> June 16, 2015 3:57 PM <jbeul...@suse.com> wrote: > >>> On 16.06.15 at 05:55, <quan...@intel.com> wrote: > >> From: Zhang, Yang wrote on June 16, 2015 11:07 AM > >>> Jan Beulich wrote on 2015-06-15: > >> >>>> On 13.06.15 at 16:44, <quan...@intel.com> wrote: > >> >>> On 12.06.15 at 14:47, <jbeul...@suse.com> wrote: > >> >>>>>> On 12.06.15 at 04:40, <quan...@intel.com> wrote: > >> >>>> I tested it by a Myri-10G Dual-Protocol NIC, which is an ATS device. > >> >>>> for an invalidation: > >> >>>> By sync way, it takes about 1.4 ms. > >> >>>> By async way, it takes about 4.3 ms. > >> > >> It is a typo for the time: should be 1.4 us and 4.3 us. > >> > > > > yes, it is 1.4 us and 4.3 us. > > Thanks. > > > > I also have tested iotlb sync and async invalidation. > > For sync way: it takes about 3.2 us. > > For async way: it takes about 5.3 us. > > That's _longer_ than in the ATS case. Is that realistic? > > Jan
1.4 us and 4.3 us are average values of context/iotlb sync and asyc for a large sample of data. 3.2 us and 5.3 us are average values of iotlb for a small sample of data. Quan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
