At 03:58 PM 10/31/2007, Mike Tancsa wrote: >To: John Baldwin <jhb_at_freebsd.org>, freebsd-current_at_freebsd.org >From: Mike Tancsa <mike_at_sentex.net> >Subject: Re: em0: watchdog timeout ... > >At 04:21 PM 10/31/2007, John Baldwin wrote: >> > >> > em1_at_pci1:0:1: class=0x020000 card=0x115e8086 chip=0x105e8086 >> > rev=0x06 hdr=0x00 >> > vendor = 'Intel Corporation' >> > device = 'PRO/1000 PT' >> > class = network >> > subclass = ethernet >> > cap 01[c8] = powerspec 2 supports D0 D3 current D0 >> > cap 05[d0] = MSI supports 1 message, 64 bit >> > cap 10[e0] = PCI-Express 1 endpoint >> > >> > its also in FastE mode and not gigE. Not sure if that makes a >> > difference or not. >> >>What if you use MSI? > >How do I enable that ? Just to follow up on this thread for the archives, enabling MSI does indeed seem to stop, or at least mitigate watchdog timeouts. Its been almost 2 weeks on this one box and we have had zero watchdog timeouts. # vmstat -i interrupt total rate irq1: atkbd0 6 0 irq4: sio0 59020 0 irq17: em3 225204 0 irq19: atapci1 243645 0 cpu0: timer 1985129675 1997 irq256: em0 1460563078 1470 irq257: em1 2360550 2 irq258: em2 1300707554 1309 cpu1: timer 1985084642 1997 Total 6734373374 6777 However, it *seems* to increase the amount of missed packets. But, traffic patterns are a little higher, so I cant be certain. em0: Missed Packets = 5514 em0: Receive No Buffers = 1950 em0: RX overruns = 9 em2: Missed Packets = 220073 em2: Receive No Buffers = 29034 em2: RX overruns = 1498 ---MikeReceived on Wed Nov 14 2007 - 14:15:11 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:22 UTC