Hi
I've got a quite large network here and a busy squid proxy server (~1500 boxes... filled until top 6Mb/s internet link). I've already tunned the number of filedescriptors and memory (cache_mem) available to squid and I'm using LFUDA as removal policy. Looking around to improve squid's performance I'm testing diskd and async-io storage systems. Trying async-io I've compiled squid with:
--enable-async-io=30 --enable-removal-policies="heap,lru" --enable-storeio="aufs,coss,diskd,ufs"
and a snippet of my squid.conf (it's just for testing):
cache_dir aufs /cache1 100 64 256
So... When I start squid, It should spawn 30 threads, shouldn't it? But it isn't spawnning... Is this the right behaviour or I am messing thing up ?
thanks a lot in advance.
--
[]'s Lucas Brasilino [EMAIL PROTECTED] http://www.recife.pe.gov.br Emprel - Empresa Municipal de Informatica (pt_BR) Municipal Computing Enterprise (en_US) Recife - Pernambuco - Brasil Fone: +55-81-32327078
