alexskysilk's latest activity

  • A
    alexskysilk replied to the thread ZFS on SAN LUN(s).
    I think we're using support in different ways. the software stack you describe can run on those (or any other) linux. whether you want to depend on the solution and have someone who can assert its uptime, thats what I mean. see...
  • A
    alexskysilk replied to the thread ZFS on SAN LUN(s).
    this is true, but have you ever implemented it? its slow as molasses. mdadm parity raid... brrr. THAT is brave. also, there is no "self healing" of any kind. This has the same problems as a HA zfs filer. the only "upside" is that you dont have...
  • A
    alexskysilk replied to the thread ZFS on SAN LUN(s).
    Not uncommon, but fraught. I've seen effort to make a HA ZFS filer solution for AT LEAST 20 years. There are 3 commercial solutions I'm aware of (Truenas/Nexenta/Intelliflash) but all three have either migrated/migrating to a different method of...
  • A
    alexskysilk replied to the thread ZFS on SAN LUN(s).
    in before @UdoB ;) thats a bad idea. you can make it work but it would be brittle, unsupported and unsupportable.
  • A
    So not a network problem. next step is to perform an strace on the qemu process and see whats locking up.
  • A
    alexskysilk replied to the thread ZFS on SAN LUN(s).
    Running ZFS on a obfuscated device (eg, RAID LUN) isnt dangerous per se; its no safer then any other filesystem on raid- which is to say you have no checksum correction facility at the filesystem level so you're paying the zfs tax for no gain...
  • A
    If the discussion is strictly on a "worth it" basis, its worth noting by what metric. Ram costs more then storage. Fast dedup is less hungry but thats still ~2G per deduplicated TB- although you could substitute a special device for SOME ram usage.
  • A
    alexskysilk replied to the thread Snapshot best practices.
    ceph and zfs are CoW native; snapshots are not "real" in the sense that the data isnt separated- think of snapshots as bookmarks. VMDK isnt, and so snapshots are addon files. qcow2 can exhibit similar performance degradation. In summary-...
  • A
    when you say the VM freezes, do you mean it isnt responding to network traffic or local (console) access? if its console access, is it a specific VM or all VMs on the nodes? If its network access, check your raw interfaces for faults. ifconfig...
  • A
    Someone has to maintain it, which means proper testing and release management. If the goal is Microsoft certification/WHQL, that also means establishing the appropriate relationship with Microsoft, going through their certification process, and...
  • A
    NFS doesnt care; certain write patterns can benefit. a slog is useful when the following two things are true: - The write pattern is large number of synchronous small IO (eg, backing a database) - The backing store is an order of magnitude...
  • A
    true. If you want to buy an 18 wheeler for haul groceries thats your call- it doesnt mean you need an 18 wheeler. match the solution to the problem. Not every usecase benefits. Thats an argument for a newer drive, not for a plp. technology...
  • A
    Hi @galffing , I hope you don't mind me saying this, but based on the questions you've asked, it seems like W365 would be the best fit for your business needs. Blockbridge : Ultra low latency all-NVME shared storage for Proxmox -...
  • A
    words like "terrible" are terrible. they provide no context. You could say "RAIDz1 performs poorly compared to RAID10" or "RAIDz1 provides poor risk management vs RAIDz2" but without knowing the use case and expected performance and fault...
  • A
    the gold standard for volume partitioning is the same regardless of number of disks: part 1 (optional, default using pve installer) legacy grub part 2 efi part 3 root part 4 data/payload part4 layout and usage will depends on how you partition...
  • A
    It has been ready for years. A high-friction CLI/UX workflow is not the same thing as a system being "unusable" or "not production-grade." Thousands of enterprise nodes run multipath iSCSI in production every day—it just requires Linux systems...
  • A
    alexskysilk replied to the thread Loadbalancing.
    DO you have a load balancer? what provides your internet service?
  • A
    Or more. all designs based on chiplets (eg, all modern AMD) will have more then one per socket. /pedantic
  • A
    From scratch? the same as any other restoration RTO calculation- the longest of (- time to read from source - time to transfer - time to write to destination) * processing coefficient (1.2 is safe with typical current hardware.) HOWEVER, PBS has...