DISK      OK             -       -       p11   -       931.312   
u0-1     DISK      OK             -       -       p10   -       931.312   
u0-2     DISK      OK             -       -       p9    -       931.312   
u0-3     DISK      OK             -       -       p8    -       931.312   
u0-4     DISK      OK             -       -       p7    -       931.312   
u0-5     DISK      OK             -       -       p6    -       931.312   
u0-6     DISK      OK             -       -       p5    -       931.312   
u0-7     DISK      OK             -       -       p4    -       931.312   
u0-8     DISK      OK             -       -       p3    -       931.312   
u0-9     DISK      OK             -       -       p2    -       931.312   
u0-10    DISK      OK             -       -       p1    -       931.312   
u0-11    DISK      OK             -       -       p0    -       931.312   
u0-12    DISK      OK             -       -       p12   -       931.312   
u0-13    DISK      OK             -       -       p13   -       931.312   
u0-14    DISK      OK             -       -       p14   -       931.312   
u0-15    DISK      OK             -       -       p15   -       931.312   
u0-16    DISK      OK             -       -       p16   -       931.312   
u0-17    DISK      OK             -       -       p17   -       931.312   
u0-18    DISK      OK             -       -       p18   -       931.312   
u0-19    DISK      OK             -       -       p19   -       931.312   
u0-20    DISK      DEGRADED       -       -       p23   -       931.312   
u0-21    DISK      OK             -       -       p21   -       931.312   
u0-22    DISK      OK             -       -       p22   -       931.312   
u0/v0    Volume    -              -       -       -     -       19557.6 

Head 7

S/N

Initial Hardware Issues

  • Faulty APC front panel: lights are either all off or all on. Replacement shipped from APC-vendor on 10/27/2009.

«  Hydra Cluster Configuration and Maintenance   ::   Home   ::   Software  »