Re: [PATCH] Setting SO_KEEPALIVE on outbound connections

From: Alex Rousskov <rousskov_at_measurement-factory.com>
Date: Tue, 28 Jan 2014 15:21:42 -0700

On 01/28/2014 02:52 PM, eam_at_frap.net wrote:
> On Tue, Jan 28, 2014 at 01:03:24PM -0700, Alex Rousskov wrote:
>> Should this directive implementation be adjusted to also work for
>> disabling TCP keepalive for outbound connections if the admin wants to
>> overwrite a system-wide setting?
>
> I think this is a good idea. I don't want to disable system settings by
> default, however. Would this preclude using an onoff config type? I'd need
> a third "not set" state.

See memory_cache_shared in src/cf.data.pre and class YesNoNone.

> Maybe putting the formula for calculating the probe count in the docs
> would've headed off this confusion on my part? Or how about adding
> keep_count withouit deprecating timeout, as a conflicting parameter?
>
> (Now that I understand the intent here I care much less about it)

Matching an existing OS interface certainly has some merit. If you want
to do it, adding an option to specify the probe count directly is
acceptable IMHO, provided the new code rejects self-conflicting
configurations.

If you would rather not deal with coding this up, documentation
improvements are always welcome. You can, for example, submit a patch to
describe the mapping between Squid and popular sysctl or /proc settings.

Thank you,

Alex.
Received on Tue Jan 28 2014 - 22:22:04 MST

This archive was generated by hypermail 2.2.0 : Wed Jan 29 2014 - 12:00:14 MST