Whereas memory ballooning simply reduces the amount of RAM that is available to a VM, Page Fusion works differently. It avoids memory duplication between several similar running VMs.

In a server environment running several similar VMs on the same host, lots of memory pages are identical. For example, if the VMs are using identical operating systems. 's Page Fusion technology can efficiently identify these identical memory pages and share them between multiple VMs.

The more similar the VMs on a given host are, the more efficiently Page Fusion can reduce the amount of host memory that is in use. It therefore works best if all VMs on a host run identical operating systems. Instead of having a complete copy of each operating system in each VM, Page Fusion identifies the identical memory pages in use by these operating systems and eliminates the duplicates, sharing host memory between several machines. This is called deduplication. If a VM tries to modify a page that has been shared with other VMs, a new page is allocated again for that VM with a copy of the shared page. This is called copy on write. All this is fully transparent to the virtual machine.

You may be familiar with this kind of memory overcommitment from other hypervisor products, which call this feature page sharing or same page merging. However, Page Fusion differs significantly from those other solutions, whose approaches have several drawbacks:

• Traditional hypervisors scan all guest memory and compute checksums, also called hashes, for every single memory page. Then, they look for pages with identical hashes and compare the entire content of those pages. If two pages produce the same hash, it is very likely that the pages are identical in content. This process can take rather long, especially if the system is not idling. As a result, the additional memory only becomes available after a significant amount of time, such as hours or sometimes days. Even worse, this kind of page sharing algorithm generally consumes significant CPU resources and increases the virtualization overhead by 10 to 20%.

  Page Fusion in uses logic in the Guest Additions to quickly identify memory cells that are most likely identical across VMs. It can therefore achieve most of the possible savings of page sharing almost immediately and with almost no overhead.

• Page Fusion is also much less likely to be confused by identical memory that it will eliminate, just to learn seconds later that the memory will now change and having to perform a highly expensive and often service-disrupting reallocation.

At this time, Page Fusion can only be controlled with VBoxManage, and only while a VM is shut down. To enable Page Fusion for a VM, use the following command:

VBoxManage modifyvm "VM name" --page-fusion on

You can observe Page Fusion operation using some metrics. RAM/VMM/Shared shows the total amount of fused pages, whereas the per-VM metric Guest/RAM/Usage/Shared will return the amount of fused memory for a given VM. See for information on how to query metrics.