Re: offline_mode

From: Adrian Chadd <adrian@dont-contact.us>
Date: Sat, 5 Apr 2008 14:56:16 +0800

I think its something that should be better fleshed out, yes.

There's probably bigger fish to fry in the codebase though.

Adrian

On Sat, Apr 05, 2008, Amos Jeffries wrote:
> Bug 1356 brings up some confusion over what the true meaning of
> 'offline' is for this option.
>
> As Henrik pointed out fairly early in the discussion there, squids
> actual behavior is to 'aggressively cache', not a true
> "network-disconnected" mode.
>
> I'm proposing that the option have one or both of two things done to it:
>
> 1) simply renamed to something more descriptive ie cache_aggressive on/off.
>
> 2) that it be kept as 'offline' but changed to accept a range of flags
> indicating which of the external-interface engines inside squid are to
> behave as if they were offline. ie "offine cache dns auth"
>
> When any given feature is marked for offline it behaves in a true "not
> packet leaves the interface" fashion.
> ie
> - 'dns' means no new DNS lookups are performed.
> - 'cache' means no refreshes are performed (RFC 2616 allows for
> stale objects already in cache to be used with certain response types)
> - etc.
>
> We may need to exempt localhost traffic from offline mode explicitly.
> But will need to be consistent with it.
>
> The existing 'aggressive caching' behaviour may be possible by other
> means with cache ACL or refresh_patterns. Or a 'cache=semi' style tag
> might be chosen.
>
> Or, we may choose to do both of the above changes.
>
> Amos
> --
> Please use Squid 2.6.STABLE19 or 3.0.STABLE4

-- 
- Xenion - http://www.xenion.com.au/ - VPS Hosting - Commercial Squid Support -
- $25/pm entry-level VPSes w/ capped bandwidth charges available in WA -
Received on Sat Apr 05 2008 - 00:38:59 MDT

This archive was generated by hypermail 2.2.0 : Wed Apr 30 2008 - 12:00:07 MDT