Results 1 -
2 of
2
The Slab Allocator: An Object-Caching Kernel Memory Allocator
- USENIX SUMMER TECHNICAL CONFERENCE
, 1994
"... This paper presents a comprehensive design overview of the SunOS 5.4 kernel memory allocator. This allocator is based on a set of object-caching primitives that reduce the cost of allocating complex objects by retaining their state between uses. These same primitives prove equally effective for mana ..."
Abstract
-
Cited by 54 (3 self)
- Add to MetaCart
This paper presents a comprehensive design overview of the SunOS 5.4 kernel memory allocator. This allocator is based on a set of object-caching primitives that reduce the cost of allocating complex objects by retaining their state between uses. These same primitives prove equally effective for managing stateless memory (e.g. data pages and temporary buffers) because they are space-efficient and fast. The allocator’s object caches respond dynamically to global memory pressure, and employ an objectcoloring scheme that improves the system’s overall cache utilization and bus balance. The allocator also has several statistical and debugging features that can detect a wide range of problems throughout the system. 1.
A Framework for Storage Management Evaluation in Persistent Object Systems
, 1997
"... With the advent of object oriented database management systems, the need to evaluate and improve the performance of these systems has led to research in the area of system benchmarking. One traditional approach has been to implement an application using a particular database management system and in ..."
Abstract
- Add to MetaCart
With the advent of object oriented database management systems, the need to evaluate and improve the performance of these systems has led to research in the area of system benchmarking. One traditional approach has been to implement an application using a particular database management system and incorporate methods in the application to perform analysis and experimentation on functions of the system, such as storage management. In this paper, we present another approach to performance evaluation. We describe PTFF, a common trace file format, and Tragedy, a trace generation tool. The advantages of our approach include: Applications can be modeled independent of any database management language or system. The instrumentation necessary to perform experimentation and analysis of storage management is transparent to the application layer. The trace event files only have to be generated once and can be used for several experiments. The development of applications for system benchmar...

