On Fri, Nov 18, 2011 at 01:39:37PM -0800, Jesse Gross wrote: > On Fri, Nov 18, 2011 at 1:36 PM, Ben Pfaff <b...@nicira.com> wrote: > > On Fri, Nov 18, 2011 at 11:08:08AM -0800, Jesse Gross wrote: > >> Both datapath and vport stats contain 64-bit members in a struct > >> but we write them directly in Netlink attributes which only > >> guarantee 32-bit alignment. ??This causes problems on RISC > >> architectures that care about alignment so this computes the stats > >> on the stack and then memcpy's them. > >> > >> Signed-off-by: Jesse Gross <je...@nicira.com> > > > > I think that it only causes performance problems. ??The network stack > > doesn't worry about unaligned accesses in cases where the unaligned > > accesses are rare. > > I thought that as well but it doesn't appear to be the case for > accesses in process context: on SPARC this was filling the kernel log > with error messages and killing ovs-vswitchd.
Wow. I learned something. Thanks for letting me know. _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
