Date: Sun, 21 Mar 2004 14:38:04 -0500 From: "Ketrien I. Saihr-Kesenchedra" <ketrien@error404.nls.net> To: Martin Blapp <mb@imp.ch> Cc: current@freebsd.org Subject: Re: Disable HTT on Serverworks GC-HE chipset Message-ID: <6.0.1.1.2.20040321142158.039509c8@error404.nls.net> In-Reply-To: <20040320142809.S45059@cvs.imp.ch> References: <20040320031651.I45059@cvs.imp.ch> <405C3582.2070208@freebsd.org> <20040320142809.S45059@cvs.imp.ch>
next in thread | previous in thread | raw e-mail | index | archive | help
At 09:02 AM 3/20/2004, you wrote: >Hi Scott, >I have tried without HTT because someone on #bsdcode told me >to do so (ket_). Maybe you know who he is :-) Not all revisions >of the chipset seem to be buggy so far, but rev. 0 is for sure. Hi everyone. Yes, I'm here. :) Been a bit busy, haven't had time to toss in my $0.02. The issues I've seen are strictly limited to the GC-HE when HTT is enabled, though I have had issues with other areas on some boards. (I won't bore you with the details.) I've heard of and seen them reproduced on Linux (2.4.x and 2.6.x) and Windows as well, so it's not just FreeBSD. >Serversboards with this chipset are: >- Dell PowerEdge 2650 >- IBM xSeries >- Supermicro E7500 The E7500 is actually an Intel E7500 chipset. If there are HTT issues with the E7500, those are more likely operating system related. As far as I can tell, Supermicro doesn't currently offer any Serverworks boards. Tyan, on the other hand, has the Thunder GC-HE. The four-way Xeon Dells are also Serverworks, but I can't recall the model numbers offhand. >While using google I found the GC-LE chipsets seems to have problems >with write-coalescing: As I told Martin on IRC, I'm personally not sure on this one. It wouldn't surprise me, but I haven't had any issues with the GC-LE's personally. I wish I could offer some suggestions, but I really don't have enough experience with the GC-HE's to know what's going on. However, I know the typical GC-HE + HTT symptoms on Linux are excessive context switching (>250,000/sec) followed by semi-random panics. Windows is usually a sudden drop in performance, which requires a reboot to correct - sometimes the drivers can work around this apparently. Also random BSODs on occasion, but again, usually without drivers. -Ketrien I. Saihr-Kesenchedra <ketrien AT error404 DOT nls DOT net> # Maybe this world is another planet's hell. --Aldous Huxley Feanor smiles, "We, of course, are enlightened and s/Maybe t/T"
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?6.0.1.1.2.20040321142158.039509c8>