wiki:entropy_upgrade_2016

entropy upgrade 2016

issues to resolve

  • disk space
  • backup
  • os upgrade

reference info

  • fstab
    #
    # /etc/fstab
    # Created by anaconda on Thu Apr 24 07:19:39 2014
    #
    # Accessible filesystems, by reference, are maintained under '/dev/disk'
    # See man pages fstab(5), findfs(8), mount(8) and/or blkid(8) for more info
    #
    UUID=f248c222-1299-4ead-b2af-10c108105be0 /                       ext4    defaults        1 1
    UUID=8090159f-16dc-4691-bcd8-4d58e05e3454 /state/partition1       ext4    defaults        1 2
    UUID=62d969e2-b83f-4084-8e4d-52ec8f0b6ab3 /var                    ext4    defaults        1 2
    UUID=da536898-0719-4cf9-953a-b130244e6075 swap                    swap    defaults        0 0
    tmpfs                   /dev/shm                tmpfs   defaults        0 0
    devpts                  /dev/pts                devpts  gid=5,mode=620  0 0
    sysfs                   /sys                    sysfs   defaults        0 0
    proc                    /proc                   proc    defaults        0 0
    
    # added by JEC: 6/23/2015
    #[root@entropy drobo]# mount /dev/sde1 /drobo/
    #/dev/sde1        16T  129M   16T   1% /drobo
    /dev/sde1		/drobo		ext3	defaults 0 0	
    
    # The ram-backed filesystem for ganglia RRD graph databases.
    tmpfs /var/lib/ganglia/rrds tmpfs size=4103631000,gid=nobody,uid=nobody,defaults 1 0	
    
  • df snapshot
    entropy:
    Filesystem      Size  Used Avail Use% Mounted on
    /dev/sda1        16G   13G  2.4G  84% /
    tmpfs            40G  8.0K   40G   1% /dev/shm
    /dev/sda5       1.8T  1.4T  282G  84% /state/partition1
    /dev/sda2       3.9G  1.5G  2.3G  39% /var
    tmpfs           3.9G  2.7M  3.9G   1% /var/lib/ganglia/rrds
    /dev/sde1        16T  1.9T   15T  12% /drobo
    
    $ ssh compute-0-0 df -h
    Filesystem            Size  Used Avail Use% Mounted on
    /dev/sda1              16G  9.7G  5.0G  67% /
    tmpfs                  64G   32K   64G   1% /dev/shm
    /dev/sda5             897G  386M  851G   1% /state/partition1
    /dev/sda2             3.9G  622M  3.1G  17% /var
    entropy.local:/export/apps
                          1.8T  1.4T  282G  84% /share/apps
    entropy.local:/export/home/jobrunner
                          1.8T  1.4T  282G  84% /home/jobrunner
    entropy.local:/export/home/emre
                          1.8T  1.4T  282G  84% /home/emre
    
    $ ssh compute-0-1 df -h
    Filesystem            Size  Used Avail Use% Mounted on
    /dev/sda1              16G  9.9G  4.8G  68% /
    tmpfs                  64G     0   64G   0% /dev/shm
    /dev/sda5             897G  386M  851G   1% /state/partition1
    /dev/sda2             3.9G  274M  3.4G   8% /var
    entropy.local:/export/home/james
                          1.8T  1.4T  282G  84% /home/james
    entropy.local:/export/home/emre
                          1.8T  1.4T  282G  84% /home/emre
    
  • current drive info
    Model: DELL PERC H710 (scsi)
    Disk /dev/sda: 1979GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type      File system     Flags
     1      1049kB  16.8GB  16.8GB  primary   ext4            boot
     2      16.8GB  21.0GB  4194MB  primary   ext4
     3      21.0GB  22.0GB  1049MB  primary   linux-swap(v1)
     4      22.0GB  1979GB  1957GB  extended
     5      22.0GB  1979GB  1957GB  logical   ext4
    
    
    Model: DELL PERC H710 (scsi)
    Disk /dev/sdb: 1979GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type     File system  Flags
     1      32.3kB  1979GB  1979GB  primary               lvm
    
    
    Model: DELL PERC H710 (scsi)
    Disk /dev/sdc: 1979GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type     File system  Flags
     1      32.3kB  1979GB  1979GB  primary               lvm
    
    
    Model: DELL PERC H710 (scsi)
    Disk /dev/sdd: 62.2GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type     File system  Flags
     1      32.3kB  62.2GB  62.2GB  primary               lvm
    
    
    Model: Drobo 5D (scsi)
    Disk /dev/sde: 17.6TB
    Sector size (logical/physical): 512B/512B
    Partition Table: gpt
    
    Number  Start   End     Size    File system  Name  Flags
     1      17.4kB  17.6TB  17.6TB               pri
    
    
    Model: Linux device-mapper (linear) (dm)
    Disk /dev/mapper/vgpool-lvscratch: 3865GB
    Sector size (logical/physical): 512B/512B
    Partition Table: loop
    
    Number  Start  End     Size    File system  Flags
     1      0.00B  3865GB  3865GB  ext3
    
    $ ssh compute-0-0 parted -l
    Model: ATA ST1000NM0033-9ZM (scsi)
    Disk /dev/sda: 1000GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type      File system     Flags
     1      1049kB  16.8GB  16.8GB  primary   ext4            boot
     2      16.8GB  21.0GB  4194MB  primary   ext4
     3      21.0GB  22.0GB  1049MB  primary   linux-swap(v1)
     4      22.0GB  1000GB  978GB   extended
     5      22.0GB  1000GB  978GB   logical   ext4
    
    $ ssh compute-0-1 parted -l
    Model: ATA ST1000NM0033-9ZM (scsi)
    Disk /dev/sda: 1000GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start   End     Size    Type      File system     Flags
     1      1049kB  16.8GB  16.8GB  primary   ext4            boot
     2      16.8GB  21.0GB  4194MB  primary   ext4
     3      21.0GB  22.0GB  1049MB  primary   linux-swap(v1)
     4      22.0GB  1000GB  978GB   extended
     5      22.0GB  1000GB  978GB   logical   ext4
    
    
    Model: ATA ST1000NM0033-9ZM (scsi)
    Disk /dev/sdb: 1000GB
    Sector size (logical/physical): 512B/512B
    Partition Table: msdos
    
    Number  Start  End  Size  Type  File system  Flags
    
    

resources

questions

  • how many free drive slots does entropy have ?
    • currently parted shows 2TB drives in /dev/sda, /dev/sdb, /dev/sdc and a lvm of 4TB (is this a mapping of /dev/sdb, /dev/sdc ?)
  • do we want to upgrade the boot drive or leave it and simply install the new os
  • does the host support hardware RAID ?
    • maybe we should mirror ?
    • if a drive fails, how are we notified ?
      • i use adaptec controllers that have a loud audible alarm that is painfully loud
  • it appears drobo is using usb 2.0 (480 Mb/s) we should really have a usb 3.0 backup (5Gb/s)
     lsusb -v | grep bcdUSB
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               2.00
      bcdUSB               1.10
      bcdUSB               2.10
      bcdUSB               2.00
      bcdUSB               2.00
    

raid explore

  • microsemi adaptec
    • sales 408.957.7274
    • dell poweredge R320
      • gen 3 pcie standard height half length x16 link width x16 slot width
      • external raid case
        • sas 12 Gb/s support ?
        • recommended cards ?
          • 8 series
          • 8 drives externally + 8 internal
          • 8885q max cache
        • latest firmware and motherboard bios
      • 5 or 6 x 8 TB SAS 12Gb/s amazon
      • controller + 5 drives ~ $2900
      • additionally need
        • case
        • hot swap caddies

plan of action

  • hardware inventory, disk storage plan, any OS upgrade plans done before trip. Order required parts.
  • make binary backup copy of all disks on entropy
  • need to install OS on separate partition
  • setup rsync, and notifications
  • add CUDA reinstallation bits to compute nodes so it is done automatically
  • power cycle entire system multiple times the day before leaving.
  • define other testing protocols so that everything that has to be done while at UTK is done.
  • review hardware, OS, and future maintenance issues with Johnny Jones.
  • setup remote rsync to NIST science drive
  • implement cron job to move / remove stale files from sassie2, sassie2test, and other genapp powered apps
  • test backup reboot capability
  • bring one drive image of root disk back to NIST
  • make a VM of entropy after imaging??
    • entropy is Rocks, right? we could make a copy to a disk and run it as a vm, but the network and compute nodes wouldn't be there...

Last modified 22 months ago Last modified on Apr 30, 2016, 3:26:57 PM

Attachments (1)

Download all attachments as: .zip