> with decent hardware. Because of the Unix FS, you really need
> 10000 RPM drives, and would be better off and cost less with 3
> 10,000RPM drives (6 10000RPM drives even better) then the 6
> cheap drives it was tested with in the bake-off. Also, a
Do you really think so? It's pretty common knowledge that number of spindles
is one of the bigger factors out there. I don't know that simply higher
throughput drives would buy all that much performance, when still saddled
with the FS.
> of course should still be tested.... but I think the low end
> would be better off with 2 7600RPM IDE drives.
That's *awfully* low end. I think the guys did a really nice job of proving
good price/performance for low-throughput markets. While Squid would
certainly perform better with more expensive hardware, it would then be
directly competing with every other entry, which all have the advantage of a
non-standard FS against Squid.
IMHO, Squid's advantages have always been the price, the openness, the
community and the feature set (including compliance), rather than raw
performance; most people that I know running high-throughput Squids spend an
awful lot of time tuning them.
Received on Thu Apr 08 1999 - 00:30:34 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:45:45 MST