Date: Wed, 23 Feb 2000 11:06:55 -0500 (EST) From: David Gilbert <dgilbert@velocet.ca> To: Nick Sayer <nsayer@quack.kfu.com> Cc: David Gilbert <dgilbert@velocet.ca>, freebsd-current@freebsd.org Subject: Re: Wierd AMD panics caused by VMWare? Message-ID: <14516.1439.654452.424962@trooper.velocet.net> In-Reply-To: <38B40262.FC4EEDD0@quack.kfu.com> References: <14515.59795.632514.748870@trooper.velocet.net> <38B40262.FC4EEDD0@quack.kfu.com>
next in thread | previous in thread | raw e-mail | index | archive | help
>>>>> "Nick" == Nick Sayer <nsayer@quack.kfu.com> writes: Nick> The only thing I would add is that by AMD I didn't mean Advanced Nick> Micro Devices. I meant /usr/sbin/amd. In my case this behavior Nick> has been observed on a Pentium III and on a K7, so it's CPU Nick> independent. Nick> The common denominator seems to be that the machine has to be Nick> very active. VMware stresses the vm system quite a bit (64M of Nick> shared memory with multiple processes digging around, etc). A Nick> very busy web server is going to do a lot of context switching Nick> (I think?). In that situation, it appears that the stack is Nick> being smashed. Nick> I tried insulating the code where my machines go nuts inside of Nick> splhigh() / splx(), but it didn't help. Nick> Is your machine running the automounter? No... but someone sent me some patches that deal with file descriptor coruption that may (or may not) solve my problem. It at least sounds plausable. Dave. -- ============================================================================ |David Gilbert, Velocet Communications. | Two things can only be | |Mail: dgilbert@velocet.net | equal if and only if they | |http://www.velocet.net/~dgilbert | are precisely opposite. | =========================================================GLO================ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?14516.1439.654452.424962>
