Phoronix has published a nice 5 page article, which includes some in-depth file system benchmarks. They tested file systems such as Btrfs, Ext4, Xfs, ZFS-Fuse and the ZFS kernel module from KQ Infotech.
Here is an excerpt taken from the conclusion section of the article:
“In terms of our ZFS on Linux benchmarks if you have desired this Sun-created file-system on Linux, hopefully it is not because of the performance expectations for this file-system. As these results illustrate, this ZFS file-system implementation for Linux is not superior to the Linux popular file-systems like EXT4, Btrfs, and XFS. There are a few areas where the ZFS Linux disk performance was competitive, but overall it was noticeably slower than the big three Linux file-systems in a common single disk configuration. That though is not to say ZFS on Linux will be useless as the performance is at least acceptable and clearly superior to that of ZFS-FUSE. More importantly, there are a number of technical merits to the ZFS file-system that makes it one of the most interesting file-systems around.”
With that being said…I believe that a lot of times when people are choosing to use ZFS as an underlying filesystem for a project, they are not doing so due to it’s reputation as a wonderfully fast file system. ZFS features such as data integrity, large capacity, snapshotting and deduplication are more likely going to drive your rational for using ZFS as part of your backend storage solution.
Another thing to note about these benchmarks is that these tests were run on the beta version of the kernel module, and I assume that once the GA version (and source code) is released, there will be plenty of opportunities to try and mitigate some of these concerns as much as possible, however on the other hand you are going to have to live with some of the overhead that comes with using ZFS if you want to take advantage of it’s large feature set.