From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <48B2AC6E.9060100@domain.hid> Date: Mon, 25 Aug 2008 14:58:22 +0200 From: Jan Kiszka MIME-Version: 1.0 References: <20080812075358.4cg1ix9945msccsc@domain.hid> <48A12EA8.4070601@domain.hid> <48A34D75.9090509@domain.hid> <48A359D4.9090002@domain.hid> <48A3D20B.2080509@domain.hid> <48A3D595.9040607@domain.hid> <20080814125307.1uviqgmj95no4k0k@domain.hid> <48A43555.3070701@domain.hid> <48A45084.3000208@domain.hid> <48A46408.7010602@domain.hid> <48A6B8EC.8020302@domain.hid> <48AA9DAA.3040801@domain.hid> <20080819123133.n9ool6j5d5msowk8@domain.hid> <48AAD622.8030402@domain.hid> <48AB32B8.5040403@domain.hid> <48ABE629.5090303@domain.hid> <20080825141624.3hk4ndxf9xwcgkcg@domain.hid> In-Reply-To: <20080825141624.3hk4ndxf9xwcgkcg@domain.hid> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: [Adeos-main] [RTnet-users] e1000 & MSI List-Id: General discussion about Adeos List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: bernhard@domain.hid Cc: adeos-main , rpm@xenomai.org, RTnet-users@domain.hid bernhard@domain.hid wrote: > Zitat von Philippe Gerum : > >> The risk in ironing those PCI locks is to run with hw interrupts >> disabled for a >> long time, inducing pathological latencies, so running RTAI's latency test in >> the background should help detecting those peaks. >> >> However, we may find nothing bad if the kernel uses the MMConfig >> access method >> to the PCI space since this is basically fast mmio there. But since >> you seem to >> be running on x86_32, we may want to check whether BIOS or direct >> access to the >> PCI config does not raise the typical latency too much, as well (I'm >> unsure that >> PCI_GOBIOS will give us decent results though). >> >> To sum up: with different settings for the PCI config access method in "Bus >> options" (by order of criticality, MMConfig then Direct, then maybe >> BIOS), does >> the latency tool report pathological peaks? >> > > Hi Philippe > > I played with the different PCI configurations and the results are > devastating. Latencies (and jitter) skyrocket after some minutes of > testing and peak at several milliseconds. I didn't do the regression > with 'normal' INTs though, but that's something up next. Additionally > MMCONFIG produced some strange msg at boot. Could you catch some path traces with the ipipe latency tracer when this happens? See [1] for details. Dunno if RTAI's latency tool is prepared to support you here (triggering a trace on new peaks), but CONFIG_IPIPE_TRACE_IRQSOFF should already suffice in this case - if the latency is due to IRQ disabling over PCI code. Thanks, Jan [1] http://www.xenomai.org/index.php/I-pipe:Tracer -- Siemens AG, Corporate Technology, CT SE 2 Corporate Competence Center Embedded Linux