by Zheng Zhang, Pedro Trancoso, Josep Torrellas
ftp://ftp.csrd.uiuc.edu/pub/misc/zzhang/research/database1.ps
Add To MetaCart
Abstract:
----Submitted for publication. Please do not distribute--Although cache-coherent shared-memory multiprocessors are sometimes used to run commercial workloads, little work has been done to characterize how well they support these workloads. In particular, we do not have many insights on the demands of commercial workloads on the memory subsystem of such machines. These issues are important because of the large market for commercial applications. In this paper, we examine the memory performance of a multiprocessor emulation of Postgres95, a public-domain database. Using address traces of up to 8-processor runs of TPC-B, OO1, and TPC-D, we find three major performance problems: contention for synchronization, stall due to I/O, and misses on shared data. Our data reveals a synchronization overhead equal to 29 % of the time, which can be partially removed with finergrained locks. I/O system calls can stall workloads for a period comparable to the workloads' computation time. However, increasing the size of the buffer cache to hold the database in memory reduces the stall by over 7 times. Finally, although the stall due to misses on shared data represents a modest 1-8 % of the time, it will probably increase with more processors and, unexpectedly, is caused mostly by misses on database metadata. 1
Citations
|
255
|
Parallelism in random access machines
– Fortune, Wyllie
- 1978
|
|
227
|
The POSTGRES next-generation database management system
– Stonebraker, Kemnitz
- 1991
|
|
166
|
MINT: A Front End for Efficient Simulation of Shared-Memory Multiprocessors
– Veenstra, Fowler
- 1994
|
|
155
|
The Postgres Storage System
– Stonebraker, Sept
- 1987
|
|
134
|
Contrasting characteristics and cache performance of technical and multi-user commercial workloads
– Maynard, Donnelly, et al.
- 1994
|
|
132
|
The Impact of Architectural Trends on Operating System Performance
– Rosenblum, Bugnion, et al.
- 1995
|
|
129
|
Granularity of locks and degrees of consistency in a shared data base
– GRAY, LORIE, et al.
- 1976
|
|
112
|
An adaptive cache coherence protocol optimized for migratory sharing
– Stenstrom, Brorsson, et al.
- 1993
|
|
107
|
Analysis of cache invalidation patterns in multiprocessors
– Weber, Gupta
- 1989
|
|
64
|
Characterizing the caching and Synchronization Performance of a Multiprocessor Operating System
– Torrellas, Gupta, et al.
- 1992
|
|
61
|
The Design of XPRS
– Stonebraker, Katz, et al.
- 1988
|
|
42
|
Characterization of Alpha AXP Performance Using TP and SPEC Workloads
– Cvetanovic
- 1994
|
|
40
|
Performance of an OLTP application on Symmetry multiprocessor system
– Thakkar, Sweiger
- 1990
|
|
23
|
An engineering database benchmark
– Cattell
- 1991
|
|
17
|
Speeding up Irregular Applications in Shared-Memory Multiprocessors: Memory Binding and Group Prefetching
– Zhang, Torrellas
- 1995
|
|
11
|
The POSTGRES95
– Yu, Chen
- 1995
|
|
4
|
The design and implementation of ingres
– al
- 1976
|
