[dpdk-dev] [PATCH v4] build: optional NUMA and cpu counts detection

["Juraj Linkeš" <juraj.linkes@pantheon.tech>]

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>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
---
 MAINTAINERS                  |  2 ++
 buildtools/get-cpu-count.py  |  7 ++++++
 buildtools/get-numa-count.py | 24 ++++++++++++++++++
 buildtools/meson.build       |  2 ++
 config/meson.build           | 47 ++++++++++++++++++++++++++++++++++--
 config/x86/meson.build       |  2 ++
 meson_options.txt            |  8 +++---
 7 files changed, 86 insertions(+), 6 deletions(-)
 create mode 100644 buildtools/get-cpu-count.py
 create mode 100644 buildtools/get-numa-count.py

diff --git a/MAINTAINERS b/MAINTAINERS
index 5877a16971..0ca3d4e9f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -102,6 +102,8 @@ F: meson_options.txt
 F: config/
 F: buildtools/chkincs/
 F: buildtools/call-sphinx-build.py
+F: buildtools/get-cpu-count.py
+F: buildtools/get-numa-count.py
 F: buildtools/list-dir-globs.py
 F: buildtools/pkg-config/
 F: buildtools/symlink-drivers-solibs.sh
diff --git a/buildtools/get-cpu-count.py b/buildtools/get-cpu-count.py
new file mode 100644
index 0000000000..317b32088f
--- /dev/null
+++ b/buildtools/get-cpu-count.py
@@ -0,0 +1,7 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright (c) 2021 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 0000000000..3b67564fd4
--- /dev/null
+++ b/buildtools/get-numa-count.py
@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright (c) 2021 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'):
+        numa_nodes = glob.glob('/sys/devices/system/node/node*')
+        numa_nodes.sort()
+        print(os.path.basename(numa_nodes[-1])[4:])
+    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 0f24b15297..887882e6a5 100644
--- a/buildtools/meson.build
+++ b/buildtools/meson.build
@@ -16,6 +16,8 @@ endif
 list_dir_globs = py3 + files('list-dir-globs.py')
 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')
 
 # select library and object file format
 pmdinfo = py3 + files('gen-pmdinfo-cfile.py') + [meson.current_build_dir()]
diff --git a/config/meson.build b/config/meson.build
index 017bb2efbb..2d1db40127 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -247,8 +247,6 @@ 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'))
@@ -282,6 +280,51 @@ if meson.is_cross_build()
     endif
 endif
 
+max_lcores = get_option('max_lcores')
+if max_lcores == 'auto'
+	# Discovery makes sense only for non-cross builds
+	if meson.is_cross_build()
+		error('Discovery of max_lcores is not supported for cross-compilation.')
+	endif
+	# Overwrite the default value with discovered values
+	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)
+elif max_lcores != 'default'
+	# Overwrite the default value from arch_subdir with user input
+	dpdk_conf.set('RTE_MAX_LCORE', max_lcores.to_int())
+endif
+
+max_numa_nodes = get_option('max_numa_nodes')
+if max_numa_nodes == 'auto'
+	# Discovery makes sense only for non-cross builds
+	if meson.is_cross_build()
+		error('Discovery of max_numa_nodes not supported for cross-compilation.')
+	endif
+	# Overwrite the default value with discovered values
+	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)
+elif max_numa_nodes != 'default'
+	# Overwrite the default value from arch_subdir with user input
+	dpdk_conf.set('RTE_MAX_NUMA_NODES', max_numa_nodes.to_int())
+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 b9348c44de..872dda9585 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', 32)
diff --git a/meson_options.txt b/meson_options.txt
index 56bdfd0f0a..649a60abc9 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -32,10 +32,10 @@ option('machine', type: 'string', value: 'native', description:
        'set the target machine type or "generic", a build usable on all machines of the build machine architecture or "native", which lets the compiler pick the architecture of 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: 32, description:
-       'maximum number of NUMA nodes supported by EAL')
+option('max_lcores', type: 'string', value: 'default', description:
+       'Set maximum number of cores/threads supported by EAL. The default is different per-arch. Set to auto to detect the number of cores on the build machine.')
+option('max_numa_nodes', type: 'string', value: 'default', description:
+       'Set highest NUMA node supported by EAL. The default is different per-arch. Set to auto to detect the highest numa node on the build machine.')
 option('platform', type: 'string', value: '', description:
        'use configuration for a particular platform (such as a SoC).')
 option('enable_trace_fp', type: 'boolean', value: false, description:
-- 
2.20.1