xref: /dpdk/doc/guides/prog_guide/multi_proc_support.rst (revision 117eaa70584b73eebf6f648cf3ee6f2ab03264a0)
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
31.. _Multi-process_Support:
32
33Multi-process Support
34=====================
35
36In the DPDK, multi-process support is designed to allow a group of DPDK processes
37to work together in a simple transparent manner to perform packet processing,
38or other workloads.
39To support this functionality,
40a number of additions have been made to the core DPDK Environment Abstraction Layer (EAL).
41
42The EAL has been modified to allow different types of DPDK processes to be spawned,
43each with different permissions on the hugepage memory used by the applications.
44For now, there are two types of process specified:
45
46*   primary processes, which can initialize and which have full permissions on shared memory
47
48*   secondary processes, which cannot initialize shared memory,
49    but can attach to pre- initialized shared memory and create objects in it.
50
51Standalone DPDK processes are primary processes,
52while secondary processes can only run alongside a primary process or
53after a primary process has already configured the hugepage shared memory for them.
54
55.. note::
56
57    Secondary processes should run alongside primary process with same DPDK version.
58
59To support these two process types, and other multi-process setups described later,
60two additional command-line parameters are available to the EAL:
61
62*   ``--proc-type:`` for specifying a given process instance as the primary or secondary DPDK instance
63
64*   ``--file-prefix:`` to allow processes that do not want to co-operate to have different memory regions
65
66A number of example applications are provided that demonstrate how multiple DPDK processes can be used together.
67These are more fully documented in the "Multi- process Sample Application" chapter
68in the *DPDK Sample Application's User Guide*.
69
70Memory Sharing
71--------------
72
73The key element in getting a multi-process application working using the DPDK is to ensure that
74memory resources are properly shared among the processes making up the multi-process application.
75Once there are blocks of shared memory available that can be accessed by multiple processes,
76then issues such as inter-process communication (IPC) becomes much simpler.
77
78On application start-up in a primary or standalone process,
79the DPDK records to memory-mapped files the details of the memory configuration it is using - hugepages in use,
80the virtual addresses they are mapped at, the number of memory channels present, etc.
81When a secondary process is started, these files are read and the EAL recreates the same memory configuration
82in the secondary process so that all memory zones are shared between processes and all pointers to that memory are valid,
83and point to the same objects, in both processes.
84
85.. note::
86
87    Refer to `Multi-process Limitations`_ for details of
88    how Linux kernel Address-Space Layout Randomization (ASLR) can affect memory sharing.
89
90.. _figure_multi_process_memory:
91
92.. figure:: img/multi_process_memory.*
93
94   Memory Sharing in the DPDK Multi-process Sample Application
95
96
97The EAL also supports an auto-detection mode (set by EAL ``--proc-type=auto`` flag ),
98whereby an DPDK process is started as a secondary instance if a primary instance is already running.
99
100Deployment Models
101-----------------
102
103Symmetric/Peer Processes
104~~~~~~~~~~~~~~~~~~~~~~~~
105
106DPDK multi-process support can be used to create a set of peer processes where each process performs the same workload.
107This model is equivalent to having multiple threads each running the same main-loop function,
108as is done in most of the supplied DPDK sample applications.
109In this model, the first of the processes spawned should be spawned using the ``--proc-type=primary`` EAL flag,
110while all subsequent instances should be spawned using the ``--proc-type=secondary`` flag.
111
112The simple_mp and symmetric_mp sample applications demonstrate this usage model.
113They are described in the "Multi-process Sample Application" chapter in the *DPDK Sample Application's User Guide*.
114
115Asymmetric/Non-Peer Processes
116~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
117
118An alternative deployment model that can be used for multi-process applications
119is to have a single primary process instance that acts as a load-balancer or
120server distributing received packets among worker or client threads, which are run as secondary processes.
121In this case, extensive use of rte_ring objects is made, which are located in shared hugepage memory.
122
123The client_server_mp sample application shows this usage model.
124It is described in the "Multi-process Sample Application" chapter in the *DPDK Sample Application's User Guide*.
125
126Running Multiple Independent DPDK Applications
127~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
128
129In addition to the above scenarios involving multiple DPDK processes working together,
130it is possible to run multiple DPDK processes side-by-side,
131where those processes are all working independently.
132Support for this usage scenario is provided using the ``--file-prefix`` parameter to the EAL.
133
134By default, the EAL creates hugepage files on each hugetlbfs filesystem using the rtemap_X filename,
135where X is in the range 0 to the maximum number of hugepages -1.
136Similarly, it creates shared configuration files, memory mapped in each process, using the /var/run/.rte_config filename,
137when run as root (or $HOME/.rte_config when run as a non-root user;
138if filesystem and device permissions are set up to allow this).
139The rte part of the filenames of each of the above is configurable using the file-prefix parameter.
140
141In addition to specifying the file-prefix parameter,
142any DPDK applications that are to be run side-by-side must explicitly limit their memory use.
143This is done by passing the -m flag to each process to specify how much hugepage memory, in megabytes,
144each process can use (or passing ``--socket-mem`` to specify how much hugepage memory on each socket each process can use).
145
146.. note::
147
148    Independent DPDK instances running side-by-side on a single machine cannot share any network ports.
149    Any network ports being used by one process should be blacklisted in every other process.
150
151Running Multiple Independent Groups of DPDK Applications
152~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
153
154In the same way that it is possible to run independent DPDK applications side- by-side on a single system,
155this can be trivially extended to multi-process groups of DPDK applications running side-by-side.
156In this case, the secondary processes must use the same ``--file-prefix`` parameter
157as the primary process whose shared memory they are connecting to.
158
159.. note::
160
161    All restrictions and issues with multiple independent DPDK processes running side-by-side
162    apply in this usage scenario also.
163
164Multi-process Limitations
165-------------------------
166
167There are a number of limitations to what can be done when running DPDK multi-process applications.
168Some of these are documented below:
169
170*   The multi-process feature requires that the exact same hugepage memory mappings be present in all applications.
171    The Linux security feature - Address-Space Layout Randomization (ASLR) can interfere with this mapping,
172    so it may be necessary to disable this feature in order to reliably run multi-process applications.
173
174.. warning::
175
176    Disabling Address-Space Layout Randomization (ASLR) may have security implications,
177    so it is recommended that it be disabled only when absolutely necessary,
178    and only when the implications of this change have been understood.
179
180*   All DPDK processes running as a single application and using shared memory must have distinct coremask/corelist arguments.
181    It is not possible to have a primary and secondary instance, or two secondary instances,
182    using any of the same logical cores.
183    Attempting to do so can cause corruption of memory pool caches, among other issues.
184
185*   The delivery of interrupts, such as Ethernet* device link status interrupts, do not work in secondary processes.
186    All interrupts are triggered inside the primary process only.
187    Any application needing interrupt notification in multiple processes should provide its own mechanism
188    to transfer the interrupt information from the primary process to any secondary process that needs the information.
189
190*   The use of function pointers between multiple processes running based of different compiled binaries is not supported,
191    since the location of a given function in one process may be different to its location in a second.
192    This prevents the librte_hash library from behaving properly as in a multi-threaded instance,
193    since it uses a pointer to the hash function internally.
194
195To work around this issue, it is recommended that multi-process applications perform the hash calculations by directly calling
196the hashing function from the code and then using the rte_hash_add_with_hash()/rte_hash_lookup_with_hash() functions
197instead of the functions which do the hashing internally, such as rte_hash_add()/rte_hash_lookup().
198
199*   Depending upon the hardware in use, and the number of DPDK processes used,
200    it may not be possible to have HPET timers available in each DPDK instance.
201    The minimum number of HPET comparators available to Linux* userspace can be just a single comparator,
202    which means that only the first, primary DPDK process instance can open and mmap  /dev/hpet.
203    If the number of required DPDK processes exceeds that of the number of available HPET comparators,
204    the TSC (which is the default timer in this release) must be used as a time source across all processes instead of the HPET.
205