Chronological Thread 

< Chronological >      < Thread >

---

Just to be clear:

What I meant was that the combination of the sctplib
with the socketapilib might not be very good for
performance measurements. You can do it with the
sctplib only.

The reason is that the socketapilib use threads...

Best regards
Michael

On Jul 23, 2004, at 10:47 AM, Andreas Jungmaier wrote:

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

All,

just as a side note: the performance of sctplib by itself
is not so bad, and it easily allows saturating a 100 MBit/s
link. The performance issues come into play for instance if
you have a large number of associations on a server
(in sctplib-1.0).

This should not be a major problem in the new version
sctplib-1.3, as it uses hash structures in the sctpd daemon
to locate matches for associations when processing incoming
SCTP packets, which - even with many associations - is way more
efficient.

Best regards,
Andreas


Am Donnerstag, 22. Juli 2004 18:00 schrieb Michael Tuexen:

Just a general point: the sctplib in combination is
not very well suite for performance measurements, because
the is thread scheduling involved. So I would recommend to
use the sctplib only or use a kernel implementation.
I'll post a program which you could use during the next
week (when the SCTP Interop happens).

Best regards
Michael

On Jul 22, 2004, at 5:13 PM, Le Vinh Dat wrote:

Hi SCTP community,
I'm running sctplib-1.0.1 and socketapi-1.3.1 in Redhat 9.0
Now I would like to measure the performance of SCTP vs TCP, how to do
that?
The measure program should work for both of SCTP and TCP.
I found out there was a program called iperf, however, this program
seems only work for TCP and LKSCTP.
 
Thank you very much.
Sincerely yours,
Le Vinh Dat
 

Do you Yahoo!?
Vote for the stars of Yahoo!'s next ad campaign!

_______________________________________________
discussion mailing list
discussion AT sctp.de
http://www.sctp.de/mailman/listinfo/discussion

- --
Dipl.-Ing. Andreas Jungmaier
Computer Networking Technology Group
University of Duisburg-Essen
http://www.exp-math.uni-essen.de/~ajung
PGP Key-ID: D382 4AC0

PGP Key-Fingerprint: 228C 7C2C 3381 2DD4 9998 2812 5C0B 0B04 D382 4AC0
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)

iD8DBQFBANCmXAsLBNOCSsARAtQnAKDP1+CSQO5tpGZ0HGaur4JurBMazQCgh1Gl
fN76A93vjxuxw9fv8f80ODA=
=kZZB
-----END PGP SIGNATURE-----

---

• [SCTP-Discussion] How this case is handled in SCTP, Vijaya Kumar, 07/20/2004
  • [SCTP-Discussion] SCTP performance measure, Le Vinh Dat, 07/22/2004
    • Re: [SCTP-Discussion] SCTP performance measure, Michael Tuexen, 07/22/2004
      • Re: [SCTP-Discussion] SCTP performance measure, Andreas Jungmaier, 07/23/2004
        • Re: [SCTP-Discussion] SCTP performance measure, Michael Tuexen, 07/23/2004
          • SV: [SCTP-Discussion] SCTP performance measure, Torbjörn Andersson, 07/26/2004
            • Re: SV: [SCTP-Discussion] SCTP performance measure, Thomas Dreibholz, 07/26/2004
    • Re: [SCTP-Discussion] SCTP performance measure, Thomas Dreibholz, 07/23/2004

---

Archive powered by MHonArc 2.6.19+.