Re: [dpdk-dev] [PATCH v8 10/14] build: optional NUMA and cpu counts detection

[Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>]

<snip>

> 
> Add an option to automatically discover the host's numa and cpu counts and
> use those values for a non cross-build.
> Give users the option to override the per-arch default values or values from
> cross files by specifying them on the command line with -Dmax_lcores and -
> Dmax_numa_nodes.
> 
> Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
Few nits, otherwise looks fine
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>

> ---
>  buildtools/get_cpu_count.py  |  7 ++++++  buildtools/get_numa_count.py |
> 22 +++++++++++++++++
>  buildtools/meson.build       |  2 ++
>  config/meson.build           | 47 ++++++++++++++++++++++++++++++++++--
>  config/x86/meson.build       |  2 ++
>  meson_options.txt            |  8 +++---
>  6 files changed, 82 insertions(+), 6 deletions(-)  create mode 100644
> buildtools/get_cpu_count.py  create mode 100644
> buildtools/get_numa_count.py
> 
> diff --git a/buildtools/get_cpu_count.py b/buildtools/get_cpu_count.py new
> file mode 100644 index 000000000..b269d557b
> --- /dev/null
> +++ b/buildtools/get_cpu_count.py
> @@ -0,0 +1,7 @@
> +#!/usr/bin/env python3
> +# SPDX-License-Identifier: BSD-3-Clause # Copyright (c) 2020
> +PANTHEON.tech s.r.o.
> +
> +import os
> +
> +print(os.cpu_count())
> diff --git a/buildtools/get_numa_count.py b/buildtools/get_numa_count.py
> new file mode 100644 index 000000000..be73c5c3f
> --- /dev/null
> +++ b/buildtools/get_numa_count.py
> @@ -0,0 +1,22 @@
> +#!/usr/bin/env python3
> +# SPDX-License-Identifier: BSD-3-Clause # Copyright (c) 2020
> +PANTHEON.tech s.r.o.
> +
> +import ctypes
> +import glob
> +import os
> +import subprocess
> +
> +if os.name == 'posix':
> +    if os.path.isdir('/sys/devices/system/node'):
> +        print(len(glob.glob('/sys/devices/system/node/node*')))
> +    else:
> +        subprocess.run(['sysctl', '-n', 'vm.ndomains'])
> +
> +elif os.name == 'nt':
> +    libkernel32 = ctypes.windll.kernel32
> +
> +    count = ctypes.c_ulong()
> +
> +    libkernel32.GetNumaHighestNodeNumber(ctypes.pointer(count))
> +    print(count.value + 1)
> diff --git a/buildtools/meson.build b/buildtools/meson.build index
> 04808dabc..925e733b1 100644
> --- a/buildtools/meson.build
> +++ b/buildtools/meson.build
> @@ -17,3 +17,5 @@ else
>  endif
>  map_to_win_cmd = py3 + files('map_to_win.py')  sphinx_wrapper = py3 +
> files('call-sphinx-build.py')
> +get_cpu_count_cmd = py3 + files('get_cpu_count.py') get_numa_count_cmd
> += py3 + files('get_numa_count.py')
> diff --git a/config/meson.build b/config/meson.build index
> c7f7aa6e2..2974f7f6f 100644
> --- a/config/meson.build
> +++ b/config/meson.build
> @@ -231,8 +231,6 @@ foreach arg: warning_flags  endforeach
> 
>  # set other values pulled from the build options -
> dpdk_conf.set('RTE_MAX_LCORE', get_option('max_lcores')) -
> dpdk_conf.set('RTE_MAX_NUMA_NODES', get_option('max_numa_nodes'))
> dpdk_conf.set('RTE_MAX_ETHPORTS', get_option('max_ethports'))
> dpdk_conf.set('RTE_LIBEAL_USE_HPET', get_option('use_hpet'))
> dpdk_conf.set('RTE_ENABLE_TRACE_FP', get_option('enable_trace_fp')) @@
> -251,6 +249,51 @@ compile_time_cpuflags = []
>  subdir(arch_subdir)
>  dpdk_conf.set('RTE_COMPILE_TIME_CPUFLAGS',
> ','.join(compile_time_cpuflags))
> 
> +max_lcores = get_option('max_lcores')
> +if max_lcores > 0
> +	# Overwrite the default value from arch_subdir with user input
> +	dpdk_conf.set('RTE_MAX_LCORE', max_lcores) elif max_lcores == -1
> +	# Overwrite the default value with discovered values
> +	if meson.is_cross_build()
> +		error('Discovered values (user setting -1) are not supported
> be used when cross-compiling.')
Suggest something like:
'Discovery of max_lcore value not supported for cross-compilation'

> +	endif
> +	# Discovery makes sense only for non-cross builds
> +	max_lcores = run_command(get_cpu_count_cmd).stdout().to_int()
> +	min_lcores = 2
> +	# DPDK must be build for at least 2 cores
> +	if max_lcores < min_lcores
> +		message('Found less than @0@ cores, building for @0@
> cores'.format(min_lcores))
> +		max_lcores = min_lcores
> +	else
> +		message('Found @0@ cores'.format(max_lcores))
> +	endif
> +	dpdk_conf.set('RTE_MAX_LCORE', max_lcores) endif
> +
> +max_numa_nodes = get_option('max_numa_nodes') if max_numa_nodes >
> 0
> +	# Overwrite the default value from arch_subdir with user input
> +	dpdk_conf.set('RTE_MAX_NUMA_NODES', max_numa_nodes) elif
> +max_numa_nodes == -1
> +	# Overwrite the default value with discovered values
> +	if meson.is_cross_build()
> +		error('Discovered values (user setting -1) are not supported
> be used when cross-compiling.')
Suggest something like:
'Discovery of max_numa_nodes value not supported for cross-compilation'

> +	endif
> +	# Discovery makes sense only for non-cross builds
> +	max_numa_nodes =
> run_command(get_numa_count_cmd).stdout().to_int()
> +	message('Found @0@ numa nodes'.format(max_numa_nodes))
> +	dpdk_conf.set('RTE_MAX_NUMA_NODES', max_numa_nodes) endif
> +
> +# check that cpu and numa count is set and error out if it's not set if
> +not dpdk_conf.has('RTE_MAX_LCORE')
> +	error('Number of cores not specified.') endif if not
> +dpdk_conf.has('RTE_MAX_NUMA_NODES')
> +	error('Number of numa nodes not specified.') endif
> +
>  # set the install path for the drivers
>  dpdk_conf.set_quoted('RTE_EAL_PMD_PATH', eal_pmd_path)
> 
> diff --git a/config/x86/meson.build b/config/x86/meson.build index
> 31bfa63b1..4989d47f3 100644
> --- a/config/x86/meson.build
> +++ b/config/x86/meson.build
> @@ -57,3 +57,5 @@ else
>  endif
> 
>  dpdk_conf.set('RTE_CACHE_LINE_SIZE', 64)
> +dpdk_conf.set('RTE_MAX_LCORE', 128)
> +dpdk_conf.set('RTE_MAX_NUMA_NODES', 4)
> diff --git a/meson_options.txt b/meson_options.txt index
> ce23289e3..e1059fb16 100644
> --- a/meson_options.txt
> +++ b/meson_options.txt
> @@ -26,10 +26,10 @@ option('machine', type: 'string', value: 'native',
>  	description: 'set the target machine type. Set to generic for a build
> usable on most machines of the build machine architecture, set to native to let
> the compiler choose the best fit for the build machine.')
> option('max_ethports', type: 'integer', value: 32,
>  	description: 'maximum number of Ethernet devices') -
> option('max_lcores', type: 'integer', value: 128,
> -	description: 'maximum number of cores/threads supported by EAL')
> -option('max_numa_nodes', type: 'integer', value: 4,
> -	description: 'maximum number of NUMA nodes supported by EAL')
> +option('max_lcores', type: 'integer', value: 0,
> +	description: 'maximum number of cores/threads supported by EAL.
> Set to
> +positive integer to overwrite per-arch or cross-compilation defaults. Set to -1
> to use number of cores on the build machine.') option('max_numa_nodes',
        ^^^ detect? will be aligned with the comment above

> type: 'integer', value: 0,
> +	description: 'maximum number of NUMA nodes supported by EAL.
> Set to
> +positive integer to overwrite per-arch or cross-compilation defaults.
> +Set to -1 to use number of numa nodes on the build machine.')
                          ^^^ detect? will be aligned with the comment above

>  option('enable_trace_fp', type: 'boolean', value: false,
>  	description: 'enable fast path trace points.')  option('tests', type:
> 'boolean', value: true,
> --
> 2.20.1