Search results

It does that on storage that doesnt have Windows supported SED. Since virtio doesnt support sed passthrough (not afaik) its probably that you just have a different virtio configuration on your vms which explain the perceived difference in performance between your two vms. It PROBABLY would work...

I know that home use is usually of less criticality than one that is used for "business" production, but when choosing equipment for a given purpose, your questions should look more like this: 1. How much data do my applications generate/require? 2. Is the data all of the same value? is there...

it doesnt REQUIRE it- the use can BENEFIT from it. Not related. A RAID controller BBU is to account for controller write cache, not the drives. PLP doesnt protect you from unwritten changes. PLP protects you from data accepted by the drive to be written, but remains in drive memory as a...

https://github.com/intel/gvt-linux/wiki/GVTg_Setup_Guide should have the answers to all your questions.

probably safe/desirable to do even with one socket, especially on modern AMD cpus.

You're not alone. I see this a LOT with first time system design. "big numbers" are just sexy, and its only human nature to aim at the visible "numbers." its not until you operated a system "in anger" where you see what true pains a system can inflict on you. To that end, consider that your...

Thats not what I meant. What was the backing store? were you reading it from the same filesystem as you were writing to?

so you have two bridges set up, but what networks are carrying your various traffic types? of specific relevance, ceph.conf.

your disk(s) associated with myvg is full. either add more disks to the volume group or delete or move stuff.

one other thing- whats the source of the data copied? is it using the same network interface?

This could be completely normal/expected. Post your interfaces file for a more nuanced discussion; but generally speaking if you have both your public and private ceph traffic on the same interface you can only expect half the throughput, and thats if you're not comingling other traffic on top...

Correct. and you wouldnt want to even if that was possible (IBM LSI firmware allows this) because that would require the card to process IO through its controller (and cache) which would introduce all manner of issues for file systems such as ceph.

Not precisely, but they did start taking a LONG time to come up to operation after reboot. this behavior remained through all quincy point updates and not resolved until the cluster was upgraded to reef.

the H730p can be set to jbod (passthrough) mode. works fine (I have many in operation.)

install and enable multipathd.

I was trying to disabuse you of that notion. keep complaining though, I suppose you might feel better. You have two choices. you either get a grip on what Proxmox is, what Linux is, and what Proxmox GMBH is providing you. Or dont. either way, the only thing that changes is your expectations...

I think you misunderstand the whole concept of Linux. NO ONE IS RESPONSIBLE FOR YOUR EXPERIENCE. if "someone" didnt do it for you, "someone" isnt responsible for it to you unless you commissioned them to do so. and I know I'd like to get paid for my time and expertise before accepting any such...

what software is that?

ummm, no. dumping smart data just shows if any problems were trapped in the past, not if there are any faults present. run a full test before you retry to use the drive smartctl --test=long /dev/sd[x] many ssd's dont even have smart test functionality available, in which case I'd replace the...

smartctl --test=long /dev/sda if it passes, probably the cable/hba. if it doesnt, replace the drive.