fio has support for testing NBD servers directly

fio (“flexible I/O tester”) is a key tool for testing performance of filesystems and block devices. A couple of weeks ago I added support for testing NBD servers directly.

You will need libnbd 0.9.8 and to compile fio from git with:

./configure --enable-libnbd
make

Testing either nbdkit or qemu-nbd is trivial. Just follow the instructions here.

2 Comments

Filed under Uncategorized

2 responses to “fio has support for testing NBD servers directly

  1. Chris Murphy

    I’m wondering if libnbd is a useful substitute for loopback mounting an encrypted LUKS file for use as /home (or even individual user files)? The kernel’s loop device is brain dead simple so it should have super low latencies. But what if it doesn’t? And do either loop devices or nbd support multiqueuing? I know XFS and Btrfs make a lot of use of parallelism, so I wonder if certain workloads would suddenly hit a performance wall? Maybe ext4 parallelises journal and metadata writes, I’m not sure.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.