Date: Sat, 17 Aug 2013 10:26:51 -0700 From: aurfalien <aurfalien@gmail.com> To: freebsd-net@freebsd.org Subject: Myrinet 10GB, odd log errors Message-ID: <E29E80B6-71EC-40F3-AAC2-4BDF07AC73A5@gmail.com>
next in thread | raw e-mail | index | archive | help
Hi all, I posted on the general list but felt that perhaps this one list is more = appropriate. First, my setup, FreeBSD 9.2RC1 Myrinet 10GB card w/jumbo enabled. myri_info tool spits out this info; pci-dev at 05:00.0 vendor:product(rev)=3D14c1:0008(00) behind bridge root-port: 00:03.0 8086:3c08 (x8.1/x16.3) Myri-10G-PCIE-8A -- Link x8 EEPROM String-spec: MAC=3D00:60:dd:45:73:23 SN=3D413665 PWR=3D100 PC=3D10G-PCIE-8A-R PN=3D09-03852 XFI=3DAEL1010 TAG=3Dze_tools-1_4_45 EEPROM MCP, PRESENT, length =3D 95812, crc=3D0x92df14e9 ETHZ::1.4.55b-ht2100 2012/03/06 22:14:18 self extracting = firmware Simple-bundle: exec_len =3D 95808 Running MCP: ETH ::1.4.55b-ht2100 -P- 2012/03/06 22:14:18 myri10ge netq = firmware loader,conf; if_mxge_load=3D"YES" I'm getting these messages every 10-15-20 min or so; Aug 17 09:55:22 prometheus kernel: mxge0: slice 0 struck? ring state: Aug 17 09:55:22 prometheus kernel: mxge0: tx.req=3D493367942 = tx.done=3D493367886, tx.queue_active=3D0 Aug 17 09:55:22 prometheus kernel: mxge0: tx.activate=3D0 = tx.deactivate=3D0 Aug 17 09:55:22 prometheus kernel: mxge0: pkt_done=3D370348316 = fw=3D370348339 Aug 17 09:55:22 prometheus kernel: mxge0: Watchdog reset! Aug 17 09:55:22 prometheus kernel: mxge0: NIC did not reboot, not = resetting And my performance is somewhat crappy, avg 100MB/s (Megabytes). Any insight? Thanks in advance, - aurf=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E29E80B6-71EC-40F3-AAC2-4BDF07AC73A5>