hi, we have 5 nodes in a cluster configuration. All uses ISCSI over 2 x 1 GB in multipath configuration (ISCSI hosts are open-E DSS7 in cluster setup, connected to 2 x Raid5 volumes ( 6 x SAS 2TB Seagate) JBod via 6Gib/s SAS). At the moment we have ~30 KVM VMs active. Some with very low I/O, some with a lot of (NFS/Samba/LDAP/TFTP). As I started with Proxmox I never used any kind of limits. So I want to change it. Last week I saw a lot of veth0 RX drops in a few VMs with high I/Os (NFS/LDAP) and I think "unlimited" in the VM config is the problem. Now I asking for good practices of limiting the VMs:
- list NFS Server: -> Used for $HOMES with ~few hundreds of active users per week (sometimes 100 per day)
- list TFTP: -> Used for 100 diskless (NFS root) clients. ~30-40 active per day
- list LDAP Server: -> Used for nearly everything Keep in mind, local disks aren't used, only ISCSI.
Last edited: