Introduction to Virtualization - Oracle Solaris 10 System Virtualization Essentials - page 12

Persistent storage bandwidth consumed: Some technologies offer the ability
to limit storage bandwidth consumed by one VE

■

Use of kernel data structures: Examples include shared memory identifiers,
including structures of finite size and ones that use another finite resource
such as RAM.

■

Types of Resource Controls Several methods of control exist. Some divide a resource
into chunks and assign each chunk to one workload. Resources with a finite size,
such as RAM or CPUs, can be divided using that method. However, this approach
wastes a portion of the resource because the portion that is currently assigned
to one VE is not in use but could be used by another VE. Some implementations
of this method reduce the amount of waste by dynamically resizing the reserved
resource based on resource usage.
Another method is a software-regulated limit, also called a resource cap . The
controlling mechanism—hypervisor or operating system—prevents VEs from us-
ing more than a specified amount. Unused portions of the resource can be used by
other VEs.
A third method to apportion CPU cycles—and the least wasteful of the three
methods—is the fair share scheduler (FSS). If there is sufficient capacity for every
VE to get the amount of CPU cycles it wants, each VE can use that amount.
Conversely, if there is contention for the resource, instead of enforcing a maxi-
mum amount of consumption, this method guarantees availability of a minimum
portion of a resource. An FSS allocates the resource in portions controlled by the
administrator, a strategy akin to that underlying the concept of a service level
agreement (SLA) that corporate customers require.
Allocation of network bandwidth is similar to allocation of CPU cycles. If you
are patient, you can always get more of a resource: a time slice for CPUs, a time
slot for network access. For this type of resource, it may not make sense to reserve
a quantity, but it does make sense to cap the rate at which one VE consumes the
resource over a brief sampling period. 2
The following resource controls are available in virtualization implementa-
tions. They can be used to manage the resource categories listed earlier.

CPU partitioning is the ability to assign a particular CPU or set of CPUs to
a VE. It reserves all of the compute power of a set of CPUs, but any unused
CPU cycles cannot be used by another VE and are wasted unless the reserva-
tion can be changed dynamically and automatically. However, this method

■

2. There are exceptions—for example, very-low-latency applications such as video and financial transac-

tions that require reserved bandwidth to function correctly.