Messages in this thread | | | Date | Thu, 25 Mar 2004 23:15:32 -0600 | From | Matt Mackall <> | Subject | Re: Fw: potential /dev/urandom scalability improvement |
| |
On Thu, Mar 25, 2004 at 08:51:54PM -0800, David Mosberger wrote: > >>>>> On Thu, 25 Mar 2004 22:19:26 -0600, Matt Mackall <mpm@selenic.com> said: > > > struct entropy_store { > > + /* mostly-read data: */ > > + struct poolinfo poolinfo; > > + __u32 *pool; > > + > > + /* read-write data: */ > > + spinlock_t lock ____cacheline_aligned; > > unsigned add_ptr; > > int entropy_count; > > int input_rotate; > > - struct poolinfo poolinfo; > > - __u32 *pool; > > - spinlock_t lock; > > }; > > Matt> Also, I think in general we'd prefer to stick the aligned bit at the > Matt> front of the structure rather than at the middle, as we'll avoid extra > Matt> padding. The size of cachelines is getting rather obscene on some > Matt> modern processors. > > Not sharing the cacheline between the mostly-read data and the > read-write data is the _point_ of this change. If you reverse the > order, the "poolinfo" and "pool" members will also get invalidated > whenever someone updates the write-intensive data.
Ok, previous observation made no sense; I should really be taking a nap right now. Hopefully this next one will make more sense: it ought to be ____cacheline_aligned_in_smp as the zero-byte spinlock struct still forces alignment.
-- Matt Mackall : http://www.selenic.com : Linux development and consulting - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |