Skip Navigation

lightrush

@ lightrush @lemmy.ca

Posts
6
Comments
18
Joined
3 yr. ago

  • Preparing for the hardware market disruption

    Jump

  • 9x 14TB, WD HC530. Paid 25% less for some 16TB HC550 in 2024.

  • Preparing for the hardware market disruption

    Jump

  • Being poor sucks.

    No kidding. This didn't ruin me but it was painful. And on top of that, it's smaller disks for significantly more than I did last year.

    I bought them for years ahead. My primary pool is gonna start having drives fail from age and use, and it'll need replacements. So I'm gonna be sticking these in as they fail over time so I use all the service life I can get from the existing (8TB) drives.

  • Promised myself I will support them after they go stable. They kept their promise and so did I

    Jump

  • The AI search is just crazy, especially when you adjust the model quality.

  • 7 years later, Valve's Proton has been an incredible game-changer for Linux

    Jump

  • To Gaben's credit he collects a lot less of the surplus these workers create than most other billionaires. But yes.

  • Silicon Valley Is Panicking About Zohran Mamdani. NYC’s Tech Scene Is Not

    Jump
  • Linux @lemmy.ml
    lightrush @lemmy.ca

    Debian 13 burning 10W playing 4K YouTube video on a Framework with max brightness 🫨

  • He's connected

    Jump

  • Not my orange. Was just passing by when I saw it.

  • cats @lemmy.world
    lightrush @lemmy.ca

    He's connected

  • Fridges never die.

    Jump

  • Your PC is an unused server.

  • Arnold Schwarzenegger endorses Kamala Harris: ‘I will always be an American before I am a Republican’

    Jump

  • This is one of those situations when you just nod and take the endorsement.

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • Iiinteresting. I'm on the larger AB350-Gaming 3 and it's got REV: 1.0 printed on it. No problems with the 5950X so far. 🤐 Either sheer luck or there could have been updated units before they officially changed the rev marking.

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • On paper it should support it. I'm assuming it's the ASRock AB350M. With a certain BIOS version of course. What's wrong with it?

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • B350 isn’t a very fast chipset to begin with

    For sure.

    I’m willing to bet the CPU in such a motherboard isn’t exactly current-gen either.

    Reasonable bet, but it's a Ryzen 9 5950X with 64GB of RAM. I'm pretty proud of how far I've managed to stretch this board. 😆 At this point I'm waiting for blown caps, but the case temp is pretty low so it may end up trucking along for surprisingly long time.

    Are you sure you’re even running at PCIe 3.0 speeds too?

    So given the CPU, it should be PCIe 3.0, but that doesn't remove any of the queues/scheduling suspicions for the chipset.

    I'm now replicating data out of this pool and the read load looks perfectly balanced. Bandwidth's fine too. I think I have no choice but to benchmark the disks individually outside of ZFS once I'm done with this operation in order to figure out whether any show problems. If not, they'll go in the spares bin.

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • I put the low IOPS disk in a good USB 3 enclosure, hooked to an on-CPU USB controller. Now things are flipped:

     
        
                                        capacity     operations     bandwidth 
pool                                  alloc   free   read  write   read  write
------------------------------------  -----  -----  -----  -----  -----  -----
storage-volume-backup                 12.6T  3.74T      0    563      0   293M
  mirror-0                            12.6T  3.74T      0    563      0   293M
    wwn-0x5000c500e8736faf                -      -      0    406      0   146M
    wwn-0x5000c500e8737337                -      -      0    156      0   146M

    You might be right about the link problem.

    Looking at the B350 diagram, the whole chipset is hooked via PCIe 3.0 x4 link to the CPU. The other pool (the source) is hooked via USB controller on the chipset. The SATA controller is also on the chipset so it also shares the chipset-CPU link. I'm pretty sure I'm also using all the PCIe links the chipset provides for SSDs. So that's 4GB/s total for the whole chipset. Now I'm probably not saturating the whole link, in this particular workload, but perhaps there's might be another related bottleneck.

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • Turns out the on-CPU SATA controller isn't available when the NVMe slot is used. 🫢 Swapped SATA ports, no diff. Put the low IOPS disk in a good USB 3 enclosure, hooked to an on-CPU USB controller. Now things are flipped:

     
        
                                        capacity     operations     bandwidth 
pool                                  alloc   free   read  write   read  write
------------------------------------  -----  -----  -----  -----  -----  -----
storage-volume-backup                 12.6T  3.74T      0    563      0   293M
  mirror-0                            12.6T  3.74T      0    563      0   293M
    wwn-0x5000c500e8736faf                -      -      0    406      0   146M
    wwn-0x5000c500e8737337                -      -      0    156      0   146M

  • Mirror seeing half the write IOPS on one disk than the other, is this normal?

    Jump

  • Interesting. SMART looks pristine on both drives. Brand new drives - Exos X22. Doesn't mean there isn't an impending problem of course. I might try shuffling the links to see if that changes the behaviour on the suggestions of the other comment. Both are currently hooked to an AMD B350 chipset SATA controller. There are two ports that should be hooked to the on-CPU SATA controller. I imagine the two SATA controllers don't share bandwidth. I'll try putting one disk on the on-CPU controller.

  • Selfhosted @lemmy.world
    lightrush @lemmy.ca

    Mirror seeing half the write IOPS on one disk than the other, is this normal?

    discourse.practicalzfs.com /t/mirror-seeing-half-the-write-iops-on-one-disk-than-the-other-is-this-normal/1814
  • Selfhosted @lemmy.world
    lightrush @lemmy.ca

    Slow sequential single file reads on ZFS

  • OWC Mercury Elite Pro Quad as USB Direct Attached Storage (DAS) for ZFS

    Jump

  • And now it no longer shows up.

  • OWC Mercury Elite Pro Quad as USB Direct Attached Storage (DAS) for ZFS

    Jump

  • I was wondering what would be better for discoverability, to write this in a blog post, on GitHub, then link it here, or to just write it here. Turns out Google's crawling Lemmy quite actively. This shows up within the first 10-15 results for "USB DAS ZFS":

    It appears that Lemmy is already a good place for writing stuff like this. ☺️

  • OWC Mercury Elite Pro Quad as USB Direct Attached Storage (DAS) for ZFS

    Jump

  • 5950X, 64GB

    It's a multipurpose machine, desktop workstation, games, running various servers.

  • Selfhosted @lemmy.world
    lightrush @lemmy.ca

    OWC Mercury Elite Pro Quad as USB Direct Attached Storage (DAS) for ZFS