Date: Wed, 11 Oct 2000 13:31:10 -0400 (EDT) From: David Miller <dmiller@search.sparks.net> To: Andy Newman <atrn@zeta.org.au> Cc: "Brandon D. Valentine" <bandix@looksharp.net>, Warner Losh <imp@village.org>, Bill Moran <wmoran@columbus.rr.com>, freebsd-stable@FreeBSD.ORG Subject: Re: Anyone using adaptec 29160 Message-ID: <Pine.BSF.4.21.0010111327520.81564-100000@search.sparks.net> In-Reply-To: <20001010191538.A36348@juju.bsn>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 10 Oct 2000, Andy Newman wrote: [snip] > During the "writing intelligently" portion of a bonnie run (which I > figure is just good sized block output)... > > (da2:ahc0:0:2:0): SCB 0x74 - timed out in Message-in phase, SEQADDR == 0x146 I'm just taking a wild guess here, but these timed-out messages, combined with: > > Also of note is that under load the Ethernet can report... > > > xl0: transmission error: 90 > xl0: tx underrun, increasing tx start threshold to 120 bytes > xl0: transmission error: 90 > xl0: tx underrun, increasing tx start threshold to 180 bytes > xl0: transmission error: 90 > xl0: tx underrun, increasing tx start threshold to 240 bytes > xl0: transmission error: 90 > xl0: tx underrun, increasing tx start threshold to 300 bytes > xl0: transmission error: 90 > xl0: tx underrun, increasing tx start threshold to 360 bytes > > > Which I gather is to do with bus hogging, i.e, the 29160. Is probably a reflection of the fact that you can hook more up to a PCI bus than you can get through it. IE, pci is only 132 MB/sec, and you can probably exceed that with just the 29160, never mind the ethernet. The Tyan thunder series is looking better all the time:) --- David To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.21.0010111327520.81564-100000>