IRON FILE SYSTEMSVijayan Prabhakaran Disk drives are widely used as a primary medium for storing information.While commodity file systems trust disks to either work or fail completely, modern disks exhibit complex failure modes such as latent sector faults and block corrup-tions, where only portions of a disk fail.

We propose a novel method to measure the dependability of journaling file systems. In our approach, we build models of how journaling file systems must behave under different journaling modes and use these models to analyze file system behavior under disk failures. Using our techniques, we measure the robustness of three important Linux journaling file systems: ext3, Reiserfs and IBM JFS. From our analysis, we identify several design flaws and correctness bugs present in these file systems, which can cause serious file system errors ranging from data corruption to unmountable file systems. 1

We introduce general methodologies for benchmarking the availability and maintainability of computer systems. Our methodologies are based on fault injection, used to purposefully compromise availability and to bring systems to a state where maintenance is required. Our availability benchmarks leverage existing performance benchmarks for workload generation and data collection, measure availability in terms of quality of service variation over time, and can produce results in both detail-rich graphical presentations or in distilled numerical summaries.

Benchmarks have historically played a key role in guiding the progress of computer science systems research and development, but have traditionally neglected the areas of availability, maintainability, and evolutionary growth, areas that have recently become critically important in high-end system design. As a first step in addressing this deficiency, we introduce a general methodology for benchmarking the availability of computer systems. Our methodology uses fault injection to provoke situations where availability may be compromised, leverages existing performance benchmarks for workload generation and data collection, and can produce results in both detail-rich graphical presentations or in distilled numerical summaries. We apply the methodology to measure the availability of the software RAID systems shipped with Linux, Solaris 7 Server, and Windows 2000 Server, and find that the methodology is powerful enough not only to quantify the impact of various failure conditions on the availability of these systems, but also to unearth their design philosophies with respect to transient errors and recovery policy.

We introduce general methodologies for benchmarking the availability and maintainability of computer systems. Our methodologies are based on fault injection, used to purposefully compromise availability and to bring systems to a state where maintenance is required. Our availability benchmarks leverage existing performance benchmarks for workload generation and data collection, measure availability in terms of quality of service variation over time, and can produce results in both detail-rich graphical presentations or in distilled numerical summaries.

Benchmarks have historically played a key role in guiding the progress of computer science systems research and development, but have traditionally neglected the areas of availability, maintainability, and evolutionary growth, areas that have recently become critically important in high-end system design. As a first step in addressing this deficiency, we introduce a general methodology for benchmarking the availability of computer systems. Our methodology uses fault injection to provoke situations where availability may be compromised, leverages existing performance benchmarks for workload generation and data collection, and can produce results in both detail-rich graphical presentations or in distilled numerical summaries. We apply the methodology to measure the availability of the software RAID systems shipped with Linux, Solaris 7 Server, and Windows 2000 Server, and find that the methodology is powerful enough not only to quantify the impact of various failure conditions on the availability of these systems, but also to unearth their design philosophies with respect to transient errors and recovery policy.

We introduce general methodologies for benchmarking the availability and maintainability of computer systems. Our methodologies are based on fault injection, used to purposefully compromise availability and to bring systems to a state where maintenance is required. Our availability benchmarks leverage existing performance benchmarks for workload generation and data collection, measure availability in terms of quality of service variation over time, and can produce results in both detail-rich graphical presentations or in distilled numerical summaries. Our