Messages in this thread | | | Subject | Re: [patch v3]numa: add a sysctl to control interleave allocation granularity from each node to improve I/O performance | From | Shaohua Li <> | Date | Thu, 15 Dec 2011 09:27:51 +0800 |
| |
On Thu, 2011-12-15 at 01:53 +0800, Andi Kleen wrote: > > That's what I want to avoid letting each apps to explicitly do it, it's > > a lot of burden. > > Usually apps that set NUMA policy can change it. Most don't anyways. > If it's just a script with numactl it's easily changed. Hmm, why should apps set different granularity? the granularity change is to speed up I/O, which should have the same value for all apps.
> > That's true only workload with heavy I/O wants this. but I don't expect > > it will harm other workloads. > > How do you know? I can't imagine how it could harm. Some arches can use big pages, big granularity should already been tested for years.
Thanks, Shaohua
| |