From: "Yordan Karadzhov (VMware)" <y.karadz@gmail.com>
To: linux-trace-devel@vger.kernel.org
Cc: rostedt@goodmis.org, Douglas.Raillard@arm.com,
Valentin.Schneider@arm.com, nd@arm.com,
"Yordan Karadzhov (VMware)" <y.karadz@gmail.com>
Subject: [PATCH v2 03/12] trace-cruncher: Refactor NumPy based data wrapper
Date: Tue, 7 Jan 2020 19:03:03 +0200 [thread overview]
Message-ID: <20200107170312.27116-4-y.karadz@gmail.com> (raw)
In-Reply-To: <20200107170312.27116-1-y.karadz@gmail.com>
The data wrapper is the only thing that remains being built with Cython.
It is now a subpackage called "tracecruncher.datawrapper".
Signed-off-by: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
---
setup.py | 12 ++-
src/datawrapper.pyx | 201 ++++++++++++++++++++++++++++++++++++++++++++
src/trace2matrix.c | 29 +++++++
3 files changed, 241 insertions(+), 1 deletion(-)
create mode 100644 src/datawrapper.pyx
create mode 100644 src/trace2matrix.c
diff --git a/setup.py b/setup.py
index 62912e2..526e1e7 100644
--- a/setup.py
+++ b/setup.py
@@ -9,12 +9,22 @@ Copyright 2019 VMware Inc, Yordan Karadzhov (VMware) <y.karadz@gmail.com>
from setuptools import setup, find_packages
from distutils.core import Extension
from Cython.Build import cythonize
+import numpy as np
def main():
kshark_path = '/usr/local/lib/kernelshark'
traceevent_path = '/usr/local/lib/traceevent/'
tracecmd_path = '/usr/local/lib/trace-cmd/'
+ cythonize('src/datawrapper.pyx')
+ module_data = Extension('tracecruncher.datawrapper',
+ sources=['src/datawrapper.c'],
+ include_dirs=[np.get_include()],
+ library_dirs=[kshark_path, traceevent_path, tracecmd_path],
+ runtime_library_dirs=[kshark_path, traceevent_path, tracecmd_path],
+ libraries=['kshark', 'traceevent', 'tracecmd']
+ )
+
module_ks = Extension('tracecruncher.ksharkpy',
sources=['src/ksharkpy.c'],
library_dirs=[kshark_path],
@@ -41,7 +51,7 @@ def main():
url='https://github.com/vmware/trace-cruncher',
license='LGPL-2.1',
packages=find_packages(),
- ext_modules=[module_ks, module_ft],
+ ext_modules=[module_data, module_ks, module_ft],
classifiers=[
'Development Status :: 3 - Alpha',
'Programming Language :: Python :: 3',
diff --git a/src/datawrapper.pyx b/src/datawrapper.pyx
new file mode 100644
index 0000000..070d4e4
--- /dev/null
+++ b/src/datawrapper.pyx
@@ -0,0 +1,201 @@
+"""
+SPDX-License-Identifier: LGPL-2.1
+
+Copyright 2019 VMware Inc, Yordan Karadzhov (VMware) <y.karadz@gmail.com>
+"""
+
+import ctypes
+
+# Import the Python-level symbols of numpy
+import numpy as np
+# Import the C-level symbols of numpy
+cimport numpy as np
+
+import json
+
+from libcpp cimport bool
+
+from libc.stdlib cimport free
+
+from cpython cimport PyObject, Py_INCREF
+
+from libc cimport stdint
+ctypedef stdint.int16_t int16_t
+ctypedef stdint.uint16_t uint16_t
+ctypedef stdint.int32_t int32_t
+ctypedef stdint.uint32_t uint32_t
+ctypedef stdint.int64_t int64_t
+ctypedef stdint.uint64_t uint64_t
+
+cdef extern from 'numpy/ndarraytypes.h':
+ int NPY_ARRAY_CARRAY
+
+# Numpy must be initialized!!!
+np.import_array()
+
+cdef extern from 'trace2matrix.c':
+ ssize_t trace2matrix(uint64_t **offset_array,
+ uint16_t **cpu_array,
+ uint64_t **ts_array,
+ uint16_t **pid_array,
+ int **event_array)
+
+data_column_types = {
+ 'cpu': np.NPY_UINT16,
+ 'pid': np.NPY_UINT16,
+ 'event': np.NPY_INT,
+ 'offset': np.NPY_UINT64,
+ 'time': np.NPY_UINT64
+ }
+
+cdef class KsDataWrapper:
+ cdef int item_size
+ cdef int data_size
+ cdef int data_type
+ cdef void* data_ptr
+
+ cdef init(self, int data_type,
+ int data_size,
+ int item_size,
+ void* data_ptr):
+ """ This initialization cannot be done in the constructor because
+ we use C-level arguments.
+ """
+ self.item_size = item_size
+ self.data_size = data_size
+ self.data_type = data_type
+ self.data_ptr = data_ptr
+
+ def __array__(self):
+ """ Here we use the __array__ method, that is called when numpy
+ tries to get an array from the object.
+ """
+ cdef np.npy_intp shape[1]
+ shape[0] = <np.npy_intp> self.data_size
+
+ ndarray = np.PyArray_New(np.ndarray,
+ 1, shape,
+ self.data_type,
+ NULL,
+ self.data_ptr,
+ self.item_size,
+ NPY_ARRAY_CARRAY,
+ <object>NULL)
+
+ return ndarray
+
+ def __dealloc__(self):
+ """ Free the data. This is called by Python when all the references to
+ the object are gone.
+ """
+ free(<void*>self.data_ptr)
+
+
+def load(ofst_data=True, cpu_data=True, ts_data=True,
+ pid_data=True, evt_data=True):
+ """ Python binding of the 'kshark_load_data_matrix' function that does not
+ copy the data. The input parameters can be used to avoid loading the
+ data from the unnecessary fields.
+ """
+ cdef uint64_t *ofst_c
+ cdef uint16_t *cpu_c
+ cdef uint64_t *ts_c
+ cdef uint16_t *pid_c
+ cdef int *evt_c
+
+ cdef np.ndarray ofst
+ cdef np.ndarray cpu
+ cdef np.ndarray ts
+ cdef np.ndarray pid
+ cdef np.ndarray evt
+
+ if not ofst_data:
+ ofst_c = NULL
+
+ if not cpu_data:
+ cpu_c = NULL
+
+ if not ts_data:
+ ts_c = NULL
+
+ if not pid_data:
+ pid_c = NULL
+
+ if not evt_data:
+ evt_c = NULL
+
+ data_dict = {}
+
+ cdef ssize_t size
+
+ size = trace2matrix(&ofst_c, &cpu_c, &ts_c, &pid_c, &evt_c)
+ if size <= 0:
+ raise Exception('No data has been loaded.')
+
+ if cpu_data:
+ column = 'cpu'
+ array_wrapper_cpu = KsDataWrapper()
+ array_wrapper_cpu.init(data_type=data_column_types[column],
+ data_size=size,
+ item_size=0,
+ data_ptr=<void *> cpu_c)
+
+ cpu = np.array(array_wrapper_cpu, copy=False)
+ cpu.base = <PyObject *> array_wrapper_cpu
+ data_dict.update({column: cpu})
+ Py_INCREF(array_wrapper_cpu)
+
+ if pid_data:
+ column = 'pid'
+ array_wrapper_pid = KsDataWrapper()
+ array_wrapper_pid.init(data_type=data_column_types[column],
+ data_size=size,
+ item_size=0,
+ data_ptr=<void *>pid_c)
+
+ pid = np.array(array_wrapper_pid, copy=False)
+ pid.base = <PyObject *> array_wrapper_pid
+ data_dict.update({column: pid})
+ Py_INCREF(array_wrapper_pid)
+
+ if evt_data:
+ column = 'event'
+ array_wrapper_evt = KsDataWrapper()
+ array_wrapper_evt.init(data_type=data_column_types[column],
+ data_size=size,
+ item_size=0,
+ data_ptr=<void *>evt_c)
+
+ evt = np.array(array_wrapper_evt, copy=False)
+ evt.base = <PyObject *> array_wrapper_evt
+ data_dict.update({column: evt})
+ Py_INCREF(array_wrapper_evt)
+
+ if ofst_data:
+ column = 'offset'
+ array_wrapper_ofst = KsDataWrapper()
+ array_wrapper_ofst.init(data_type=data_column_types[column],
+ data_size=size,
+ item_size=0,
+ data_ptr=<void *> ofst_c)
+
+
+ ofst = np.array(array_wrapper_ofst, copy=False)
+ ofst.base = <PyObject *> array_wrapper_ofst
+ data_dict.update({column: ofst})
+ Py_INCREF(array_wrapper_ofst)
+
+ if ts_data:
+ column = 'time'
+ array_wrapper_ts = KsDataWrapper()
+ array_wrapper_ts.init(data_type=data_column_types[column],
+ data_size=size,
+ item_size=0,
+ data_ptr=<void *> ts_c)
+
+ ts = np.array(array_wrapper_ts, copy=False)
+ ts.base = <PyObject *> array_wrapper_ts
+ data_dict.update({column: ts})
+ Py_INCREF(array_wrapper_ts)
+
+ return data_dict
diff --git a/src/trace2matrix.c b/src/trace2matrix.c
new file mode 100644
index 0000000..aaf8322
--- /dev/null
+++ b/src/trace2matrix.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright 2019 VMware Inc, Yordan Karadzhov <ykaradzhov@vmware.com>
+ */
+
+// KernelShark
+#include "kernelshark/libkshark.h"
+
+ssize_t trace2matrix(uint64_t **offset_array,
+ uint16_t **cpu_array,
+ uint64_t **ts_array,
+ uint16_t **pid_array,
+ int **event_array)
+{
+ struct kshark_context *kshark_ctx = NULL;
+ ssize_t total = 0;
+
+ if (!kshark_instance(&kshark_ctx))
+ return -1;
+
+ total = kshark_load_data_matrix(kshark_ctx, offset_array,
+ cpu_array,
+ ts_array,
+ pid_array,
+ event_array);
+
+ return total;
+}
--
2.20.1
next prev parent reply other threads:[~2020-01-07 17:04 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-07 17:03 [PATCH v2 00/12] Build trace-cruncher as Python pakage Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 01/12] trace-cruncher: Refactor the part of the interface that relies on libkshark Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 02/12] trace-cruncher: Refactor the part of the interface that relies on libtraceevent Yordan Karadzhov (VMware)
2020-01-07 17:03 ` Yordan Karadzhov (VMware) [this message]
2020-01-07 17:03 ` [PATCH v2 04/12] trace-cruncher: Add "utils" Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 05/12] trace-cruncher: Adapt sched_wakeup.py to use the new module Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 06/12] trace-cruncher: Add Makefile Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 07/12] trace-cruncher: Adapt gpareto_fit.py to use the new module Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 08/12] trace-cruncher: Adapt page_faults.py " Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 09/12] trace-cruncher: Automate the third-party build Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 10/12] trace-cruncher: Update README.md Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 11/12] trace-cruncher: Remove all leftover files Yordan Karadzhov (VMware)
2020-01-07 17:03 ` [PATCH v2 12/12] trace-cruncher: Improve Makefile Provide more robust and better looking build process Yordan Karadzhov (VMware)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200107170312.27116-4-y.karadz@gmail.com \
--to=y.karadz@gmail.com \
--cc=Douglas.Raillard@arm.com \
--cc=Valentin.Schneider@arm.com \
--cc=linux-trace-devel@vger.kernel.org \
--cc=nd@arm.com \
--cc=rostedt@goodmis.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).