Re: [MERGE] 1/2: Populate cache_mem on disk hits

Henrik Nordstrom wrote:
> fre 2009-08-14 klockan 11:23 +1200 skrev Amos Jeffries:
>
>> cache_mem is where the fastest HITS/sec come from. Trashing it will
>> impact the very upper req/sec of Squid. As will forcing everything to
>> disk first. Then again with things going disk->memory (how soon Henrik?)
>> it may not be noticeable with very hot objects always being from memory.
>
> NAME: memory_cache_mode
> TYPE: memcachemode
> LOC: Config
> DEFAULT: always
> DOC_START
> Controls which objects to keep in the memory cache (cache_mem)
>
> always Keep most recently fetched objects in memory (default)
>
> disk Only disk cache hits are kept in memory, which means
> an object must first be cached on disk and then hit
> a second time before cached in memory.
>
> network Only objects fetched from network is kept in memory
> DOC_END
>
>
> Could easily add a tunable to require more than one hit to bring a disk
> object back into memory if desired.

Hmm, actually thinking further ahead (and getting off topic now that the
feature is approved 4:nil) ...

Do we want to start planning for when the memory cache settings are all
options on the one base tag?

ie. memory_cache <size> <options>

where <options> ::= <mode> <replacement_policy> <max-object-size>
<min-object-size> ... etc.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE6 or 3.0.STABLE18
   Current Beta Squid 3.1.0.13