From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Mosberger Date: Wed, 19 Jan 2005 17:31:05 +0000 Subject: Re: pipe performance regression on ia64 Message-Id: <16878.39257.133688.118974@napali.hpl.hp.com> List-Id: References: <200501181741.j0IHfGf30058@unix-os.sc.intel.com> <41ED9D06.1070301@yahoo.com.au> <16877.60406.192245.106565@napali.hpl.hp.com> <41EE5601.7060700@yahoo.com.au> In-Reply-To: <41EE5601.7060700@yahoo.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Nick Piggin Cc: davidm@hpl.hp.com, Linus Torvalds , "Luck, Tony" , linux-ia64@vger.kernel.org, linux-kernel@vger.kernel.org >>>>> On Wed, 19 Jan 2005 23:43:45 +1100, Nick Piggin said: Nick> Oh that's quite true. A bad score on SMP on the pipe benchmark Nick> does not mean anything is broken. Nick> And IMO, probably many (most?) lmbench tests should be run Nick> with all processes bound to the same CPU on SMP systems to get Nick> the best repeatability and an indication of the basic serial Nick> speed of the operation (which AFAIK is what they aim to Nick> measure). We need to keep an eye on both the intra- and the inter-cpu pipe-bandwidth and should measure them explicitly. The problem is that at the moment, we get one, the other, or a mixture of the two, subject to the vagaries of the scheduler. If we could reliably measure both intra and inter-cpu cases, we may well find new optimization opportunities (I'm almost certain that's the case for the cross-cpu case; which is probably the more important case, actually). --david