This paper presents Chameleon, an adaptive infrastructure, which allows dif
ferent levels of availability requirements to be simultaneously supported i
n a networked environment. Chameleon provides dependability through the use
of special ARMORs-Adaptive, Reconfigurable, and Mobile Objects for Reliabi
lity-that control all operations in the Chameleon environment. Three broad
classes of ARMORs are defined: 1) Managers oversee other ARMORs and recover
from failures in their subordinates. 2) Daemons provide communication gate
ways to the ARMORs at the host node. They also make available a host's reso
urces to the Chameleon environment. 3) Common ARMORs implement specific tec
hniques for providing application-required dependability. Employing ARMORs,
Chameleon makes available different fault-tolerant configurations and main
tains run-time adaptation to changes in the availability requirements of an
application; Flexible ARMOR architecture allows their composition to be re
configured at run-time, i.e., the ARMORS may dynamically adapt to changing
application requirements. In this paper, we describe ARMOR architecture, in
cluding ARMOR class hierarchy, basic building blocks, ARMOR composition, an
d use of ARMOR factories. We present how ARMORs can be reconfigured and ree
ngineered and demonstrate how the architecture serves our objective of prov
iding an adaptive software infrastructure. To our knowledge, Chameleon is o
ne of the few real implementations which enables multiple fault tolerance s
trategies to exist in the same environment and supports fault-tolerant exec
ution of substantially off-the-shelf applications via a software infrastruc
ture only. Chameleon provides fault tolerance from the application's point
of view as well as from the software infrastructure's point of view. To dem
onstrate the Chameleon capabilities, we have implemented a prototype infras
tructure which provides set of ARMORs to initialize the environment and to
support the dual and TMR application execution modes. Through this testbed
environment, we measure the execution overhead and recovery times from fail
ures in the user application, the Chameleon ARMORs, the hardware, and the o
perating system.