[Linux-ha-dev] ipcsocket.c, ipctest.c: advice, please

[David Lee]

On Fri, 9 Mar 2007, Lars Marowsky-Bree wrote:

> On 2007-03-09T13:19:36, David Lee <t.d.lee at durham.ac.uk> wrote:
>
> > So what I would like to do is extend 'ipctest' to be closer to 'real life'
> > (e.g. using BSC-like data).  What sort of data sizes would you regard as
> > 'real life'?  (Also any hints about content-like issues that might affect
> > things, that could be used in the 'ipctest' exerciser, would be welcome.)
>
> Content won't matter.
>
> I suggest using large datasets - 4K, 64K, 512K blocks.
>
> Great idea, thanks.

OK.  Thanks.

A prelimary test indicates that as the data size gets close to 0x80000
(524288) it begins to fail.  The exact number varies from OS to OS, but it
is around this on Solaris and Linux.  (Alas this probably doesn't help as
much as I had hoped it might with my Solaris/BSC failure.  Sigh.)

Anyway I've just pushed up a patch for a "-s size" argument to 'ipctest'.



-- 

:  David Lee                                I.T. Service          :
:  Senior Systems Programmer                Computer Centre       :
:  UNIX Team Leader                         Durham University     :
:                                           South Road            :
:  http://www.dur.ac.uk/t.d.lee/            Durham DH1 3LE        :
:  Phone: +44 191 334 2752                  U.K.                  :