Dynamic memory is a new feature of Hyper-V R2 Service Pack 1. With Hyper-V Dynamic Memory, the host automatically rebalances memory among virtual machines (VMs) on a moment-by-moment basis. Memory is pooled on one physical host, then it is dynamically distributed to VMs as necessary. But there's a problem with this memory allocation: Hyper-V assigns the memory in one-second intervals. Hyper-V includes a couple of settings to help tune the 1 second interval (Memory Buffer and Memory Priority).
The Memory Buffer reserves extra RAM for each VM. The VM uses this space if RAM requirements change between one-second intervals. Without a buffer, an increase in memory requirements during this mere second automatically forces a VM into an out-of-memory condition and memory pages are swapped to disk. The Memory Buffer can be configured on a VM bases.
Since Memory Buffer over-allocates RAM per VM, a host server could run out of available physical RAM causing a contention for memory. The Memory Priority setting allows you to prioritize VMs. You essentially give Hyper-V an ordered list of VMs from which it should pull memory first. Lower-priority VMs lose memory before higher-priority VMs during memory allocation.
For more information about Memory Buffer and Memory Priority, check out Greg Shields article at TechTarget...