Showing papers by "Jason Nieh published in 2001"

Virtual-Time Round-Robin: An O(1) Proportional Share Scheduler

Abstract: Proportional share resource management provides a flexible and useful abstraction for multiplexing timeshared resources. However, previous proportional share mechanisms have either weak proportional sharing accuracy or high scheduling overhead. We present VirtualTime Round-Robin (VTRR), a proportional share scheduler that can provide good proportional sharing accuracy with O(1) scheduling overhead. VTRR achieves this by combining the benefits of fair queueing algorithms with a round-robin scheduling mechanism. Unlike many other schedulers, VTRR is simple to implement. We have implemented a VTRR CPU scheduler in Linux in less than 100 lines of code. Our performance results demonstrate that VTRR provides accurate proportional share allocation with constant, sub-microsecond scheduling overhead. The scheduling overhead using VTRR is two orders of magnitude less than the standard Linux scheduler for large numbers of clients.

Fast Indexing: Support for Size-Changing Algorithms in Stackable File Systems

Abstract: Stackable file systems can provide extensible file system functionality with minimal performance overhead and development cost. However, previous approaches provide only limited functionality. In particular, they do not support size-changing algorithms (SCAs), which are important and useful for many applications such as compression and encryption. We propose fast indexing, a technique for efficient support of SCAs in stackable file systems. Fast indexing provides a page mapping between file system layers in a way that can be used with any SCA. We use index files to store this mapping. Index files are designed to be recoverable if lost and add less than 0.1% disk space overhead. We have implemented fast indexing using portable stackable templates, and we have used this system to build several example file systems with SCAs. We demonstrate that fast index files have low overhead for typical user workloads such as large compilations, only 2.3% over other stacked file systems and 4.7%over non-stackable file systems. Our system can deliver better performance with SCAs than userlevel applications, as much as five times faster.

Fist: a system for stackable file-system code generation

Abstract: FiST: A Systemfor StackableFile-SystemCodeGeneration