Re: OT: high frequency trading

Hey team,

A very interesting thread.

So what can you impact with the network? Where do we start and end?

Propagation delay is what it is ... used to be a rule of thumb for 10ms for
every 1000 miles ... this is still 'roughly true'. Can you change this?
No! --) Distance is what it is ... lol.

Can you impact the software and folks who write it? Probably not. You can
be sure they are blaming the network for any and every delay / problem ...
So what can you impact in your role?

Can you make the management team buy the best gear, have good support, and
upgrade the circuits? Probably you can ... if you can show your design will
affect the bottom line.

Abdul - I took a tour of the CME ... loved it; an amazing group there. Went
out there to talk to them about QoS and QoS design ... and every second
delay made a lot of dollars of difference ... too cool. Really cool stuff
... my eyes were wide open for the entire trip!

So lets take an example: Your data center is 10Gig and your servers are
state of the art. Hopefully the programmers have written written their
programs in a optimal way.

So again, 10Gig servers goes into 10Gig switches / uplinks and then into
10Gig feeds / additional links. Really? Probably not ...

Where does the queuing occur and how can you affect this? How should your
configurations be made to ensure that your 'money-applications' gets high
priority? What about VoIP? For trading, this is a high priority too ...
Does your network design cause additional delays? What about during a
re-convergence / change in network?

What design choices can you make / recommend that can make even a slight
difference?

Anthony - to your original posting ... I think you are correct to believe
that you need very good equipment for your environment. Not only will the
equipment be fast, but also convergence at all levels should be fast. I am
referring to the internal processors and data paths within the network
device itself. As I understand it, the Nexus is way ahead of the pack on
this ...

Think in terms of support too!!! When the crap hits the fan you better have
a good support team. Also, do not email this GS mailer when you are having
trouble ;-) ... always cracks me up to see people ask us for help when the
production network is down / experiencing trouble ...

So as you consider your gear, think also in terms of L2 and L3 convergence,
protocol messaging, etc ... Think also in terms of re-convergence etc ...

You have a lot of pressure on you, and understandably so ... do please hit
us back with any additional questions!!!

Andrew Lissitz

.
On Sat, Feb 13, 2010 at 8:17 PM, Nahskur Udniraht <
expertinternetwork_at_gmail.com> wrote:

> yes ... AFAIK, there are few companies who are doing it less than 100us.
> :-)
>
>
> but 99% customers satisfy with 1ms range ...
>
>
> On Sun, Feb 14, 2010 at 12:02 AM, Joseph L. Brunner <
> joe_at_affirmedsystems.com
> > wrote:
>
> > There are no "db calls".... The algo loads, sits on Nehalem cores, scans
> > the
> > exchanges, strikes, backs off, etc. there is no database loaded on the
> > boxes...
> >
> > The 1ms marker has long been smashed... check
> > http://www.automatedtrader.net/
> >
> >
> >
> > -Joe
> >
> > From: Keegan.Holley_at_sungard.com [mailto:Keegan.Holley_at_sungard.com]
> > Sent: Saturday, February 13, 2010 8:20 AM
> > To: Joseph L. Brunner
> > Cc: Anthony Bonilla; ccielab_at_groupstudy.com; Gregory Gombas;
> > nobody_at_groupstudy.com
> > Subject: RE: OT: high frequency trading
> >
> >
> > This has been done and re-done over and over. You can colo at the
> exchange
> > itself or there are probably a wealth of carrier hotels within 10ms of
> it.
> > The bottleneck is almost always going to be the software though. I
> haven't
> > actually seen studies on this, but off the top of my head I'm curious
> about
> > the benefit of lowering latency from 15ms to say 2 or 3. The software
> can
> > take 1 or 2 full seconds or more to do it's DB calls and actually use the
> > connection.
> >
> >
> > From:
> >
> > "Joseph L. Brunner" <joe_at_affirmedsystems.com>
> >
> > To:
> >
> > Gregory Gombas <ggombas_at_gmail.com>, Anthony Bonilla
> > <anthonybonilla.ccie_at_gmail.com>
> >
> > Cc:
> >
> > "ccielab_at_groupstudy.com" <ccielab_at_groupstudy.com>
> >
> > Date:
> >
> > 02/12/2010 10:54 AM
> >
> > Subject:
> >
> > RE: OT: high frequency trading
> >
> > Sent by:
> >
> > <nobody_at_groupstudy.com>
> >
> >
> > ________________________________
> >
> >
> >
> > Actually most shops send the orders to different exchanges and black
> books
> > and
> > of course arbitrage between the price differences they can exploit.
> > The can often find liquidity before anyone else knows it exists, and they
> > can
> > send orders our for a very short time, of course pulling them if they
> don't
> > get the price they want...
> >
> > It's kind of a nice study to work with these guys- they do eat the slower
> > players lunch (that may be software not just location based slowness).
> >
> > Pretty much all the major players are already at the exchanges and
> > therefore
> > you have to do it.
> >
> > -Joe
> >
> > -----Original Message-----
> > From: nobody_at_groupstudy.com [mailto:nobody_at_groupstudy.com] On Behalf Of
> > Gregory Gombas
> > Sent: Friday, February 12, 2010 9:17 AM
> > To: Anthony Bonilla
> > Cc: ccielab_at_groupstudy.com
> > Subject: Re: OT: high frequency trading
> >
> > Tell them it won't matter anyway because whatever slight edge they
> > will get over their competitor by collocating at the exchange will
> > disappear once their competitor does the same :-)
> >
> > On Thu, Feb 11, 2010 at 10:23 PM, Anthony Bonilla
> > <anthonybonilla.ccie_at_gmail.com> wrote:
> > > Hi all, I am back again. Have a question regarding high frequency
> > trading.
> > > We are planning on collocating at an exchange for trading and are
> looking
> > > for doing lowest latency possible. I wanted to see if anyone else is
> > doing
> > > this and if there are any recommendations. I am currently thinking
> about
> > > 4900M and nexus 5k (layer 2) but am interested in seeing what others
> have
> > > done and whether there are any best practices from cisco to ensure that
> > we
> > > achive lowest latency. TIA.
> > >
> > >
> > > Blogs and organic groups at http://www.ccie.net<http://www.ccie.net/>
> > >
> > > _______________________________________________________________________
> > > Subscription information may be found at:
> > > http://www.groupstudy.com/list/CCIELab.html
> >
> >
> > Blogs and organic groups at http://www.ccie.net<http://www.ccie.net/>
> >
> > _______________________________________________________________________
> > Subscription information may be found at:
> > http://www.groupstudy.com/list/CCIELab.html
> >
> >
> > Blogs and organic groups at http://www.ccie.net<http://www.ccie.net/>
> >
> > _______________________________________________________________________
> > Subscription information may be found at:
> > http://www.groupstudy.com/list/CCIELab.html
> >
> >
> > Blogs and organic groups at http://www.ccie.net
> >
> > _______________________________________________________________________
> > Subscription information may be found at:
> > http://www.groupstudy.com/list/CCIELab.html
> >
> >
> >
> >
> >
> >
> >
> >
>
>
> --
> Nahskur Udniraht
> expertinetwork.blogspot.com
>
>
> Blogs and organic groups at http://www.ccie.net
>
> _______________________________________________________________________
> Subscription information may be found at:
> http://www.groupstudy.com/list/CCIELab.html
>
>
>
>
>
>
>
>

-- 
Andrew Lee Lissitz
all.from.nj_at_gmail.com
Blogs and organic groups at http://www.ccie.net