xref: /dpdk/doc/guides/prog_guide/profile_app.rst (revision 25d11a86c56d50947af33d0b79ede622809bd8b9)
1..  SPDX-License-Identifier: BSD-3-Clause
2    Copyright(c) 2010-2014 Intel Corporation.
3
4Profile Your Application
5========================
6
7The following sections describe methods of profiling DPDK applications on
8different architectures.
9
10
11Profiling on x86
12----------------
13
14Intel processors provide performance counters to monitor events.
15Some tools provided by Intel, such as Intel® VTune™ Amplifier, can be used
16to profile and benchmark an application.
17See the *VTune Performance Analyzer Essentials* publication from Intel Press for more information.
18
19For a DPDK application, this can be done in a Linux* application environment only.
20
21The main situations that should be monitored through event counters are:
22
23*   Cache misses
24
25*   Branch mis-predicts
26
27*   DTLB misses
28
29*   Long latency instructions and exceptions
30
31Refer to the
32`Intel Performance Analysis Guide <http://software.intel.com/sites/products/collateral/hpc/vtune/performance_analysis_guide.pdf>`_
33for details about application profiling.
34
35
36Profiling with VTune
37~~~~~~~~~~~~~~~~~~~~
38
39To allow VTune attaching to the DPDK application, reconfigure and recompile
40the DPDK with ``CONFIG_RTE_ETHDEV_RXTX_CALLBACKS`` and
41``CONFIG_RTE_ETHDEV_PROFILE_WITH_VTUNE`` enabled.
42
43
44Profiling on ARM64
45------------------
46
47Using Linux perf
48~~~~~~~~~~~~~~~~
49
50The ARM64 architecture provide performance counters to monitor events.  The
51Linux ``perf`` tool can be used to profile and benchmark an application.  In
52addition to the standard events, ``perf`` can be used to profile arm64
53specific PMU (Performance Monitor Unit) events through raw events (``-e``
54``-rXX``).
55
56For more derails refer to the
57`ARM64 specific PMU events enumeration <http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.100095_0002_04_en/way1382543438508.html>`_.
58
59
60High-resolution cycle counter
61~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
62
63The default ``cntvct_el0`` based ``rte_rdtsc()`` provides a portable means to
64get a wall clock counter in user space. Typically it runs at <= 100MHz.
65
66The alternative method to enable ``rte_rdtsc()`` for a high resolution wall
67clock counter is through the armv8 PMU subsystem. The PMU cycle counter runs
68at CPU frequency. However, access to the PMU cycle counter from user space is
69not enabled by default in the arm64 linux kernel. It is possible to enable
70cycle counter for user space access by configuring the PMU from the privileged
71mode (kernel space).
72
73By default the ``rte_rdtsc()`` implementation uses a portable ``cntvct_el0``
74scheme.  Application can choose the PMU based implementation with
75``CONFIG_RTE_ARM_EAL_RDTSC_USE_PMU``.
76
77The example below shows the steps to configure the PMU based cycle counter on
78an armv8 machine.
79
80.. code-block:: console
81
82    git clone https://github.com/jerinjacobk/armv8_pmu_cycle_counter_el0
83    cd armv8_pmu_cycle_counter_el0
84    make
85    sudo insmod pmu_el0_cycle_counter.ko
86    cd $DPDK_DIR
87    make config T=arm64-armv8a-linuxapp-gcc
88    echo "CONFIG_RTE_ARM_EAL_RDTSC_USE_PMU=y" >> build/.config
89    make
90
91.. warning::
92
93   The PMU based scheme is useful for high accuracy performance profiling with
94   ``rte_rdtsc()``. However, this method can not be used in conjunction with
95   Linux userspace profiling tools like ``perf`` as this scheme alters the PMU
96   registers state.
97