packet_distrib_lib.rst revision 97f17497
1..  BSD LICENSE
2    Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
3    All rights reserved.
4
5    Redistribution and use in source and binary forms, with or without
6    modification, are permitted provided that the following conditions
7    are met:
8
9    * Redistributions of source code must retain the above copyright
10    notice, this list of conditions and the following disclaimer.
11    * Redistributions in binary form must reproduce the above copyright
12    notice, this list of conditions and the following disclaimer in
13    the documentation and/or other materials provided with the
14    distribution.
15    * Neither the name of Intel Corporation nor the names of its
16    contributors may be used to endorse or promote products derived
17    from this software without specific prior written permission.
18
19    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22    A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23    OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24    SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25    LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26    DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27    THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28    (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31Packet Distributor Library
32==========================
33
34The DPDK Packet Distributor library is a library designed to be used for dynamic load balancing of traffic
35while supporting single packet at a time operation.
36When using this library, the logical cores in use are to be considered in two roles: firstly a distributor lcore,
37which is responsible for load balancing or distributing packets,
38and a set of worker lcores which are responsible for receiving the packets from the distributor and operating on them.
39The model of operation is shown in the diagram below.
40
41.. figure:: img/packet_distributor1.*
42
43   Packet Distributor mode of operation
44
45
46Distributor Core Operation
47--------------------------
48
49The distributor core does the majority of the processing for ensuring that packets are fairly shared among workers.
50The operation of the distributor is as follows:
51
52#.  Packets are passed to the distributor component by having the distributor lcore thread call the "rte_distributor_process()" API
53
54#.  The worker lcores all share a single cache line with the distributor core in order to pass messages and packets to and from the worker.
55    The process API call will poll all the worker cache lines to see what workers are requesting packets.
56
57#.  As workers request packets, the distributor takes packets from the set of packets passed in and distributes them to the workers.
58    As it does so, it examines the "tag" -- stored in the RSS hash field in the mbuf -- for each packet
59    and records what tags are being processed by each  worker.
60
61#.  If the next packet in the input set has a tag which is already being processed by a worker,
62    then that packet will be queued up for processing by that worker
63    and given to it in preference to other packets when that work next makes a request for work.
64    This ensures that no two packets with the same tag are processed in parallel,
65    and that all packets with the same tag are processed in input order.
66
67#.  Once all input packets passed to the process API have either been distributed to workers
68    or been queued up for a worker which is processing a given tag,
69    then the process API returns to the caller.
70
71Other functions which are available to the distributor lcore are:
72
73*   rte_distributor_returned_pkts()
74
75*   rte_distributor_flush()
76
77*   rte_distributor_clear_returns()
78
79Of these the most important API call is "rte_distributor_returned_pkts()"
80which should only be called on the lcore which also calls the process API.
81It returns to the caller all packets which have finished processing by all worker cores.
82Within this set of returned packets, all packets sharing the same tag will be returned in their original order.
83
84**NOTE:**
85If worker lcores buffer up packets internally for transmission in bulk afterwards,
86the packets sharing a tag will likely get out of order.
87Once a worker lcore requests a new packet, the distributor assumes that it has completely finished with the previous packet and
88therefore that additional packets with the same tag can safely be distributed to other workers --
89who may then flush their buffered packets sooner and cause packets to get out of order.
90
91**NOTE:**
92No packet ordering guarantees are made about packets which do not share a common packet tag.
93
94Using the process and returned_pkts API, the following application workflow can be used,
95while allowing packet order within a packet flow -- identified by a tag -- to be maintained.
96
97
98.. figure:: img/packet_distributor2.*
99
100   Application workflow
101
102
103The flush and clear_returns API calls, mentioned previously,
104are likely of less use that the process and returned_pkts APIS, and are principally provided to aid in unit testing of the library.
105Descriptions of these functions and their use can be found in the DPDK API Reference document.
106
107Worker Operation
108----------------
109
110Worker cores are the cores which do the actual manipulation of the packets distributed by the packet distributor.
111Each worker calls "rte_distributor_get_pkt()" API to request a new packet when it has finished processing the previous one.
112[The previous packet should be returned to the distributor component by passing it as the final parameter to this API call.]
113
114Since it may be desirable to vary the number of worker cores, depending on the traffic load
115i.e. to save power at times of lighter load,
116it is possible to have a worker stop processing packets by calling "rte_distributor_return_pkt()" to indicate that
117it has finished the current packet and does not want a new one.
118