Date: Mon, 26 Mar 2001 20:40:53 -0500 From: "Deepak Jain" <deepak@ai.net> To: <freebsd-questions@freebsd.org> Subject: Network lockups on fxp0? Message-ID: <MLEFIJIDEIDHLFKGNEILEEBHCFAA.deepak@ai.net>
next in thread | raw e-mail | index | archive | help
This weekend we started seeing a bunch of new and stable machines (all 4.2-RELEASE) with varying levels of traffic (3mb/s to 15mb/s) withdrawing their MAC addresses from the network layer: fxp0: SCA timeout fxp0: DMA timeout (repeating) or: fxp0: SCB timeout fxp0: DMA timeout (repeating) Reboots clear it, but the systems are completely responsive at the console. The strangest thing is that of 10 machines that showed this over the weekend, machines would lock up in pairs and singles. This, even though the users on the servers were completely unrelated. 5 locked up in one data center another 5 in a different one, no other servers anywhere had any issues. These systems are all Tyan Thunder motherboards, with dual integrated sym controllers (SCSI) and dual integrated fast ethernet (fxp) ports. 1GB RAM, single and dual hard drives. The kernel's buffers and things are known good well over 50mb/s and the kernel is identical across all of them as well as 400 other 4.2 machines. No single server has gone down twice yet, so I have no idea of how long between occurrences. Occurrences don't seem to be related to traffic flows or system load. Any ideas of where to track down these issues? Thanks, Deepak Jain AiNET To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?MLEFIJIDEIDHLFKGNEILEEBHCFAA.deepak>