LVS
lvs-users
Google
 
Web LinuxVirtualServer.org

Re: Scalability

To: jamal <hadi@xxxxxxxxxx>
Subject: Re: Scalability
Cc: Julian Anastasov <uli@xxxxxxxxxxxxxxxxxxxxxx>, Joseph Mack <mack@xxxxxxxxxxx>, S Ashok Kumar <gsaki@xxxxxxxxxxxxx>, lvs-users@xxxxxxxxxxxxxxxxxxxxxx
From: bobby.moore@xxxxxxxxxxxxx
Date: Tue, 16 May 2000 08:38:38 -0400
My LVS's had a ONE-TIME cost of around $50.00, and access to a broom closet
full of discarded p133's and p200's. For that $50 I also got 'heartbeat',
mon, ipchains, iptraf, power tools, a programmable unix environment, a
plethora of monitoring and benchmarking tools, enough routers, firewalls,
and virtual servers to potentially put throughout our entire enterprise,
and TONS of free help and support, not to mention my company's appreciation
to solutions to some problems that have been dogging us for quite some
time. I haven't had a throughput problem yet. I haven't stress-tested it
yet. But my plan is to simply add another LVS and use DNS to round-robin
them - something we're doing today with another product. To me, the
potential of this is enormous. I'm starting to see the huge benefit of open
source. This is not a marketing pitch. Marketing is not my business. There
is a beauty to LVS, and as a programmer I'd rather have this type product
to run on this type of system to do what I want with, and produce products
that will work for me, and to give my 'clients' what they want, rather then
have them play by my rules. My bent, of course, is that of a programmer and
not a network guy.

Bobby Moore Worldspan
Phone: 770.563.7362 Fax: 770.563.6406
bobby.moore@xxxxxxxxxxxxx


                                                                                
                              
                    jamal                                                       
                              
                    <hadi@cyberus        To:     Julian Anastasov 
<uli@xxxxxxxxxxxxxxxxxxxxxx>                
                    .ca>                 cc:     Joseph Mack 
<mack@xxxxxxxxxxx>, S Ashok Kumar                
                                         <gsaki@xxxxxxxxxxxxx>, 
lvs-users@xxxxxxxxxxxxxxxxxxxxxx              
                    05/15/2000           Subject:     Re: Scalability           
                              
                    05:33 PM                                                    
                              
                                                                                
                              
                                                                                
                              




On Mon, 15 May 2000, Julian Anastasov wrote:

>
>          Yes.  This is only one real example. With keep alive
> ON,  most of  the connections can  be closed  first from the
> client.

But it does explain the reduced ratio you see ;->

> > 2.3 networking scales linearly with number of processors. Example
typical
> > routing max capacities are around 30-40K packets/sec; same in 2.3 but
if
> > you add another procesor, you end somewhere in the 60-70Kpps with 2.3
(2.2
> > doesnt change).
>
>          You forgot to describe the hardware :)

Sorry, this was the same motherboard with one processor and then two
processors so the numbers are relative; a really shitty motherboard known
as the ABIT6 which can take upto 2 400Mhz (?)celeron processors.
64MB of RAM.

> > your connection setup because it includes a little more overhead than
> > typical routing should get less performance.
>
>          Right.  With faster enough CPU this is only latency,
> not  less performance! If  we start to  drop packets this is
> bad.


I would think it would be a little more complicated than that.
Depends on a lot of other tunings (simple example: if you use DMAing NICs,
how big are those receive Ring/lists). Latency would probably hover around
the PCI latency then.

>          Lets see his results :)

I hope he's going to do it.

>
>          Well,  I didn't  performed such  tests. That doesn't
> mean  that there are no such tests. Please, I'm not the only
> LVS user :)
>

I thought you were one of the developers (in which case this should
concern you).

>          I  don't know  your needs, really!  If this hardware
> is faster and cheaper and you think that is enough just save
> your  money and  don't buy PC  :) The  people have different
> needs.   One needs  PIII 2GB LVS  box another  can live with
> 128MB box :) I can't give you the universal solution.
>
>          The  only thing I can do  is to explain the details.
> The  users always have questions about the LVS internals.  I
> can't  tell you "You must use LVS  - It is free".  There are
> so  many things that must be  considered. May be the simpler
> answer  is "Buy hardware for load balancing. It has good TCP
> stack  and  it  is  without  bugs  and  ...".   May  be this
> hardware  is better, may be the support is better.  Why not!
> Why the only load balancing solution must be LVS?

I am just a curious observer as far as LVS is concerned. I have absolutely
no need for it (maybe at some later point, since i know exists).

I am not asking you to justify why LVS exists or why people should use
LVS; i am just making a statement that load balancing h/ware is becoming
commodity. If the trend continues, you should be able to buy a black box
worth $200 which will have the same features as LVS does; perhaps i am
exagerating a bit, but if this is the case, why should someone continue to
use LVS? I was hoping you will enlighten me in some way instead you become
defensive and give me a marketing pitch.
Maybe someone else has an answer.

cheers,
jamal










<Prev in Thread] Current Thread [Next in Thread>