Messages in this thread | | | Date | Fri, 7 Dec 2012 20:39:49 -0500 | From | Chris Mason <> | Subject | Re: [PATCH, 3.7-rc7, RESEND] fs: revert commit bbdd6808 to fallocate UAPI |
| |
On Fri, Dec 07, 2012 at 05:17:05PM -0700, Dave Chinner wrote: > On Fri, Dec 07, 2012 at 02:03:06PM -0500, Chris Mason wrote:
[ dead and beaten fallocate ponies ]
> > > On a single flash drive doing random 4K writes, xfs does 950MB/s into > > regular extents but only 400MB/s into preallocated extents. > > > > http://masoncoding.com/presentation/perf-linuxcon12/fallocate.png > > This is bordering on irrelevancy, but can you provide the workload > you were running to generate this graph? Random 4k writes could be > anything, really.
This one was fio aio/dio, I'll dig out the job file and rerun it on 3.7-rc on Monday. Any real random write is going to show this with enough load.
> > In my experience, applications that actually do processing between > random write IOs don't see anywhere near the same degradation as > such micro-benchmarks tend to indicate can occur with unwritten > extents. Are you seeing this level of degradation in real-world applications? > If you give me a reason to fix it (and the hardware to test it on), > I'm pretty sure I can bring the overhead down to just a few percent > on fully featured SSDs like FusionIO devices...
We should have a card I can send, drop me the address.
For the workload...that's harder. We can talk all day about what a normal random write workload is, but if you have a fio job that you think represents real world, I can run that.
[ much nodding ;) ]
| |