On 4/9/08, Jeffrey 'jf' Lim wrote:
I'm running dual mini-ITX Migrus C787-1.5G motherboards in a 1U case - both
have the Via C7 1.5 GHz processor and a gig of RAM each. Aside from the
issue of versions of OpenBSD up to 4.2 not liking the three-port gigabit
ethernet daughter boards very much, the machines are just downright
painfully slow. Slow like molasses, and the OS doesn't seem to matter as I
have tried several OpenBSDs, both Enterprise and Desktop editions of Ubuntu
4.07 and 4.10, and even Windows XP Home, Pro, and Server 2003. Nothing
speeds them up and even drawing a window using any manager is sometimes more
than the things can handle.
I can't help but think that the C7s aren't as i386-compatible as Via would
have us believe, even though they were billed as great for home media center
PCs that could handle encrypted and copy-protected media better than
anything else with the build-in decryption hardware. I wasn't interested in
this particular application - I needed something very small and minus
towering heat sinks to fit in the 1U case. The ml was full of Soekris
router throughput issues at the time, so I didn't consider them to be the
best option.
I bought them to be part of a 6U portable rack that served out VSAT
non-military internet access to my unit when deployed, and while they did
the job they about killed me with frustration in the process. I could be
persuaded to part with one of the motherboards if someone in the project is
interested in doing development work for this arch.
JC
| Steven Rostedt | Re: Major regression on hackbench with SLUB |
| Jeremy Fitzhardinge | [PATCH 02 of 36] x86: add memory clobber to save/loadsegment |
| Tarkan Erimer | Re: Dual-Licensing Linux Kernel with GPL V2 and GPL V3 |
| Paul Jackson | Re: cpuset-remove-sched-domain-hooks-from-cpusets |
git: | |
| David Miller | Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock(). |
| Arjan van de Ven | Re: [GIT]: Networking |
| Gerrit Renker | [PATCH 03/37] dccp: List management for new feature negotiation |
| Jarek Poplawski | [PATCH iproute2] Re: HTB accuracy for high speed |
