On Tue, Mar 11, 2003 at 11:20:36AM -0800, Doug Ambrisko wrote: >Wes Peters writes: >| Flood it with wire speed 64-byte packets and drive it into receive >| interrupt livelock. Yup, the PCI bus is (most of) the problem here too. > >Can't reproduce it. Maybe they fixed it in the 8100L rev.? > >I tried a ping -f -s 22 to hit it with 64 byte packets. I also had >traffic going to the onboard gig and it wasn't impacted (granted the >source was a 100bit link tied to the gig link).
Are you sure you were generating "wire speed" packets - this is about 200,000 packets/sec at Fast speed. "ping -f" runs at whatever rate the remote end returns the packets at (or 100pps) - since it (mostly) waits for a response before sending another packet, you will never see livelock. In order to get 200,000 pps, you're going to need 5-10 hosts generating traffic, each with a good NIC and connected to the test system via a decent switch. You also need a proper network benchmarking tool - netperf (ports/netperf) or similar rather than ping. Peter To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
