Size Can Matter: Throughput Performance with a Disk-Based Journal - Part 4
Feb 04, 2010, 00:03 (0 Talkback[s])
(Other stories by Jeffrey B. Layton)
"Metadata performance is one of the most overlooked aspects of
file system performance. It can have a tremendous impact on how the
performance of a file system “feels” and, perhaps more
importantly, can affect the execution time of applications that do
a great deal of metadata (and, believe me, there are some).
However, there are applications that do a great deal of streaming
of data to the file system. Consequently, there are driven by
throughput performance, not metadata performance. Besides, most
people quote the performance of systems in terms of throughput so
it’s always good to present results where people have an
innate understanding of the results.
"In this article we use IOzone to measure throughput performance
for various journal sizes when the journal is located on a separate
disk. The block size is also varied to understand the impact of
block size on throughput performance. The results can be a bit more
complex to interpret because we now have two variables - journal
size and block size. Plus the IOzone tests run 13 different IO
tests as executed in this article.
"It’s been a while since the IOzone has been used in an
article here so let’s begin with a quick review."
- Size Can Matter: Would You Prefer the Hard Drive or the Ramdisk this Evening? Part 3(Jan 27, 2010)
- Size Can Matter: Ramdisk Journal Metadata Performance - Part 2(Jan 20, 2010)
- Improving MetaData Performance of the Ext4 Journaling Device(Dec 30, 2009)
- Helping Out SSDs(Nov 04, 2009)
- Tuning CFQ - What Station is That?(Oct 15, 2009)
- I Have a Schedule to Keep - IO Schedulers(Oct 07, 2009)
- I Feel the Need for Speed: Linux File System Throughput Performance, Part 1(Sep 16, 2009)
- Metadata Performance Exploration Part 2: XFS, JFS, ReiserFS, ext2, and Reiser4(Sep 11, 2009)
- Metadata Performance of Four Linux File Systems(Sep 02, 2009)