1 /*! \page platform Step 1: %Model the underlying platform
5 In order to run any simulation, SimGrid must be provided with three things:
6 something to run (i.e., your code), a description of the platform on which you
7 want to simulate your application and lastly information about the deployment
8 process: Which process should be deployed to which processor/core?
10 For the last two items, there are essentially two possible ways you can provide
11 this information as an input:
12 \li You can program it, either by using the Lua console (
13 \ref MSG_Lua_funct) or, if you're using MSG, some of MSG's platform and
14 deployment functions (\ref msg_simulation). If you want to use this,
15 check the particular documentation. (You can also check the section
16 \ref pf_flexml_bypassing, however, this documentation is deprecated;
17 there is a new, but undocumented, way to do it properly).
18 \li You can use two XML files: one contains the platform description while
19 the other contains the deployment instructions.
21 For more information on SimGrid's deployment features, please refer to
22 the \ref deployment documentation.
24 The platform description may be intricate. This documentation is all
25 about how to write this file: The basic concepts are introduced. Furthermore,
26 advanced options are explained. Additionally, some hints and tips on how to
27 write a good platform description are given.
29 \section pf_overview Some words about XML and DTD
31 We chose to use XML not only because it's extensible but also because many
32 tools (and plugins for existing tools) are available that facilitate editing and
33 validating XML files. Furthermore, libraries that parse XML are often already
34 available and very well tested.
36 The XML checking is done based on the Document Type Definition (DTD) file,
38 <a href="http://simgrid.gforge.inria.fr/simgrid.dtd">http://simgrid.gforge.inria.fr/simgrid.dtd</a>.
40 If you read the DTD, you should notice the following:
41 \li The platform tags contain a version attribute; the current version is 3.
42 This property might be used in the future to provide backwards
44 \li The DTD contains definitions for the two files used by SimGrid (i.e.,
45 platform description and deployment).
47 \section pf_basics Basic concepts
49 Nowadays, the Internet is composed of a bunch of independently managed
50 networks. Within each of those networks, there are entry and exit
51 points (most of the time, you can both enter and exit through the same
52 point); this allows to leave the current network and reach other
53 networks, possibly even in other locations.
54 At the upper level, such a network is called
55 <b>Autonomous System (AS)</b>, while at the lower level it is named
56 sub-network, or LAN (local area network).
57 They are indeed autonomous: routing is defined
58 (within the limits of his network) by the administrator, and so, those
59 networks can operate without a connection to other
60 networks. So-called gateways allow you to go from one network to
61 another, if such a (physical) connection exists. Every node in one network
62 that can be directly reached (i.e., without traversing other nodes) from
63 another network is called a gateway.
64 Each autonomous system consists of equipment such as cables (network links),
65 routers and switches as well as computers.
67 The structure of the SimGrid platform description relies exactly on the same
68 concept as a real-life platform (see above). Every resource (computers,
69 network equipment etc.) belongs to an AS, which can be defined by using the
70 \<AS\> tag. Within an AS, the routing between its elements can be defined
71 abitrarily. There are several modes for routing, and exactly one mode must be
72 selected by specifying the routing attribute in the AS tag:
75 <AS id="AS0" routing="Full">
79 Other supported values for the routing attribute can be found below, Section
82 There is also the ``<route>`` tag; this tag takes two attributes, ``src`` (source)
83 and ``dst`` (destination). Both source and destination must be valid identifiers
84 for routers (these will be introduced later). Contained by the ``<route>`` are
85 network links; these links must be used in order to communicate from the source
86 to the destination specified in the tag. Hence, a route merely describes
87 how to reach a router from another router.
90 More information and (code-)examples can be found in Section \ref pf_rm.
92 An AS can also contain itself one or more AS; this allows you to
93 model the hierarchy of your platform.
95 ### Within each AS, the following types of resources exist:
97 %Resource | Documented in Section | Description
98 --------------- | --------------------- | -----------
99 AS | | Every Autonomous System (AS) may contain one or more AS.
100 host | \ref pf_host | This entity carries out the actual computation. For this reason, it contains processors (with potentially multiple cores).
101 router | \ref pf_router | In SimGrid, routers are used to provide helpful information to routing algorithms. Routers may also act as gateways, connecting several autonomous systems with each other.
102 link | \ref pf_link | In SimGrid, (network)links define a connection between two or potentially even more resources. Every link has a bandwidth and a latency and may potentially experience congestion.
103 cluster | \ref pf_cluster | In SimGrid, clusters were introduced to model large and homogenous environments. They are not really a resource by themselves - technically, they are only a shortcut, as they will internally set up all the hosts, network and routing for you, i.e., using this resource, one can easily setup thousands of hosts and links in a few lines of code. Each cluster is itself an AS.
105 %As it is desirable to interconnect these resources, a routing has to be
106 defined. The AS is supposed to be Autonomous, hence this has to be done at the
107 AS level. The AS handles two different types of entities (<b>host/router</b>
108 and <b>AS</b>). However, the user is responsible to define routes between those resources,
109 otherwise entities will be unconnected and therefore unreachable from other
110 entities. Although several routing algorithms are built into SimGrid (see
111 \ref pf_rm), you might encounter a case where you want to define routes
112 manually (for instance, due to specific requirements of your platform).
114 There are three tags to use:
115 \li <b>ASroute</b>: to define routes between two <b>AS</b>
116 \li <b>route</b>: to define routes between two <b>host/router</b>
117 \li <b>bypassRoute</b>: to define routes between two <b>AS</b> that
118 will bypass default routing (as specified by the ``routing`` attribute
119 supplied to ``<AS>``, see above).
121 Here is an illustration of these concepts:
123 
124 Circles represent processing units and squares represent network routers. Bold
125 lines represent communication links. AS2 models the core of a national
126 network interconnecting a small flat cluster (AS4) and a larger
127 hierarchical cluster (AS5), a subset of a LAN (AS6), and a set of peers
128 scattered around the world (AS7).
130 \section pf_pftags Resource description
132 \subsection pf_As Platform: The <AS> tag
134 The concept of an AS was already outlined above (Section \ref pf_basics);
135 recall that the AS is so important because it groups other resources (such
136 as routers/hosts) together (in fact, these resources must be contained by
139 Available attributes :
141 Attribute name | Mandatory | Values | Description
142 --------------- | --------- | ------ | -----------
143 id | yes | String | The identifier of an AS; facilitates referring to this AS. ID must be unique.
144 routing | yes | Full\| Floyd\| Dijkstra\| DijkstraCache\| None\| Vivaldi\| Cluster | See Section \ref pf_rm for details.
149 <AS id="AS0" routing="Full">
150 <host id="host1" power="1000000000"/>
151 <host id="host2" power="1000000000"/>
152 <link id="link1" bandwidth="125000000" latency="0.000100"/>
153 <route src="host1" dst="host2"><link_ctn id="link1"/></route>
157 In this example, AS0 contains two hosts (host1 and host2). The route
158 between the hosts goes through link1.
160 \subsection pf_Cr Computing resources: hosts, clusters and peers.
162 \subsubsection pf_host <host/>
164 A <b>host</b> represents a computer/node card. Every host is able to execute
165 code and it can send and receive data to/from other hosts. Most importantly,
166 a host can contain more than 1 core.
170 Attribute name | Mandatory | Values | Description
171 --------------- | --------- | ------ | -----------
172 id | yes | String | The identifier of the host. facilitates referring to this AS.
173 power | yes | double (must be > 0.0) | Computational power of every core of this host in FLOPS. Must be larger than 0.0.
174 core | no | int (Default: 1) | The number of cores of this host. If more than one core is specified, the "power" parameter refers to every core, i.e., the total computational power is no_of_cores*power.<br /> If 6 cores are specified, up to 6 tasks can be executed without sharing the computational power; if more than 6 tasks are executed, computational power will be shared among these tasks. <br /> <b>Warning:</b> Although functional, this model was never scientifically assessed.
175 availability | no | int | <b>Specify if the percentage of power available.</b> (What? TODO)
176 availability_file| no | string | (Relative or absolute) filename to use as input; must contain availability traces for this host. The syntax of this file is defined below. <br /> <b>Note:</b> The filename must be specified with your system's format.
177 state | no | ON\|OFF<br/> (Default: ON) | Is this host running or not?
178 state_file | no | string | Same mechanism as availability_file.<br /> <b>Note:</b> The filename must be specified with your system's format.
179 coordinates | no | string | Must be provided when choosing the Vivaldi, coordinate-based routing model for the AS the host belongs to. More details can be found in the Section \ref pf_P2P_tags.
181 ### Possible children: ###
183 Tag name | Description | Documentation
184 ------------ | ----------- | -------------
185 \<mount/\> | Defines mounting points between some storage resource and the host. | \ref pf_storage_entity_mount
186 \<prop/\> | 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. | N/A
191 <host id="host1" power="1000000000"/>
192 <host id="host2" power="1000000000">
193 <prop id="color" value="blue"/>
194 <prop id="rendershape" value="square"/>
199 \anchor pf_host_dynamism
200 ### Expressing dynamism ###
202 SimGrid provides mechanisms to change a hosts' availability over
203 time, using the ``availability_file`` attribute to the ``\<host\>`` tag
204 and a separate text file whose syntax is exemplified below.
206 #### Adding a trace file ####
209 <platform version="1">
210 <host id="bob" power="500000000" availability_file="bob.trace" />
214 #### Example of "bob.trace" file ####
223 Let us begin to explain this example by looking at line 2. (Line 1 will become clear soon).
224 The first column describes points in time, in this case, time 0. The second column
225 describes the relative amount of power this host is able to deliver (relative
226 to the maximum performance specified in the ``\<host\>`` tag). (Clearly, the
227 second column needs to contain values that are not smaller than 0 and not larger than 1).
228 In this example, our host will deliver 500 Mflop/s at time 0, as 500 Mflop/s is the
229 maximum performance of this host. At time 11.0, it will
230 deliver half of its maximum performance, i.e., 250 Mflop/s until time 20.0 when it will
231 will start delivering 80\% of its power. In this example, this amounts to 400 Mflop/s.
233 Since the periodicity in line 1 was set to be 1.0, i.e., 1 timestep, this host will
234 continue to provide 500 Mflop/s from time 21. From time 32 it will provide 250 MFlop/s and so on.
236 ### Changing initial state ###
238 It is also possible to specify whether the host is up or down by setting the
239 ``state`` attribute to either <b>ON</b> (default value) or <b>OFF</b>.
241 #### Example: Expliciting the default value "ON" ####
244 <platform version="1">
245 <host id="bob" power="500000000" state="ON" />
249 If you want this host to be unavailable, simply substitute ON with OFF.
251 \anchor pf_host_churn
252 ### Expressing churn ###
254 To express the fact that a host can change state over time (as in P2P
255 systems, for instance), it is possible to use a file describing the time
256 at which the host is turned on or off. An example of the content
257 of such a file is presented below.
259 #### Adding a state file ####
262 <platform version="1">
263 <host id="bob" power="500000000" state_file="bob.fail" />
267 #### Example of "bob.fail" file ####
275 A negative value means <b>down</b> (i.e., OFF) while a positive one means <b>up and
276 running</b> (i.e., ON). From time 0.0 to time 1.0, the host is on. At time 1.0, it is
277 turned off and at time 2.0, it is turned on again until time 12 (2.0 plus the
278 periodicity 10.0). It will be turned on again at time 13.0 until time 23.0, and
282 \subsubsection pf_cluster <cluster>
284 ``<cluster />`` represents a machine-cluster. It is most commonly used
285 when one wants to define many hosts and a network quickly. Technically,
286 ``cluster`` is a meta-tag: <b>from the inner SimGrid point of
287 view, a cluster is an AS where some optimized routing is defined</b>.
288 The default inner organization of the cluster is as follow:
294 ____________|__________|_____________ backbone
296 l0| l1| l2| l97| l96 | | l99
302 Here, a set of <b>host</b>s is defined. Each of them has a <b>link</b>
303 to a central backbone (backbone is a link itself, as a link can
304 be used to represent a switch, see the switch / link section
305 below for more details about it). A <b>router</b> allows to connect a
306 <b>cluster</b> to the outside world. Internally,
307 SimGrid treats a cluster as an AS containing all hosts: the router is the default
308 gateway for the cluster.
310 There is an alternative organization, which is as follows:
324 The principle is the same, except that there is no backbone. This representation
325 can be obtained easily: just do not set the bb_* attributes.
328 Attribute name | Mandatory | Values | Description
329 --------------- | --------- | ------ | -----------
330 id | yes | string | The identifier of the cluster. Facilitates referring to this cluster.
331 prefix | yes | string | Each node of the cluster has to have a name. This name will be prefixed with this prefix.
332 suffix | yes | string | Each node of the cluster will be suffixed with this suffix
333 radical | yes | string | Regexp used to generate cluster nodes name. Syntax: "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.
334 power | yes | int | Same as the ``power`` attribute of the ``\<host\>`` tag.
335 core | no | int (default: 1) | Same as the ``core`` attribute of the ``\<host\>`` tag.
336 bw | yes | int | Bandwidth for the links between nodes and backbone (if any). See the \ref pf_link "link section" for syntax/details.
337 lat | yes | int | Latency for the links between nodes and backbone (if any). See <b>link</b> section for syntax/details.
338 sharing_policy | no | string | Sharing policy for the links between nodes and backbone (if any). See <b>link</b> section for syntax/details.
339 bb_bw | no | int | Bandwidth for backbone (if any). See <b>link</b> section for syntax/details. If bb_bw and bb_lat (see below) attributes are omitted, no backbone is created (alternative cluster architecture <b>described before</b>).
340 bb_lat | no | int | Latency for backbone (if any). See <b>link</b> section for syntax/details. If bb_lat and bb_bw (see above) attributes are omitted, no backbone is created (alternative cluster architecture <b>described before</b>).
341 bb_sharing_policy | no | string | Sharing policy for the backbone (if any). See <b>link</b> section for syntax/details.
342 availability_file | no | string | Allows you to use a file as input for availability. Similar to <b>hosts</b> attribute.
343 state_file | no | string | Allows you to use a file as input for states. Similar to <b>hosts</b> attribute.
344 loopback_bw | no | int | Bandwidth for loopback (if any). See <b>link</b> section for syntax/details. If loopback_bw and loopback_lat (see below) attributes are omitted, no loopback link is created and all intra-node communication will use the main network link of the node. Loopback link is a \ref pf_sharing_policy_fatpipe "\b FATPIPE".
345 loopback_lat | no | int | Latency for loopback (if any). See <b>link</b> section for syntax/details. See loopback_bw for more info.
346 topology | no | FLAT\|TORUS\|FAT_TREE (default: FLAT) | Network topology to use. SimGrid currently supports FLAT (with or without backbone, as described before), <a href="http://en.wikipedia.org/wiki/Torus_interconnect">TORUS </a> and FAT_TREE attributes for this tag.
347 topo_parameters | no | string | Specific parameters to pass for the topology defined in the topology tag. For torus networks, comma-separated list of the number of nodes in each dimension of the torus. For fat trees, refer to \ref AsClusterFatTree "AsClusterFatTree documentation".
351 the router name is defined as the resulting String in the following
355 router_name = prefix + clusterId + _router + suffix;
359 #### Cluster example ####
361 Consider the following two (and independent) uses of the ``cluster`` tag:
364 <cluster id="my_cluster_1" prefix="" suffix="" radical="0-262144"
365 power="1e9" bw="125e6" lat="5E-5"/>
367 <cluster id="my_cluster_2" prefix="c-" suffix=".me" radical="0-99"
368 power="1e9" bw="125e6" lat="5E-5"
369 bb_bw="2.25e9" bb_lat="5E-4"/>
372 The second example creates one router and 100 machines with the following names:
374 c-my_cluster_2_router.me
382 \subsubsection pf_cabinet <cabinet>
385 This tag is only available when the routing mode of the AS
386 is set to ``Cluster``.
388 The ``<cabinet />`` tag is, like the \ref pf_cluster "<cluster>" tag,
389 a meta-tag. This means that it is simply a shortcut for creating a set of (homogenous) hosts and links quickly;
390 unsurprisingly, this tag was introduced to setup cabinets in data centers quickly. Unlike
391 <cluster>, however, the <cabinet> assumes that you create the backbone
392 and routers yourself; see our examples below.
396 Attribute name | Mandatory | Values | Description
397 --------------- | --------- | ------ | -----------
398 id | yes | string | The identifier of the cabinet. Facilitates referring to this cluster.
399 prefix | yes | string | Each node of the cabinet has to have a name. This name will be prefixed with this prefix.
400 suffix | yes | string | Each node of the cabinet will be suffixed with this suffix
401 radical | yes | string | Regexp used to generate cabinet nodes name. Syntax: "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.
402 power | yes | int | Same as the ``power`` attribute of the \ref pf_host "<host>" tag.
403 bw | yes | int | Bandwidth for the links between nodes and backbone (if any). See the \ref pf_link "link section" for syntax/details.
404 lat | yes | int | Latency for the links between nodes and backbone (if any). See the \ref pf_link "link section" for syntax/details.
407 Please note that as of now, it is impossible to change attributes such as,
408 amount of cores (always set to 1), the initial state of hosts/links
409 (always set to ON), the sharing policy of the links (always set to \ref pf_sharing_policy_fullduplex "FULLDUPLEX").
413 The following example was taken from ``examples/platforms/meta_cluster.xml`` and
414 shows how to use the cabinet tag.
417 <AS id="my_cluster1" routing="Cluster">
418 <cabinet id="cabinet1" prefix="host-" suffix=".cluster1"
419 power="1Gf" bw="125MBps" lat="100us" radical="1-10"/>
420 <cabinet id="cabinet2" prefix="host-" suffix=".cluster1"
421 power="1Gf" bw="125MBps" lat="100us" radical="11-20"/>
422 <cabinet id="cabinet3" prefix="host-" suffix=".cluster1"
423 power="1Gf" bw="125MBps" lat="100us" radical="21-30"/>
425 <backbone id="backbone1" bandwidth="2.25GBps" latency="500us"/>
430 Please note that you must specify the \ref pf_backbone "<backbone>"
431 tag by yourself; this is not done automatically and there are no checks
432 that ensure this backbone was defined.
434 The hosts generated in the above example are named host-1.cluster, host-2.cluster1
438 \subsubsection pf_peer The <peer> tag
440 This tag represents a peer, as in Peer-to-Peer (P2P) networks. However, internally,
441 SimGrid transforms a peer into an AS (similar to Cluster). Hence, this tag
442 is virtually only a shortcut that comes with some pre-defined resources
443 and values. These are:
445 \li A tiny AS whose routing type is cluster is created
447 \li Two links: One for download and one for upload. This is
448 convenient to use and simulate stuff under the last mile model (e.g., ADSL peers).
449 \li It connects the two links to the host
450 \li It creates a router (a gateway) that serves as an entry point for this peer zone.
451 This router has coordinates.
455 Attribute name | Mandatory | Values | Description
456 --------------- | --------- | ------ | -----------
457 id | yes | string | The identifier of the peer. Facilitates referring to this peer.
458 power | yes | int | See the description of the ``host`` tag for this attribute
459 bw_in | yes | int | Bandwidth downstream
460 bw_out | yes | int | Bandwidth upstream
461 lat | yes | double | Latency for both up- and downstream, in seconds.
462 coordinates | no | string | Coordinates of the gateway for this peer. Example value: 12.8 14.4 6.4
463 sharing_policy | no | SHARED\|FULLDUPLEX (default: FULLDUPLEX) | Sharing policy for links. See <b>link</b> description for details.
464 availability_file| no | string | Availability file for the peer. Same as host availability file. See <b>host</b> description for details.
465 state_file | no | string | State file for the peer. Same as host state file. See <b>host</b> description for details.
467 Internally, SimGrid transforms any ``\<peer/\>`` construct such as
470 coordinates="12.8 14.4 6.4"
476 into an ``\<AS\>`` (see Sections \ref pf_basics and \ref pf_As). In fact, this example of the ``\<peer/\>`` tag
477 is completely equivalent to the following declaration:
480 <AS id="as_FOO" routing="Cluster">
481 <host id="peer_FOO" power="1.5Gf"/>
482 <link id="link_FOO_UP" bandwidth="2.25GBps" latency="500us"/>
483 <link id="link_FOO_DOWN" bandwidth="2.25GBps" latency="500us"/>
484 <router id="router_FOO" coordinates="25.5 9.4 1.4"/>
485 <host_link id="peer_FOO" up="link_FOO_UP" down="link_FOO_DOWN"/>
490 \subsection pf_ne Network equipments: links and routers
492 There are two tags at all times available to represent network entities and
493 several other tags that are available only in certain contexts.
494 1. ``<link>``: Represents a entity that has a limited bandwidth, a
495 latency, and that can be shared according to TCP way to share this
498 The concept of links in SimGrid may not be intuitive, as links are not
499 limited to connecting (exactly) two entities; in fact, you can have more than
500 two equipments connected to it. (In graph theoretical terms: A link in
501 SimGrid is not an edge, but a hyperedge)
503 2. ``<router/>``: Represents an entity that a message can be routed
504 to, but that is unable to execute any code. In SimGrid, routers have also
505 no impact on the performance: Routers do not limit any bandwidth nor
506 do they increase latency. As a matter of fact, routers are (almost) ignored
507 by the simulator when the simulation has begun.
509 3. ``<backbone/>``: This tag is only available when the containing AS is
510 used as a cluster (i.e., mode="Cluster")
513 If you want to represent an entity like a switch, you must use ``<link>`` (see section). Routers are used
514 to run some routing algorithm and determine routes (see Section \ref pf_routing for details).
516 \subsubsection pf_router <router/>
518 %As said before, <b>router</b> is used only to give some information
519 for routing algorithms. So, it does not have any attributes except :
523 Attribute name | Mandatory | Values | Description
524 --------------- | --------- | ------ | -----------
525 id | yes | string | The identifier of the router to be used when referring to it.
526 coordinates | yes | string | Must be provided when choosing the Vivaldi, coordinate-based routing model for the AS the router belongs to. More details can be found in the Section \ref pf_P2P_tags.
531 <router id="gw_dc1_horizdist"/>
534 \subsubsection pf_link <link/>
536 Network links can represent one-hop network connections. They are
537 characterized by their id and their bandwidth; links can (but may not) be subject
542 Attribute name | Mandatory | Values | Description
543 --------------- | --------- | ------ | -----------
544 id | yes | string | The identifier of the link to be used when referring to it.
545 bandwidth | yes | int | Maximum bandwidth for this link, given in bytes/s
546 latency | no | double (default: 0.0) | Latency for this link.
547 sharing_policy | no | \ref sharing_policy_shared "SHARED"\|\ref pf_sharing_policy_fatpipe "FATPIPE"\|\ref pf_sharing_policy_fullduplex "FULLDUPLEX" (default: SHARED) | Sharing policy for the link.
548 state | no | ON\|OFF (default: ON) | Allows you to to turn this link on or off (working / not working)
549 bandwidth_file | no | string | Allows you to use a file as input for bandwidth.
550 latency_file | no | string | Allows you to use a file as input for latency.
551 state_file | no | string | Allows you to use a file as input for states.
554 #### Possible shortcuts for ``latency`` ####
556 When using the latency attribute, you can specify the latency by using the scientific
557 notation or by using common abbreviations. For instance, the following three tags
561 <link id="LINK1" bandwidth="125000000" latency="5E-6"/>
562 <link id="LINK1" bandwidth="125000000" latency="5us"/>
563 <link id="LINK1" bandwidth="125000000" latency="0.000005"/>
566 Here, the second tag uses "us", meaning "microseconds". Other shortcuts are:
568 Name | Abbreviation | Time (in seconds)
569 ---- | ------------ | -----------------
570 Week | w | 7 * 24 * 60 * 60
571 Day | d | 24 * 60 * 60
575 Millisecond | ms | 0.001 = 10^(-3)
576 Microsecond | us | 0.000001 = 10^(-6)
577 Nanosecond | ns | 0.000000001 = 10^(-9)
578 Picosecond | ps | 0.000000000001 = 10^(-12)
580 #### Sharing policy ####
582 \anchor sharing_policy_shared
583 By default a network link is \b SHARED, i.e., if two or more data flows go
584 through a link, the bandwidth is shared fairly among all data flows. This
585 is similar to the sharing policy TCP uses.
587 \anchor pf_sharing_policy_fatpipe
588 On the other hand, if a link is defined as a \b FATPIPE,
589 each flow going through this link will be provided with the complete bandwidth,
590 i.e., no sharing occurs and the bandwidth is only limiting each flow individually.
591 Please note that this is really on a per-flow basis, not only on a per-host basis!
592 The complete bandwidth provided by this link in this mode
593 is ``number_of_flows*bandwidth``, with at most ``bandwidth`` being available per flow.
595 Using the FATPIPE mode allows to model backbones that won't affect performance
598 \anchor pf_sharing_policy_fullduplex
599 The last mode available is \b FULLDUPLEX. This means that SimGrid will
600 automatically generate two links (one carrying the suffix _UP and the other the
601 suffix _DOWN) for each ``<link>`` tag. This models situations when the direction
602 of traffic is important.
605 Transfers from one side to the other will interact similarly as
606 TCP when ACK returning packets circulate on the other direction. More
607 discussion about it is available in the description of link_ctn description.
609 In other words: The SHARED policy defines a physical limit for the bandwidth.
610 The FATPIPE mode defines a limit for each application,
611 with no upper total limit.
614 Tip: By using the FATPIPE mode, you can model big backbones that
615 won't affect performance (except latency).
620 <link id="SWITCH" bandwidth="125000000" latency="5E-5" sharing_policy="FATPIPE" />
623 #### Expressing dynamism and failures ####
625 Similar to hosts, it is possible to declare links whose state, bandwidth
626 or latency changes over time (see Section \ref pf_host_dynamism for details).
628 In the case of network links, the ``bandwidth`` and ``latency`` attributes are
629 replaced by the ``bandwidth_file`` and ``latency_file`` attributes.
630 The following XML snippet demonstrates how to use this feature in the platform
631 file. The structure of the files "link1.bw" and "link1.lat" is shown below.
634 <link id="LINK1" state_file="link1.fail" bandwidth="80000000" latency=".0001" bandwidth_file="link1.bw" latency_file="link1.lat" />
638 Even if the syntax is the same, the semantic of bandwidth and latency
639 trace files differs from that of host availability files. For bandwidth and
640 latency, the corresponding files do not
641 express availability as a fraction of the available capacity but directly in
642 bytes per seconds for the bandwidth and in seconds for the latency. This is
643 because most tools allowing to capture traces on real platforms (such as NWS)
644 express their results this way.
646 ##### Example of "link1.bw" file #####
654 In this example, the bandwidth changes repeatedly, with all changes
655 being repeated every 12 seconds.
657 At the beginning of the the simulation, the link's bandwidth is 80,000,000
658 B/s (i.e., 80 Mb/s); this value was defined in the XML snippet above.
659 After four seconds, it drops to 40 Mb/s (line 2), and climbs
660 back to 60 Mb/s after another 4 seconds (line 3). The value does not change any
661 more until the end of the period, that is, after 12 seconds have been simulated).
662 At this point, periodicity kicks in and this behavior is repeated: Seconds
663 12-16 will experience 80 Mb/s, 16-20 40 Mb/s etc.).
665 ##### Example of "link1.lat" file #####
674 In this example, the latency varies with a period of 5 seconds.
675 In the xml snippet above, the latency is initialized to be 0.0001s (100µs). This
676 value will be kept during the first second, since the latency_file contains
677 changes to this value at second one, two and three.
678 At second one, the value will be 0.001, i.e., 1ms. One second later it will
679 be adjusted to 0.01 (or 10ms) and one second later it will be set again to 1ms. The
680 value will not change until second 5, when the periodicity defined in line 1
681 kicks in. It then loops back, starting at 100µs (the initial value) for one second.
684 #### The ``<prop/>`` tag ####
686 Similar to the ``<host>`` tag, a link may also contain the ``<prop/>`` tag; see the host
687 documentation (Section \ref pf_host) for an example.
690 \subsubsection pf_backbone <backbone/>
693 This tag is <b>only available</b> when the containing AS uses the "Cluster" routing mode!
695 Using this tag, you can designate an already existing link to be a backbone.
697 Attribute name | Mandatory | Values | Description
698 --------------- | --------- | ------ | -----------
699 id | yes | string | Name of the link that is supposed to act as a backbone.
701 \subsection pf_storage Storage
704 This is a prototype version that should evolve quickly, hence this
705 is just some doc valuable only at the time of writing.
706 This section describes the storage management under SimGrid ; nowadays
707 it's only usable with MSG. It relies basically on linux-like concepts.
708 You also may want to have a look to its corresponding section in \ref
709 msg_file_management ; access functions are organized as a POSIX-like
712 \subsubsection pf_sto_conc Storage - Main Concepts
714 The storage facilities implemented in SimGrid help to model (and account for)
715 storage devices, such as tapes, hard-drives, CD or DVD devices etc.
716 A typical situation is depicted in the figure below:
718 \image html ./images/storage_sample_scenario.png
719 \image latex ./images/storage_sample_scenario.png "storage_sample_scenario" width=\textwidth
721 In this figure, two hosts called Bob and Alice are interconnected via a network
722 and each host is physically attached to a disk; it is not only possible for each host to
723 mount the disk they are attached to directly, but they can also mount disks
724 that are in a remote location. In this example, Bob mounts Alice's disk remotely
725 and accesses the storage via the network.
727 SimGrid provides 3 different entities that can be used to model setups
728 that include storage facilities:
730 Entity name | Description
731 --------------- | -----------
732 \ref pf_storage_entity_storage_type "storage_type" | Defines a template for a particular kind of storage (such as a hard-drive) and specifies important features of the storage, such as capacity, performance (read/write), contents, ... Different models of hard-drives use different storage_types (because the difference between an SSD and an HDD does matter), as they differ in some specifications (e.g., different sizes or read/write performance).
733 \ref pf_storage_entity_storage "storage" | Defines an actual instance of a storage type (disk, RAM, ...); uses a ``storage_type`` template (see line above) so that you don't need to re-specify the same details over and over again.
734 \ref pf_storage_entity_mount "mount" | Must be wrapped by a \ref pf_host tag; declares which storage(s) this host has mounted and where (i.e., the mountpoint).
737 \anchor pf_storage_content_file
738 ### %Storage Content File ###
740 In order to assess exactly how much time is spent reading from the storage,
741 SimGrid needs to know what is stored on the storage device (identified by distinct (file-)name, like in a file system)
742 and what size this content has.
745 The content file is never changed by the simulation; it is parsed once
746 per simulation and kept in memory afterwards. When the content of the
747 storage changes, only the internal SimGrid data structures change.
749 \anchor pf_storage_content_file_structure
750 #### Structure of a %Storage Content File ####
752 Here is an excerpt from two storage content file; if you want to see the whole file, check
753 the file ``examples/platforms/content/storage_content.txt`` that comes with the
756 SimGrid essentially supports two different formats: UNIX-style filepaths should
757 follow the well known format:
760 /lib/libsimgrid.so.3.6.2 12710497
764 /bin/simgrid_update_xml 5018
765 /bin/graphicator 66986
766 /bin/simgrid-colorizer 2993
771 Windows filepaths, unsurprisingly, use the windows style:
774 \Windows\avastSS.scr 41664
775 \Windows\bfsvc.exe 75264
776 \Windows\bootstat.dat 67584
777 \Windows\CoreSingleLanguage.xml 31497
779 \Windows\dchcfg64.exe 335464
780 \Windows\dcmdev64.exe 93288
784 The different file formats come at a cost; in version 3.12 (and most likely
785 in later versions, too), copying files from windows-style storages to unix-style
786 storages (and vice versa) is not supported.
788 \anchor pf_storage_content_file_create
789 #### Generate a %Storage Content File ####
791 If you want to generate a storage content file based on your own filesystem (or at least a filesystem you have access to),
792 try running this command (works only on unix systems):
795 find . -type f -exec ls -1s --block=1 {} \; 2>/dev/null | awk '{ print $2 " " $1}' > ./content.txt
798 \subsubsection pf_storage_entities The Storage Entities
800 These are the entities that you can use in your platform files to include
801 storage in your model. See also the list of our \ref pf_storage_example_files "example files";
802 these might also help you to get started.
804 \anchor pf_storage_entity_storage_type
805 #### \<storage_type\> ####
807 Attribute name | Mandatory | Values | Description
808 --------------- | --------- | ------ | -----------
809 id | yes | string | Identifier of this storage_type; used when referring to it
810 model | yes | string | For reasons of future backwards compatibility only; specifies the name of the model for the storage that should be used
811 size | yes | string | Specifies the amount of available storage space; you can specify storage like "500GiB" or "500GB" if you want. (TODO add a link to all the available abbreviations)
812 content | yes | string | Path to a \ref pf_storage_content_file "Storage Content File" on your system. This file must exist.
813 content_type | no | ("txt_unix"\|"txt_win") | Determines which kind of filesystem you're using; make sure the filenames (stored in that file, see \ref pf_storage_content_file_structure "Storage Content File Structure"!)
815 This tag must contain some predefined model properties, specified via the <model_prop> tag. Here is a list,
816 see below for an example:
818 Property id | Mandatory | Values | Description
819 --------------- | --------- | ------ | -----------
820 Bwrite | yes | string | Bandwidth for write access; in B/s (but you can also specify e.g. "30MBps")
821 Bread | yes | string | Bandwidth for read access; in B/s (but you can also specify e.g. "30MBps")
822 Bconnexion | yes | string | Throughput (of the storage connector) in B/s.
825 A storage_type can also contain the <b><prop></b> tag. The <prop> tag allows you
826 to associate additional information to this <storage_type> and follows the
827 attribute/value schema; see the example below. You may want to use it to give information to
828 the tool you use for rendering your simulation, for example.
830 Here is a complete example for the ``storage_type`` tag:
832 <storage_type id="single_HDD" model="linear_no_lat" size="4000" content_type="txt_unix">
833 <model_prop id="Bwrite" value="30MBps" />
834 <model_prop id="Bread" value="100MBps" />
835 <model_prop id="Bconnection" value="150MBps" />
836 <prop id="Brand" value="Western Digital" />
840 \anchor pf_storage_entity_storage
841 #### <storage> ####
843 ``storage`` attributes:
845 Attribute name | Mandatory | Values | Description
846 -------------- | --------- | ------ | -----------
847 id | yes | string | Identifier of this ``storage``; used when referring to it
848 typeId | yes | string | Here you need to refer to an already existing \ref pf_storage_entity_storage_type "\<storage_type\>"; the storage entity defined by this tag will then inherit the properties defined there.
849 attach | yes | string | Name of a host (see Section \ref pf_host) to which this storage is <i>physically</i> attached to (e.g., a hard drive in a computer)
850 content | no | string | When specified, overwrites the content attribute of \ref pf_storage_entity_storage_type "\<storage_type\>"
851 content_type | no | string | When specified, overwrites the content_type attribute of \ref pf_storage_entity_storage_type "\<storage_type\>"
853 Here are two examples:
856 <storage id="Disk1" typeId="single_HDD" attach="bob" />
858 <storage id="Disk2" typeId="single_SSD"
859 content="content/win_storage_content.txt"
860 content_type="txt_windows" attach="alice" />
863 The first example is straightforward: A disk is defined and called "Disk1"; it is
864 of type "single_HDD" (shown as an example of \ref pf_storage_entity_storage_type "\<storage_type\>" above) and attached
865 to a host called "bob" (the definition of this host is omitted here).
867 The second storage is called "Disk2", is still of the same type as Disk1 but
868 now specifies a new content file (so the contents will be different from Disk1)
869 and the filesystem uses the windows style; finally, it is attached to a second host,
870 called alice (which is again not defined here).
872 \anchor pf_storage_entity_mount
873 #### <mount> ####
876 | Attribute name | Mandatory | Values | Description |
877 | ---------------- | ----------- | -------- | ------------- |
878 | id | yes | string | Refers to a \ref pf_storage_entity_storage "<storage>" entity that will be mounted on that computer |
879 | name | yes | string | Path/location to/of the logical reference (mount point) of this disk
881 This tag must be enclosed by a \ref pf_host tag. It then specifies where the mountpoint of a given storage device (defined by the ``id`` attribute)
882 is; this location is specified by the ``name`` attribute.
884 Here is a simple example, taken from the file ``examples/platform/storage.xml``:
887 <storage_type id="single_SSD" model="linear_no_lat" size="500GiB">
888 <model_prop id="Bwrite" value="60MBps" />
889 <model_prop id="Bread" value="200MBps" />
890 <model_prop id="Bconnection" value="220MBps" />
893 <storage id="Disk2" typeId="single_SSD"
894 content="content/win_storage_content.txt"
895 content_type="txt_windows" attach="alice" />
896 <storage id="Disk4" typeId="single_SSD"
897 content="content/small_content.txt"
898 content_type="txt_unix" attach="denise"/>
900 <host id="alice" power="1Gf">
901 <mount storageId="Disk2" name="c:"/>
904 <host id="denise" power="1Gf">
905 <mount storageId="Disk2" name="c:"/>
906 <mount storageId="Disk4" name="/home"/>
910 This example is quite interesting, as the same device, called "Disk2", is mounted by
911 two hosts at the same time! Note, however, that the host called ``alice`` is actually
912 attached to this storage, as can be seen in the \ref pf_storage_entity_storage "<storage>"
913 tag. This means that ``denise`` must access this storage through the network, but SimGrid automatically takes
914 care of that for you.
916 Furthermore, this example shows that ``denise`` has mounted two storages with different
917 filesystem types (unix and windows). In general, a host can mount as many storage devices as
921 Again, the difference between ``attach`` and ``mount`` is simply that
922 an attached storage is always physically inside (or connected to) that machine;
923 for instance, a USB stick is attached to one and only one machine (where it's plugged-in)
924 but it can only be mounted on others, as mounted storage can also be a remote location.
926 ###### Example files #####
928 \verbinclude example_filelist_xmltag_mount
930 \anchor pf_storage_entity_mstorage
931 #### <mstorage> ####
933 This is currently unused.
935 <b>mstorage</b> attributes :
936 \li <b>typeId (mandatory)</b>: the id of the <b>storage</b> that must
937 be mounted on that computer.
938 \li <b>name (mandatory)</b>: the name that will be the logical
939 reference to this disk (the mount point).
941 \subsubsection pf_storage_example_files Example files
943 Several examples were already discussed above; if you're interested in full examples,
944 check the the following platforms:
946 1. ``examples/platforms/storage.xml``
947 2. ``examples/platforms/remote_io.xml``
949 If you're looking for some examplary C code, you may find the source code
950 available in the directory ``examples/msg/io/`` useful.
952 \subsubsection pf_storage_examples_modelling Modelling different situations
954 The storage functionality of SimGrid is type-agnostic, that is, the implementation
955 does not presume any type of storage, such as HDDs/SSDs, RAM,
956 CD/DVD devices, USB sticks etc.
958 This allows the user to apply the simulator for a wide variety of scenarios; one
959 common scenario would be the access of remote RAM.
961 #### Modelling the access of remote RAM ####
963 How can this be achieved in SimGrid? Let's assume we have a setup where three hosts
964 (HostA, HostB, HostC) need to access remote RAM:
974 An easy way to model this scenario is to setup and define the RAM via the
975 \ref pf_storage_entity_storage "storage" and \ref pf_storage_entity_storage_type "storage type"
976 entities and attach it to a remote dummy host; then, every host can have their own links
977 to this host (modelling for instance certain scenarios, such as PCIe ...)
982 RAM - Dummy -- Host B
987 Now, if read from this storage, the host that mounts this storage
988 communicates to the dummy host which reads from RAM and
989 sends the information back.
992 \section pf_routing Routing
994 To achieve high performance, the routing tables used within SimGrid are
995 static. This means that routing between two nodes is calculated once
996 and will not change during execution. The SimGrid team chose to use this
997 approach as it is rare to have a real deficiency of a resource;
998 most of the time, a communication fails because the links experience too much
999 congestion and hence, your connection stops before the timeout or
1000 because the computer designated to be the destination of that message
1003 We also chose to use shortest paths algorithms in order to emulate
1004 routing. Doing so is consistent with the reality: [RIP](https://en.wikipedia.org/wiki/Routing_Information_Protocol),
1005 [OSPF](https://en.wikipedia.org/wiki/Open_Shortest_Path_First), [BGP](https://en.wikipedia.org/wiki/Border_Gateway_Protocol)
1006 are all calculating shortest paths. They do require some time to converge, but
1007 eventually, when the routing tables have stabilized, your packets will follow
1010 \subsection pf_rm Routing models
1012 For each AS, you must define explicitly which routing model will
1013 be used. There are 3 different categories for routing models:
1015 1. \ref pf_routing_model_shortest_path "Shortest-path" based models: SimGrid calculates shortest
1016 paths and manages them. Behaves more or less like most real life
1018 2. \ref pf_routing_model_manual "Manually-entered" route models: you have to define all routes
1019 manually in the platform description file; this can become
1020 tedious very quickly, as it is very verbose.
1021 Consistent with some manually managed real life routing.
1022 3. \ref pf_routing_model_simple "Simple/fast models": those models offer fast, low memory routing
1023 algorithms. You should consider to use this type of model if
1024 you can make some assumptions about your AS.
1025 Routing in this case is more or less ignored.
1027 \subsubsection pf_raf The router affair
1029 Using routers becomes mandatory when using shortest-path based
1030 models or when using the bindings to the ns-3 packet-level
1031 simulator instead of the native analytical network model implemented
1034 For graph-based shortest path algorithms, routers are mandatory, because these
1035 algorithms require a graph as input and so we need to have source and
1036 destination for each edge.
1038 Routers are naturally an important concept ns-3 since the
1039 way routers run the packet routing algorithms is actually simulated.
1040 SimGrid's analytical models however simply aggregate the routing time
1041 with the transfer time.
1043 So why did we incorporate routers in SimGrid? Rebuilding a graph representation
1044 only from the route information turns out to be a very difficult task, because
1045 of the missing information about how routes intersect. That is why we
1046 introduced routers, which are simply used to express these intersection points.
1047 It is important to understand that routers are only used to provide topological
1050 To express this topological information, a <b>route</b> has to be
1051 defined in order to declare which link is connected to a router.
1054 \subsubsection pf_routing_model_shortest_path Shortest-path based models
1056 The following table shows all the models that compute routes using
1057 shortest-paths algorithms are currently available in SimGrid. More detail on how
1058 to choose the best routing model is given in the Section called \"\ref pf_routing_howto_choose_wisely\".
1060 | Name | Description |
1061 | --------------------------------------------------- | -------------------------------------------------------------------------- |
1062 | \ref pf_routing_model_floyd "Floyd" | Floyd routing data. Pre-calculates all routes once |
1063 | \ref pf_routing_model_dijkstra "Dijkstra" | Dijkstra routing data. Calculates routes only when needed |
1064 | \ref pf_routing_model_dijkstracache "DijkstraCache" | Dijkstra routing data. Handles some cache for already calculated routes. |
1066 All those shortest-path models are instanciated in the same way and are
1067 completely interchangeable. Here are some examples:
1069 \anchor pf_routing_model_floyd
1074 <AS id="AS0" routing="Floyd">
1076 <cluster id="my_cluster_1" prefix="c-" suffix=""
1077 radical="0-1" power="1000000000" bw="125000000" lat="5E-5"
1078 router_id="router1"/>
1080 <AS id="AS1" routing="None">
1081 <host id="host1" power="1000000000"/>
1084 <link id="link1" bandwidth="100000" latency="0.01"/>
1086 <ASroute src="my_cluster_1" dst="AS1"
1089 <link_ctn id="link1"/>
1095 ASroute given at the end gives a topological information: link1 is
1096 between router1 and host1.
1098 #### Example platform files ####
1100 This is an automatically generated list of example files that use the Floyd
1101 routing model (the path is given relative to SimGrid's source directory)
1103 \verbinclude example_filelist_routing_floyd
1105 \anchor pf_routing_model_dijkstra
1108 #### Example platform files ####
1110 This is an automatically generated list of example files that use the Dijkstra
1111 routing model (the path is given relative to SimGrid's source directory)
1113 \verbinclude example_filelist_routing_dijkstra
1117 <AS id="AS_2" routing="Dijsktra">
1118 <host id="AS_2_host1" power="1000000000"/>
1119 <host id="AS_2_host2" power="1000000000"/>
1120 <host id="AS_2_host3" power="1000000000"/>
1121 <link id="AS_2_link1" bandwidth="1250000000" latency="5E-4"/>
1122 <link id="AS_2_link2" bandwidth="1250000000" latency="5E-4"/>
1123 <link id="AS_2_link3" bandwidth="1250000000" latency="5E-4"/>
1124 <link id="AS_2_link4" bandwidth="1250000000" latency="5E-4"/>
1125 <router id="central_router"/>
1126 <router id="AS_2_gateway"/>
1127 <!-- routes providing topological information -->
1128 <route src="central_router" dst="AS_2_host1"><link_ctn id="AS_2_link1"/></route>
1129 <route src="central_router" dst="AS_2_host2"><link_ctn id="AS_2_link2"/></route>
1130 <route src="central_router" dst="AS_2_host3"><link_ctn id="AS_2_link3"/></route>
1131 <route src="central_router" dst="AS_2_gateway"><link_ctn id="AS_2_link4"/></route>
1135 \anchor pf_routing_model_dijkstracache
1136 ### DijkstraCache ###
1138 DijsktraCache example:
1140 <AS id="AS_2" routing="DijsktraCache">
1141 <host id="AS_2_host1" power="1000000000"/>
1143 (platform unchanged compared to upper example)
1146 #### Example platform files ####
1148 This is an automatically generated list of example files that use the DijkstraCache
1149 routing model (the path is given relative to SimGrid's source directory):
1151 Editor's note: At the time of writing, no platform file used this routing model - so
1152 if there are no example files listed here, this is likely to be correct.
1154 \verbinclude example_filelist_routing_dijkstra_cache
1156 \subsubsection pf_routing_model_manual Manually-entered route models
1158 | Name | Description |
1159 | ---------------------------------- | ------------------------------------------------------------------------------ |
1160 | \ref pf_routing_model_full "Full" | You have to enter all necessary routers manually; that is, every single route. This may consume a lot of memory when the XML is parsed and might be tedious to write; i.e., this is only recommended (if at all) for small platforms. |
1162 \anchor pf_routing_model_full
1167 <AS id="AS0" routing="Full">
1168 <host id="host1" power="1000000000"/>
1169 <host id="host2" power="1000000000"/>
1170 <link id="link1" bandwidth="125000000" latency="0.000100"/>
1171 <route src="host1" dst="host2"><link_ctn id="link1"/></route>
1175 #### Example platform files ####
1177 This is an automatically generated list of example files that use the Full
1178 routing model (the path is given relative to SimGrid's source directory):
1180 \verbinclude example_filelist_routing_full
1182 \subsubsection pf_routing_model_simple Simple/fast models
1184 | Name | Description |
1185 | ---------------------------------------- | ------------------------------------------------------------------------------ |
1186 | \ref pf_routing_model_cluster "Cluster" | This is specific to the \ref pf_cluster "<cluster/>" tag and should not be used by the user, as several assumptions are made. |
1187 | \ref pf_routing_model_none "None" | No routing at all. Unless you know what you're doing, avoid using this mode in combination with a non-constant network model. |
1188 | \ref pf_routing_model_vivaldi "Vivaldi" | Perfect when you want to use coordinates. Also see the corresponding \ref pf_P2P_tags "P2P section" below. |
1190 \anchor pf_routing_model_cluster
1194 In this mode, the \ref pf_cabinet "<cabinet/>" tag is available.
1196 #### Example platform files ####
1198 This is an automatically generated list of example files that use the Cluster
1199 routing model (the path is given relative to SimGrid's source directory):
1201 \verbinclude example_filelist_routing_cluster
1203 \anchor pf_routing_model_none
1206 This model does exactly what it's name advertises: Nothing. There is no routing
1207 available within this model and if you try to communicate within the AS that
1208 uses this model, SimGrid will fail unless you have explicitly activated the
1209 \ref options_model_select_network_constant "Constant Network Model" (this model charges
1210 the same for every single communication). It should
1211 be noted, however, that you can still attach an \ref pf_routing_tag_asroute "ASroute",
1212 as is demonstrated in the example below:
1214 \verbinclude platforms/cluster_and_one_host.xml
1216 #### Example platform files ####
1218 This is an automatically generated list of example files that use the None
1219 routing model (the path is given relative to SimGrid's source directory):
1221 \verbinclude example_filelist_routing_none
1224 \anchor pf_routing_model_vivaldi
1227 For more information on how to use the [Vivaldi Coordinates](https://en.wikipedia.org/wiki/Vivaldi_coordinates),
1228 see also Section \ref pf_P2P_tags "P2P tags".
1230 For documentation on how to activate this model (as some initialization must be done
1231 in the simulator), see Section \ref options_model_network_coord "Activating Coordinate Based Routing".
1233 Note that it is possible to combine the Vivaldi routing model with other routing models;
1234 an example can be found in the file \c examples/platforms/cloud.xml. This
1235 examples models an AS using Vivaldi that contains other ASes that use different
1238 #### Example platform files ####
1240 This is an automatically generated list of example files that use the None
1241 routing model (the path is given relative to SimGrid's source directory):
1243 \verbinclude example_filelist_routing_vivaldi
1246 \subsection ps_dec Defining routes
1248 There are currently four different ways to define routes:
1250 | Name | Description |
1251 | ------------------------------------------------- | ----------------------------------------------------------------------------------- |
1252 | \ref pf_routing_tag_route "route" | Used to define route between host/router |
1253 | \ref pf_routing_tag_asroute "ASroute" | Used to define route between different AS |
1254 | \ref pf_routing_tag_bypassroute "bypassRoute" | Used to supersede normal routes as calculated by the network model between host/router; e.g., can be used to use a route that is not the shortest path for any of the shortest-path routing models. |
1255 | \ref pf_routing_tag_bypassasroute "bypassASroute" | Used in the same way as bypassRoute, but for AS |
1257 Basically all those tags will contain an (ordered) list of references
1258 to link that compose the route you want to define.
1260 Consider the example below:
1263 <route src="Alice" dst="Bob">
1264 <link_ctn id="link1"/>
1265 <link_ctn id="link2"/>
1266 <link_ctn id="link3"/>
1270 The route here from host Alice to Bob will be first link1, then link2,
1271 and finally link3. What about the reverse route? \ref pf_routing_tag_route "Route" and
1272 \ref pf_routing_tag_asroute "ASroute" have an optional attribute \c symmetrical, that can
1273 be either \c YES or \c NO. \c YES means that the reverse route is the same
1274 route in the inverse order, and is set to \c YES by default. Note that
1275 this is not the case for bypass*Route, as it is more probable that you
1276 want to bypass only one default route.
1278 For an \ref pf_routing_tag_asroute "ASroute", things are just slightly more complicated, as you have
1279 to give the id of the gateway which is inside the AS you want to access ...
1280 So it looks like this:
1283 <ASroute src="AS1" dst="AS2"
1284 gw_src="router1" gw_dst="router2">
1285 <link_ctn id="link1"/>
1289 gw == gateway, so when any message are trying to go from AS1 to AS2,
1290 it means that it must pass through router1 to get out of the AS, then
1291 pass through link1, and get into AS2 by being received by router2.
1292 router1 must belong to AS1 and router2 must belong to AS2.
1294 \subsubsection pf_linkctn <link_ctn/>
1296 This entity has only one purpose: Refer to an already existing
1297 \ref pf_link "<link/>" when defining a route, i.e., it
1298 can only occur as a child of \ref pf_routing_tag_route "<route/>"
1300 | Attribute name | Mandatory | Values | Description |
1301 | --------------- | --------- | ------ | ----------- |
1302 | id | yes | String | The identifier of the link that should be added to the route. |
1303 | direction | maybe | UP\|DOWN | If the link referenced by \c id has been declared as \ref pf_sharing_policy_fullduplex "FULLDUPLEX", this indicates which direction the route traverses through this link: UP or DOWN. If you don't use FULLDUPLEX, this attribute has no effect.
1305 #### Example Files ####
1307 This is an automatically generated list of example files that use the \c <link_ctn/gt;
1308 entity (the path is given relative to SimGrid's source directory):
1310 \verbinclude example_filelist_xmltag_linkctn
1312 \subsubsection pf_routing_tag_asroute ASroute
1314 The purpose of this entity is to define a route between two ASes.
1315 This is mainly useful when you're in the \ref pf_routing_model_full "Full routing model".
1317 #### Attributes ####
1319 | Attribute name | Mandatory | Values | Description |
1320 | --------------- | --------- | ------ | ----------- |
1321 | src | yes | String | The identifier of the source AS |
1322 | dst | yes | String | See the \c src attribute |
1323 | gw_src | yes | String | The gateway that will be used within the src AS; this can be any \ref pf_host "Host" or \ref pf_router "Router" defined within the src AS. |
1324 | gw_dst | yes | String | Same as \c gw_src, but with the dst AS instead. |
1325 | symmetrical | no | YES\|NO (Default: YES) | If this route is symmetric, the opposite route (from dst to src) will also be declared implicitly. |
1330 <AS id="AS0" routing="Full">
1331 <cluster id="my_cluster_1" prefix="c-" suffix=".me"
1332 radical="0-149" power="1000000000" bw="125000000" lat="5E-5"
1333 bb_bw="2250000000" bb_lat="5E-4"/>
1335 <cluster id="my_cluster_2" prefix="c-" suffix=".me"
1336 radical="150-299" power="1000000000" bw="125000000" lat="5E-5"
1337 bb_bw="2250000000" bb_lat="5E-4"/>
1339 <link id="backbone" bandwidth="1250000000" latency="5E-4"/>
1341 <ASroute src="my_cluster_1" dst="my_cluster_2"
1342 gw_src="c-my_cluster_1_router.me"
1343 gw_dst="c-my_cluster_2_router.me">
1344 <link_ctn id="backbone"/>
1346 <ASroute src="my_cluster_2" dst="my_cluster_1"
1347 gw_src="c-my_cluster_2_router.me"
1348 gw_dst="c-my_cluster_1_router.me">
1349 <link_ctn id="backbone"/>
1354 \subsubsection pf_routing_tag_route route
1356 The principle is the same as for
1357 \ref pf_routing_tag_asroute "ASroute": The route contains a list of links that
1358 provide a path from \c src to \c dst. Here, \c src and \c dst can both be either a
1359 \ref pf_host "host" or \ref pf_router "router". This is mostly useful for the
1360 \ref pf_routing_model_full "Full routing model" as well as for the
1361 \ref pf_routing_model_shortest_path "shortest-paths" based models (as they require
1362 topological information).
1365 | Attribute name | Mandatory | Values | Description |
1366 | --------------- | --------- | ---------------------- | ----------- |
1367 | src | yes | String | The value given to the source's "id" attribute |
1368 | dst | yes | String | The value given to the destination's "id" attribute. |
1369 | symmetrical | no | YES\| NO (Default: YES) | If this route is symmetric, the opposite route (from dst to src) will also be declared implicitly. |
1374 A route in the \ref pf_routing_model_full "Full routing model" could look like this:
1376 <route src="Tremblay" dst="Bourassa">
1377 <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"/>
1381 A route in the \ref pf_routing_model_shortest_path "Shortest-Path routing model" could look like this:
1383 <route src="Tremblay" dst="Bourassa">
1388 You must only have one link in your routes when you're using them to provide
1389 topological information, as the routes here are simply the edges of the
1390 (network-)graph and the employed algorithms need to know which edge connects
1391 which pair of entities.
1393 \subsubsection pf_routing_tag_bypassasroute bypassASroute
1395 %As said before, once you choose
1396 a model, it (most likely; the constant network model, for example, doesn't) calculates routes for you. But maybe you want to
1397 define some of your routes, which will be specific. You may also want
1398 to bypass some routes defined in lower level AS at an upper stage:
1399 <b>bypassASroute</b> is the tag you're looking for. It allows to
1400 bypass routes defined between already defined between AS (if you want
1401 to bypass route for a specific host, you should just use byPassRoute).
1402 The principle is the same as ASroute : <b>bypassASroute</b> contains
1403 list of links that are in the path between src and dst.
1405 #### Attributes ####
1407 | Attribute name | Mandatory | Values | Description |
1408 | --------------- | --------- | ---------------------- | ----------- |
1409 | src | yes | String | The value given to the source AS's "id" attribute |
1410 | dst | yes | String | The value given to the destination AS's "id" attribute. |
1411 | gw_src | yes | String | The value given to the source gateway's "id" attribute; this can be any host or router within the src AS |
1412 | gw_dst | yes | String | The value given to the destination gateway's "id" attribute; this can be any host or router within the dst AS|
1413 | symmetrical | no | YES\| NO (Default: YES) | If this route is symmetric, the opposite route (from dst to src) will also be declared implicitly. |
1418 <bypassASRoute src="my_cluster_1" dst="my_cluster_2"
1419 gw_src="my_cluster_1_router"
1420 gw_dst="my_cluster_2_router">
1421 <link_ctn id="link_tmp"/>
1425 This example shows that link \c link_tmp (definition not displayed here) directly
1426 connects the router \c my_cluster_1_router in the source cluster to the router
1427 \c my_cluster_2_router in the destination router. Additionally, as the \c symmetrical
1428 attribute was not given, this route is presumed to be symmetrical.
1430 \subsubsection pf_routing_tag_bypassroute bypassRoute
1432 %As said before, once you choose
1433 a model, it (most likely; the constant network model, for example, doesn't) calculates routes for you. But maybe you want to
1434 define some of your routes, which will be specific. You may also want
1435 to bypass some routes defined in lower level AS at an upper stage :
1436 <b>bypassRoute</b> is the tag you're looking for. It allows to bypass
1437 routes defined between <b>host/router</b>. The principle is the same
1438 as route : <b>bypassRoute</b> contains list of links references of
1439 links that are in the path between src and dst.
1441 #### Attributes ####
1443 | Attribute name | Mandatory | Values | Description |
1444 | --------------- | --------- | ---------------------- | ----------- |
1445 | src | yes | String | The value given to the source AS's "id" attribute |
1446 | dst | yes | String | The value given to the destination AS's "id" attribute. |
1447 | symmetrical | no | YES \| NO (Default: YES) | If this route is symmetric, the opposite route (from dst to src) will also be declared implicitly. |
1452 <bypassRoute src="host_1" dst="host_2">
1453 <link_ctn id="link_tmp"/>
1457 This example shows that link \c link_tmp (definition not displayed here) directly
1458 connects host \c host_1 to host \c host_2. Additionally, as the \c symmetrical
1459 attribute was not given, this route is presumed to be symmetrical.
1461 \subsection pb_baroex Basic Routing Example
1463 Let's say you have an AS named AS_Big that contains two other AS, AS_1
1464 and AS_2. If you want to make a host (h1) from AS_1 with another one
1465 (h2) from AS_2 then you'll have to proceed as follows:
1466 \li First, you have to ensure that a route is defined from h1 to the
1467 AS_1's exit gateway and from h2 to AS_2's exit gateway.
1468 \li Then, you'll have to define a route between AS_1 to AS_2. %As those
1469 AS are both resources belonging to AS_Big, then it has to be done
1470 at AS_big level. To define such a route, you have to give the
1471 source AS (AS_1), the destination AS (AS_2), and their respective
1472 gateway (as the route is effectively defined between those two
1473 entry/exit points). Elements of this route can only be elements
1474 belonging to AS_Big, so links and routers in this route should be
1475 defined inside AS_Big. If you choose some shortest-path model,
1476 this route will be computed automatically.
1478 %As said before, there are mainly 2 tags for routing :
1479 \li <b>ASroute</b>: to define routes between two <b>AS</b>
1480 \li <b>route</b>: to define routes between two <b>host/router</b>
1482 %As we are dealing with routes between AS, it means that those we'll
1483 have some definition at AS_Big level. Let consider AS_1 contains 1
1484 host, 1 link and one router and AS_2 3 hosts, 4 links and one router.
1485 There will be a central router, and a cross-like topology. At the end
1486 of the crosses arms, you'll find the 3 hosts and the router that will
1487 act as a gateway. We have to define routes inside those two AS. Let
1488 say that AS_1 contains full routes, and AS_2 contains some Floyd
1489 routing (as we don't want to bother with defining all routes). %As
1490 we're using some shortest path algorithms to route into AS_2, we'll
1491 then have to define some <b>route</b> to gives some topological
1492 information to SimGrid. Here is a file doing it all :
1495 <AS id="AS_Big" routing="Dijsktra">
1496 <AS id="AS_1" routing="Full">
1497 <host id="AS_1_host1" power="1000000000"/>
1498 <link id="AS_1_link" bandwidth="1250000000" latency="5E-4"/>
1499 <router id="AS_1_gateway"/>
1500 <route src="AS_1_host1" dst="AS_1_gateway">
1501 <link_ctn id="AS_1_link"/>
1504 <AS id="AS_2" routing="Floyd">
1505 <host id="AS_2_host1" power="1000000000"/>
1506 <host id="AS_2_host2" power="1000000000"/>
1507 <host id="AS_2_host3" power="1000000000"/>
1508 <link id="AS_2_link1" bandwidth="1250000000" latency="5E-4"/>
1509 <link id="AS_2_link2" bandwidth="1250000000" latency="5E-4"/>
1510 <link id="AS_2_link3" bandwidth="1250000000" latency="5E-4"/>
1511 <link id="AS_2_link4" bandwidth="1250000000" latency="5E-4"/>
1512 <router id="central_router"/>
1513 <router id="AS_2_gateway"/>
1514 <!-- routes providing topological information -->
1515 <route src="central_router" dst="AS_2_host1"><link_ctn id="AS_2_link1"/></route>
1516 <route src="central_router" dst="AS_2_host2"><link_ctn id="AS_2_link2"/></route>
1517 <route src="central_router" dst="AS_2_host3"><link_ctn id="AS_2_link3"/></route>
1518 <route src="central_router" dst="AS_2_gateway"><link_ctn id="AS_2_link4"/></route>
1520 <link id="backbone" bandwidth="1250000000" latency="5E-4"/>
1522 <ASroute src="AS_1" dst="AS_2"
1523 gw_src="AS_1_gateway"
1524 gw_dst="AS_2_gateway">
1525 <link_ctn id="backbone"/>
1530 \section pf_other_tags Tags not (directly) describing the platform
1532 There are 3 tags, that you can use inside a \<platform\> tag that are
1533 not describing the platform:
1534 \li \ref pf_random "random": it allows you to define random generators you want to use
1535 for your simulation.
1536 \li \ref pf_config "config": it allows you to pass some configuration stuff like, for
1537 example, the network model and so on. It follows the
1538 \li \ref pf_include "include": allows you to include another file into the current one.
1540 \subsection pf_config config
1542 The only purpose of this tag is to contain the \c prop tags, as described below.
1543 These tags will then configure the options as described by Section \ref options.
1546 #### Attributes ####
1548 | Attribute name | Mandatory | Values | Description |
1549 | --------------- | --------- | ---------------------- | ----------- |
1550 | id | yes | String | The identifier of the config tag when referring to id; this is basically useless, though. |
1552 #### Possible children ####
1554 Tag name | Description | Documentation
1555 ------------ | ----------- | -------------
1556 \<prop/\> | The prop tag allows you to define different configuration options following the attribute/value schema. See the \ref options page. | N/A
1561 <?xml version='1.0'?>
1562 <!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
1563 <platform version="3">
1564 <config id="General">
1565 <prop id="maxmin/precision" value="0.000010"></prop>
1566 <prop id="cpu/optim" value="TI"></prop>
1567 <prop id="host/model" value="compound"></prop>
1568 <prop id="network/model" value="SMPI"></prop>
1569 <prop id="path" value="~/"></prop>
1570 <prop id="smpi/bw_factor" value="65472:0.940694;15424:0.697866;9376:0.58729"></prop>
1573 <AS id="AS0" routing="Full">
1578 \subsection pf_random random
1580 <b>This has not yet been implemented.</b>
1582 \subsection pf_include include
1584 The \c include tag allows you to import other platforms into your
1585 local file. This is done with the intention to help people
1586 combine their different AS and provide new platforms. Those files
1587 should contain XML that consists of
1588 \ref pf_include "include", \ref pf_cluster "cluster", \ref pf_peer "peer", \ref pf_As "AS", \ref pf_trace "trace", \ref pf_trace "tags".
1591 Due to some obscure technical reasons, you have to open
1592 and close the tag in order to make it work.
1594 #### Attributes ####
1596 | Attribute name | Mandatory | Values | Description |
1597 | --------------- | --------- | ---------------------- | ----------- |
1598 | file | yes | String | Filename of the path you want to include with either relative or absolute path. Syntax is defined by your OS |
1603 The following example includes two files, clusterA.xml and clusterB.xml and
1604 combines them two one platform file; all hosts, routers etc. defined in
1605 each of them will then be usable.
1608 <?xml version='1.0'?>
1609 <!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
1610 <platform version="3">
1611 <AS id="main" routing="Full">
1612 <include file="clusterA.xml"></include>
1613 <include file="clusterB.xml"></include>
1618 \subsection pf_trace trace and trace_connect
1620 Both tags are an alternate way to pass files containing information on
1621 availability, state etc. to an entity. (See also, for instance, Section \ref
1622 pf_host_churn "Churn", as described for the host entity.) Instead of referring
1623 to the file directly in the host, link, or cluster tag, you proceed by defining
1624 a trace with an id corresponding to a file, later a host/link/cluster, and
1625 finally using trace_connect you say that the file trace must be used by the
1632 <AS id="AS0" routing="Full">
1633 <host id="bob" power="1000000000"/>
1635 <trace id="myTrace" file="bob.trace" periodicity="1.0"/>
1636 <trace_connect trace="myTrace" element="bob" kind="POWER"/>
1640 The order here is important. \c trace_connect must come
1641 after the elements \c trace and \c host, as both the host
1642 and the trace definition must be known when \c trace_connect
1643 is parsed; the order of \c trace and \c host is arbitrary.
1646 #### \c trace attributes ####
1649 | Attribute name | Mandatory | Values | Description |
1650 | --------------- | --------- | ---------------------- | ----------- |
1651 | id | yes | String | Identifier of this trace; this is the name you pass on to \c trace_connect. |
1652 | file | no | String | Filename of the file that contains the information - the path must follow the style of your OS. You can omit this, but then you must specifiy the values inside of <trace> and </trace> - see the example below. |
1653 | trace_periodicity | yes | String | This is the same as for \ref pf_host "hosts" (see there for details) |
1655 Here is an example of trace when no file name is provided:
1658 <trace id="myTrace" periodicity="1.0">
1665 #### \c trace_connect attributes ####
1667 | Attribute name | Mandatory | Values | Description |
1668 | --------------- | --------- | ---------------------- | ----------- |
1669 | kind | no | HOST_AVAIL\|POWER\|<br/>LINK_AVAIL\|BANDWIDTH\|LATENCY (Default: HOST_AVAIL) | Describes the kind of trace. |
1670 | trace | yes | String | Identifier of the referenced trace (specified of the trace's \c id attribute) |
1671 | element | yes | String | The identifier of the referenced entity as given by its \c id attribute |
1673 \section pf_hints Hints and tips, or how to write a platform efficiently
1675 Now you should know at least the syntax and be able to create a
1676 platform by your own. However, after having ourselves wrote some platforms, there
1677 are some best practices you should pay attention to in order to
1678 produce good platform and some choices you can make in order to have
1679 faster simulations. Here's some hints and tips, then.
1681 \subsection pf_as_h AS Hierarchy
1682 The AS design allows SimGrid to go fast, because computing route is
1683 done only for the set of resources defined in this AS. If you're using
1684 only a big AS containing all resource with no AS into it and you're
1685 using Full model, then ... you'll loose all interest into it. On the
1686 other hand, designing a binary tree of AS with, at the lower level,
1687 only one host, then you'll also loose all the good AS hierarchy can
1688 give you. Remind you should always be "reasonable" in your platform
1689 definition when choosing the hierarchy. A good choice if you try to
1690 describe a real life platform is to follow the AS described in
1691 reality, since this kind of trade-off works well for real life
1694 \subsection pf_exit_as Exit AS: why and how
1695 Users that have looked at some of our platforms may have notice a
1696 non-intuitive schema ... Something like that :
1700 <AS id="AS_4" routing="Full">
1701 <AS id="exitAS_4" routing="Full">
1702 <router id="router_4"/>
1704 <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"/>
1705 <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"/>
1706 <link id="4_1" bandwidth="2250000000" latency="5E-5"/>
1707 <link id="4_2" bandwidth="2250000000" latency="5E-5"/>
1708 <link id="bb_4" bandwidth="2250000000" latency="5E-4"/>
1709 <ASroute src="cl_4_1"
1711 gw_src="c_4_1-cl_4_1_router"
1712 gw_dst="c_4_2-cl_4_2_router"
1714 <link_ctn id="4_1"/>
1715 <link_ctn id="bb_4"/>
1716 <link_ctn id="4_2"/>
1718 <ASroute src="cl_4_1"
1720 gw_src="c_4_1-cl_4_1_router"
1723 <link_ctn id="4_1"/>
1724 <link_ctn id="bb_4"/>
1726 <ASroute src="cl_4_2"
1728 gw_src="c_4_2-cl_4_2_router"
1731 <link_ctn id="4_2"/>
1732 <link_ctn id="bb_4"/>
1737 In the AS_4, you have an exitAS_4 defined, containing only one router,
1738 and routes defined to that AS from all other AS (as cluster is only a
1739 shortcut for an AS, see cluster description for details). If there was
1740 an upper AS, it would define routes to and from AS_4 with the gateway
1741 router_4. It's just because, as we did not allowed (for performances
1742 issues) to have routes from an AS to a single host/router, you have to
1743 enclose your gateway, when you have AS included in your AS, within an
1744 AS to define routes to it.
1746 \subsection pf_P2P_tags P2P or how to use coordinates
1747 SimGrid allows you to use some coordinated-based system, like vivaldi,
1748 to describe a platform. The main concept is that you have some peers
1749 that are located somewhere: this is the function of the
1750 <b>coordinates</b> of the \<peer\> or \<host\> tag. There's nothing
1751 complicated in using it, here is an example of it:
1754 <?xml version='1.0'?>
1755 <!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
1756 <platform version="3">
1758 <config id="General">
1759 <prop id="network/coordinates" value="yes"></prop>
1761 <AS id="AS0" routing="Vivaldi">
1762 <host id="100030591" coordinates="25.5 9.4 1.4" power="1500000000.0" />
1763 <host id="100036570" coordinates="-12.7 -9.9 2.1" power="730000000.0" />
1765 <host id="100429957" coordinates="17.5 6.7 18.8" power="830000000.0" />
1770 Coordinates are then used to calculate latency between two hosts by
1771 calculating the euclidean distance between the two hosts coordinates.
1772 The results express the latency in ms.
1774 Note that the previous example defines a routing directly between hosts but it could be also used to define a routing between AS.
1775 That is for example what is commonly done when using peers (see Section \ref pf_peer).
1777 <?xml version='1.0'?>
1778 <!DOCTYPE platform SYSTEM "http://simgrid.gforge.inria.fr/simgrid.dtd">
1779 <platform version="3">
1781 <config id="General">
1782 <prop id="network/coordinates" value="yes"></prop>
1784 <AS id="AS0" routing="Vivaldi">
1785 <peer id="peer-0" coordinates="173.0 96.8 0.1" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us"/>
1786 <peer id="peer-1" coordinates="247.0 57.3 0.6" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us" />
1787 <peer id="peer-2" coordinates="243.4 58.8 1.4" power="730Mf" bw_in="13.38MBps" bw_out="1.024MBps" lat="500us" />
1791 In such a case though, we connect the AS created by the <b>peer</b> tag with the Vivaldi routing mechanism.
1792 This means that to route between AS1 and AS2, it will use the coordinates of router_AS1 and router_AS2.
1793 This is currently a convention and we may offer to change this convention in the DTD later if needed.
1794 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.
1797 \subsection pf_routing_howto_choose_wisely Choosing wisely the routing model to use
1800 Choosing wisely the routing model to use can significantly fasten your
1801 simulation/save your time when writing the platform/save tremendous
1802 disk space. Here is the list of available model and their
1803 characteristics (lookup : time to resolve a route):
1805 \li <b>Full</b>: Full routing data (fast, large memory requirements,
1807 \li <b>Floyd</b>: Floyd routing data (slow initialization, fast
1808 lookup, lesser memory requirements, shortest path routing only).
1809 Calculates all routes at once at the beginning.
1810 \li <b>Dijkstra</b>: Dijkstra routing data (fast initialization, slow
1811 lookup, small memory requirements, shortest path routing only).
1812 Calculates a route when necessary.
1813 \li <b>DijkstraCache</b>: Dijkstra routing data (fast initialization,
1814 fast lookup, small memory requirements, shortest path routing
1815 only). Same as Dijkstra, except it handles a cache for latest used
1817 \li <b>None</b>: No routing (usable with Constant network only).
1818 Defines that there is no routes, so if you try to determine a
1819 route without constant network within this AS, SimGrid will raise
1821 \li <b>Vivaldi</b>: Vivaldi routing, so when you want to use coordinates
1822 \li <b>Cluster</b>: Cluster routing, specific to cluster tag, should
1825 \subsection pf_switch Hey, I want to describe a switch but there is no switch tag !
1827 Actually we did not include switch tag, ok. But when you're trying to
1828 simulate a switch, the only major impact it has when you're using
1829 fluid model (and SimGrid uses fluid model unless you activate
1830 ns-3 or constant network mode) is the impact of the upper limit of
1831 the switch motherboard speed that will eventually be reached if you're
1832 using intensively your switch. So, the switch impact is similar to a
1833 link one. That's why we are used to describe a switch using a link tag
1834 (as a link is not an edge by a hyperedge, you can connect more than 2
1837 \subsection pf_platform_multipath How to express multipath routing in platform files?
1839 It is unfortunately impossible to express the fact that there is more
1840 than one routing path between two given hosts. Let's consider the
1841 following platform file:
1844 <route src="A" dst="B">
1847 <route src="B" dst="C">
1850 <route src="A" dst="C">
1855 Although it is perfectly valid, it does not mean that data traveling
1856 from A to C can either go directly (using link 3) or through B (using
1857 links 1 and 2). It simply means that the routing on the graph is not
1858 trivial, and that data do not following the shortest path in number of
1859 hops on this graph. Another way to say it is that there is no implicit
1860 in these routing descriptions. The system will only use the routes you
1861 declare (such as <route src="A" dst="C"><link_ctn
1862 id="3"/></route>), without trying to build new routes by aggregating
1865 You are also free to declare platform where the routing is not
1866 symmetric. For example, add the following to the previous file:
1869 <route src="C" dst="A">
1875 This makes sure that data from C to A go through B where data from A
1876 to C go directly. Don't worry about realism of such settings since
1877 we've seen ways more weird situation in real settings (in fact, that's
1878 the realism of very regular platforms which is questionable, but
1879 that's another story).
1881 \section pf_flexml_bypassing Bypassing the XML parser with your own C functions
1882 <b>NOTE THAT THIS DOCUMENTATION, WHILE STILL WORKING, IS STRONGLY DEPRECATED</b>
1884 So you want to bypass the XML files parser, uh? Maybe doing some parameter
1885 sweep experiments on your simulations or so? This is possible, and
1886 it's not even really difficult (well. Such a brutal idea could be
1887 harder to implement). Here is how it goes.
1889 For this, you have to first remember that the XML parsing in SimGrid is done
1890 using a tool called FleXML. Given a DTD, this gives a flex-based parser. If
1891 you want to bypass the parser, you need to provide some code mimicking what
1892 it does and replacing it in its interactions with the SURF code. So, let's
1893 have a look at these interactions.
1895 FleXML parser are close to classical SAX parsers. It means that a
1896 well-formed SimGrid platform XML file might result in the following
1899 - start "platform_description" with attribute version="2"
1900 - start "host" with attributes id="host1" power="1.0"
1902 - start "host" with attributes id="host2" power="2.0"
1904 - start "link" with ...
1906 - start "route" with ...
1907 - start "link_ctn" with ...
1910 - end "platform_description"
1912 The communication from the parser to the SURF code uses two means:
1913 Attributes get copied into some global variables, and a surf-provided
1914 function gets called by the parser for each event. For example, the event
1915 - start "host" with attributes id="host1" power="1.0"
1917 let the parser do something roughly equivalent to:
1919 strcpy(A_host_id,"host1");
1924 In SURF, we attach callbacks to the different events by initializing the
1925 pointer functions to some the right surf functions. Since there can be
1926 more than one callback attached to the same event (if more than one
1927 model is in use, for example), they are stored in a dynar. Example in
1930 /* Adding callback functions */
1931 surf_parse_reset_parser();
1932 surfxml_add_callback(STag_surfxml_host_cb_list, &parse_cpu_init);
1933 surfxml_add_callback(STag_surfxml_prop_cb_list, &parse_properties);
1934 surfxml_add_callback(STag_surfxml_link_cb_list, &parse_link_init);
1935 surfxml_add_callback(STag_surfxml_route_cb_list, &parse_route_set_endpoints);
1936 surfxml_add_callback(ETag_surfxml_link_c_ctn_cb_list, &parse_route_elem);
1937 surfxml_add_callback(ETag_surfxml_route_cb_list, &parse_route_set_route);
1939 /* Parse the file */
1940 surf_parse_open(file);
1941 xbt_assert(!surf_parse(), "Parse error in %s", file);
1945 So, to bypass the FleXML parser, you need to write your own version of the
1946 surf_parse function, which should do the following:
1947 - Fill the A_<tag>_<attribute> variables with the wanted values
1948 - Call the corresponding STag_<tag>_fun function to simulate tag start
1949 - Call the corresponding ETag_<tag>_fun function to simulate tag end
1950 - (do the same for the next set of values, and loop)
1952 Then, tell SimGrid that you want to use your own "parser" instead of the stock one:
1954 surf_parse = surf_parse_bypass_environment;
1955 MSG_create_environment(NULL);
1956 surf_parse = surf_parse_bypass_application;
1957 MSG_launch_application(NULL);
1960 A set of macros are provided at the end of
1961 include/surf/surfxml_parse.h to ease the writing of the bypass
1962 functions. An example of this trick is distributed in the file
1963 examples/msg/masterslave/masterslave_bypass.c
