Systems Performance: Enterprise and the Cloud by Gregg Brendan

Author:Gregg, Brendan [Gregg, Brendan]
Language: eng
Format: mobi
Publisher: Pearson Education
Published: 2013-10-06T16:00:00+00:00

Table 8.5 File System Benchmark Expectations

Some file system benchmark tools are not clear about what they are testing and may imply a disk benchmark but use a small total file size and return entirely from cache instead. See Section 8.3.12, Logical versus Physical I/O, to understand the difference between testing the file system (logical I/O) and testing the disks (physical I/O).

Some disk benchmark tools operate via the file system by using direct I/O to avoid caching and buffering. The file system still plays a minor role, adding code path overheads and mapping differences between file and on-disk placement. This is sometimes a deliberate strategy for testing the file system: analyzing worst-case performance (0% cache hit rate). This strategy is becoming increasingly unrealistic, as applications are more commonly expecting a significant cache hit rate due to larger memory systems.

See Chapter 12, Benchmarking, for more on this general topic.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.