Recent content by Kevin Myers

and what are people doing for database / atomic backups inside the vm’s

might also be some bad auto negotiation on your switch, try in the switch hard setting the port / duplex speed tp match the nic

nowdays i prefer ssds for system drives, and overprovision them to 50%, spinning disks also inevitably fail, while a ssd at 50% overprovisioned for an os drive will outlive the server most the time

or install proxmox 6 on a node using ext4 and lvm, and migrate the vms over .....

check https://docs.ceph.com/docs/mimic/rados/operations/cache-tiering/

Hi Fabian, The patches did fix the MTU issue, however another ugly issue has raised its head . I have a cluster of around 30 nodes, ( I know all the warnings of corosync2 and 16 nodes however this worked awesomely on corrosync2) . I started to move nodes from CS2 to CS3 in prep of the 5-6...

Hi Fabian, It seems a patch have been applied to fix this, could it be integrated :) Best regards Kev

I had tried earlier fiddling with netmtu, but decided to try setting some different values, (1500, 20000 , 65520) , all of which make nod difference we end up with Jul 29 14:40:14 kvm1 corosync[4039025]: [KNET ] pmtud: Aborting PMTUD process: Too many attempts. MTU might have changed during...

Hi, Im having a peculiar issue. My nodes used infiniband in connected mode for cluster network, and storage (different interfaces) . The cluster network runs on a 10.1,100.x range, and the ipoib device looks like ib1: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 65520 inet...

i'll rephrase that.. I see in qemu if you have defined disk throttles, and include burstable limits, the burst limit is reduced to the normal limit after iops_max_length , ,bps_max_length, etc number of seconds. Is their any plans to expose these in the gui ?

I see that with qemu the disk throttling for iops kicks in after iops_max_length number of seconds, would it be possible to create a parameter under the 'disk throttle' gui to control this ?

answering my own question for any lost sole's that see the same problem, if you have upgraded from jewel to proxmox 5 stable (with ceph luminious) , then ensure you have a ceph mngr installed and working.

check corosync service is running on all nodes

hard adding --filestore to API2/Ceph.pm eg my $cmd = ['ceph-disk', 'prepare', '--zap-disk', '--filestore' , '--fs-type', $fstype, does create the the osd with the filestore type. still have the other issue where new osd's added backfill, but the reported capacity the...

I 'guess' its caused by this : http://ceph.com/releases/v12-1-0-luminous-rc-released/ " Notable Changes bluestore: ceph-disk: add –filestore argument, default to –bluestore (pr#15437, Loic Dachary, Sage Weil)" so --filestore now needs to be passed else bluestore will be created