[Serusers] Re: [Users] TM : retransmission timers

[Weiter Leiter]

This definitely sounds impressive, but, FMI:

On 11/28/06, Andrei Pelinescu-Onciul <andrei at iptel.org> wrote:

> Why would you want to change the hash size from the config? Do you
> really know somebody who wanted/needed to do this? If you use a variable
> for the hash size the compiler will not be able to optimize the modulo
> operation (x % hash_size) and it will have to implement it using slow
> DIVs. Using a 2^k constant the whole modulo operation will be optimized
> to  & (2^k - 1). A DIV takes minimum 56 cycles on a P4 and 16 on an
> AMD64 (and this if the operands are in _registers_ which will probably
> not happen for the variable containing the hash size). An  "and" takes
> only 1 cycle (and the operand is an immediate constant).
> Look also at the rest of the hash function: it uses only XORs, shifts
> and additions, operations that all execute in 1 cycle => for normal small
> uris your DIV operation will take a very significant time from the
> total ammount spent hashing.


Unfortunately Daniel didn't reply anymore (maybe he wants to cover trade
secrets ;-) ), but OpenSER uses now the much faster masking operation
instead of the always costly modulo (which I expect to execute faster even
with the cost of extra memory fetch for the hash size). I don't know whether
hashing is also cheap or the result has a good distribution, but this should
be something you should look at: I expect he did some research too, before
changing, maybe this is a fix worth porting.

WL.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.kamailio.org/pipermail/users/attachments/20061129/1907d3a7/attachment.htm