[149833] in North American Network Operators' Group
Re: Hi speed trading - hi speed monitoring
daemon@ATHENA.MIT.EDU (Rodrick Brown)
Thu Feb 16 08:36:37 2012
In-Reply-To: <5.1.0.14.2.20120216150028.00c2df78@efes.iucc.ac.il>
From: Rodrick Brown <rodrick.brown@gmail.com>
Date: Thu, 16 Feb 2012 08:35:28 -0500
To: Hank Nussbacher <hank@efes.iucc.ac.il>
Cc: "nanog@nanog.org" <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
On Feb 16, 2012, at 8:03 AM, Hank Nussbacher <hank@efes.iucc.ac.il> wrote:
> Nanosecond Trading Could Make Markets Go Haywire
> http://www.wired.com/wiredscience/2012/02/high-speed-trading/
>=20
> "Below the 950-millisecond level, where computerized trading occurs so qui=
ckly that human traders can't even react, no fewer than 18,520 crashes and s=
pikes occurred."
>=20
> Anyone who has managed a network knows that when you look at your MRTG/Cac=
ti graphs at 5min, 10min ,15min intervals - all looks well. Start looking a=
t 1sec intervals and you will see spikes that hit 100% of capacity - even on=
networks running at 25% average utilization
I've had great success using appliances from network monitoring vendor Corv=
il - http://www.corvil.com/ and TS-A's TipOff - www.ts-a.com/TipOff/tipoff.h=
tml=20
Both can decode most market data feeds formats and drill down to provide a s=
lew of details when trying to debug jitter and latency on networks where sub=
-millisecond thresholds are essential for analysis.
Disclaimer: I'm no way affiliated with any of these companies or products.
>=20
> I guess trading and networking do have many unseen similarities.
>=20
> -Hank
>=20
>=20
