Search results

I use LACP bonds with 2 nics and use Jumbo frames with Ceph. I put the howto in the proxmox wiki for openvswitch http://pve.proxmox.com/wiki/Open_vSwitch Depending on how many physical nodes you have, having 3 ports may not help because LACP bonds don't just act like a bigger trunk. Unless...

That thread is talking about the 845DC EVO, I explicitly said "PRO (not EVO!)". Samsung 845DC EVO is comparable to the Intel DC S3500 Samsung 845DC PRO is comparable to the Intel DC S3700 -Brad

Be careful with the S3500's, its not the performance why you'd want to use the S3700's, its the fact that the S3700's use eMLC and give you endurance of 10 DWPD. Using an SSD as a journal across multiple HDDs will mean it is used more heavily than as a storage device. The S3500 will probably...

RGManager won't start unless you have something marked for high-availability. We usually put a VIP entry in the cluster.conf as it is useful, and always causes RGManager to start even if we haven't marked any VMs for high availability. Here's what we typically put in there (after the...

We use such a setup for small office clusters. With the NICs bonded, we've found you get around theoretical performance out of the network. So it will definitely work fine if you don't have disk-intensive operations. IOPS are actually showing about the same as our 10G cluster, just overall...

You should use the 'linux ext4' boot option, see https://pve.proxmox.com/wiki/Debugging_Installation for more info.

Can you describe your freezes a little more? Is it the VM guest that is freezing? If so, I've had that issue too when using the 3.10 kernel, and it goes away if you use the 2.6.32 kernel. I've got a recent forum thread on it and ceph bugs filed but ceph blames the kernel.

Are you sure your cluster communication is in good health? You can have really weird issues if not, such as if you are having multicast issues. You should check things like "fence_tool ls", "clustat", "pvecm status", "group_tool ls" and make sure everything appears in good health. If not...

According to the ceph guys it didn't appear there was a deadlock waiting on a mutex or anything like that. They're convinced its a scheduling issue and a thread just isn't getting scheduled that should, basically a stall of some sort, so they think it is the kernel. krbd with your patch worked...

I didn't see any place to ask a pre-purchase question other than the forum. Not seeing any email or phone numbers on the proxmox.com website :/ We have a unique situation where we need to deploy the proxmox hosts in a PCI DSS (Payment Card Industry Data Security Standard) environment, and to...

It looks like the 3.10.0-5-pve kernel is the culprit of my lockups. The ceph guys had me back off to the 2.6.32-34-pve kernel and I can't get it to lock up. Granted, I'm now taking about a 30% performance hit, but it's stable. I just need to decide if I should go 2.6.32, or 3.10 with krbd. I...

Hmm, when I add --direct=1 the numbers change completely. Maybe it is invalid without --direct=1. fio --direct=1 --rw=randrw --refill_buffers --norandommap --randrepeat=0 --ioengine=libaio --bs=4k --rwmixread=100 --iodepth=16 --numjobs=16 --runtime=60 --group_reporting --name=4ktest...

Using krbd appears to work without locking up. So that's the good news. However, this is much slower for me than librbd. Any idea what may be doing on since you seem to be reporting the opposite. I'd expect to be getting at least 10k iops from this, but I'm getting 1/10th of that...

The ceph guys are asking if we have debug symbols available for the qemu binary. Obviously I'm using pve-qemu-kvm, but I don't see a -dbg package for that that I can install. Is there one available somewhere?

I guess pve-no-subscription is basically the same as pvetest these days as pvetest didn't say there were any updates available, and passing the iothread: 1 flag in the vm configuration did show modifications to the kvm command line, so I'll give that a shot. Regarding the pve-storage git, what...

I can definitely give that a try. I noticed someone commented on the ceph ticket as well and suggested trying krbd instead of librbd, is that also in pvetest?

I see the CPU go up briefly before it deadlocks, then it sits at 0% CPU and dumping in-flight ops from ceph itself shows 0 during the deadlock on all OSDs. I've got 3 nodes, each with 1 OSD in the pool that is dual purpose (ceph + proxmox). Ceph is using size=2 min_size=1 standard replication...

What does the 'Output' column of that same screen show? Status is usually just a summary, I think the Output tab should have the real console message. But yes, definitely looks like something to do with the proxmox binding to ceph. My keyring also uses client.admin and it works fine. The...

I just meant you need to make sure the keyring in /etc/ceph/ currently matches the one in /etc/pve/priv/ceph/ as if it got replaced when you started over and you're still using the old one that could explain it. Really, you need a better error message to know what is going on. I assume you've...

You mentioned you killed your first attempt and restarted. Your keyring isn't the original from the first attempt is it? You might get more information from the actual proxmox logs on why it couldn't connect. I want to say if you attempt to create a vm on that storage pool and let it fail...