RE: CA Connect rates under RTEMS

[Kate Feng <feng1@bnl.gov>]

Hi all,

A while ago, wnolan wrote:

> I was curious what sort or rates are being observed using the catime
> utility for RTEMS installations.

Here is another comparison between vxWorks and RTEMS for the
1GHZ NIC of the mvme5500. I will not compare it with that of
the 10/100MHZ NIC I posted on Mar. 24 because it was taken on
a different day.  One thing I forgot to mention in my previous
E-mail was that I experienced 'buffer problems'  on the subnets
of NSLS while testing the 10/100MHZ port of the vxWorks-mvme5500.
Steve Singleton experienced the same with the subnets of DLS.


Many thanks again to Mark Heron and Steve Singleton of Diamond
Light Source for collaborations in obtaining data for
EPICS/vxWorks/mvme5500.


-----------------------------------------------------------------------
 catime performance of 1GHZ port    (April 5,2005 Kate Feng)
       between
  EPICS3.14.6/RTEMS: 4.6.0/mvme5500
        and
          EPIICS3.14.x/vxWorks/mvme5500

--------------------------------------------------------------------
Table 1: RTEMS/osdPoolStatus.c :osiSufficentSpaceInPool() calls
malloc_free_space(), which was patched with a more efficient
algorithm implemented by Joel Sherrill <joel@OARcorp.com>:

1GHZ
            RTEMS-m5500  vxworks-m5500    RTEMS-m5500  vxworks-m5500
                (1000 channels)              (10000 channels)
search       5.7  Mbps     4.8  Mbps      24.6  Mbps    21.1  Mbps
pend       453.1K It/s   450.0K It/s     453.5K It/s   450.9K It/s
async put   15.6  Mbps    15.6  Mbps      31.3  Mbps    30.7  Mbps
async get   19.5  Mbps    18.3  Mbps      54.0  Mbps    43.8  Mbps
sync  get    1.1  Mbps     0.7 Mbps        0.4  Mbps     0.3  Mbp
--------------------------------------------------------------------


Regards,
Kate