[simgrid.git] / doc / doxygen / platform.doc

/*! \page platform Platform Description

@tableofcontents

In order to run any simulation, SimGrid needs 3 things: something to run
(so, your code), a description of the platform on which you want to run your
application, and finally it needs something to know where to deploy what.

For the latest 2 entries, you have basically 2 ways to give it as an input :
\li You can program it, either using the Lua console (\ref
    MSG_Lua_funct) or if you're using MSG some of its platform and
    deployments functions(\ref msg_simulation). If you want to use it,
    please refer to its doc. (you can also check the section \ref
    pf_flexml_bypassing but this is strongly deprecated, as there is a
    new way to do it properly, but not yet documented).
\li You can use two XML files: a platform description file and a
    deployment description one.

For the deployment stuff, please take a look at \ref deployment

The platform description may be complicated. This documentation is all
about how to write this file: what are the basic concept it relies on,
what possibilities are offered, and some hints and tips on how to
write a good platform description.

\section pf_overview Some words about XML and DTD

We choose to use XML because of some of its possibilities: if you're
using an accurate XML editor, or simply using any XML plug-in for
eclipse, it will allow you to have cool stuff like auto-completion,
validation and checking, so all syntax errors may be avoided this
way.

the XML checking is done based on the dtd which is nowadays online at
<a href="http://simgrid.gforge.inria.fr/simgrid.dtd">http://simgrid.gforge.inria.fr/simgrid.dtd</a>
while you might be tempted to read it, it will not help you that much.

If you read it, you should notice two or three important things :
\li The platform tags contains a version attributes. At the time of
    writing this doc the current version is 3.    
\li The DTD contains definitions for the 2 files used by SimGrid (platform
    description and deployment).
\li There is a bunch of possibilities ! Let's see what's in it


\section pf_basics Basic concepts

Nowadays, the Internet is composed of a bunch of independently managed
networks. Within each of those networks, there are entry and exit
points (most of the time, you can both enter and exit through the same
point) that allows to go out of the current network and reach other
networks. At the upper level, these networks are known as
<b>Autonomous System (AS)</b>, while at the lower level they are named
sub-networks, or LAN. Indeed they are autonomous: routing is defined
within the limits of his network by the administrator, and so, those
networks can continue to operate without the existence of other
networks. There are some rules to get out of networks by the entry
points (or gateways). Those gateways allow you to go from a network to
another one. Inside of each autonomous system, there is a bunch of
equipments (cables, routers, switches, computers) that belong to the
autonomous system owner.

SimGrid platform description file relies exactly on the same concepts
as real life platform. Every resource (computers, network equipments,
and so on) belongs to an AS. Within this AS, you can define the
routing you want between its elements (that's done with the routing
model attribute and eventually with some \<route\> tag). You define AS
by using ... well ... the \<AS\> tag. An AS can also contain some AS :
AS allows you to define the hierarchy of your platform.

Within each AS, you basically have the following type of resources:
\li <b>host</b>: an host, with cores in it, and so on
\li <b>router</b>: a router or a gateway.
\li <b>link</b>: a link, that defines a connection between two (or
    more) resources (and have a bandwidth and a latency) 
\li <b>cluster</b>: like a real cluster, contains many hosts
    interconnected by some dedicated network. 

Between those elements, a routing has to be defined. As the AS is
supposed to be Autonomous, this has to be done at the AS level. As AS
handles two different types of entities (<b>host/router</b> and
<b>AS</b>) you will have to define routes between those elements. A
network model have to be provided for AS, but you may/will need,
depending of the network model, or because you want to bypass the
default behavior to defines routes manually. There are 3 tags to use: 
\li <b>ASroute</b>: to define routes between two  <b>AS</b>
\li <b>route</b>: to define routes between two <b>host/router</b>
\li <b>bypassRoute</b>: to define routes between two <b>AS</b> that
    will bypass default routing. 

Here is an illustration of the overall concepts:

\htmlonly
<a href="AS_hierarchy.png" border=0><img src="AS_hierarchy.png" width="30%" border=0 align="center"></a>
<br/>
\endhtmlonly
 Circles represent processing units and squares represent network routers. Bold
    lines represent communication links. AS2 models the core of a national
    network interconnecting a small flat cluster (AS4) and a larger
    hierarchical cluster (AS5), a subset of a LAN (AS6), and a set of peers
    scattered around the world (AS7).


This is all for the concepts ! To make a long story short, a SimGrid
platform is made of a hierarchy of AS, each of them containing
resources, and routing is defined at AS level. Let's have a deeper
look in the tags.



\section pf_pftags Describing resources and their organization

\subsection  pf_As Platform organization tag : AS

AS (or Autonomous System) is an organizational unit that contains
resources and defines routing between them, and eventually some other
AS. So it allows you to define a hierarchy into your platform.
<b>*ANY*</b> resource <b>*MUST*</b> belong to an AS. There are a few
attributes.

<b>AS</b> attributes :
\li <b>id (mandatory)</b>: the identifier of AS to be used when
    referring to it.     
\li <b>routing (mandatory)</b>: the routing model used into it. By
    model we mean the internal way the simulator will manage routing.
    That also have a big impact on how many information you'll have to
    provide to help the simulator to route between the AS elements.
    <b>routing</b> possible values are <b>Full, Floyd, Dijkstra,
    DijkstraCache, none, RuleBased, Vivaldi, Cluster</b>. For more
    explanation about what to choose, take a look at the section
    devoted to it below.  

Elements into an AS are basically resources (computers, network
equipments) and some routing information if necessary (see below for
more explanation).

<b>AS example</b>
\verbatim
<AS  id="AS0"  routing="Full">
   <host id="host1" power="1000000000"/>
   <host id="host2" power="1000000000"/>
   <link id="link1" bandwidth="125000000" latency="0.000100"/>
   <route src="host1" dst="host2"><link_ctn id="link1"/></route>
 </AS>
\endverbatim

In this example, AS0 contains two hosts (host1 and host2). The route
between the hosts goes through link1.


\subsection pf_Cr Computing resources: hosts, clusters and peers.

\subsubsection pf_host host

A <b>host</b> represents a computer, where you will be able to execute
code and from which you can send and receive information. A host can
contain more than 1 core. Here are the attributes of a host :


<b>host</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the host to be used when
    referring to it.
\li <b>power (mandatory)</b>:the peak number FLOPS the CPU can manage.
    Expressed in flop/s.
\li <b>core</b>: The number of core of this host. If set, the power
    gives the power of one core. The specified computing power will be
    available to up to 6 sequential tasks without sharing. If more
    tasks are placed on this host, the resource will be shared
    accordingly. For example, if you schedule 12 tasks on the host,
    each will get half of the computing power. Please note that
    although sound, this model were never scientifically assessed.
    Please keep this fact in mind when using it.

\li <b>availability</b>: specify if the percentage of power available.
\li <b>availability_file</b>: Allow you to use a file as input. This
    file will contain availability traces for this computer. The
    syntax of this file is defined below. Possible values : absolute
    or relative path, syntax similar to the one in use on your system.
\li <b>state</b>: the computer state, as in : is that computer ON or
    OFF. Possible values : "ON" or "OFF". 
\li <b>state_file</b>: Same mechanism as availability_file, similar
    syntax for value.     
\li <b>coordinates</b>: you'll have to give it if you choose the
    vivaldi, coordinate-based routing model for the AS the host
    belongs to. More details about it in the P2P coordinate based
    section. 

An host can contain some <b>mount</b> that defines mounting points
between some storage resource and the <b>host</b>. Please refer to the
storage doc for more information.

An host can also contain the <b>prop</b> tag. the prop tag allows you
to define additional information on this host following the
attribute/value schema. You may want to use it to give information to
the tool you use for rendering your simulation, for example.

<b>host example</b>
\verbatim
   <host id="host1" power="1000000000"/>
   <host id="host2" power="1000000000">
        <prop id="color" value="blue"/>
        <prop id="rendershape" value="square"/>
   </host>
\endverbatim


<b>Expressing dynamicity.</b>
It is also possible to seamlessly declare a host whose
availability changes over time using the availability_file
attribute and a separate text file whose syntax is exemplified below.

<b>Adding a trace file</b>
\verbatim
    <platform version="1">
      <host id="bob" power="500000000"
            availability_file="bob.trace" />
    </platform>
\endverbatim
<b>Example of "bob.trace" file</b>
\verbatim
PERIODICITY 1.0
  0.0 1.0
  11.0 0.5
  20.0 0.8
\endverbatim

At time 0, our host will deliver 500~Mflop/s. At time 11.0, it will
deliver half, that is 250~Mflop/s until time 20.0 where it will
will start delivering 80\% of its power, that is 400~Mflop/s. Last, at
time 21.0 (20.0 plus the periodicity 1.0), we loop back to the
beginning and the host will deliver again 500~Mflop/s.

<b>Changing initial state</b>

It is also possible to specify whether the host
is up or down by setting the <b>state</b> attribute to either <b>ON</b>
(default value) or <b>OFF</b>.

<b>Expliciting the default value "ON"</b>
\verbatim
  <platform version="1">
     <host id="bob"
           power="500000000"
          state="ON" />
  </platform>
\endverbatim
<b>Host switched off</b>
\verbatim
  <platform version="1">
     <host id="bob"
           power="500000000"
           state="OFF" />
  </platform>
\endverbatim
<b>Expressing churn</b>
To express the fact that a host can change state over time (as in P2P
systems, for instance), it is possible to use a file describing the time
at which the host is turned on or off. An example of the content
of such a file is presented below.
<b>Adding a state file</b>
  \verbatim
    <platform version="1">
      <host id="bob" power="500000000"
           state_file="bob.fail" />
    </platform>
  \endverbatim
<b>Example of "bob.fail" file</b>
\verbatim
  PERIODICITY 10.0
  1.0 -1.0
  2.0 1.0
\endverbatim

A negative value means <b>down</b> while a positive one means <b>up and
  running</b>. From time 0.0 to time 1.0, the host is on. At time 1.0, it is
turned off and at time 2.0, it is turned on again until time 12 (2.0 plus the
periodicity 10.0). It will be turned on again at time 13.0 until time 23.0, and
so on.



\subsubsection pf_cluster cluster

A <b>cluster</b> represents a cluster. It is most of the time used
when you want to have a bunch of machine defined quickly. It must be
noted that cluster is meta-tag : <b>from the inner SimGrid point of
view, a cluster is an AS where some optimized routing is defined</b>.
The default inner organization of the cluster is as follow:

\verbatim
                 _________
                |          |
                |  router  |
    ____________|__________|_____________ backbone
      |   |   |              |     |   |
    l0| l1| l2|           l97| l96 |   | l99
      |   |   |   ........   |     |   |
      |                                |
    c-0.me                             c-99.me
\endverbatim

You have a set of <b>host</b> defined. Each of them has a <b>link</b>
to a central backbone (backbone is a <b>link</b> itself, as a link can
be used to represent a switch, see the switch or <b>link</b> section
below for more details about it). A <b>router</b> gives a way to the
<b>cluster</b> to be connected to the outside world. Internally,
cluster is then an AS containing all hosts : the router is the default
gateway for the cluster.

There is an alternative organization, which is as follow :
\verbatim
                 _________
                |          |
                |  router  |
                |__________|
                    / | \
                   /  |  \
               l0 / l1|   \l2
                 /    |    \
                /     |     \
            host0   host1   host2
\endverbatim

The principle is the same, except we don't have the backbone. The way
to obtain it is simple : you just have to let bb_* attributes
unset.



<b>cluster</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the cluster to be used
    when referring to it. 
\li <b>prefix (mandatory)</b>: each node of the cluster has to have a
    name. This is its prefix. 
\li <b>suffix (mandatory)</b>: node suffix name.
\li <b>radical (mandatory)</b>: regexp used to generate cluster nodes
    name. Syntax is quite common, "10-20" will give you 11 machines
    numbered from 10 to 20, "10-20;2" will give you 12 machines, one
    with the number 2, others numbered as before. The produced number
    is concatenated between prefix and suffix to form machine names.
\li <b>power (mandatory)</b>: same as <b>host</b> power.
\li <b>core</b>: same as <b>host</b> core.
\li <b>bw (mandatory)</b>: bandwidth for the links between nodes and
    backbone (if any). See <b>link</b> section for syntax/details.
\li <b>lat (mandatory)</b>: latency for the links between nodes and
    backbone (if any). See <b>link</b> section for syntax/details. 
\li <b>sharing_policy</b>: sharing policy for the links between nodes
    and backbone (if any). See <b>link</b> section for syntax/details.     
\li <b>bb_bw </b>: bandwidth for backbone (if any). See <b>link</b>
    section for syntax/details. If both bb_* attributes are omitted,
    no backbone is created (alternative cluster architecture described
    before). 
\li <b>bb_lat </b>: latency for backbone (if any). See <b>link</b>
    section for syntax/details. If both bb_* attributes are omitted,
    no backbone is created (alternative cluster architecture described
    before).
\li <b>bb_sharing_policy</b>: sharing policy for the backbone (if
    any). See <b>link</b> section for syntax/details.
\li <b>availability_file</b>: Allow you to use a file as input for
    availability. Similar to <b>hosts</b> attribute. 
\li <b>state_file</b>: Allow you to use a file as input for states.
    Similar to <b>hosts</b> attribute. 

the router name is defined as the resulting String in the following
java line of code: 

@verbatim
router_name = prefix + clusterId + router_ + suffix;
@endverbatim


<b>cluster example</b>
\verbatim
<cluster id="my_cluster_1" prefix="" suffix=""
                radical="0-262144"      power="1000000000"    bw="125000000"     lat="5E-5"/>
<cluster id="my_cluster_1" prefix="c-" suffix=".me"
                radical="0-99"  power="1000000000"    bw="125000000"     lat="5E-5"
        bb_bw="2250000000" bb_lat="5E-4"/>
\endverbatim
The second examples creates 100 machines, which names are the following:
\verbatim
c-0.my_cluster_1.me
c-1.my_cluster_1.me
c-2.my_cluster_1.me
...
c-99.my_cluster_1.me
\endverbatim

\subsubsection pf_peer peer
A <b>peer</b> represents a peer, as in Peer-to-Peer (P2P). Basically,
as cluster, <b>A PEER IS INTERNALLY INTERPRETED AS AN \<AS\></b>. It's
just a kind of shortcut that does the following :

\li It creates a tiny AS whose routing type is cluster
\li It creates an host
\li Two links : one for download and one for upload. This is
    convenient to use and simulate stuff under the last mile model (as
    ADSL peers). 
\li It connects the two links to the host
\li It creates a router (a gateway) that serve as entry point for this peer zone.
    This router has coordinates.

<b>peer</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the peer to be used when
    referring to it.
\li <b>power CDATA (mandatory)</b>: as in host
\li <b>bw_in CDATA (mandatory)</b>: bandwidth in.
\li <b>bw_out CDATA (mandatory)</b>:bandwidth out.
\li <b>lat CDATA (mandatory)</b>: Latency for in and out links.
\li <b>coordinates</b>: coordinates of the gateway for this peer.
\li <b>sharing_policy</b>: sharing policy for links. Can be SHARED or
    FULLDUPLEX, FULLDUPLEX is the default. See <b>link</b> description
    for details.
\li <b>availability_file</b>: availability file for the peer. Same as
    host availability file. See <b>host</b> description for details.   
\li <b>state_file </b>: state file for the peer. Same as host state
    file. See <b>host</b> description for details. 

In term of XML, the <b>peer</b> construct can be explained as follows: it transforms
\verbatim
  <peer id="FOO"
        coordinates="12.8 14.4 6.4"
        power="1.5Gf"
        bw_in="2.25GBps"
        bw_out="2.25GBps"
        lat="500us" />
\endverbatim
into
\verbatim
   <AS id="as_FOO" routing="Cluster">
      <host id="peer_FOO" power="1.5Gf"/>
      <link id="link_FOO_UP" bandwidth="2.25GBps" latency="500us"/>
      <link id="link_FOO_DOWN" bandwidth="2.25GBps" latency="500us"/>
      <router id="router_FOO" coordinates="25.5 9.4 1.4"/>
      <host_link id="peer_FOO" up="link_FOO_UP" down="link_FOO_DOWN"/>
   </AS>
\endverbatim


\subsection pf_ne Network equipments: links and routers

You have basically two entities available to represent network entities:
\li <b>link</b>: represents something that has a limited bandwidth, a
    latency, and that can be shared according to TCP way to share this
    bandwidth. <b>LINKS ARE NOT EDGES BUT HYPEREDGES</b>: it means
    that you can have more than 2 equipments connected to it.
\li <b>router</b>: represents something that one message can be routed
    to, but does not accept any code, nor have any influence on the
    performances (no bandwidth, no latency, not anything).<b>ROUTERS
    ARE ENTITIES (ALMOST) IGNORED BY THE SIMULATOR WHEN THE SIMULATION
    HAS BEGUN</b>. If you want to represent something like a switch,
    you must use <b>link</b> (see section below). Routers are used in
    order to run some routing algorithm and determine routes (see
    routing section for details).

let's see deeper what those entities hide.

\subsubsection pf_router router
As said before, <b>router</b> is used only to give some information
for routing algorithms. So, it does not have any attributes except :

<b>router</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the router to be used
    when referring to it.
    \li <b>coordinates</b>: you'll have to give it if you choose the
    vivaldi, coordinate-based routing model for the AS the host
    belongs to. More details about it in the P2P coordinates based
    section.

<b>router example</b>
\verbatim
 <router id="gw_dc1_horizdist"/>
\endverbatim

\subsubsection pf_link link

Network links can represent one-hop network connections. They are
characterized by their id and their bandwidth. The latency is optional
with a default value of 0.0. For instance, we can declare a network
link named link1 having bandwidth of 1Gb/s and a latency of 50µs.
Example link:

\verbatim
 <link id="LINK1" bandwidth="125000000" latency="5E-5"/>
\endverbatim
<b>Expressing sharing policy</b>

By default a network link is SHARED, that is if more than one flow go
through a link, each gets a share of the available bandwidth similar
to the share TCP connections offers.

Conversely if a link is defined as a FATPIPE, each flow going through
this link will get all the available bandwidth, whatever the number of
flows. The FATPIPE behavior allows to describe big backbones that
won't affect performances (except latency). Finally a link can be
considered as FULLDUPLEX, that means that in the simulator, 2 links
(one named UP and the other DOWN) will be created for each link, so as
the transfers from one side to the other will interact similarly as
TCP when ACK returning packets circulate on the other direction. More
discussion about it is available in <b>link_ctn</b> description.

\verbatim
 <link id="SWITCH" bandwidth="125000000" latency="5E-5" sharing_policy="FATPIPE" />
\endverbatim

<b>Expressing dynamicity and failures</b>

As for hosts, it is possible to declare links whose state, bandwidth
or latency change over the time. In this case, the bandwidth and
latency attributes are respectively replaced by the bandwidth file and
latency file attributes and the corresponding text files.

\verbatim
 <link id="LINK1" state_file="link1.fail" bandwidth="80000000" latency=".0001" bandwidth_file="link1.bw" latency_file="link1.lat" />
\endverbatim

It has to be noted that even if the syntax is the same, the semantic
of bandwidth and latency trace files differs from that of host
availability files. Those files do not express availability as a
fraction of the available capacity but directly in bytes per seconds
for the bandwidth and in seconds for the latency. This is because most
tools allowing to capture traces on real platforms (such as NWS)
express their results this way.

<b>Example of "link1.bw" file</b>
\verbatim

1 PERIODICITY 12.0
2 4.0 40000000
3 8.0 60000000
\endverbatim
<b>Example of "link1.lat" file</b>
\verbatim
 1 PERIODICITY 5.0
2 1.0 0.001
3 2.0 0.01
4 3.0 0.001
\endverbatim

In this example, the bandwidth varies with a period of 12 seconds
while the latency varies with a period of 5 seconds. At the beginning
of simulation, the link’s bandwidth is of 80,000,000 B/s (i.e., 80
Mb/s). After four seconds, it drops at 40 Mb/s, and climbs back to 60
Mb/s after eight seconds. It keeps that way until second 12 (ie, until
the end of the period), point at which it loops its behavior (seconds
12-16 will experience 80 Mb/s, 16-20 40 Mb/s and so on). In the same
time, the latency values are 100µs (initial value) on the [0, 1[ time
interval, 1ms on [1, 2[, 10ms on [2, 3[, 1ms on [3,5[ (i.e., until the
end of period). It then loops back, starting at 100µs for one second.

<b>link</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the link to be used when referring to it.
\li <b>bandwidth (mandatory)</b>: bandwidth for the link.
\li <b>lat </b>: latency for the link. Default is 0.0.
\li <b>sharing_policy</b>: sharing policy for the link.
\li <b>state</b>: Allow you to to set link as ON or OFF. Default is ON.
\li <b>bandwidth_file</b>: Allow you to use a file as input for bandwidth.
\li <b>latency_file</b>: Allow you to use a file as input for latency.
\li <b>state_file</b>: Allow you to use a file as input for states.

As an host, a <b>link</b> tag can also contain the <b>prop</b> tag.

<b>link example</b>
\verbatim
   <link id="link1" bandwidth="125000000" latency="0.000100"/>
\endverbatim


\subsection pf_storage Storage

<b>Note : This is a prototype version that should evolve quickly, this
is just some doc valuable only at the time of writing this doc</b>
This section describes the storage management under SimGrid ; nowadays
it's only usable with MSG. It relies basically on linux-like concepts.
You also may want to have a look to its corresponding section in \ref
msg_file_management ; functions access are organized as a POSIX-like
interface.

\subsubsection pf_sto_conc Storage Main concepts
Basically there is 3 different entities to know :
\li the <b>storage_type</b>: here you define some kind of storage that
    you will instantiate many type on your platform. Think of it like
    a definition of throughput of a specific disk. 
\li the <b>storage</b>: instance of a <b>storage_type</b>. Defines a
    new storage of <b>storage_type</b>     
\li the <b>mount</b>: says that the storage is located into this
    specific resource.

the content of a storage has to be defined in a content file that
contains the content. The path to this file has to be passed within
the <b>content</b> attribute . Here is a way to generate it:

\verbatim
find /path/you/want -type f -exec ls -l {} \; 2>/dev/null > ./content.txt
\endverbatim

\subsubsection pf_sto_sttp storage_type


<b>storage_type</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the storage_type to be
    used when referring to it. 
\li <b>model (mandatory)</b>: Unused for now by the simulator (but
    mandatory, ok) 
\li <b>content</b>: default value 0. The file containing the disk
    content. (may be moved soon or later to <b>storage</b> tag. 

The tag must contains some predefined prop, as may do some other
resources tags. This should moved to attributes soon or later. 
<b>storage_type</b> mandatory <b>prop</b> :
\li <b>Bwrite</b>: value in B/s. Write throughput
\li <b>Bread</b>: value in B/s. Read throughput
\li <b>Bconnexion</b>: value in B/s. Connection throughput (i.e. the
    throughput of the storage connector). 

\subsubsection pf_sto_st storage

<b>storage_type</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the storage to be used
    when referring to it. 
\li <b>typeId (mandatory)</b>: the identifier of the storage_type that
    this storage  belongs to. 


\subsubsection pf_sto_mo mount

<b>mount</b> attributes :
\li <b>id (mandatory)</b>: the id of the <b>storage</b> that must be
    mounted on that computer. 
\li <b>name (mandatory)</b>: the name that will be the logical
    reference to this disk (the mount point). 

\subsubsection pf_sto_mst mstorage
<b>Note : unused for now</b>
<b>mstorage</b> attributes :
\li <b>typeId (mandatory)</b>: the id of the <b>storage</b> that must
    be mounted on that computer. 
\li <b>name (mandatory)</b>: the name that will be the logical
    reference to this disk (the mount point). 

\section pf_routing Routing

In order to run fast, it has been chosen to use static routing within
SimGrid. By static, it means that it is calculated once (or almost),
and will not change during execution. We chose to do that because it
is rare to have a real deficiency of a resource ; most of the time, a
communication fails because the links are too overloaded, and so your
connection stops before the time out, or because the computer at the
other end is not answering.

We also chose to use shortest paths algorithms in order to emulate
routing. Doing so is consistent with the reality: RIP, OSPF, BGP are
all calculating shortest paths. They have some convergence time, but
at the end, so when the platform is stable (and this should be the
moment you want to simulate something using SimGrid) your packets will
follow the shortest paths.

\subsection pf_rm Routing models

Within each AS, you have to define a routing model to use. You have
basically 3 main kind of routing models :

\li Shortest-path based models: you let SimGrid calculates shortest
    paths and manage it. Behaves more or less as most real life
    routing.
\li Manually-entered route models: you'll have to define all routes
    manually by yourself into the platform description file.
    Consistent with some manually managed real life routing.
\li Simple/fast models: those models offers fast, low memory routing
    algorithms. You should consider to use it if you can make some
    assumptions about your AS. Routing in this case is more or less
    ignored

\subsubsection pf_raf The router affair

Expressing routers becomes mandatory when using shortest-path based
models or when using ns-3 or the bindings to the GTNetS packet-level
simulator instead of the native analytical network model implemented
in SimGrid.

For graph-based shortest path algorithms, routers are mandatory,
because both algorithms need a graph, and so we need to have source
and destination for each edge.

Routers are naturally an important concept in GTNetS or ns-3 since the
way they run the packet routing algorithms is actually simulated.
Instead, the SimGrid’s analytical models aggregate the routing time
with the transfer time. Rebuilding a graph representation only from
the route information turns to be a very difficult task, because of
the missing information about how routes intersect. That is why we
introduced a \<router\> tag, which is simply used to express these
intersection points. The only attribute accepted by this tag an id. It
is important to understand that the \<router\> tag is only used to
provide topological information.

To express those topological information, some <b>route</b> have to be
defined saying which link is between which routers. Description or the
route syntax is given below, as well as example for the different
models.

\subsubsection pf_rm_sh Shortest-path based models

Here is the complete list of such models, that computes routes using
classic shortest-paths algorithms. How to choose the best suited
algorithm is discussed later in the section devoted to it.

\li <b>Floyd</b>: Floyd routing data. Pre-calculates all routes once. 
\li <b>Dijkstra</b>: Dijkstra routing data ,calculating routes when
    necessary. 
\li <b>DijkstraCache</b>: Dijkstra routing data. Handle some cache for
    already calculated routes. 

All those shortest-path models are instanciated the same way. Here are
some example of it:

Floyd example :
\verbatim
<AS  id="AS0"  routing="Floyd">

  <cluster id="my_cluster_1" prefix="c-" suffix=""
                radical="0-1"   power="1000000000"    bw="125000000"     lat="5E-5"
        router_id="router1"/>

 <AS id="AS1" routing="none">
    <host id="host1" power="1000000000"/>
 </AS>

  <link id="link1" bandwidth="100000" latency="0.01"/>

  <ASroute src="my_cluster_1" dst="AS1"
    gw_src="router1"
    gw_dst="host1">
    <link_ctn id="link1"/>
  </ASroute>

</AS>
\endverbatim

ASroute given at the end gives a topological information: link1 is
between router1 and host1.

Dijsktra example :
\verbatim
 <AS id="AS_2" routing="Dijsktra">
     <host id="AS_2_host1" power="1000000000"/>
     <host id="AS_2_host2" power="1000000000"/>
     <host id="AS_2_host3" power="1000000000"/>
     <link id="AS_2_link1" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link2" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link3" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link4" bandwidth="1250000000" latency="5E-4"/>
     <router id="central_router"/>
     <router id="AS_2_gateway"/>
     <!-- routes providing topological information -->
     <route src="central_router" dst="AS_2_host1"><link_ctn id="AS_2_link1"/></route>
     <route src="central_router" dst="AS_2_host2"><link_ctn id="AS_2_link2"/></route>
     <route src="central_router" dst="AS_2_host3"><link_ctn id="AS_2_link3"/></route>
     <route src="central_router" dst="AS_2_gateway"><link_ctn id="AS_2_link4"/></route>
  </AS>
\endverbatim

DijsktraCache example :
\verbatim
<AS id="AS_2" routing="DijsktraCache">
     <host id="AS_2_host1" power="1000000000"/>
     ...
(platform unchanged compared to upper example)
\endverbatim

\subsubsection pf_rm_me Manually-entered route models

\li <b>Full</b>: You have to enter all necessary routes manually
\li <b>RuleBased</b>: Rule-Based routing data; same as Full except you
    can use regexp to express route. As SimGrid has to evaluate the
    regexp, it's slower than Full, but requires less memory. Regexp
    syntax is similar as <a href="http://www.pcre.org">pcre</a> ones,
    as this is the lib SimGrid use to do so.


Full example :
\verbatim
<AS  id="AS0"  routing="Full">
   <host id="host1" power="1000000000"/>
   <host id="host2" power="1000000000"/>
   <link id="link1" bandwidth="125000000" latency="0.000100"/>
   <route src="host1" dst="host2"><link_ctn id="link1"/></route>
 </AS>
\endverbatim

RuleBased example :
\verbatim
<AS id="AS_orsay" routing="RuleBased" >
                        <cluster id="AS_gdx" prefix="gdx-" suffix=".orsay.grid5000.fr"
                                radical="1-310" power="4.7153E9" bw="1.25E8" lat="1.0E-4"
                                bb_bw="1.25E9" bb_lat="1.0E-4"></cluster>
                        <link   id="link_gdx" bandwidth="1.25E9" latency="1.0E-4"/>

                        <cluster id="AS_netgdx" prefix="netgdx-" suffix=".orsay.grid5000.fr"
                                radical="1-30" power="4.7144E9" bw="1.25E8" lat="1.0E-4"
                                bb_bw="1.25E9" bb_lat="1.0E-4"></cluster>
                        <link   id="link_netgdx" bandwidth="1.25E9" latency="1.0E-4"/>

                        <AS id="gw_AS_orsay" routing="Full">
                                <router id="gw_orsay"/>
                        </AS>
                        <link   id="link_gw_orsay" bandwidth="1.25E9" latency="1.0E-4"/>

                        <ASroute src="^AS_(.*)$" dst="^AS_(.*)$"
                                gw_src="$1src-AS_$1src_router.orsay.grid5000.fr"
                                gw_dst="$1dst-AS_$1dst_router.orsay.grid5000.fr"
                                symmetrical="YES">
                                        <link_ctn id="link_$1src"/>
                                        <link_ctn id="link_$1dst"/>
                        </ASroute>

                        <ASroute src="^AS_(.*)$" dst="^gw_AS_(.*)$"
                                gw_src="$1src-AS_$1src_router.orsay.grid5000.fr"
                                gw_dst="gw_$1dst"
                                symmetrical="NO">
                                        <link_ctn id="link_$1src"/>
                        </ASroute>

                        <ASroute src="^gw_AS_(.*)$" dst="^AS_(.*)$"
                                gw_src="gw_$1src"
                                gw_dst="$1dst-AS_$1dst_router.orsay.grid5000.fr"
                                symmetrical="NO">
                                        <link_ctn id="link_$1dst"/>
                        </ASroute>

                </AS>
\endverbatim

The example upper contains $1src and $1dst. It's simply a reference to
string matching regexp enclosed by "()" within respectively <b>src</b>
and <b>dst</b> attributes. If they were more than 1 "()", then you
could refer to it as $2src, $3src and so on.

\subsubsection pf_rm_sf Simple/fast models

\li <b>none</b>: No routing (Unless you know what you are doing, avoid
using this mode in combination with a non Constant network model). 
None Example :
\verbatim
<AS id="exitAS"  routing="none">
        <router id="exit_gateway"/>
</AS>\endverbatim

\li <b>Vivaldi</b>: Vivaldi routing, so when you want to use
    coordinates. See the corresponding section P2P below for details. 
\li <b>Cluster</b>: Cluster routing, specific to cluster tag, should
    not be used, except internally. 

\subsection ps_dec Defining routes

The principle of route definition is the same for the 4 available tags
for doing it. Those for tags are:

\li <b>route</b>: to define route between host/router
\li <b>ASroute</b>: to define route between AS
\li <b>bypassRoute</b>: to bypass normal routes as calculated by the
    network model between host/router 
\li <b>bypassASroute</b>: same as bypassRoute, but for AS

Basically all those tags will contain an (ordered) list of references
to link that compose the route you want to define.

Consider the example below:

\verbatim
<route src="Alice" dst="Bob">
        <link_ctn id="link1"/>
        <link_ctn id="link2"/>
        <link_ctn id="link3"/>
   </route>
\endverbatim

The route here from host Alice to Bob will be first link1, then link2,
and finally link3. What about the reverse route ? <b>route</b> and
<b>ASroute</b> have an optional attribute <b>symmetrical</b>, that can
be either YES or NO. YES means that the reverse route is the same
route in the inverse order, and is set to YES by default. Note that
this is not the case for bypass*Route, as it is more probable that you
want to bypass only one default route.

For an ASroute, things are just slightly more complicated, as you have
to give the id of the gateway which is inside the AS you're talking
about you want to access ... So it looks like this :


\verbatim
  <ASroute src="AS1" dst="AS2"
    gw_src="router1" gw_dst="router2">
    <link_ctn id="link1"/>
  </ASroute>
\endverbatim

gw == gateway, so when any message are trying to go from AS1 to AS2,
it means that it must pass through router1 to get out of the AS, then
pass through link1, and get into AS2 by being received by router2.
router1 must belong to AS1 and router2 must belong to AS2.

\subsubsection pf_linkctn link_ctn

a <b>link_ctn</b> is the tag that is used in order to reference a
<b>link</b> in a route. Its id is the link id it refers to.

<b>link_ctn</b> attributes :
\li <b>id (mandatory)</b>: Id of the link this tag refers to
\li <b>direction</b>: if the link referenced by <b>id</b> has been
    declared as FULLDUPLEX, this is used to indicate in which
    direction the route you're defining is going through this link.
    Possible values "UP" or "DOWN".

\subsubsection pf_asro ASroute

ASroute tag purpose is to let people write manually their routes
between AS. It's usefull when you're in Full or Rule-based model.

<b>ASroute</b> attributes :
\li <b>src (mandatory)</b>: the source AS id.
\li <b>dst (mandatory)</b>: the destination AS id.
\li <b>gw_src (mandatory)</b>: the gateway to be used within the AS.
    Can be any <b>host</b> or \b router defined into the \b src AS or
    into one of the AS it includes.
\li <b>gw_dst (mandatory)</b>: the gateway to be used within the AS.
    Can be any <b>host</b> or \b router defined into the \b dst AS or
    into one of the AS it includes.
\li <b>symmetrical</b>: if the route is symmetric, the reverse route
    will be the opposite of the one defined. Can be either YES or NO,
    default is YES.

<b>Example of ASroute with RuleBased</b>
\verbatim
<ASroute src="^gw_AS_(.*)$" dst="^AS_(.*)$"
                                gw_src="gw_$1src"
                                gw_dst="$1dst-AS_$1dst_router.orsay.grid5000.fr"
                                symmetrical="NO">
                                        <link_ctn id="link_$1dst"/>
                        </ASroute>
\endverbatim
<b>Example of ASroute with Full</b>
\verbatim
<AS  id="AS0"  routing="Full">
  <cluster id="my_cluster_1" prefix="c-" suffix=".me"
                radical="0-149" power="1000000000"    bw="125000000"     lat="5E-5"
        bb_bw="2250000000" bb_lat="5E-4"/>

  <cluster id="my_cluster_2" prefix="c-" suffix=".me"
            radical="150-299" power="1000000000"        bw="125000000"  lat="5E-5"
            bb_bw="2250000000" bb_lat="5E-4"/>

     <link id="backbone" bandwidth="1250000000" latency="5E-4"/>

     <ASroute src="my_cluster_1" dst="my_cluster_2"
         gw_src="c-my_cluster_1_router.me"
         gw_dst="c-my_cluster_2_router.me">
                <link_ctn id="backbone"/>
     </ASroute>
     <ASroute src="my_cluster_2" dst="my_cluster_1"
         gw_src="c-my_cluster_2_router.me"
         gw_dst="c-my_cluster_1_router.me">
                <link_ctn id="backbone"/>
     </ASroute>
</AS>
\endverbatim

\subsubsection pf_ro route
The principle is the same as ASroute : <b>route</b> contains list of
links that are in the path between src and dst, except that it is for
routes between a src that can be either <b>host</b> or \b router and a
dst that can be either <b>host</b> or \b router. Useful for Full and
RuleBased, as well as for the shortest-paths based models, where you
have to give topological information.


<b>route</b> attributes :
\li <b>src (mandatory)</b>: the source id.
\li <b>dst (mandatory)</b>: the destination id.
\li <b>symmetrical</b>: if the route is symmetric, the reverse route
    will be the opposite of the one defined. Can be either YES or NO,
    default is YES.

<b>route example in Full</b>
\verbatim
 <route src="Tremblay" dst="Bourassa">
     <link_ctn id="4"/><link_ctn id="3"/><link_ctn id="2"/><link_ctn id="0"/><link_ctn id="1"/><link_ctn id="6"/><link_ctn id="7"/>
   </route>
\endverbatim

<b>route example in a shortest-path model</b>
\verbatim
 <route src="Tremblay" dst="Bourassa">
     <link_ctn id="3"/>
   </route>
\endverbatim
Note that when using route to give topological information, you have
to give routes with one link only in it, as SimGrid needs to know
which host are at the end of the link.

\subsubsection pf_byro bypassASroute

<b>Note : bypassASroute and bypassRoute are under rewriting to perform
better ; so you may not use it yet</b> As said before, once you choose
a model, it (if so) calculates routes for you. But maybe you want to
define some of your routes, which will be specific. You may also want
to bypass some routes defined in lower level AS at an upper stage :
<b>bypassASroute</b> is the tag you're looking for. It allows to
bypass routes defined between already defined between AS (if you want
to bypass route for a specific host, you should just use byPassRoute).
The principle is the same as ASroute : <b>bypassASroute</b> contains
list of links that are in the path between src and dst.

<b>bypassASroute</b> attributes :
\li <b>src (mandatory)</b>: the source AS id.
\li <b>dst (mandatory)</b>: the destination AS id.
\li <b>gw_src (mandatory)</b>: the gateway to be used within the AS.
    Can be any <b>host</b> or \b router defined into the \b src AS or
    into one of the AS it includes.
\li <b>gw_dst (mandatory)</b>: the gateway to be used within the AS.
    Can be any <b>host</b> or \b router defined into the \b dst AS or
    into one of the AS it includes.
\li <b>symmetrical</b>: if the route is symmetric, the reverse route
    will be the opposite of the one defined. Can be either YES or NO,
    default is YES.

<b>bypassASroute Example</b>
\verbatim
    <bypassASRoute src="my_cluster_1" dst="my_cluster_2"
     gw_src="my_cluster_1_router"
     gw_dst="my_cluster_2_router">
        <link_ctn id="link_tmp"/>
     </bypassASroute>
\endverbatim

\subsubsection pf_byro bypassRoute
<b>Note : bypassASRoute and bypassRoute are under rewriting to perform
better ; so you may not use it yet</b> As said before, once you choose
a model, it (if so) calculates routes for you. But maybe you want to
define some of your routes, which will be specific. You may also want
to bypass some routes defined in lower level AS at an upper stage :
<b>bypassRoute</b> is the tag you're looking for. It allows to bypass
routes defined between <b>host/router</b>. The principle is the same
as route : <b>bypassRoute</b> contains list of links references of
links that are in the path between src and dst.

<b>bypassRoute</b> attributes :
\li <b>src (mandatory)</b>: the source AS id.
\li <b>dst (mandatory)</b>: the destination AS id.
\li <b>symmetrical</b>: if the route is symmetric, the reverse route
    will be the opposite of the one defined. Can be either YES or NO,
    default is YES.

<b>bypassRoute Example</b>
\verbatim
<b>bypassRoute Example</b>
\verbatim
    <bypassRoute src="host_1" dst="host_2">
        <link_ctn id="link_tmp"/>
     </bypassRoute>
\endverbatim


\subsection pb_baroex Basic Routing Example

Let's say you have an AS named AS_Big that contains two other AS, AS_1
and AS_2. If you want to make an host (h1) from AS_1 with another one
(h2) from AS_2 then you'll have to proceed as follow:
\li First, you have to ensure that a route is defined from h1 to the
    AS_1's exit gateway and from h2 to AS_2's exit gateway.
\li Then, you'll have to define a route between AS_1 to AS_2. As those
    AS are both resources belonging to AS_Big, then it has to be done
    at AS_big level. To define such a route, you have to give the
    source AS (AS_1), the destination AS (AS_2), and their respective
    gateway (as the route is effectively defined between those two
    entry/exit points). Elements of this route can only be elements
    belonging to AS_Big, so links and routers in this route should be
    defined inside AS_Big. If you choose some shortest-path model,
    this route will be computed automatically.

As said before, there are mainly 2 tags for routing :
\li <b>ASroute</b>: to define routes between two  <b>AS</b>
\li <b>route</b>: to define routes between two <b>host/router</b>

As we are dealing with routes between AS, it means that those we'll
have some definition at AS_Big level. Let consider AS_1 contains 1
host, 1 link and one router and AS_2 3 hosts, 4 links and one router.
There will be a central router, and a cross-like topology. At the end
of the crosses arms, you'll find the 3 hosts and the router that will
act as a gateway. We have to define routes inside those two AS. Let
say that AS_1 contains full routes, and AS_2 contains some Floyd
routing (as we don't want to bother with defining all routes). As
we're using some shortest path algorithms to route into AS_2, we'll
then have to define some <b>route</b> to gives some topological
information to SimGrid. Here is a file doing it all :

\verbatim
<AS  id="AS_Big"  routing="Dijsktra">
  <AS id="AS_1" routing="Full">
     <host id="AS_1_host1" power="1000000000"/>
     <link id="AS_1_link" bandwidth="1250000000" latency="5E-4"/>
     <router id="AS_1_gateway"/>
     <route src="AS_1_host1" dst="AS_1_gateway">
            <link_ctn id="AS_1_link"/>
     </route>
  </AS>
  <AS id="AS_2" routing="Floyd">
     <host id="AS_2_host1" power="1000000000"/>
     <host id="AS_2_host2" power="1000000000"/>
     <host id="AS_2_host3" power="1000000000"/>
     <link id="AS_2_link1" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link2" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link3" bandwidth="1250000000" latency="5E-4"/>
     <link id="AS_2_link4" bandwidth="1250000000" latency="5E-4"/>
     <router id="central_router"/>
     <router id="AS_2_gateway"/>
     <!-- routes providing topological information -->
     <route src="central_router" dst="AS_2_host1"><link_ctn id="AS_2_link1"/></route>
     <route src="central_router" dst="AS_2_host2"><link_ctn id="AS_2_link2"/></route>
     <route src="central_router" dst="AS_2_host3"><link_ctn id="AS_2_link3"/></route>
     <route src="central_router" dst="AS_2_gateway"><link_ctn id="AS_2_link4"/></route>
  </AS>
    <link id="backbone" bandwidth="1250000000" latency="5E-4"/>

     <ASroute src="AS_1" dst="AS_2"
         gw_src="AS_1_gateway"
         gw_dst="AS_2_gateway">
                <link_ctn id="backbone"/>
     </ASroute>
</AS>
\endverbatim

\section pf_other_tags Tags not (directly) describing the platform

There are 3 tags, that you can use inside a \<platform\> tag that are
not describing the platform: 
\li random: it allows you to define random generators you want to use
    for your simulation. 
\li config: it allows you to pass some configuration stuff like, for
    example, the network model and so on. It follows the 
\li include: simply allows you to include another file into the
    current one. 

\subsection pf_conf config
<b>config</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the config to be used
    when referring to it. 


<b>config</b> tag only purpose is to include <b>prop</b> tags. Valid
id are basically the same as the list of possible parameters you can
use by command line, except that "/" are used for namespace
definition. See the \ref options config and options page for more
information.


<b>config example</b>
\verbatim
<?xml version='1.0'?>
<!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
<platform version="3">
<config id="General">
        <prop id="maxmin/precision" value="0.000010"></prop>
        <prop id="cpu/optim" value="TI"></prop>
        <prop id="workstation/model" value="compound"></prop>
        <prop id="network/model" value="SMPI"></prop>
        <prop id="path" value="~/"></prop>
        <prop id="smpi/bw_factor" value="65472:0.940694;15424:0.697866;9376:0.58729"></prop>
</config>

<AS  id="AS0"  routing="Full">
...
\endverbatim


\subsection pf_rand random
Not yet in use, and possibly subject to huge modifications.

\subsection pf_incl include
<b>include</b> tag allows to import into a file platform parts located
in another file. This is done with the intention to help people
combine their different AS and provide new platforms. Those files
should contains XML part that contains either
<b>include,cluster,peer,AS,trace,trace_connect</b> tags.  

<b>include</b> attributes :
\li <b>file (mandatory)</b>: filename of the file to include. Possible
    values: absolute or relative path, syntax similar to the one in
    use on your system. 

<b>Note</b>: due to some obscure technical reasons, you have to open
and close tag in order to let it work. 
<b>include Example</b>
\verbatim
<?xml version='1.0'?>
<!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
<platform version="3">
        <AS id="main" routing="Full">
                <include file="clusterA.xml"></include>
                <include file="clusterB.xml"></include>
        </AS>
</platform>
\endverbatim

\subsection pf_tra trace and trace_connect
Both tags are an alternate way to passe availability, state, and so on
files to entity. Instead of referring to the file directly in the host,
link, or cluster tag, you proceed by defining a trace with an id
corresponding to a file, later an host/link/cluster, and finally using
trace_connect you say that the file trace must be used by the entity.
Get it ? Let's have a look at an example : 

\verbatim
<AS  id="AS0"  routing="Full">
  <host id="bob" power="1000000000"/>
</AS>
  <trace id="myTrace" file="bob.trace" periodicity="1.0"/>
  <trace_connect trace="myTrace" element="bob" kind="POWER"/>
\endverbatim

All constraints you have is that <b>trace_connect</b> is after
<b>trace</b> and <b>host</b> definitions.


<b>trace</b> attributes :
\li <b>id (mandatory)</b>: the identifier of the trace to be used when
    referring to it.
\li <b>file</b>: filename of the file to include. Possible values :
    absolute or relative path, syntax similar to the one in use on
    your system. If omitted, the system expects that you provide the
    trace values inside the trace tags (see below).
\li <b>trace periodicity (mandatory)</b>: trace periodicity, same
    definition as in hosts (see upper for details).

Here is an example  of trace when no file name is provided:

\verbatim
 <trace id="myTrace" periodicity="1.0">
    0.0 1.0
    11.0 0.5
    20.0 0.8
  </trace>
\endverbatim

<b>trace_connect</b> attributes :
\li <b>kind</b>: the type of trace, possible values
    <b>HOST_AVAIL|POWER|LINK_AVAIL|BANDWIDTH|LATENCY,</b>  default:
    <b>HOST_AVAIL</b>  
\li <b>trace (mandatory)</b>: the identifier of the trace referenced.
\li <b>element (mandatory)</b>: the identifier of the entity referenced.



\section pf_hints Hints and tips, or how to write a platform efficiently

Now you should know at least the syntax and be able to create a
platform by your own. However, after having ourselves wrote some platforms, there
are some best practices you should pay attention to in order to
produce good platform and some choices you can make in order to have
faster simulations. Here's some hints and tips, then.

\subsection pf_as_h AS Hierarchy
The AS design allows SimGrid to go fast, because computing route is
done only for the set of resources defined in this AS. If you're using
only a big AS containing all resource with no AS into it and you're
using Full model, then ... you'll loose all interest into it. On the
other hand, designing a binary tree of AS with, at the lower level,
only one host, then you'll also loose all the good AS hierarchy can
give you. Remind you should always be "reasonable" in your platform
definition when choosing the hierarchy. A good choice if you try to
describe a real life platform is to follow the AS described in
reality, since this kind of trade-off works well for real life
platforms.

\subsection pf_exit_as Exit AS: why and how
Users that have looked at some of our platforms may have notice a
non-intuitive schema ... Something like that :


\verbatim
<AS id="AS_4"  routing="Full">
<AS id="exitAS_4"  routing="Full">
        <router id="router_4"/>
</AS>
<cluster id="cl_4_1" prefix="c_4_1-" suffix="" radical="1-20" power="1000000000" bw="125000000" lat="5E-5" bb_bw="2250000000" bb_lat="5E-4"/>
<cluster id="cl_4_2" prefix="c_4_2-" suffix="" radical="1-20" power="1000000000" bw="125000000" lat="5E-5" bb_bw="2250000000" bb_lat="5E-4"/>
<link id="4_1" bandwidth="2250000000" latency="5E-5"/>
<link id="4_2" bandwidth="2250000000" latency="5E-5"/>
<link id="bb_4" bandwidth="2250000000" latency="5E-4"/>
<ASroute src="cl_4_1"
        dst="cl_4_2"
        gw_src="c_4_1-cl_4_1_router"
        gw_dst="c_4_2-cl_4_2_router"
        symmetrical="YES">
                <link_ctn id="4_1"/>
                <link_ctn id="bb_4"/>
                <link_ctn id="4_2"/>
</ASroute>
<ASroute src="cl_4_1"
        dst="exitAS_4"
        gw_src="c_4_1-cl_4_1_router"
        gw_dst="router_4"
        symmetrical="YES">
                <link_ctn id="4_1"/>
                <link_ctn id="bb_4"/>
</ASroute>
<ASroute src="cl_4_2"
        dst="exitAS_4"
        gw_src="c_4_2-cl_4_2_router"
        gw_dst="router_4"
        symmetrical="YES">
                <link_ctn id="4_2"/>
                <link_ctn id="bb_4"/>
</ASroute>
</AS>
\endverbatim

In the AS_4, you have an exitAS_4 defined, containing only one router,
and routes defined to that AS from all other AS (as cluster is only a
shortcut for an AS, see cluster description for details). If there was
an upper AS, it would define routes to and from AS_4 with the gateway
router_4. It's just because, as we did not allowed (for performances
issues) to have routes from an AS to a single host/router, you have to
enclose your gateway, when you have AS included in your AS, within an
AS to define routes to it.

\subsection pf_P2P_tags P2P or how to use coordinates
SimGrid allows you to use some coordinated-based system, like vivaldi,
to describe a platform. The main concept is that you have some peers
that are located somewhere: this is the function of the 
<b>coordinates</b> of the \<peer\> or \<host\> tag. There's nothing
complicated in using it, here is an example of it:

\verbatim
<?xml version='1.0'?>
<!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
<platform version="3">

<config id="General">
        <prop id="network/coordinates" value="yes"></prop>
</config>
 <AS  id="AS0"  routing="Vivaldi">
        <host id="100030591" coordinates="25.5 9.4 1.4" power="1500000000.0" />
        <host id="100036570" coordinates="-12.7 -9.9 2.1" power="730000000.0" />
        ...
        <host id="100429957" coordinates="17.5 6.7 18.8" power="830000000.0" />
        </AS>
</platform>
\endverbatim

Coordinates are then used to calculate latency between two hosts by
calculating the euclidean distance between the two hosts coordinates.
The results express the latency in ms.

Note that the previous example defines a routing directly between hosts but it could be also used to define a routing between AS.
That is for example what is commonly done when using peers (see Section \ref pf_peer).
\verbatim
<?xml version='1.0'?>
<!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
<platform version="3">

<config id="General">
        <prop id="network/coordinates" value="yes"></prop>
</config>
 <AS  id="AS0"  routing="Vivaldi">
   <peer id="peer-0" coordinates="173.0 96.8 0.1" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us"/>
   <peer id="peer-1" coordinates="247.0 57.3 0.6" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us" />
   <peer id="peer-2" coordinates="243.4 58.8 1.4" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us" />
</AS>
</platform>
\endverbatim
In such a case though, we connect the AS created by the <b>peer</b> tag with the Vivaldi routing mechanism. 
This means that to route between AS1 and AS2, it will use the coordinates of router_AS1 and router_AS2. 
This is currently a convention and we may offer to change this convention in the DTD later if needed.
You may have noted that conveniently, a peer named FOO defines an AS named FOO and a router named router_FOO, which is why it works seamlessly with the <b>peer</b> tag.


\subsection pf_wisely Choosing wisely the routing model to use


Choosing wisely the routing model to use can significantly fasten your
simulation/save your time when writing the platform/save tremendous
disk space. Here is the list of available model and their
characteristics (lookup : time to resolve a route):

\li <b>Full</b>: Full routing data (fast, large memory requirements,
    fully expressive)    
\li <b>Floyd</b>: Floyd routing data (slow initialization, fast
    lookup, lesser memory requirements, shortest path routing only).
    Calculates all routes at once at the beginning.
\li <b>Dijkstra</b>: Dijkstra routing data (fast initialization, slow
    lookup, small memory requirements, shortest path routing only).
    Calculates a route when necessary.
\li <b>DijkstraCache</b>: Dijkstra routing data (fast initialization,
    fast lookup, small memory requirements, shortest path routing
    only). Same as Dijkstra, except it handles a cache for latest used
    routes.
\li <b>none</b>: No routing (usable with Constant network only).
    Defines that there is no routes, so if you try to determine a
    route without constant network within this AS, SimGrid will raise
    an exception.
\li <b>RuleBased</b>: Rule-Based routing data (fast initialisation,
    relatively slow lookup, moderate memory requirements, fully
    expressive): uses regexp to define routes;
\li <b>Vivaldi</b>: Vivaldi routing, so when you want to use coordinates
\li <b>Cluster</b>: Cluster routing, specific to cluster tag, should
    not be used. 

\subsection pf_switch Hey, I want to describe a switch but there is no switch tag !

Actually we did not include switch tag, ok. But when you're trying to
simulate a switch, the only major impact it has when you're using
fluid model (and SimGrid uses fluid model unless you activate GTNetS,
ns-3, or constant network mode) is the impact of the upper limit of
the switch motherboard speed that will eventually be reached if you're
using intensively your switch. So, the switch impact is similar to a
link one. That's why we are used to describe a switch using a link tag
(as a link is not an edge by a hyperedge, you can connect more than 2
other links to it).

\subsection pf_platform_multipath How to express multipath routing in platform files?

It is unfortunately impossible to express the fact that there is more
than one routing path between two given hosts. Let's consider the
following platform file:

\verbatim
<route src="A" dst="B">
   <link_ctn id="1"/>
</route>
<route src="B" dst="C">
  <link_ctn id="2"/>
</route>
<route src="A" dst="C">
  <link_ctn id="3"/>
</route>
\endverbatim

Although it is perfectly valid, it does not mean that data traveling
from A to C can either go directly (using link 3) or through B (using
links 1 and 2). It simply means that the routing on the graph is not
trivial, and that data do not following the shortest path in number of
hops on this graph. Another way to say it is that there is no implicit
in these routing descriptions. The system will only use the routes you
declare (such as &lt;route src="A" dst="C"&gt;&lt;link_ctn
id="3"/&gt;&lt;/route&gt;), without trying to build new routes by aggregating
the provided ones.

You are also free to declare platform where the routing is not
symmetric. For example, add the following to the previous file:

\verbatim
<route src="C" dst="A">
  <link_ctn id="2"/>
  <link_ctn id="1"/>
</route>
\endverbatim

This makes sure that data from C to A go through B where data from A
to C go directly. Don't worry about realism of such settings since
we've seen ways more weird situation in real settings (in fact, that's
the realism of very regular platforms which is questionable, but
that's another story).

\section pf_flexml_bypassing Bypassing the XML parser with your own C functions
<b>NOTE THAT THIS DOCUMENTATION, WHILE STILL WORKING, IS STRONGLY DEPRECATED</b>

So you want to bypass the XML files parser, uh? Maybe doing some parameter
sweep experiments on your simulations or so? This is possible, and
it's not even really difficult (well. Such a brutal idea could be
harder to implement). Here is how it goes.

For this, you have to first remember that the XML parsing in SimGrid is done
using a tool called FleXML. Given a DTD, this gives a flex-based parser. If
you want to bypass the parser, you need to provide some code mimicking what
it does and replacing it in its interactions with the SURF code. So, let's
have a look at these interactions.

FleXML parser are close to classical SAX parsers. It means that a
well-formed SimGrid platform XML file might result in the following
"events":

  - start "platform_description" with attribute version="2"
  - start "host" with attributes id="host1" power="1.0"
  - end "host"
  - start "host" with attributes id="host2" power="2.0"
  - end "host"
  - start "link" with ...
  - end "link"
  - start "route" with ...
  - start "link_ctn" with ...
  - end "link_ctn"
  - end "route"
  - end "platform_description"

The communication from the parser to the SURF code uses two means:
Attributes get copied into some global variables, and a surf-provided
function gets called by the parser for each event. For example, the event
  - start "host" with attributes id="host1" power="1.0"

let the parser do something roughly equivalent to:
\verbatim
  strcpy(A_host_id,"host1");
  A_host_power = 1.0;
  STag_host();
\endverbatim

In SURF, we attach callbacks to the different events by initializing the
pointer functions to some the right surf functions. Since there can be
more than one callback attached to the same event (if more than one
model is in use, for example), they are stored in a dynar. Example in
workstation_ptask_L07.c:
\verbatim
  /* Adding callback functions */
  surf_parse_reset_parser();
  surfxml_add_callback(STag_surfxml_host_cb_list, &parse_cpu_init);
  surfxml_add_callback(STag_surfxml_prop_cb_list, &parse_properties);
  surfxml_add_callback(STag_surfxml_link_cb_list, &parse_link_init);
  surfxml_add_callback(STag_surfxml_route_cb_list, &parse_route_set_endpoints);
  surfxml_add_callback(ETag_surfxml_link_c_ctn_cb_list, &parse_route_elem);
  surfxml_add_callback(ETag_surfxml_route_cb_list, &parse_route_set_route);

  /* Parse the file */
  surf_parse_open(file);
  xbt_assert(!surf_parse(), "Parse error in %s", file);
  surf_parse_close();
\endverbatim

So, to bypass the FleXML parser, you need to write your own version of the
surf_parse function, which should do the following:
   - Fill the A_<tag>_<attribute> variables with the wanted values
   - Call the corresponding STag_<tag>_fun function to simulate tag start
   - Call the corresponding ETag_<tag>_fun function to simulate tag end
   - (do the same for the next set of values, and loop)

Then, tell SimGrid that you want to use your own "parser" instead of the stock one:
\verbatim
  surf_parse = surf_parse_bypass_environment;
  MSG_create_environment(NULL);
  surf_parse = surf_parse_bypass_application;
  MSG_launch_application(NULL);
\endverbatim

A set of macros are provided at the end of
include/surf/surfxml_parse.h to ease the writing of the bypass
functions. An example of this trick is distributed in the file
examples/msg/masterslave/masterslave_bypass.c


*/