Messages in this thread | | | Date | Mon, 23 Feb 2009 10:34:58 -0500 (EST) | From | Christoph Lameter <> | Subject | Re: [RFC PATCH 00/20] Cleanup and optimise the page allocato |
| |
On Mon, 23 Feb 2009, Andi Kleen wrote:
> > Counters are surprising expensive, we spent a good chuck of our time in > > functions like __dec_zone_page_state and __dec_zone_state. In a profiled > > run of kernbench, the time spent in __dec_zone_state was roughly equal to > > the combined cost of the rest of the page free path. A quick check showed > > that almost half of the time in that function is spent on line 233 alone > > which for me is; > > > > (*p)--; > > > > That's worth a separate investigation but it might be a case that > > manipulating int8_t on the machine I was using for profiling is unusually > > expensive. > > What machine was that? > > In general I wouldn't expect even on a system with slow char > operations to be that expensive. It sounds more like a cache miss or a > cache line bounce. You could possibly confirm by using appropiate > performance counters.
I have seen similar things occur with some processors. 16 bit or 8 bit arithmetic can be a problem.
> > Converting this to an int might be faster but the increased > > memory consumption and cache footprint might be a problem. Opinions? > > One possibility would be to move the zone statistics to allocated > per cpu data. Or perhaps just stop counting per zone at all and > only count per cpu.
Statistics are in a structure allocated and dedicated for a certain cpu. It cannot be per cpu data as long as the per cpu allocator has not been merged. Cache line footprint is reduced with the per cpu allocator.
> > So, by and large it's an improvement of some sort. > > That seems like an understatement.
Ack. There is certainly more work to be done on the page allocator. Looks like a good start to me though.
| |