Re: Follow up on Benchmarking results for 3.1.10 vs 2.7.9

On 11/01/11 11:10, Henrik Nordström wrote:
> fre 2011-01-07 klockan 16:49 +1300 skrev Amos Jeffries:
>
>> This ticks off one more checkbox on the 2.7 obsoletion requirements (3.x
>> achieving RPS parity with 2.7).
>
> Well CPU usage on the 3.2 node was fairly higher so not quite there yet.
>
> Version 3.1.10-20101227 51.63%
> Version 2.7.STABLE9-20100923 33.42%

Yes, getting that down would be another plus. CPU load has not really
been put forward as a blocker for upgrades by the users though.

>
>> Now we are just waiting for feature parity to prevent upgrade problems.
>
> Not entirely sure we are even waiting for that.. squid-2 maintenance is
> pretty much non-existing today.

On my list of outstanding feature requirements:
  * port stale-while-revalidate (underway)
  * port storeurl_rewrite (underway)
  * fix COSS or merge rockstore (underway?)
  * port location_rewrite
  * collapsed forwarding
  * error_map
  * cache_peer monitor* options

The other options marked as regressions from 2.7->3.HEAD on a
convenience basis may happen or remain dropped.

I'm fairly confident now that 3.3 or somewhere in the 3.2 series can
take over from 2.7.

Amos

-- 
Please be using
   Current Stable Squid 2.7.STABLE9 or 3.1.10
   Beta testers wanted for 3.2.0.4