Nemesiz's latest activity
-
NNemesiz replied to the thread Is this a ZFS related problem?.S3610 stats is not bad. Do you feel slow system then doing multi read/write tasking? Or you just look at the graph and try to decide from there ? Do you still see blocked messages? Try to disable ZFS sync write, maybe it will help.
-
NNemesiz replied to the thread CEPH setup.Everything have a cost. You can find some talk then network was changed from 10/25GB to 100GB improved performance event network load was 10-20%.
-
NNemesiz replied to the thread Is this a ZFS related problem?.Temporary: #swapoff -a Permanently: edit /etc/fstab
-
NNemesiz replied to the thread Very specific setup, needing very specific advisory.Samba ?
-
NNemesiz replied to the thread CEPH setup.SSD as DB/WAL for SSD may not give expected performance. What was Ceph slow performance at the beginning ( not disk itself )? As of small/lab Ceph cluster I do not see much lose of using EC vs replica.
-
NNemesiz replied to the thread CEPH setup.You told it is slow but did not told the numbers. With ceph you can create CRUSH rules where pool must save data. You can create new class, new root to distribute the data.
-
NNemesiz replied to the thread Is this a ZFS related problem?.Hi, looking at given issue link try to turn off swap
-
NNemesiz posted the thread STEC ssd disk wearout show in GUI in Proxmox VE: Installation and configuration.Hello, I use a bunch of STEC ssd. They are old but runs good and have high endurance. Regular smartctl doesn't return all needed information. Proxmox GUI show wearout as N/A. To get more information I use #sdmcmd64 In Diskmanage.pm...
-
NNemesiz replied to the thread [bug] [WebUI] Ceph OSD control and multiple roots.This is my types # types type 0 osd type 1 osd-link type 2 disk-group type 3 host type 4 chassis type 5 rack type 6 row type 7 pdu type 8 pod type 9 room type 10 datacenter type 11 zone type 12 region type 13 root If OSD belongs directly to...
-
NNemesiz replied to the thread CEPH setup.You can rise osd_memory_target but HP PM9A3 is more for read intensive. Try not to use them to see how will Ceph performance.
-
NNemesiz replied to the thread High Latency on a new HDD-disks (ceph).Take IO metering tools and watch HDD load
-
NNemesiz replied to the thread Cannot migrate VM, because HA resource vm is not allowed.To recreate bug I delete all HA rules and created again. From that moment all server shutdown went very well.
-
NNemesiz replied to the thread High Latency on a new HDD-disks (ceph).Try to disable write-cache for HDD
-
NNemesiz replied to the thread Cannot migrate VM, because HA resource vm is not allowed.VM could exist only in one HA rule. It should be a bug.
-
NNemesiz replied to the thread Cannot migrate VM, because HA resource vm is not allowed.It require to be upgraded. In node shutdown VM should be moved to another node by HA rule priority but it stays blocked.
-
NNemesiz replied to the thread Cannot migrate VM, because HA resource vm is not allowed.Could it be related to this? https://github.com/proxmox/pve-ha-manager/commit/dc200f10963fcb7ca81ea05246ce69bf03117629 # pveversion -v proxmox-ve: 9.2.0 (running kernel: 7.0.12-1-pve) pve-manager: 9.2.3 (running version: 9.2.3/d0fde103346cf89a)...
-
NNemesiz posted the thread Cannot migrate VM, because HA resource vm is not allowed in Proxmox VE: Installation and configuration.Hello, I'm not sure which update caused this issue, but using HA Affinity Rules I can't migrate a VM to another node. In migration dialog I see: Cannot migrate VM, because HA resource vm:121 is not allowed on the selected target node. Using...
-
NNemesiz replied to the thread [Feature Request] Limits of unsuccessful migration to the same node.Created https://bugzilla.proxmox.com/show_bug.cgi?id=7755
-
NNemesiz posted the thread [Feature Request] Limits of unsuccessful migration to the same node in Proxmox VE: Installation and configuration.Hello, I am facing a problem where the rebooted server gets stuck with VM migration for various reasons and the process repeats endlessly [1]. The HA migration process should have a retry counter in case of unsuccessful migration to the same...