XFS / EXT4 / Btrfs / F2FS / NILFS2 Performance On Linux 5.8

[Spam]

see https://openbenchmarking.org/embed.p...ha=a11596e&p=2
for each file system there are show the default options, and i take that NONE as the IO scheduler

Thanks. Yes, that probably makes sense.

[adriansev]

I can't find any info in the specs. Can you show me?

see https://openbenchmarking.org/embed.p...ha=a11596e&p=2
for each file system there are show the default options, and i take that NONE as the IO scheduler

[Spam]

I can't find any info in the specs. Can you show me?

[adriansev]

What IO-Scheduler was used?

I think this is shown in the first box, the one with system details, and i take it from there that "None" was de default IO scheduler for all (AFAIK ubuntu defaults to None for all nvme drives)

[Spam]

Great article

What IO-Scheduler was used? It is likely it would affect the Application Start-up times a lot. Michael could you re-run the test with different IO schedulers like mq-eadline, bfq and none?

[adriansev]

I would be really curious on the numbers on hdds ...

[Mario Junior]

Is f2fs stable enough for daily usage?

I used F2FS for months last year on my Gentoo installation. Zero problems!

[morydris]

Current OpenZFS in Ubuntu doesn't support Linux 5.8 kernel, looks like some compat patches were added to OpenZFS Git just a few weeks ago. Plus this was a comparison of mainline file-systems with a focus on Btrfs.

Understandable, but let me add my +1 for running including ZFS _when possible_ in these comparisons. (I use only ZFS everywhere except for /tmp-like storage)

[sandy8925]

Yet another *facepalm* for my decision to move all drives from XFS to EXT4, back when I got my first SSD.

Well I tried using F2FS and while it works, I had to disable automount because it required a file system check at boot time, which then slowed down boot time. Sigh.

I think I'll just do XFS in the future, see how it goes.

[Zan Lynx]

It's nice to see just how amazing XFS still is compared to more 'modern' file systems

XFS started out very modern for its time. It is still quite modern, in my opinion.

Anyway, nothing much has changed since the 1980s in computer science. If it was good then, it's still good now.