EXT4, Btrfs, NILFS2 Performance Benchmarks
Phoronix: EXT4, Btrfs, NILFS2 Performance Benchmarks
The past few Linux kernel releases have brought a number of new file-systems to the Linux world, such as with EXT4 having been stabilized in the Linux 2.6.28 kernel, Btrfs being merged into Linux 2.6.29, and most recently the NILFS2 file-system premiering with the Linux 2.6.30 kernel. Other file-systems have been introduced too during the past few Linux kernel release cycles, but these three have been the most talked about and are often looked at as being the next-generation Linux file-systems. Being the benchmarking junkies that we are, we have set out to compare the file-system performance of EXT4, Btrfs, and NILFS2 under Ubuntu using the Linux 2.6.30 kernel. We also looked at how these file-systems compared to EXT3 and XFS.
I guess the performance advantage of ext3 vs ext4 in some benches are due to ext3 defaulting to writeback data mode in 2.6.30 while ext4 still defaults to the slower and more secure ordered data mode, so that's not exactly a fair comparison.
Does this test used btrfs v0.19 from Jun 2009?
First of all, thanks for the great articles! Phoronix is great!
Btrfs developers were aware of lower performance from older benchmarks articles, as acknowledged here: http://btrfs.wiki.kernel.org/index.p...e#Benchmarking
They delivered one improvement on v0.19:
"In general, v0.19 is a dramatic speed improvement over v0.18 in almost every workload."
btrfs v0.19 is post-2.6.30
... so the benchmark probably didn't consider the latest v0.19 yet perhaps.
No it didn't. Linux 2.6.31 will include btrfs v0.19+ and therefore the dramatic performance improvements.
Originally Posted by andre.goddard
What's the point of benchmarking btrfs just before a major format change?
Red capslock text and reiser4 propaganda... where have I seen that before?
You have gotz to be kidding me...
Originally Posted by Sleuth
when the database numbers are as far off as they are in this test it makes me suspect that the fsyncs are being ignored by some filesystems and not by others. none of these filesystems are so far apart in design (except for possibly nilfs) that a 20x-60x variation is reasonable.