Date: Fri, 4 May 2001 13:50:30 +0200 (CEST) From: Riccardo.Veraldi@fi.infn.it To: Wilko Bulte <wkb@freebie.demon.nl> Cc: <freebsd-alpha@freebsd.org> Subject: Re: vector: 0x670 Message-ID: <Pine.NEB.4.33.0105041341050.18872-100000@nikita.fi.infn.it> In-Reply-To: <E14vb8I-0006Zc-00@post.mail.nl.demon.net>
next in thread | previous in thread | raw e-mail | index | archive | help
yes it has the standard heatsink but looking at it, it so really too hot... there is also the patch foil but it looks a little bit messed the surface looks like not the same in all its part the colour changed, maybe the foil does not work anymore very fine... so that I have been thinking to add some of that special "glue" which is used on the Pee See between the Pee Sea CPU and the dissipator. My alpha dissipator looks realy vey very hot... and testing the system without the CPU dissipator it crashes with the same error in 2 minutes... there are 2 possibilites now, the cache is fucked or it is the CPU overheating problem. Someone told me it is really not likely a CPU internal problem like a TLB problem. Someone told me if the CPU is fucked because of overheating permanent damage it will not even start. IF it is the overheating problem I think I will solve it with a bigger dissipator the one from a Pentium 4 carefully adapted to the alpha CPU and adding a new fan also over the dissipator. I have no way right now to know if it is a CPU problem or cache problem or do I have one way to discover it ?? If it is the cache I have no chances, I have to throw away my motherboard I guess. The cache modules are hard wired on the motherboard I wanted to try something else anyway to see if the problem is a problem due overheating. if I put some very vold water in a proper glass box and put the box over the CPU it will help a lot to cool the system, and I Can try to stress the system in that way... I dunno... Iam desperate at this point! thanks Rick On Fri, 4 May 2001, Wilko Bulte wrote: > Date: Fri, 4 May 2001 08:40:14 GMT > From: Wilko Bulte <wkb@freebie.demon.nl> > To: Riccardo.Veraldi@fi.infn.it, Wilko Bulte <wkb@freebie.demon.nl>, > Terry Lambert <tlambert@primenet.com>, Riccardo.Veraldi@fi.infn.it, > freebsd-alpha@freebsd.org > Subject: Re: vector: 0x670 > > > Hi all thanks a lot for yoyur valuable help. > > I Think it might be a problem due to over heating. > > I removed the dissipator and when I did it hte machine crashed after a few > > minutes with the machien check 0x670 error... I will change dissipator > > Why? I expect this machine to have the standard DEC heatsink? Or has somebody > messed with it? > > > size and will add special glue for disipation between the CPU and > > Alpha CPUs by default have a Grafoil heat conducting foil between the > CPU and the heatsink. It is a small dark gray patch of foil. Is that one > missing? Bad idea.. Also, be careful not to over-torque the heatsink mounting > nuts! > > > dissipator and I will add a fan and let you know what is going to happen. > > Now hte CPU is so hot that Icannot even try to put my finger over it!! > > Be careful! You could permanently kill it this way!! > > Any chance you can make a picture available (borrowing a digital camera or > so) of what you have in this machine? > > Wilko > > > > > Rick > > > > > > On Wed, 2 May > > 2001, Wilko Bulte wrote: > > > > > Date: Wed, 2 May 2001 20:37:06 +0200 > > > From: Wilko Bulte <wkb@freebie.demon.nl> > > > To: Terry Lambert <tlambert@primenet.com> > > > Cc: Riccardo.Veraldi@fi.infn.it, freebsd-alpha@freebsd.org > > > Subject: Re: vector: 0x670 > > > > > > On Wed, May 02, 2001 at 06:27:38PM +0000, Terry Lambert wrote: > > > > > 670 Processor Uncorrectable unrecoverable cache or TLB errors, or > > > > > read of a non-existent I/O space > > > > > > > > > > > > > > > Do you think it can be an error due to overheating or do I have to throw > > > > > my AlphaStation away ?? > > > > > > > > No quick answers, but some things to try, and some advice and > > > > opinions... > > > > > > > > > > > > A cache error means that the processor is bad, if it's L1 cache; > > > > this could be the result of overheating. If it's L2 cache, the > > > > cause could still be overheating, but I've seen a lot of people > > > > trying to use cache chips that were too slow. > > > > > > I don't recall which AS version this was, but most of the have > > > SMD soldered on caches. Some have cache modules, some cache SIMMs. > > > In case of cache modules of any shape or form please check if they > > > are seated well. > > > > > > > - If it's overheating, that's usually the result of overclocking, > > > > either intentionally, or unintentionally. Make sure you are not > > > > doing that. > > > > > > Easily tested by trying if your fingers get fried when touching the > > > heatsink. > > > > > > > You might also be using memory which is too slow, or has fake > > > > parity instead of real parity (don't do that). Slow memory > > > > tends to become more of an issue when you stick in a lot of it, > > > > since the DMA refresh doesn't get around to each bank in time; > > > > this is particularly problematic if you are doing heavy I/O, > > > > so that the memory bus is latched for DMA, and refresh is thus > > > > delayed really long due to bus hold times; this is usually > > > > possible to adjust in the drivers or controller configurations > > > > and is often called "bus on" time. > > > > > > *Very* unlikely. Alpha machines are built to really drive lots > > > of memory. Not this whimpy PC stuff that drives only 4 SIMMs/DIMMs > > > from a single ASIC. > > > > > > > - I've occasionally loaded a machine with too much memory for > > > > it to reasonably handle refresh, given the memory bus speed > > > > and the bus-on time for some PCI controllers (I had an Adaptec > > > > that was a bus hog; when I loaded the disk subsystem with the > > > > extra amount of RAM, the refresh failed, and the system lost > > > > its mind). > > > > > > Again, unlikely. > > > > > > > A TLB error means that the contents of a Translation Lookaside > > > > Buffer are incorrect. This could be a kernel bug. > > > > > > Or the CPU is dead/dying. Seen that before.. > > > > > > -- > > > | / o / / _ Arnhem, The Netherlands email: wilko@freebsd.org > > > |/|/ / / /( (_) Bulte Powered by FreeBSD/alpha http://www.freebsd.org > > > > > > > > -- > | / o / / _ Arnhem, The Netherlands email: wilko@freebsd.org > |/|/ / / /( (_) Bulte http://www.freebsd.org > http://www.nlfug.nl > > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.NEB.4.33.0105041341050.18872-100000>