Date: Mon, 05 Oct 1998 19:04:55 +0200 From: Andre Oppermann <oppermann@pipeline.ch> To: dg@root.com Cc: "Mikhail A. Sokolov" <mishania@demos.net>, current@FreeBSD.ORG Subject: Re: -current panics.. Message-ID: <3618FC37.94EFFB2@pipeline.ch> References: <199810051526.IAA12441@implode.root.com>
next in thread | previous in thread | raw e-mail | index | archive | help
David Greenman wrote: > > >It comes out (once again, emprecially) that this is somehow caused > >by NMBCLUSTERS being >12288. Strange, since I recall wcarchive has it set to > >1024*48 or something, right? > > Wcarchive does NOT run a standard kernel. It has various tweaks, such as > greatly expanded kernel virtual address space, which are specific to that > machine and not appropriate for 99.999% of FreeBSD users. NMBCLUSTERS on Are those changes useful for networking only boxes (eg. Proxies)? Do you mind to write a small doc what to tweak where? > wcarchive is currently set to 80000, but will need to be doubled again to > 160000 before we can support 10000 concurrent users. The VM is evenly split Wow... 10'000 concurrent users... thats REALLY cool... > for 2GB for user processes and 2GB for the kernel (contrast that with > standard FreeBSD which is 3.75GB user and .25GB kernel). Does that mean the box will run with 4Gig of Memory (on the Xeon box)? -- Andre 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?3618FC37.94EFFB2>