Messages in this thread | | | Subject | Re: [RFC PATCH] fuse: support splice() reading from fuse device | From | Miklos Szeredi <> | Date | Thu, 20 May 2010 22:22:05 +0200 |
| |
On Thu, 20 May 2010, Matthew Wilcox wrote: > On Thu, May 20, 2010 at 10:07:23PM +0200, Miklos Szeredi wrote: > > > It says nothing at all, in short. You need to have a real source, and a > > > real destination. Not some empty filesystem and /dev/null destination. > > > > Sure, I will do that. It's just a lot harder to measure the effects > > on hardware I have access to, where the CPU speed is just damn too > > large compared to I/O speed. > > Try running a CPU burner on all the cores. Something that's low priority, > so it'll be preempted by FUSE, and doesn't consume much cache.
Umm, that doesn't really make the CPU any slower, it just makes it consume more power.
Miklos
| |