Hmmm, were the file copy tests done on the same disk as the OS was installed to? In that case, it's a flawed benchmark (disks are slower towards the higher sector counts, and Windows takes up more space than linux). It also seems like a bad idea to turn off write caching... I wonder whether this means "turn off HD write caching" for linux but additionally "turn off FS write cache" for Windows? (there's a big
difference between the two).
Obviously Windows does have to worry about some things that Linux doesn't, namely DRM checks
Oh ffs, STOP THROWING THAT BLANKET STATEMENT.
Also, they forget to mention which mount options are used for ext3/ext4 - like, does it run with journalling, and in that case, which kind? If they compare unjournalled ext3 to NTFS, no wonder NTFS loses out on lots-of-small-files
I'd love to see more 'scientific' benchmarks, as I'm pretty sure NTFS isn't always the
best filesystem... but comparisons do have to be fair (ie., comparing to a journalled FS, copying from/to "comparable" locations (to avoid harddrive-speed issues), et cetera). This benchmark looks somewhat pseudo to me, but at least not as pseudo as the ones from that Adrian Kingsley-Hughes
BTW: imho benchmark results shouldn't be averaged, as that means abnormal spikes will influence the result. Instead, the best
timings should be chosen...