> > > > Are there parameters in the configuration to tell squid to go full > > > > throttle with the server, close the connection and then continue alone with > > > > the client? > > > http://www.squid-cache.org/Versions/v3/3.0/cfgman/read_ahead_gap.html > > Thx, works great. > > Can I set the same value as maximum_object_size, or should it be a little bit > > lower? > It buffers in memory so don't be too agressive about it.. Ahhh... when will it be written in the cache_dir and freed from RAM? Only at the end of the client's connection? I suppose there is no option to tell squid to write it asap? The problem is that the squids will be used to cache videos. 100 clients asking for 100 different (not cached yet) xxMB videos will indeed exhaust the RAM... Is there a way to avoid this scenario? More generally, when a client asks for a cached object; is the whole object loaded in RAM or is it loaded "block" by "block"? Thx, JD
