Hacker News Reader

&totse users ran tests of zfs-fuse back in the day and found that it was actually noticeably slower than native ext3. From that, I'm inclined to argue the opposite: filesystems should almost definitely be in-kernel. Granted, their tests were on Linux, not on a modern microkernel.

Linux, fuse

there's your problem. it's not designed for it

I wouldn't use Fuse as your benchmark. All of plan9's filesystems are userspace (except the one that uses a dedicated machine). They can saturate 10gbe so your objections really concern Fuse and it's hosts.

Well, with the last sentence I tried to write:

Unfortunately userspace file systems like NTFS-3G are lot slower than their native counterparts.

Which is understandable, regarding kernel calls are still quite expensive.