Hendrik Voigtl�nder wrote: > I wonder: Is my squid not fast enough, are there other bottlenecks or is > simply the demand not higher.
Unless the average service time seems high or users are noticing delays, then Squid is probably not bottlenecking enough to worry about. > Requests/s: 35...40 > Hit Service Time: 3ms > Miss Service Time: 250ms Those service times look fine. > Load average ist at 0.5...0.8 (single xeon, HT enabled), load sometimes > at 1.0...1.2 when monitoring probes are forked. Perfectly acceptable. Why are you concerned about performance? What bottlenecks are you seeing? Adam
