Re: [PATCH] Do not reuse persistent connections for PUTs

> ons 2012-08-29 klockan 12:42 -0600 skrev Alex Rousskov:
>> Hello,
>>
>> I saw bogus ERR_ZERO_SIZE_OBJECT responses while testing Squid v3.1,
>> but the same problem ought to be present in v3.2 as well.
>>
>> A compliant proxy may retry PUTs, but Squid lacks the [rather
>> complicated] code required to protect the PUT request body from being
>> nibbled during the first try, when pconn races are possible.
>
> +1 on the patch from me.

Committed to trunk as r12319.

>> Today, we have a choice:
>>
>> A. Fail some PUTs. Close fewer pconns (current code).
>> B. Handle all PUTs. Open more connections (patched code).
>>
>> If this patch is accepted, performance bug 3398 will resurface. Henrik,
>> do you think committing the patch is the right decision here even though
>> it will reopen bug 3398?
>
> Yes, but with a plan to fix it correctly.
...

>> The bug title is wrong. There is a long discussion in the bug report
>> about what the bug is really about. I think a better bug title would be:
>> "persistent server connection closed before PUT".
>
> yes.
>
> Fix the bug title, reopen it with comment above and restore the check.

Done. Quality patches preserving PUT bodies (via 100-continue and/or
buffering) to optimize Squid pconn handling are welcomed.

Thank you,

Alex.
Received on Mon Sep 10 2012 - 23:20:38 MDT