Re: [PATCH] Propagate pinned connection persistency and closures to the client.

From: Alex Rousskov <rousskov_at_measurement-factory.com>
Date: Fri, 18 Jan 2013 10:07:54 -0700

On 01/18/2013 05:28 AM, Amos Jeffries wrote:

> In src/client_side_reply.cc:
>
> * "not sending to a closing on pinned zero reply " does not make any sense.
> Did you mean "not sending more data after a pinned zero reply "?
> although even that is a bit unclear. Since this is public log text I
> think we better clarify it a lot before this patch goes in.

"not sending more data after a pinned zero reply " is a good fix IMO.

This text is printed at level 3 so only developers need to understand
it. If you prefer, we can do "not sending more data after a pinned
ERR_ZERO_SIZE_OBJECT" but "zero reply" has a better chance of being
valid as errors change.

FWIW, this check is needed because Squid produces an
ERR_ZERO_SIZE_OBJECT response (as it should!), and we need to stop that
response from being sent to the client while an async notification is
being delivered to the client-side connection closing code. This race
happens because Store still delivers responses synchronously while many
other parts of the code have been already converted to use async calls.

Thank you,

Alex.
Received on Fri Jan 18 2013 - 17:07:59 MST

This archive was generated by hypermail 2.2.0 : Fri Jan 18 2013 - 12:00:07 MST