Messages in this thread | | | Date | Wed, 11 Sep 2002 22:05:14 +0530 | From | Dipankar Sarma <> | Subject | Re: [PATCH] Read-Copy Update 2.5.34 |
| |
On Wed, Sep 11, 2002 at 10:03:28AM -0400, Robert Love wrote: > On Wed, 2002-09-11 at 08:20, Dipankar Sarma wrote: > > > Not sure how reliable these numbers are. > > And how bad is the performance drop from 2.5.34-preempt to > 2.5.34-preempt-rcu?
Hi Robert,
Here are the detailed results from reflex benchmark all with 2.5.34 kernel and 4CPU p3 xeon with 1MB L2 cache and 1GB RAM.
vanilla-preempt rcu_poll-preempt vanilla rcu_poll -------------- ---------------- ------- -------- 80 , 40 , 1.593 1.569 1.545 1.536 112 , 40 , 1.544 1.554 1.544 1.535 144 , 40 , 1.595 1.552 1.545 1.586 176 , 40 , 1.568 1.605 1.615 1.536 198 , 40 , 1.562 1.577 1.582 1.651 230 , 40 , 1.563 1.583 1.581 1.554 244 , 40 , 1.671 1.638 1.631 1.571
> > I am glad you guys support kernel preemption (not that you have a chance > at this point) but I hope it was not an afterthought. >
Forgot to mention, earlier implementations of RCU like in K42 had complete preemption support, so the linux implementation is not really new. We added it after preemption support went into Linus' tree.
Thanks -- Dipankar Sarma <dipankar@in.ibm.com> http://lse.sourceforge.net Linux Technology Center, IBM Software Lab, Bangalore, India. - 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/
| |