diff options
Diffstat (limited to 'tools/perf/scripts/python')
62 files changed, 11365 insertions, 0 deletions
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Build b/tools/perf/scripts/python/Perf-Trace-Util/Build new file mode 100644 index 000000000..7d0e33ce6 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/Build @@ -0,0 +1,3 @@ +perf-y += Context.o + +CFLAGS_Context.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-nested-externs diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c new file mode 100644 index 000000000..895f5fc23 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Context.c. Python interfaces for perf script. + * + * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com> + */ + +/* + * Use Py_ssize_t for '#' formats to avoid DeprecationWarning: PY_SSIZE_T_CLEAN + * will be required for '#' formats. + */ +#define PY_SSIZE_T_CLEAN + +#include <Python.h> +#include "../../../util/trace-event.h" +#include "../../../util/event.h" +#include "../../../util/symbol.h" +#include "../../../util/thread.h" +#include "../../../util/map.h" +#include "../../../util/maps.h" +#include "../../../util/auxtrace.h" +#include "../../../util/session.h" +#include "../../../util/srcline.h" +#include "../../../util/srccode.h" + +#if PY_MAJOR_VERSION < 3 +#define _PyCapsule_GetPointer(arg1, arg2) \ + PyCObject_AsVoidPtr(arg1) +#define _PyBytes_FromStringAndSize(arg1, arg2) \ + PyString_FromStringAndSize((arg1), (arg2)) +#define _PyUnicode_AsUTF8(arg) \ + PyString_AsString(arg) + +PyMODINIT_FUNC initperf_trace_context(void); +#else +#define _PyCapsule_GetPointer(arg1, arg2) \ + PyCapsule_GetPointer((arg1), (arg2)) +#define _PyBytes_FromStringAndSize(arg1, arg2) \ + PyBytes_FromStringAndSize((arg1), (arg2)) +#define _PyUnicode_AsUTF8(arg) \ + PyUnicode_AsUTF8(arg) + +PyMODINIT_FUNC PyInit_perf_trace_context(void); +#endif + +static struct scripting_context *get_args(PyObject *args, const char *name, PyObject **arg2) +{ + int cnt = 1 + !!arg2; + PyObject *context; + + if (!PyArg_UnpackTuple(args, name, 1, cnt, &context, arg2)) + return NULL; + + return _PyCapsule_GetPointer(context, NULL); +} + +static struct scripting_context *get_scripting_context(PyObject *args) +{ + return get_args(args, "context", NULL); +} + +static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args) +{ + struct scripting_context *c = get_scripting_context(args); + + if (!c) + return NULL; + + return Py_BuildValue("i", common_pc(c)); +} + +static PyObject *perf_trace_context_common_flags(PyObject *obj, + PyObject *args) +{ + struct scripting_context *c = get_scripting_context(args); + + if (!c) + return NULL; + + return Py_BuildValue("i", common_flags(c)); +} + +static PyObject *perf_trace_context_common_lock_depth(PyObject *obj, + PyObject *args) +{ + struct scripting_context *c = get_scripting_context(args); + + if (!c) + return NULL; + + return Py_BuildValue("i", common_lock_depth(c)); +} + +static PyObject *perf_sample_insn(PyObject *obj, PyObject *args) +{ + struct scripting_context *c = get_scripting_context(args); + + if (!c) + return NULL; + + if (c->sample->ip && !c->sample->insn_len && + c->al->thread->maps && c->al->thread->maps->machine) + script_fetch_insn(c->sample, c->al->thread, c->al->thread->maps->machine); + + if (!c->sample->insn_len) + Py_RETURN_NONE; /* N.B. This is a return statement */ + + return _PyBytes_FromStringAndSize(c->sample->insn, c->sample->insn_len); +} + +static PyObject *perf_set_itrace_options(PyObject *obj, PyObject *args) +{ + struct scripting_context *c; + const char *itrace_options; + int retval = -1; + PyObject *str; + + c = get_args(args, "itrace_options", &str); + if (!c) + return NULL; + + if (!c->session || !c->session->itrace_synth_opts) + goto out; + + if (c->session->itrace_synth_opts->set) { + retval = 1; + goto out; + } + + itrace_options = _PyUnicode_AsUTF8(str); + + retval = itrace_do_parse_synth_opts(c->session->itrace_synth_opts, itrace_options, 0); +out: + return Py_BuildValue("i", retval); +} + +static PyObject *perf_sample_src(PyObject *obj, PyObject *args, bool get_srccode) +{ + struct scripting_context *c = get_scripting_context(args); + unsigned int line = 0; + char *srcfile = NULL; + char *srccode = NULL; + PyObject *result; + struct map *map; + int len = 0; + u64 addr; + + if (!c) + return NULL; + + map = c->al->map; + addr = c->al->addr; + + if (map && map->dso) + srcfile = get_srcline_split(map->dso, map__rip_2objdump(map, addr), &line); + + if (get_srccode) { + if (srcfile) + srccode = find_sourceline(srcfile, line, &len); + result = Py_BuildValue("(sIs#)", srcfile, line, srccode, (Py_ssize_t)len); + } else { + result = Py_BuildValue("(sI)", srcfile, line); + } + + free(srcfile); + + return result; +} + +static PyObject *perf_sample_srcline(PyObject *obj, PyObject *args) +{ + return perf_sample_src(obj, args, false); +} + +static PyObject *perf_sample_srccode(PyObject *obj, PyObject *args) +{ + return perf_sample_src(obj, args, true); +} + +static PyMethodDef ContextMethods[] = { + { "common_pc", perf_trace_context_common_pc, METH_VARARGS, + "Get the common preempt count event field value."}, + { "common_flags", perf_trace_context_common_flags, METH_VARARGS, + "Get the common flags event field value."}, + { "common_lock_depth", perf_trace_context_common_lock_depth, + METH_VARARGS, "Get the common lock depth event field value."}, + { "perf_sample_insn", perf_sample_insn, + METH_VARARGS, "Get the machine code instruction."}, + { "perf_set_itrace_options", perf_set_itrace_options, + METH_VARARGS, "Set --itrace options."}, + { "perf_sample_srcline", perf_sample_srcline, + METH_VARARGS, "Get source file name and line number."}, + { "perf_sample_srccode", perf_sample_srccode, + METH_VARARGS, "Get source file name, line number and line."}, + { NULL, NULL, 0, NULL} +}; + +#if PY_MAJOR_VERSION < 3 +PyMODINIT_FUNC initperf_trace_context(void) +{ + (void) Py_InitModule("perf_trace_context", ContextMethods); +} +#else +PyMODINIT_FUNC PyInit_perf_trace_context(void) +{ + static struct PyModuleDef moduledef = { + PyModuleDef_HEAD_INIT, + "perf_trace_context", /* m_name */ + "", /* m_doc */ + -1, /* m_size */ + ContextMethods, /* m_methods */ + NULL, /* m_reload */ + NULL, /* m_traverse */ + NULL, /* m_clear */ + NULL, /* m_free */ + }; + PyObject *mod; + + mod = PyModule_Create(&moduledef); + /* Add perf_script_context to the module so it can be imported */ + PyObject_SetAttrString(mod, "perf_script_context", Py_None); + + return mod; +} +#endif diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py new file mode 100644 index 000000000..54ace2f6b --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -0,0 +1,116 @@ +# Core.py - Python extension for perf script, core functions +# +# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com> +# +# This software may be distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. + +from collections import defaultdict + +def autodict(): + return defaultdict(autodict) + +flag_fields = autodict() +symbolic_fields = autodict() + +def define_flag_field(event_name, field_name, delim): + flag_fields[event_name][field_name]['delim'] = delim + +def define_flag_value(event_name, field_name, value, field_str): + flag_fields[event_name][field_name]['values'][value] = field_str + +def define_symbolic_field(event_name, field_name): + # nothing to do, really + pass + +def define_symbolic_value(event_name, field_name, value, field_str): + symbolic_fields[event_name][field_name]['values'][value] = field_str + +def flag_str(event_name, field_name, value): + string = "" + + if flag_fields[event_name][field_name]: + print_delim = 0 + for idx in sorted(flag_fields[event_name][field_name]['values']): + if not value and not idx: + string += flag_fields[event_name][field_name]['values'][idx] + break + if idx and (value & idx) == idx: + if print_delim and flag_fields[event_name][field_name]['delim']: + string += " " + flag_fields[event_name][field_name]['delim'] + " " + string += flag_fields[event_name][field_name]['values'][idx] + print_delim = 1 + value &= ~idx + + return string + +def symbol_str(event_name, field_name, value): + string = "" + + if symbolic_fields[event_name][field_name]: + for idx in sorted(symbolic_fields[event_name][field_name]['values']): + if not value and not idx: + string = symbolic_fields[event_name][field_name]['values'][idx] + break + if (value == idx): + string = symbolic_fields[event_name][field_name]['values'][idx] + break + + return string + +trace_flags = { 0x00: "NONE", \ + 0x01: "IRQS_OFF", \ + 0x02: "IRQS_NOSUPPORT", \ + 0x04: "NEED_RESCHED", \ + 0x08: "HARDIRQ", \ + 0x10: "SOFTIRQ" } + +def trace_flag_str(value): + string = "" + print_delim = 0 + + for idx in trace_flags: + if not value and not idx: + string += "NONE" + break + + if idx and (value & idx) == idx: + if print_delim: + string += " | "; + string += trace_flags[idx] + print_delim = 1 + value &= ~idx + + return string + + +def taskState(state): + states = { + 0 : "R", + 1 : "S", + 2 : "D", + 64: "DEAD" + } + + if state not in states: + return "Unknown" + + return states[state] + + +class EventHeaders: + def __init__(self, common_cpu, common_secs, common_nsecs, + common_pid, common_comm, common_callchain): + self.cpu = common_cpu + self.secs = common_secs + self.nsecs = common_nsecs + self.pid = common_pid + self.comm = common_comm + self.callchain = common_callchain + + def ts(self): + return (self.secs * (10 ** 9)) + self.nsecs + + def ts_format(self): + return "%d.%d" % (self.secs, int(self.nsecs / 1000)) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py new file mode 100755 index 000000000..21a7a1298 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py @@ -0,0 +1,97 @@ +# EventClass.py +# SPDX-License-Identifier: GPL-2.0 +# +# This is a library defining some events types classes, which could +# be used by other scripts to analyzing the perf samples. +# +# Currently there are just a few classes defined for examples, +# PerfEvent is the base class for all perf event sample, PebsEvent +# is a HW base Intel x86 PEBS event, and user could add more SW/HW +# event classes based on requirements. +from __future__ import print_function + +import struct + +# Event types, user could add more here +EVTYPE_GENERIC = 0 +EVTYPE_PEBS = 1 # Basic PEBS event +EVTYPE_PEBS_LL = 2 # PEBS event with load latency info +EVTYPE_IBS = 3 + +# +# Currently we don't have good way to tell the event type, but by +# the size of raw buffer, raw PEBS event with load latency data's +# size is 176 bytes, while the pure PEBS event's size is 144 bytes. +# +def create_event(name, comm, dso, symbol, raw_buf): + if (len(raw_buf) == 144): + event = PebsEvent(name, comm, dso, symbol, raw_buf) + elif (len(raw_buf) == 176): + event = PebsNHM(name, comm, dso, symbol, raw_buf) + else: + event = PerfEvent(name, comm, dso, symbol, raw_buf) + + return event + +class PerfEvent(object): + event_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_GENERIC): + self.name = name + self.comm = comm + self.dso = dso + self.symbol = symbol + self.raw_buf = raw_buf + self.ev_type = ev_type + PerfEvent.event_num += 1 + + def show(self): + print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % + (self.name, self.symbol, self.comm, self.dso)) + +# +# Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer +# contains the context info when that event happened: the EFLAGS and +# linear IP info, as well as all the registers. +# +class PebsEvent(PerfEvent): + pebs_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS): + tmp_buf=raw_buf[0:80] + flags, ip, ax, bx, cx, dx, si, di, bp, sp = struct.unpack('QQQQQQQQQQ', tmp_buf) + self.flags = flags + self.ip = ip + self.ax = ax + self.bx = bx + self.cx = cx + self.dx = dx + self.si = si + self.di = di + self.bp = bp + self.sp = sp + + PerfEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type) + PebsEvent.pebs_num += 1 + del tmp_buf + +# +# Intel Nehalem and Westmere support PEBS plus Load Latency info which lie +# in the four 64 bit words write after the PEBS data: +# Status: records the IA32_PERF_GLOBAL_STATUS register value +# DLA: Data Linear Address (EIP) +# DSE: Data Source Encoding, where the latency happens, hit or miss +# in L1/L2/L3 or IO operations +# LAT: the actual latency in cycles +# +class PebsNHM(PebsEvent): + pebs_nhm_num = 0 + def __init__(self, name, comm, dso, symbol, raw_buf, ev_type=EVTYPE_PEBS_LL): + tmp_buf=raw_buf[144:176] + status, dla, dse, lat = struct.unpack('QQQQ', tmp_buf) + self.status = status + self.dla = dla + self.dse = dse + self.lat = lat + + PebsEvent.__init__(self, name, comm, dso, symbol, raw_buf, ev_type) + PebsNHM.pebs_nhm_num += 1 + del tmp_buf diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py new file mode 100644 index 000000000..cac7b2542 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py @@ -0,0 +1,184 @@ +# SchedGui.py - Python extension for perf script, basic GUI code for +# traces drawing and overview. +# +# Copyright (C) 2010 by Frederic Weisbecker <fweisbec@gmail.com> +# +# This software is distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. + + +try: + import wx +except ImportError: + raise ImportError("You need to install the wxpython lib for this script") + + +class RootFrame(wx.Frame): + Y_OFFSET = 100 + RECT_HEIGHT = 100 + RECT_SPACE = 50 + EVENT_MARKING_WIDTH = 5 + + def __init__(self, sched_tracer, title, parent = None, id = -1): + wx.Frame.__init__(self, parent, id, title) + + (self.screen_width, self.screen_height) = wx.GetDisplaySize() + self.screen_width -= 10 + self.screen_height -= 10 + self.zoom = 0.5 + self.scroll_scale = 20 + self.sched_tracer = sched_tracer + self.sched_tracer.set_root_win(self) + (self.ts_start, self.ts_end) = sched_tracer.interval() + self.update_width_virtual() + self.nr_rects = sched_tracer.nr_rectangles() + 1 + self.height_virtual = RootFrame.Y_OFFSET + (self.nr_rects * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + + # whole window panel + self.panel = wx.Panel(self, size=(self.screen_width, self.screen_height)) + + # scrollable container + self.scroll = wx.ScrolledWindow(self.panel) + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale) + self.scroll.EnableScrolling(True, True) + self.scroll.SetFocus() + + # scrollable drawing area + self.scroll_panel = wx.Panel(self.scroll, size=(self.screen_width - 15, self.screen_height / 2)) + self.scroll_panel.Bind(wx.EVT_PAINT, self.on_paint) + self.scroll_panel.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll_panel.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + self.scroll.Bind(wx.EVT_PAINT, self.on_paint) + self.scroll.Bind(wx.EVT_KEY_DOWN, self.on_key_press) + self.scroll.Bind(wx.EVT_LEFT_DOWN, self.on_mouse_down) + + self.scroll.Fit() + self.Fit() + + self.scroll_panel.SetDimensions(-1, -1, self.width_virtual, self.height_virtual, wx.SIZE_USE_EXISTING) + + self.txt = None + + self.Show(True) + + def us_to_px(self, val): + return val / (10 ** 3) * self.zoom + + def px_to_us(self, val): + return (val / self.zoom) * (10 ** 3) + + def scroll_start(self): + (x, y) = self.scroll.GetViewStart() + return (x * self.scroll_scale, y * self.scroll_scale) + + def scroll_start_us(self): + (x, y) = self.scroll_start() + return self.px_to_us(x) + + def paint_rectangle_zone(self, nr, color, top_color, start, end): + offset_px = self.us_to_px(start - self.ts_start) + width_px = self.us_to_px(end - self.ts_start) + + offset_py = RootFrame.Y_OFFSET + (nr * (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE)) + width_py = RootFrame.RECT_HEIGHT + + dc = self.dc + + if top_color is not None: + (r, g, b) = top_color + top_color = wx.Colour(r, g, b) + brush = wx.Brush(top_color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(offset_px, offset_py, width_px, RootFrame.EVENT_MARKING_WIDTH) + width_py -= RootFrame.EVENT_MARKING_WIDTH + offset_py += RootFrame.EVENT_MARKING_WIDTH + + (r ,g, b) = color + color = wx.Colour(r, g, b) + brush = wx.Brush(color, wx.SOLID) + dc.SetBrush(brush) + dc.DrawRectangle(offset_px, offset_py, width_px, width_py) + + def update_rectangles(self, dc, start, end): + start += self.ts_start + end += self.ts_start + self.sched_tracer.fill_zone(start, end) + + def on_paint(self, event): + dc = wx.PaintDC(self.scroll_panel) + self.dc = dc + + width = min(self.width_virtual, self.screen_width) + (x, y) = self.scroll_start() + start = self.px_to_us(x) + end = self.px_to_us(x + width) + self.update_rectangles(dc, start, end) + + def rect_from_ypixel(self, y): + y -= RootFrame.Y_OFFSET + rect = y / (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + height = y % (RootFrame.RECT_HEIGHT + RootFrame.RECT_SPACE) + + if rect < 0 or rect > self.nr_rects - 1 or height > RootFrame.RECT_HEIGHT: + return -1 + + return rect + + def update_summary(self, txt): + if self.txt: + self.txt.Destroy() + self.txt = wx.StaticText(self.panel, -1, txt, (0, (self.screen_height / 2) + 50)) + + + def on_mouse_down(self, event): + (x, y) = event.GetPositionTuple() + rect = self.rect_from_ypixel(y) + if rect == -1: + return + + t = self.px_to_us(x) + self.ts_start + + self.sched_tracer.mouse_down(rect, t) + + + def update_width_virtual(self): + self.width_virtual = self.us_to_px(self.ts_end - self.ts_start) + + def __zoom(self, x): + self.update_width_virtual() + (xpos, ypos) = self.scroll.GetViewStart() + xpos = self.us_to_px(x) / self.scroll_scale + self.scroll.SetScrollbars(self.scroll_scale, self.scroll_scale, self.width_virtual / self.scroll_scale, self.height_virtual / self.scroll_scale, xpos, ypos) + self.Refresh() + + def zoom_in(self): + x = self.scroll_start_us() + self.zoom *= 2 + self.__zoom(x) + + def zoom_out(self): + x = self.scroll_start_us() + self.zoom /= 2 + self.__zoom(x) + + + def on_key_press(self, event): + key = event.GetRawKeyCode() + if key == ord("+"): + self.zoom_in() + return + if key == ord("-"): + self.zoom_out() + return + + key = event.GetKeyCode() + (x, y) = self.scroll.GetViewStart() + if key == wx.WXK_RIGHT: + self.scroll.Scroll(x + 1, y) + elif key == wx.WXK_LEFT: + self.scroll.Scroll(x - 1, y) + elif key == wx.WXK_DOWN: + self.scroll.Scroll(x, y + 1) + elif key == wx.WXK_UP: + self.scroll.Scroll(x, y - 1) diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py new file mode 100644 index 000000000..7384dcb62 --- /dev/null +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py @@ -0,0 +1,91 @@ +# Util.py - Python extension for perf script, miscellaneous utility code +# +# Copyright (C) 2010 by Tom Zanussi <tzanussi@gmail.com> +# +# This software may be distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. +from __future__ import print_function + +import errno, os + +FUTEX_WAIT = 0 +FUTEX_WAKE = 1 +FUTEX_PRIVATE_FLAG = 128 +FUTEX_CLOCK_REALTIME = 256 +FUTEX_CMD_MASK = ~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME) + +NSECS_PER_SEC = 1000000000 + +def avg(total, n): + return total / n + +def nsecs(secs, nsecs): + return secs * NSECS_PER_SEC + nsecs + +def nsecs_secs(nsecs): + return nsecs / NSECS_PER_SEC + +def nsecs_nsecs(nsecs): + return nsecs % NSECS_PER_SEC + +def nsecs_str(nsecs): + str = "%5u.%09u" % (nsecs_secs(nsecs), nsecs_nsecs(nsecs)), + return str + +def add_stats(dict, key, value): + if key not in dict: + dict[key] = (value, value, value, 1) + else: + min, max, avg, count = dict[key] + if value < min: + min = value + if value > max: + max = value + avg = (avg + value) / 2 + dict[key] = (min, max, avg, count + 1) + +def clear_term(): + print("\x1b[H\x1b[2J") + +audit_package_warned = False + +try: + import audit + machine_to_id = { + 'x86_64': audit.MACH_86_64, + 'alpha' : audit.MACH_ALPHA, + 'ia64' : audit.MACH_IA64, + 'ppc' : audit.MACH_PPC, + 'ppc64' : audit.MACH_PPC64, + 'ppc64le' : audit.MACH_PPC64LE, + 's390' : audit.MACH_S390, + 's390x' : audit.MACH_S390X, + 'i386' : audit.MACH_X86, + 'i586' : audit.MACH_X86, + 'i686' : audit.MACH_X86, + } + try: + machine_to_id['armeb'] = audit.MACH_ARMEB + except: + pass + machine_id = machine_to_id[os.uname()[4]] +except: + if not audit_package_warned: + audit_package_warned = True + print("Install the audit-libs-python package to get syscall names.\n" + "For example:\n # apt-get install python-audit (Ubuntu)" + "\n # yum install audit-libs-python (Fedora)" + "\n etc.\n") + +def syscall_name(id): + try: + return audit.audit_syscall_to_name(id, machine_id) + except: + return str(id) + +def strerror(nr): + try: + return errno.errorcode[abs(nr)] + except: + return "Unknown %d errno" % nr diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py new file mode 100755 index 000000000..4339692a8 --- /dev/null +++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py @@ -0,0 +1,274 @@ +# SPDX-License-Identifier: GPL-2.0 +# arm-cs-trace-disasm.py: ARM CoreSight Trace Dump With Disassember +# +# Author: Tor Jeremiassen <tor@ti.com> +# Mathieu Poirier <mathieu.poirier@linaro.org> +# Leo Yan <leo.yan@linaro.org> +# Al Grant <Al.Grant@arm.com> + +from __future__ import print_function +import os +from os import path +import sys +import re +from subprocess import * +from optparse import OptionParser, make_option + +from perf_trace_context import perf_set_itrace_options, \ + perf_sample_insn, perf_sample_srccode + +# Below are some example commands for using this script. +# +# Output disassembly with objdump: +# perf script -s scripts/python/arm-cs-trace-disasm.py \ +# -- -d objdump -k path/to/vmlinux +# Output disassembly with llvm-objdump: +# perf script -s scripts/python/arm-cs-trace-disasm.py \ +# -- -d llvm-objdump-11 -k path/to/vmlinux +# Output only source line and symbols: +# perf script -s scripts/python/arm-cs-trace-disasm.py + +# Command line parsing. +option_list = [ + # formatting options for the bottom entry of the stack + make_option("-k", "--vmlinux", dest="vmlinux_name", + help="Set path to vmlinux file"), + make_option("-d", "--objdump", dest="objdump_name", + help="Set path to objdump executable file"), + make_option("-v", "--verbose", dest="verbose", + action="store_true", default=False, + help="Enable debugging log") +] + +parser = OptionParser(option_list=option_list) +(options, args) = parser.parse_args() + +# Initialize global dicts and regular expression +disasm_cache = dict() +cpu_data = dict() +disasm_re = re.compile("^\s*([0-9a-fA-F]+):") +disasm_func_re = re.compile("^\s*([0-9a-fA-F]+)\s.*:") +cache_size = 64*1024 + +glb_source_file_name = None +glb_line_number = None +glb_dso = None + +def get_optional(perf_dict, field): + if field in perf_dict: + return perf_dict[field] + return "[unknown]" + +def get_offset(perf_dict, field): + if field in perf_dict: + return "+%#x" % perf_dict[field] + return "" + +def get_dso_file_path(dso_name, dso_build_id): + if (dso_name == "[kernel.kallsyms]" or dso_name == "vmlinux"): + if (options.vmlinux_name): + return options.vmlinux_name; + else: + return dso_name + + if (dso_name == "[vdso]") : + append = "/vdso" + else: + append = "/elf" + + dso_path = os.environ['PERF_BUILDID_DIR'] + "/" + dso_name + "/" + dso_build_id + append; + # Replace duplicate slash chars to single slash char + dso_path = dso_path.replace('//', '/', 1) + return dso_path + +def read_disam(dso_fname, dso_start, start_addr, stop_addr): + addr_range = str(start_addr) + ":" + str(stop_addr) + ":" + dso_fname + + # Don't let the cache get too big, clear it when it hits max size + if (len(disasm_cache) > cache_size): + disasm_cache.clear(); + + if addr_range in disasm_cache: + disasm_output = disasm_cache[addr_range]; + else: + start_addr = start_addr - dso_start; + stop_addr = stop_addr - dso_start; + disasm = [ options.objdump_name, "-d", "-z", + "--start-address="+format(start_addr,"#x"), + "--stop-address="+format(stop_addr,"#x") ] + disasm += [ dso_fname ] + disasm_output = check_output(disasm).decode('utf-8').split('\n') + disasm_cache[addr_range] = disasm_output + + return disasm_output + +def print_disam(dso_fname, dso_start, start_addr, stop_addr): + for line in read_disam(dso_fname, dso_start, start_addr, stop_addr): + m = disasm_func_re.search(line) + if m is None: + m = disasm_re.search(line) + if m is None: + continue + print("\t" + line) + +def print_sample(sample): + print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \ + "pid: %d tid: %d period: %d time: %d }" % \ + (sample['cpu'], sample['addr'], sample['phys_addr'], \ + sample['ip'], sample['pid'], sample['tid'], \ + sample['period'], sample['time'])) + +def trace_begin(): + print('ARM CoreSight Trace Data Assembler Dump') + +def trace_end(): + print('End') + +def trace_unhandled(event_name, context, event_fields_dict): + print(' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])) + +def common_start_str(comm, sample): + sec = int(sample["time"] / 1000000000) + ns = sample["time"] % 1000000000 + cpu = sample["cpu"] + pid = sample["pid"] + tid = sample["tid"] + return "%16s %5u/%-5u [%04u] %9u.%09u " % (comm, pid, tid, cpu, sec, ns) + +# This code is copied from intel-pt-events.py for printing source code +# line and symbols. +def print_srccode(comm, param_dict, sample, symbol, dso): + ip = sample["ip"] + if symbol == "[unknown]": + start_str = common_start_str(comm, sample) + ("%x" % ip).rjust(16).ljust(40) + else: + offs = get_offset(param_dict, "symoff") + start_str = common_start_str(comm, sample) + (symbol + offs).ljust(40) + + global glb_source_file_name + global glb_line_number + global glb_dso + + source_file_name, line_number, source_line = perf_sample_srccode(perf_script_context) + if source_file_name: + if glb_line_number == line_number and glb_source_file_name == source_file_name: + src_str = "" + else: + if len(source_file_name) > 40: + src_file = ("..." + source_file_name[-37:]) + " " + else: + src_file = source_file_name.ljust(41) + + if source_line is None: + src_str = src_file + str(line_number).rjust(4) + " <source not found>" + else: + src_str = src_file + str(line_number).rjust(4) + " " + source_line + glb_dso = None + elif dso == glb_dso: + src_str = "" + else: + src_str = dso + glb_dso = dso + + glb_line_number = line_number + glb_source_file_name = source_file_name + + print(start_str, src_str) + +def process_event(param_dict): + global cache_size + global options + + sample = param_dict["sample"] + comm = param_dict["comm"] + + name = param_dict["ev_name"] + dso = get_optional(param_dict, "dso") + dso_bid = get_optional(param_dict, "dso_bid") + dso_start = get_optional(param_dict, "dso_map_start") + dso_end = get_optional(param_dict, "dso_map_end") + symbol = get_optional(param_dict, "symbol") + + if (options.verbose == True): + print("Event type: %s" % name) + print_sample(sample) + + # If cannot find dso so cannot dump assembler, bail out + if (dso == '[unknown]'): + return + + # Validate dso start and end addresses + if ((dso_start == '[unknown]') or (dso_end == '[unknown]')): + print("Failed to find valid dso map for dso %s" % dso) + return + + if (name[0:12] == "instructions"): + print_srccode(comm, param_dict, sample, symbol, dso) + return + + # Don't proceed if this event is not a branch sample, . + if (name[0:8] != "branches"): + return + + cpu = sample["cpu"] + ip = sample["ip"] + addr = sample["addr"] + + # Initialize CPU data if it's empty, and directly return back + # if this is the first tracing event for this CPU. + if (cpu_data.get(str(cpu) + 'addr') == None): + cpu_data[str(cpu) + 'addr'] = addr + return + + # The format for packet is: + # + # +------------+------------+------------+ + # sample_prev: | addr | ip | cpu | + # +------------+------------+------------+ + # sample_next: | addr | ip | cpu | + # +------------+------------+------------+ + # + # We need to combine the two continuous packets to get the instruction + # range for sample_prev::cpu: + # + # [ sample_prev::addr .. sample_next::ip ] + # + # For this purose, sample_prev::addr is stored into cpu_data structure + # and read back for 'start_addr' when the new packet comes, and we need + # to use sample_next::ip to calculate 'stop_addr', plusing extra 4 for + # 'stop_addr' is for the sake of objdump so the final assembler dump can + # include last instruction for sample_next::ip. + start_addr = cpu_data[str(cpu) + 'addr'] + stop_addr = ip + 4 + + # Record for previous sample packet + cpu_data[str(cpu) + 'addr'] = addr + + # Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4 + if (start_addr == 0 and stop_addr == 4): + print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu) + return + + if (start_addr < int(dso_start) or start_addr > int(dso_end)): + print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso)) + return + + if (stop_addr < int(dso_start) or stop_addr > int(dso_end)): + print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso)) + return + + if (options.objdump_name != None): + # It doesn't need to decrease virtual memory offset for disassembly + # for kernel dso, so in this case we set vm_start to zero. + if (dso == "[kernel.kallsyms]"): + dso_vm_start = 0 + else: + dso_vm_start = int(dso_start) + + dso_fname = get_dso_file_path(dso, dso_bid) + if path.exists(dso_fname): + print_disam(dso_fname, dso_vm_start, start_addr, stop_addr) + else: + print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr)) + + print_srccode(comm, param_dict, sample, symbol, dso) diff --git a/tools/perf/scripts/python/bin/compaction-times-record b/tools/perf/scripts/python/bin/compaction-times-record new file mode 100644 index 000000000..6edcd40e1 --- /dev/null +++ b/tools/perf/scripts/python/bin/compaction-times-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e compaction:mm_compaction_begin -e compaction:mm_compaction_end -e compaction:mm_compaction_migratepages -e compaction:mm_compaction_isolate_migratepages -e compaction:mm_compaction_isolate_freepages $@ diff --git a/tools/perf/scripts/python/bin/compaction-times-report b/tools/perf/scripts/python/bin/compaction-times-report new file mode 100644 index 000000000..3dc13897c --- /dev/null +++ b/tools/perf/scripts/python/bin/compaction-times-report @@ -0,0 +1,4 @@ +#!/bin/bash +#description: display time taken by mm compaction +#args: [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex] +perf script -s "$PERF_EXEC_PATH"/scripts/python/compaction-times.py $@ diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-record b/tools/perf/scripts/python/bin/event_analyzing_sample-record new file mode 100644 index 000000000..5ce652dab --- /dev/null +++ b/tools/perf/scripts/python/bin/event_analyzing_sample-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# event_analyzing_sample.py can cover all type of perf samples including +# the tracepoints, so no special record requirements, just record what +# you want to analyze. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/event_analyzing_sample-report b/tools/perf/scripts/python/bin/event_analyzing_sample-report new file mode 100644 index 000000000..0941fc94e --- /dev/null +++ b/tools/perf/scripts/python/bin/event_analyzing_sample-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: analyze all perf samples +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/event_analyzing_sample.py diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-record b/tools/perf/scripts/python/bin/export-to-postgresql-record new file mode 100644 index 000000000..221d66e05 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-postgresql-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# export perf data to a postgresql database. Can cover +# perf ip samples (excluding the tracepoints). No special +# record requirements, just record what you want to export. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report new file mode 100644 index 000000000..cd335b6e2 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-postgresql-report @@ -0,0 +1,29 @@ +#!/bin/bash +# description: export perf data to a postgresql database +# args: [database name] [columns] [calls] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 3 ] ; then + echo "usage: export-to-postgresql-report [database name] [columns] [calls]" + exit +fi +if [ "$n_args" -gt 2 ] ; then + dbname=$1 + columns=$2 + calls=$3 + shift 3 +elif [ "$n_args" -gt 1 ] ; then + dbname=$1 + columns=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + dbname=$1 + shift +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-record b/tools/perf/scripts/python/bin/export-to-sqlite-record new file mode 100644 index 000000000..070204fd6 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-sqlite-record @@ -0,0 +1,8 @@ +#!/bin/bash + +# +# export perf data to a sqlite3 database. Can cover +# perf ip samples (excluding the tracepoints). No special +# record requirements, just record what you want to export. +# +perf record $@ diff --git a/tools/perf/scripts/python/bin/export-to-sqlite-report b/tools/perf/scripts/python/bin/export-to-sqlite-report new file mode 100644 index 000000000..5ff6033e7 --- /dev/null +++ b/tools/perf/scripts/python/bin/export-to-sqlite-report @@ -0,0 +1,29 @@ +#!/bin/bash +# description: export perf data to a sqlite3 database +# args: [database name] [columns] [calls] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 3 ] ; then + echo "usage: export-to-sqlite-report [database name] [columns] [calls]" + exit +fi +if [ "$n_args" -gt 2 ] ; then + dbname=$1 + columns=$2 + calls=$3 + shift 3 +elif [ "$n_args" -gt 1 ] ; then + dbname=$1 + columns=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + dbname=$1 + shift +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-sqlite.py $dbname $columns $calls diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record new file mode 100644 index 000000000..74685f318 --- /dev/null +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record @@ -0,0 +1,3 @@ +#!/bin/bash +(perf record -e raw_syscalls:sys_exit $@ || \ + perf record -e syscalls:sys_exit $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report new file mode 100644 index 000000000..fda5096d0 --- /dev/null +++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-report @@ -0,0 +1,10 @@ +#!/bin/bash +# description: system-wide failed syscalls, by pid +# args: [comm] +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" > /dev/null ; then + comm=$1 + shift + fi +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/failed-syscalls-by-pid.py $comm diff --git a/tools/perf/scripts/python/bin/flamegraph-record b/tools/perf/scripts/python/bin/flamegraph-record new file mode 100755 index 000000000..7df5a19c0 --- /dev/null +++ b/tools/perf/scripts/python/bin/flamegraph-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -g "$@" diff --git a/tools/perf/scripts/python/bin/flamegraph-report b/tools/perf/scripts/python/bin/flamegraph-report new file mode 100755 index 000000000..53c5dc90c --- /dev/null +++ b/tools/perf/scripts/python/bin/flamegraph-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: create flame graphs +perf script -s "$PERF_EXEC_PATH"/scripts/python/flamegraph.py -- "$@" diff --git a/tools/perf/scripts/python/bin/futex-contention-record b/tools/perf/scripts/python/bin/futex-contention-record new file mode 100644 index 000000000..b1495c9a9 --- /dev/null +++ b/tools/perf/scripts/python/bin/futex-contention-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e syscalls:sys_enter_futex -e syscalls:sys_exit_futex $@ diff --git a/tools/perf/scripts/python/bin/futex-contention-report b/tools/perf/scripts/python/bin/futex-contention-report new file mode 100644 index 000000000..6c4427109 --- /dev/null +++ b/tools/perf/scripts/python/bin/futex-contention-report @@ -0,0 +1,4 @@ +#!/bin/bash +# description: futext contention measurement + +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/futex-contention.py diff --git a/tools/perf/scripts/python/bin/intel-pt-events-record b/tools/perf/scripts/python/bin/intel-pt-events-record new file mode 100644 index 000000000..6b9877cfe --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-record @@ -0,0 +1,13 @@ +#!/bin/bash + +# +# print Intel PT Events including Power Events and PTWRITE. The intel_pt PMU +# event needs to be specified with appropriate config terms. +# +if ! echo "$@" | grep -q intel_pt ; then + echo "Options must include the Intel PT event e.g. -e intel_pt/pwr_evt,ptw/" + echo "and for power events it probably needs to be system wide i.e. -a option" + echo "For example: -a -e intel_pt/pwr_evt,branch=0/ sleep 1" + exit 1 +fi +perf record $@ diff --git a/tools/perf/scripts/python/bin/intel-pt-events-report b/tools/perf/scripts/python/bin/intel-pt-events-report new file mode 100644 index 000000000..beeac3fde --- /dev/null +++ b/tools/perf/scripts/python/bin/intel-pt-events-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: print Intel PT Events including Power Events and PTWRITE +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/intel-pt-events.py diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-record b/tools/perf/scripts/python/bin/mem-phys-addr-record new file mode 100644 index 000000000..5a875122a --- /dev/null +++ b/tools/perf/scripts/python/bin/mem-phys-addr-record @@ -0,0 +1,19 @@ +#!/bin/bash + +# +# Profiling physical memory by all retired load instructions/uops event +# MEM_INST_RETIRED.ALL_LOADS or MEM_UOPS_RETIRED.ALL_LOADS +# + +load=`perf list | grep mem_inst_retired.all_loads` +if [ -z "$load" ]; then + load=`perf list | grep mem_uops_retired.all_loads` +fi +if [ -z "$load" ]; then + echo "There is no event to count all retired load instructions/uops." + exit 1 +fi + +arg=$(echo $load | tr -d ' ') +arg="$arg:P" +perf record --phys-data -e $arg $@ diff --git a/tools/perf/scripts/python/bin/mem-phys-addr-report b/tools/perf/scripts/python/bin/mem-phys-addr-report new file mode 100644 index 000000000..3f2b847e2 --- /dev/null +++ b/tools/perf/scripts/python/bin/mem-phys-addr-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: resolve physical address samples +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/mem-phys-addr.py diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-record b/tools/perf/scripts/python/bin/net_dropmonitor-record new file mode 100755 index 000000000..423fb81da --- /dev/null +++ b/tools/perf/scripts/python/bin/net_dropmonitor-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e skb:kfree_skb $@ diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-report b/tools/perf/scripts/python/bin/net_dropmonitor-report new file mode 100755 index 000000000..8d698f5a0 --- /dev/null +++ b/tools/perf/scripts/python/bin/net_dropmonitor-report @@ -0,0 +1,4 @@ +#!/bin/bash +# description: display a table of dropped frames + +perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@ diff --git a/tools/perf/scripts/python/bin/netdev-times-record b/tools/perf/scripts/python/bin/netdev-times-record new file mode 100644 index 000000000..558754b84 --- /dev/null +++ b/tools/perf/scripts/python/bin/netdev-times-record @@ -0,0 +1,8 @@ +#!/bin/bash +perf record -e net:net_dev_xmit -e net:net_dev_queue \ + -e net:netif_receive_skb -e net:netif_rx \ + -e skb:consume_skb -e skb:kfree_skb \ + -e skb:skb_copy_datagram_iovec -e napi:napi_poll \ + -e irq:irq_handler_entry -e irq:irq_handler_exit \ + -e irq:softirq_entry -e irq:softirq_exit \ + -e irq:softirq_raise $@ diff --git a/tools/perf/scripts/python/bin/netdev-times-report b/tools/perf/scripts/python/bin/netdev-times-report new file mode 100644 index 000000000..8f759291d --- /dev/null +++ b/tools/perf/scripts/python/bin/netdev-times-report @@ -0,0 +1,5 @@ +#!/bin/bash +# description: display a process of packet and processing time +# args: [tx] [rx] [dev=] [debug] + +perf script -s "$PERF_EXEC_PATH"/scripts/python/netdev-times.py $@ diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-record b/tools/perf/scripts/python/bin/powerpc-hcalls-record new file mode 100644 index 000000000..b7402aa91 --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -e "{powerpc:hcall_entry,powerpc:hcall_exit}" $@ diff --git a/tools/perf/scripts/python/bin/powerpc-hcalls-report b/tools/perf/scripts/python/bin/powerpc-hcalls-report new file mode 100644 index 000000000..dd32ad746 --- /dev/null +++ b/tools/perf/scripts/python/bin/powerpc-hcalls-report @@ -0,0 +1,2 @@ +#!/bin/bash +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/powerpc-hcalls.py diff --git a/tools/perf/scripts/python/bin/sched-migration-record b/tools/perf/scripts/python/bin/sched-migration-record new file mode 100644 index 000000000..7493fddbe --- /dev/null +++ b/tools/perf/scripts/python/bin/sched-migration-record @@ -0,0 +1,2 @@ +#!/bin/bash +perf record -m 16384 -e sched:sched_wakeup -e sched:sched_wakeup_new -e sched:sched_switch -e sched:sched_migrate_task $@ diff --git a/tools/perf/scripts/python/bin/sched-migration-report b/tools/perf/scripts/python/bin/sched-migration-report new file mode 100644 index 000000000..68b037a18 --- /dev/null +++ b/tools/perf/scripts/python/bin/sched-migration-report @@ -0,0 +1,3 @@ +#!/bin/bash +# description: sched migration overview +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sched-migration.py diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record new file mode 100644 index 000000000..d6940841e --- /dev/null +++ b/tools/perf/scripts/python/bin/sctop-record @@ -0,0 +1,3 @@ +#!/bin/bash +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/sctop-report b/tools/perf/scripts/python/bin/sctop-report new file mode 100644 index 000000000..c32db2941 --- /dev/null +++ b/tools/perf/scripts/python/bin/sctop-report @@ -0,0 +1,24 @@ +#!/bin/bash +# description: syscall top +# args: [comm] [interval] +n_args=0 +for i in "$@" +do + if expr match "$i" "-" > /dev/null ; then + break + fi + n_args=$(( $n_args + 1 )) +done +if [ "$n_args" -gt 2 ] ; then + echo "usage: sctop-report [comm] [interval]" + exit +fi +if [ "$n_args" -gt 1 ] ; then + comm=$1 + interval=$2 + shift 2 +elif [ "$n_args" -gt 0 ] ; then + interval=$1 + shift +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/sctop.py $comm $interval diff --git a/tools/perf/scripts/python/bin/stackcollapse-record b/tools/perf/scripts/python/bin/stackcollapse-record new file mode 100755 index 000000000..9d8f9f0f3 --- /dev/null +++ b/tools/perf/scripts/python/bin/stackcollapse-record @@ -0,0 +1,8 @@ +#!/bin/sh + +# +# stackcollapse.py can cover all type of perf samples including +# the tracepoints, so no special record requirements, just record what +# you want to analyze. +# +perf record "$@" diff --git a/tools/perf/scripts/python/bin/stackcollapse-report b/tools/perf/scripts/python/bin/stackcollapse-report new file mode 100755 index 000000000..21a356bd2 --- /dev/null +++ b/tools/perf/scripts/python/bin/stackcollapse-report @@ -0,0 +1,3 @@ +#!/bin/sh +# description: produce callgraphs in short form for scripting use +perf script -s "$PERF_EXEC_PATH"/scripts/python/stackcollapse.py "$@" diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record new file mode 100644 index 000000000..d6940841e --- /dev/null +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record @@ -0,0 +1,3 @@ +#!/bin/bash +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-report b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report new file mode 100644 index 000000000..16eb8d65c --- /dev/null +++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-report @@ -0,0 +1,10 @@ +#!/bin/bash +# description: system-wide syscall counts, by pid +# args: [comm] +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" > /dev/null ; then + comm=$1 + shift + fi +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts-by-pid.py $comm diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record new file mode 100644 index 000000000..d6940841e --- /dev/null +++ b/tools/perf/scripts/python/bin/syscall-counts-record @@ -0,0 +1,3 @@ +#!/bin/bash +(perf record -e raw_syscalls:sys_enter $@ || \ + perf record -e syscalls:sys_enter $@) 2> /dev/null diff --git a/tools/perf/scripts/python/bin/syscall-counts-report b/tools/perf/scripts/python/bin/syscall-counts-report new file mode 100644 index 000000000..0f0e9d453 --- /dev/null +++ b/tools/perf/scripts/python/bin/syscall-counts-report @@ -0,0 +1,10 @@ +#!/bin/bash +# description: system-wide syscall counts +# args: [comm] +if [ $# -gt 0 ] ; then + if ! expr match "$1" "-" > /dev/null ; then + comm=$1 + shift + fi +fi +perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/syscall-counts.py $comm diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py new file mode 100644 index 000000000..d2c229548 --- /dev/null +++ b/tools/perf/scripts/python/check-perf-trace.py @@ -0,0 +1,84 @@ +# perf script event handlers, generated by perf script -g python +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# This script tests basic functionality such as flag and symbol +# strings, common_xxx() calls back into perf, begin, end, unhandled +# events, etc. Basically, if this script runs successfully and +# displays expected results, Python scripting support should be ok. + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from Core import * +from perf_trace_context import * + +unhandled = autodict() + +def trace_begin(): + print("trace_begin") + pass + +def trace_end(): + print_unhandled() + +def irq__softirq_entry(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, vec): + print_header(event_name, common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + + print_uncommon(context) + + print("vec=%s" % (symbol_str("irq__softirq_entry", "vec", vec))) + +def kmem__kmalloc(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, call_site, ptr, bytes_req, bytes_alloc, + gfp_flags): + print_header(event_name, common_cpu, common_secs, common_nsecs, + common_pid, common_comm) + + print_uncommon(context) + + print("call_site=%u, ptr=%u, bytes_req=%u, " + "bytes_alloc=%u, gfp_flags=%s" % + (call_site, ptr, bytes_req, bytes_alloc, + flag_str("kmem__kmalloc", "gfp_flags", gfp_flags))) + +def trace_unhandled(event_name, context, event_fields_dict): + try: + unhandled[event_name] += 1 + except TypeError: + unhandled[event_name] = 1 + +def print_header(event_name, cpu, secs, nsecs, pid, comm): + print("%-20s %5u %05u.%09u %8u %-20s " % + (event_name, cpu, secs, nsecs, pid, comm), + end=' ') + +# print trace fields not included in handler args +def print_uncommon(context): + print("common_preempt_count=%d, common_flags=%s, " + "common_lock_depth=%d, " % + (common_pc(context), trace_flag_str(common_flags(context)), + common_lock_depth(context))) + +def print_unhandled(): + keys = unhandled.keys() + if not keys: + return + + print("\nunhandled events:\n") + + print("%-40s %10s" % ("event", "count")) + print("%-40s %10s" % ("----------------------------------------", + "-----------")) + + for event_name in keys: + print("%-40s %10d\n" % (event_name, unhandled[event_name])) diff --git a/tools/perf/scripts/python/compaction-times.py b/tools/perf/scripts/python/compaction-times.py new file mode 100644 index 000000000..2560a042d --- /dev/null +++ b/tools/perf/scripts/python/compaction-times.py @@ -0,0 +1,311 @@ +# report time spent in compaction +# Licensed under the terms of the GNU GPL License version 2 + +# testing: +# 'echo 1 > /proc/sys/vm/compact_memory' to force compaction of all zones + +import os +import sys +import re + +import signal +signal.signal(signal.SIGPIPE, signal.SIG_DFL) + +usage = "usage: perf script report compaction-times.py -- [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex]\n" + +class popt: + DISP_DFL = 0 + DISP_PROC = 1 + DISP_PROC_VERBOSE=2 + +class topt: + DISP_TIME = 0 + DISP_MIG = 1 + DISP_ISOLFREE = 2 + DISP_ISOLMIG = 4 + DISP_ALL = 7 + +class comm_filter: + def __init__(self, re): + self.re = re + + def filter(self, pid, comm): + m = self.re.search(comm) + return m == None or m.group() == "" + +class pid_filter: + def __init__(self, low, high): + self.low = (0 if low == "" else int(low)) + self.high = (0 if high == "" else int(high)) + + def filter(self, pid, comm): + return not (pid >= self.low and (self.high == 0 or pid <= self.high)) + +def set_type(t): + global opt_disp + opt_disp = (t if opt_disp == topt.DISP_ALL else opt_disp|t) + +def ns(sec, nsec): + return (sec * 1000000000) + nsec + +def time(ns): + return "%dns" % ns if opt_ns else "%dus" % (round(ns, -3) / 1000) + +class pair: + def __init__(self, aval, bval, alabel = None, blabel = None): + self.alabel = alabel + self.blabel = blabel + self.aval = aval + self.bval = bval + + def __add__(self, rhs): + self.aval += rhs.aval + self.bval += rhs.bval + return self + + def __str__(self): + return "%s=%d %s=%d" % (self.alabel, self.aval, self.blabel, self.bval) + +class cnode: + def __init__(self, ns): + self.ns = ns + self.migrated = pair(0, 0, "moved", "failed") + self.fscan = pair(0,0, "scanned", "isolated") + self.mscan = pair(0,0, "scanned", "isolated") + + def __add__(self, rhs): + self.ns += rhs.ns + self.migrated += rhs.migrated + self.fscan += rhs.fscan + self.mscan += rhs.mscan + return self + + def __str__(self): + prev = 0 + s = "%s " % time(self.ns) + if (opt_disp & topt.DISP_MIG): + s += "migration: %s" % self.migrated + prev = 1 + if (opt_disp & topt.DISP_ISOLFREE): + s += "%sfree_scanner: %s" % (" " if prev else "", self.fscan) + prev = 1 + if (opt_disp & topt.DISP_ISOLMIG): + s += "%smigration_scanner: %s" % (" " if prev else "", self.mscan) + return s + + def complete(self, secs, nsecs): + self.ns = ns(secs, nsecs) - self.ns + + def increment(self, migrated, fscan, mscan): + if (migrated != None): + self.migrated += migrated + if (fscan != None): + self.fscan += fscan + if (mscan != None): + self.mscan += mscan + + +class chead: + heads = {} + val = cnode(0); + fobj = None + + @classmethod + def add_filter(cls, filter): + cls.fobj = filter + + @classmethod + def create_pending(cls, pid, comm, start_secs, start_nsecs): + filtered = 0 + try: + head = cls.heads[pid] + filtered = head.is_filtered() + except KeyError: + if cls.fobj != None: + filtered = cls.fobj.filter(pid, comm) + head = cls.heads[pid] = chead(comm, pid, filtered) + + if not filtered: + head.mark_pending(start_secs, start_nsecs) + + @classmethod + def increment_pending(cls, pid, migrated, fscan, mscan): + head = cls.heads[pid] + if not head.is_filtered(): + if head.is_pending(): + head.do_increment(migrated, fscan, mscan) + else: + sys.stderr.write("missing start compaction event for pid %d\n" % pid) + + @classmethod + def complete_pending(cls, pid, secs, nsecs): + head = cls.heads[pid] + if not head.is_filtered(): + if head.is_pending(): + head.make_complete(secs, nsecs) + else: + sys.stderr.write("missing start compaction event for pid %d\n" % pid) + + @classmethod + def gen(cls): + if opt_proc != popt.DISP_DFL: + for i in cls.heads: + yield cls.heads[i] + + @classmethod + def str(cls): + return cls.val + + def __init__(self, comm, pid, filtered): + self.comm = comm + self.pid = pid + self.val = cnode(0) + self.pending = None + self.filtered = filtered + self.list = [] + + def __add__(self, rhs): + self.ns += rhs.ns + self.val += rhs.val + return self + + def mark_pending(self, secs, nsecs): + self.pending = cnode(ns(secs, nsecs)) + + def do_increment(self, migrated, fscan, mscan): + self.pending.increment(migrated, fscan, mscan) + + def make_complete(self, secs, nsecs): + self.pending.complete(secs, nsecs) + chead.val += self.pending + + if opt_proc != popt.DISP_DFL: + self.val += self.pending + + if opt_proc == popt.DISP_PROC_VERBOSE: + self.list.append(self.pending) + self.pending = None + + def enumerate(self): + if opt_proc == popt.DISP_PROC_VERBOSE and not self.is_filtered(): + for i, pelem in enumerate(self.list): + sys.stdout.write("%d[%s].%d: %s\n" % (self.pid, self.comm, i+1, pelem)) + + def is_pending(self): + return self.pending != None + + def is_filtered(self): + return self.filtered + + def display(self): + if not self.is_filtered(): + sys.stdout.write("%d[%s]: %s\n" % (self.pid, self.comm, self.val)) + + +def trace_end(): + sys.stdout.write("total: %s\n" % chead.str()) + for i in chead.gen(): + i.display(), + i.enumerate() + +def compaction__mm_compaction_migratepages(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, nr_migrated, nr_failed): + + chead.increment_pending(common_pid, + pair(nr_migrated, nr_failed), None, None) + +def compaction__mm_compaction_isolate_freepages(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, start_pfn, end_pfn, nr_scanned, nr_taken): + + chead.increment_pending(common_pid, + None, pair(nr_scanned, nr_taken), None) + +def compaction__mm_compaction_isolate_migratepages(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, start_pfn, end_pfn, nr_scanned, nr_taken): + + chead.increment_pending(common_pid, + None, None, pair(nr_scanned, nr_taken)) + +def compaction__mm_compaction_end(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, zone_start, migrate_start, free_start, zone_end, + sync, status): + + chead.complete_pending(common_pid, common_secs, common_nsecs) + +def compaction__mm_compaction_begin(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, zone_start, migrate_start, free_start, zone_end, + sync): + + chead.create_pending(common_pid, common_comm, common_secs, common_nsecs) + +def pr_help(): + global usage + + sys.stdout.write(usage) + sys.stdout.write("\n") + sys.stdout.write("-h display this help\n") + sys.stdout.write("-p display by process\n") + sys.stdout.write("-pv display by process (verbose)\n") + sys.stdout.write("-t display stall times only\n") + sys.stdout.write("-m display stats for migration\n") + sys.stdout.write("-fs display stats for free scanner\n") + sys.stdout.write("-ms display stats for migration scanner\n") + sys.stdout.write("-u display results in microseconds (default nanoseconds)\n") + + +comm_re = None +pid_re = None +pid_regex = "^(\d*)-(\d*)$|^(\d*)$" + +opt_proc = popt.DISP_DFL +opt_disp = topt.DISP_ALL + +opt_ns = True + +argc = len(sys.argv) - 1 +if argc >= 1: + pid_re = re.compile(pid_regex) + + for i, opt in enumerate(sys.argv[1:]): + if opt[0] == "-": + if opt == "-h": + pr_help() + exit(0); + elif opt == "-p": + opt_proc = popt.DISP_PROC + elif opt == "-pv": + opt_proc = popt.DISP_PROC_VERBOSE + elif opt == '-u': + opt_ns = False + elif opt == "-t": + set_type(topt.DISP_TIME) + elif opt == "-m": + set_type(topt.DISP_MIG) + elif opt == "-fs": + set_type(topt.DISP_ISOLFREE) + elif opt == "-ms": + set_type(topt.DISP_ISOLMIG) + else: + sys.exit(usage) + + elif i == argc - 1: + m = pid_re.search(opt) + if m != None and m.group() != "": + if m.group(3) != None: + f = pid_filter(m.group(3), m.group(3)) + else: + f = pid_filter(m.group(1), m.group(2)) + else: + try: + comm_re=re.compile(opt) + except: + sys.stderr.write("invalid regex '%s'" % opt) + sys.exit(usage) + f = comm_filter(comm_re) + + chead.add_filter(f) diff --git a/tools/perf/scripts/python/event_analyzing_sample.py b/tools/perf/scripts/python/event_analyzing_sample.py new file mode 100644 index 000000000..aa1e2cfa2 --- /dev/null +++ b/tools/perf/scripts/python/event_analyzing_sample.py @@ -0,0 +1,192 @@ +# event_analyzing_sample.py: general event handler in python +# SPDX-License-Identifier: GPL-2.0 +# +# Current perf report is already very powerful with the annotation integrated, +# and this script is not trying to be as powerful as perf report, but +# providing end user/developer a flexible way to analyze the events other +# than trace points. +# +# The 2 database related functions in this script just show how to gather +# the basic information, and users can modify and write their own functions +# according to their specific requirement. +# +# The first function "show_general_events" just does a basic grouping for all +# generic events with the help of sqlite, and the 2nd one "show_pebs_ll" is +# for a x86 HW PMU event: PEBS with load latency data. +# + +from __future__ import print_function + +import os +import sys +import math +import struct +import sqlite3 + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from EventClass import * + +# +# If the perf.data has a big number of samples, then the insert operation +# will be very time consuming (about 10+ minutes for 10000 samples) if the +# .db database is on disk. Move the .db file to RAM based FS to speedup +# the handling, which will cut the time down to several seconds. +# +con = sqlite3.connect("/dev/shm/perf.db") +con.isolation_level = None + +def trace_begin(): + print("In trace_begin:\n") + + # + # Will create several tables at the start, pebs_ll is for PEBS data with + # load latency info, while gen_events is for general event. + # + con.execute(""" + create table if not exists gen_events ( + name text, + symbol text, + comm text, + dso text + );""") + con.execute(""" + create table if not exists pebs_ll ( + name text, + symbol text, + comm text, + dso text, + flags integer, + ip integer, + status integer, + dse integer, + dla integer, + lat integer + );""") + +# +# Create and insert event object to a database so that user could +# do more analysis with simple database commands. +# +def process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + + # Symbol and dso info are not always resolved + if ("dso" in param_dict): + dso = param_dict["dso"] + else: + dso = "Unknown_dso" + + if ("symbol" in param_dict): + symbol = param_dict["symbol"] + else: + symbol = "Unknown_symbol" + + # Create the event object and insert it to the right table in database + event = create_event(name, comm, dso, symbol, raw_buf) + insert_db(event) + +def insert_db(event): + if event.ev_type == EVTYPE_GENERIC: + con.execute("insert into gen_events values(?, ?, ?, ?)", + (event.name, event.symbol, event.comm, event.dso)) + elif event.ev_type == EVTYPE_PEBS_LL: + event.ip &= 0x7fffffffffffffff + event.dla &= 0x7fffffffffffffff + con.execute("insert into pebs_ll values (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", + (event.name, event.symbol, event.comm, event.dso, event.flags, + event.ip, event.status, event.dse, event.dla, event.lat)) + +def trace_end(): + print("In trace_end:\n") + # We show the basic info for the 2 type of event classes + show_general_events() + show_pebs_ll() + con.close() + +# +# As the event number may be very big, so we can't use linear way +# to show the histogram in real number, but use a log2 algorithm. +# + +def num2sym(num): + # Each number will have at least one '#' + snum = '#' * (int)(math.log(num, 2) + 1) + return snum + +def show_general_events(): + + # Check the total record number in the table + count = con.execute("select count(*) from gen_events") + for t in count: + print("There is %d records in gen_events table" % t[0]) + if t[0] == 0: + return + + print("Statistics about the general events grouped by thread/symbol/dso: \n") + + # Group by thread + commq = con.execute("select comm, count(comm) from gen_events group by comm order by -count(comm)") + print("\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)) + for row in commq: + print("%16s %8d %s" % (row[0], row[1], num2sym(row[1]))) + + # Group by symbol + print("\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)) + symbolq = con.execute("select symbol, count(symbol) from gen_events group by symbol order by -count(symbol)") + for row in symbolq: + print("%32s %8d %s" % (row[0], row[1], num2sym(row[1]))) + + # Group by dso + print("\n%40s %8s %16s\n%s" % ("dso", "number", "histogram", "="*74)) + dsoq = con.execute("select dso, count(dso) from gen_events group by dso order by -count(dso)") + for row in dsoq: + print("%40s %8d %s" % (row[0], row[1], num2sym(row[1]))) + +# +# This function just shows the basic info, and we could do more with the +# data in the tables, like checking the function parameters when some +# big latency events happen. +# +def show_pebs_ll(): + + count = con.execute("select count(*) from pebs_ll") + for t in count: + print("There is %d records in pebs_ll table" % t[0]) + if t[0] == 0: + return + + print("Statistics about the PEBS Load Latency events grouped by thread/symbol/dse/latency: \n") + + # Group by thread + commq = con.execute("select comm, count(comm) from pebs_ll group by comm order by -count(comm)") + print("\n%16s %8s %16s\n%s" % ("comm", "number", "histogram", "="*42)) + for row in commq: + print("%16s %8d %s" % (row[0], row[1], num2sym(row[1]))) + + # Group by symbol + print("\n%32s %8s %16s\n%s" % ("symbol", "number", "histogram", "="*58)) + symbolq = con.execute("select symbol, count(symbol) from pebs_ll group by symbol order by -count(symbol)") + for row in symbolq: + print("%32s %8d %s" % (row[0], row[1], num2sym(row[1]))) + + # Group by dse + dseq = con.execute("select dse, count(dse) from pebs_ll group by dse order by -count(dse)") + print("\n%32s %8s %16s\n%s" % ("dse", "number", "histogram", "="*58)) + for row in dseq: + print("%32s %8d %s" % (row[0], row[1], num2sym(row[1]))) + + # Group by latency + latq = con.execute("select lat, count(lat) from pebs_ll group by lat order by lat") + print("\n%32s %8s %16s\n%s" % ("latency", "number", "histogram", "="*58)) + for row in latq: + print("%32s %8d %s" % (row[0], row[1], num2sym(row[1]))) + +def trace_unhandled(event_name, context, event_fields_dict): + print (' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])) diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py new file mode 100644 index 000000000..3a6bdcd74 --- /dev/null +++ b/tools/perf/scripts/python/export-to-postgresql.py @@ -0,0 +1,1114 @@ +# export-to-postgresql.py: export perf data to a postgresql database +# Copyright (c) 2014, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +from __future__ import print_function + +import os +import sys +import struct +import datetime + +# To use this script you will need to have installed package python-pyside which +# provides LGPL-licensed Python bindings for Qt. You will also need the package +# libqt4-sql-psql for Qt postgresql support. +# +# The script assumes postgresql is running on the local machine and that the +# user has postgresql permissions to create databases. Examples of installing +# postgresql and adding such a user are: +# +# fedora: +# +# $ sudo yum install postgresql postgresql-server qt-postgresql +# $ sudo su - postgres -c initdb +# $ sudo service postgresql start +# $ sudo su - postgres +# $ createuser -s <your user id here> # Older versions may not support -s, in which case answer the prompt below: +# Shall the new role be a superuser? (y/n) y +# $ sudo yum install python-pyside +# +# Alternately, to use Python3 and/or pyside 2, one of the following: +# $ sudo yum install python3-pyside +# $ pip install --user PySide2 +# $ pip3 install --user PySide2 +# +# ubuntu: +# +# $ sudo apt-get install postgresql +# $ sudo su - postgres +# $ createuser -s <your user id here> +# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql +# +# Alternately, to use Python3 and/or pyside 2, one of the following: +# +# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql +# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql +# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql +# +# An example of using this script with Intel PT: +# +# $ perf record -e intel_pt//u ls +# $ perf script -s ~/libexec/perf-core/scripts/python/export-to-postgresql.py pt_example branches calls +# 2015-05-29 12:49:23.464364 Creating database... +# 2015-05-29 12:49:26.281717 Writing to intermediate files... +# 2015-05-29 12:49:27.190383 Copying to database... +# 2015-05-29 12:49:28.140451 Removing intermediate files... +# 2015-05-29 12:49:28.147451 Adding primary keys +# 2015-05-29 12:49:28.655683 Adding foreign keys +# 2015-05-29 12:49:29.365350 Done +# +# To browse the database, psql can be used e.g. +# +# $ psql pt_example +# pt_example=# select * from samples_view where id < 100; +# pt_example=# \d+ +# pt_example=# \d+ samples_view +# pt_example=# \q +# +# An example of using the database is provided by the script +# exported-sql-viewer.py. Refer to that script for details. +# +# Tables: +# +# The tables largely correspond to perf tools' data structures. They are largely self-explanatory. +# +# samples +# +# 'samples' is the main table. It represents what instruction was executing at a point in time +# when something (a selected event) happened. The memory address is the instruction pointer or 'ip'. +# +# calls +# +# 'calls' represents function calls and is related to 'samples' by 'call_id' and 'return_id'. +# 'calls' is only created when the 'calls' option to this script is specified. +# +# call_paths +# +# 'call_paths' represents all the call stacks. Each 'call' has an associated record in 'call_paths'. +# 'calls_paths' is only created when the 'calls' option to this script is specified. +# +# branch_types +# +# 'branch_types' provides descriptions for each type of branch. +# +# comm_threads +# +# 'comm_threads' shows how 'comms' relates to 'threads'. +# +# comms +# +# 'comms' contains a record for each 'comm' - the name given to the executable that is running. +# +# dsos +# +# 'dsos' contains a record for each executable file or library. +# +# machines +# +# 'machines' can be used to distinguish virtual machines if virtualization is supported. +# +# selected_events +# +# 'selected_events' contains a record for each kind of event that has been sampled. +# +# symbols +# +# 'symbols' contains a record for each symbol. Only symbols that have samples are present. +# +# threads +# +# 'threads' contains a record for each thread. +# +# Views: +# +# Most of the tables have views for more friendly display. The views are: +# +# calls_view +# call_paths_view +# comm_threads_view +# dsos_view +# machines_view +# samples_view +# symbols_view +# threads_view +# +# More examples of browsing the database with psql: +# Note that some of the examples are not the most optimal SQL query. +# Note that call information is only available if the script's 'calls' option has been used. +# +# Top 10 function calls (not aggregated by symbol): +# +# SELECT * FROM calls_view ORDER BY elapsed_time DESC LIMIT 10; +# +# Top 10 function calls (aggregated by symbol): +# +# SELECT symbol_id,(SELECT name FROM symbols WHERE id = symbol_id) AS symbol, +# SUM(elapsed_time) AS tot_elapsed_time,SUM(branch_count) AS tot_branch_count +# FROM calls_view GROUP BY symbol_id ORDER BY tot_elapsed_time DESC LIMIT 10; +# +# Note that the branch count gives a rough estimation of cpu usage, so functions +# that took a long time but have a relatively low branch count must have spent time +# waiting. +# +# Find symbols by pattern matching on part of the name (e.g. names containing 'alloc'): +# +# SELECT * FROM symbols_view WHERE name LIKE '%alloc%'; +# +# Top 10 function calls for a specific symbol (e.g. whose symbol_id is 187): +# +# SELECT * FROM calls_view WHERE symbol_id = 187 ORDER BY elapsed_time DESC LIMIT 10; +# +# Show function calls made by function in the same context (i.e. same call path) (e.g. one with call_path_id 254): +# +# SELECT * FROM calls_view WHERE parent_call_path_id = 254; +# +# Show branches made during a function call (e.g. where call_id is 29357 and return_id is 29370 and tid is 29670) +# +# SELECT * FROM samples_view WHERE id >= 29357 AND id <= 29370 AND tid = 29670 AND event LIKE 'branches%'; +# +# Show transactions: +# +# SELECT * FROM samples_view WHERE event = 'transactions'; +# +# Note transaction start has 'in_tx' true whereas, transaction end has 'in_tx' false. +# Transaction aborts have branch_type_name 'transaction abort' +# +# Show transaction aborts: +# +# SELECT * FROM samples_view WHERE event = 'transactions' AND branch_type_name = 'transaction abort'; +# +# To print a call stack requires walking the call_paths table. For example this python script: +# #!/usr/bin/python2 +# +# import sys +# from PySide.QtSql import * +# +# if __name__ == '__main__': +# if (len(sys.argv) < 3): +# print >> sys.stderr, "Usage is: printcallstack.py <database name> <call_path_id>" +# raise Exception("Too few arguments") +# dbname = sys.argv[1] +# call_path_id = sys.argv[2] +# db = QSqlDatabase.addDatabase('QPSQL') +# db.setDatabaseName(dbname) +# if not db.open(): +# raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text()) +# query = QSqlQuery(db) +# print " id ip symbol_id symbol dso_id dso_short_name" +# while call_path_id != 0 and call_path_id != 1: +# ret = query.exec_('SELECT * FROM call_paths_view WHERE id = ' + str(call_path_id)) +# if not ret: +# raise Exception("Query failed: " + query.lastError().text()) +# if not query.next(): +# raise Exception("Query failed") +# print "{0:>6} {1:>10} {2:>9} {3:<30} {4:>6} {5:<30}".format(query.value(0), query.value(1), query.value(2), query.value(3), query.value(4), query.value(5)) +# call_path_id = query.value(6) + +pyside_version_1 = True +if not "pyside-version-1" in sys.argv: + try: + from PySide2.QtSql import * + pyside_version_1 = False + except: + pass + +if pyside_version_1: + from PySide.QtSql import * + +if sys.version_info < (3, 0): + def toserverstr(str): + return str + def toclientstr(str): + return str +else: + # Assume UTF-8 server_encoding and client_encoding + def toserverstr(str): + return bytes(str, "UTF_8") + def toclientstr(str): + return bytes(str, "UTF_8") + +# Need to access PostgreSQL C library directly to use COPY FROM STDIN +from ctypes import * +libpq = CDLL("libpq.so.5") +PQconnectdb = libpq.PQconnectdb +PQconnectdb.restype = c_void_p +PQconnectdb.argtypes = [ c_char_p ] +PQfinish = libpq.PQfinish +PQfinish.argtypes = [ c_void_p ] +PQstatus = libpq.PQstatus +PQstatus.restype = c_int +PQstatus.argtypes = [ c_void_p ] +PQexec = libpq.PQexec +PQexec.restype = c_void_p +PQexec.argtypes = [ c_void_p, c_char_p ] +PQresultStatus = libpq.PQresultStatus +PQresultStatus.restype = c_int +PQresultStatus.argtypes = [ c_void_p ] +PQputCopyData = libpq.PQputCopyData +PQputCopyData.restype = c_int +PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ] +PQputCopyEnd = libpq.PQputCopyEnd +PQputCopyEnd.restype = c_int +PQputCopyEnd.argtypes = [ c_void_p, c_void_p ] + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +perf_db_export_mode = True +perf_db_export_calls = False +perf_db_export_callchains = False + +def printerr(*args, **kw_args): + print(*args, file=sys.stderr, **kw_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + +def usage(): + printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); + printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1"); + raise Exception("Too few or bad arguments") + +if (len(sys.argv) < 2): + usage() + +dbname = sys.argv[1] + +if (len(sys.argv) >= 3): + columns = sys.argv[2] +else: + columns = "all" + +if columns not in ("all", "branches"): + usage() + +branches = (columns == "branches") + +for i in range(3,len(sys.argv)): + if (sys.argv[i] == "calls"): + perf_db_export_calls = True + elif (sys.argv[i] == "callchains"): + perf_db_export_callchains = True + elif (sys.argv[i] == "pyside-version-1"): + pass + else: + usage() + +output_dir_name = os.getcwd() + "/" + dbname + "-perf-data" +os.mkdir(output_dir_name) + +def do_query(q, s): + if (q.exec_(s)): + return + raise Exception("Query failed: " + q.lastError().text()) + +printdate("Creating database...") + +db = QSqlDatabase.addDatabase('QPSQL') +query = QSqlQuery(db) +db.setDatabaseName('postgres') +db.open() +try: + do_query(query, 'CREATE DATABASE ' + dbname) +except: + os.rmdir(output_dir_name) + raise +query.finish() +query.clear() +db.close() + +db.setDatabaseName(dbname) +db.open() + +query = QSqlQuery(db) +do_query(query, 'SET client_min_messages TO WARNING') + +do_query(query, 'CREATE TABLE selected_events (' + 'id bigint NOT NULL,' + 'name varchar(80))') +do_query(query, 'CREATE TABLE machines (' + 'id bigint NOT NULL,' + 'pid integer,' + 'root_dir varchar(4096))') +do_query(query, 'CREATE TABLE threads (' + 'id bigint NOT NULL,' + 'machine_id bigint,' + 'process_id bigint,' + 'pid integer,' + 'tid integer)') +do_query(query, 'CREATE TABLE comms (' + 'id bigint NOT NULL,' + 'comm varchar(16),' + 'c_thread_id bigint,' + 'c_time bigint,' + 'exec_flag boolean)') +do_query(query, 'CREATE TABLE comm_threads (' + 'id bigint NOT NULL,' + 'comm_id bigint,' + 'thread_id bigint)') +do_query(query, 'CREATE TABLE dsos (' + 'id bigint NOT NULL,' + 'machine_id bigint,' + 'short_name varchar(256),' + 'long_name varchar(4096),' + 'build_id varchar(64))') +do_query(query, 'CREATE TABLE symbols (' + 'id bigint NOT NULL,' + 'dso_id bigint,' + 'sym_start bigint,' + 'sym_end bigint,' + 'binding integer,' + 'name varchar(2048))') +do_query(query, 'CREATE TABLE branch_types (' + 'id integer NOT NULL,' + 'name varchar(80))') + +if branches: + do_query(query, 'CREATE TABLE samples (' + 'id bigint NOT NULL,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint,' + 'flags integer)') +else: + do_query(query, 'CREATE TABLE samples (' + 'id bigint NOT NULL,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'period bigint,' + 'weight bigint,' + 'transaction bigint,' + 'data_src bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint,' + 'flags integer)') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE TABLE call_paths (' + 'id bigint NOT NULL,' + 'parent_id bigint,' + 'symbol_id bigint,' + 'ip bigint)') +if perf_db_export_calls: + do_query(query, 'CREATE TABLE calls (' + 'id bigint NOT NULL,' + 'thread_id bigint,' + 'comm_id bigint,' + 'call_path_id bigint,' + 'call_time bigint,' + 'return_time bigint,' + 'branch_count bigint,' + 'call_id bigint,' + 'return_id bigint,' + 'parent_call_path_id bigint,' + 'flags integer,' + 'parent_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint)') + +do_query(query, 'CREATE TABLE ptwrite (' + 'id bigint NOT NULL,' + 'payload bigint,' + 'exact_ip boolean)') + +do_query(query, 'CREATE TABLE cbr (' + 'id bigint NOT NULL,' + 'cbr integer,' + 'mhz integer,' + 'percent integer)') + +do_query(query, 'CREATE TABLE mwait (' + 'id bigint NOT NULL,' + 'hints integer,' + 'extensions integer)') + +do_query(query, 'CREATE TABLE pwre (' + 'id bigint NOT NULL,' + 'cstate integer,' + 'subcstate integer,' + 'hw boolean)') + +do_query(query, 'CREATE TABLE exstop (' + 'id bigint NOT NULL,' + 'exact_ip boolean)') + +do_query(query, 'CREATE TABLE pwrx (' + 'id bigint NOT NULL,' + 'deepest_cstate integer,' + 'last_cstate integer,' + 'wake_reason integer)') + +do_query(query, 'CREATE TABLE context_switches (' + 'id bigint NOT NULL,' + 'machine_id bigint,' + 'time bigint,' + 'cpu integer,' + 'thread_out_id bigint,' + 'comm_out_id bigint,' + 'thread_in_id bigint,' + 'comm_in_id bigint,' + 'flags integer)') + +do_query(query, 'CREATE VIEW machines_view AS ' + 'SELECT ' + 'id,' + 'pid,' + 'root_dir,' + 'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest' + ' FROM machines') + +do_query(query, 'CREATE VIEW dsos_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'short_name,' + 'long_name,' + 'build_id' + ' FROM dsos') + +do_query(query, 'CREATE VIEW symbols_view AS ' + 'SELECT ' + 'id,' + 'name,' + '(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,' + 'dso_id,' + 'sym_start,' + 'sym_end,' + 'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding' + ' FROM symbols') + +do_query(query, 'CREATE VIEW threads_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'process_id,' + 'pid,' + 'tid' + ' FROM threads') + +do_query(query, 'CREATE VIEW comm_threads_view AS ' + 'SELECT ' + 'comm_id,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid' + ' FROM comm_threads') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE VIEW call_paths_view AS ' + 'SELECT ' + 'c.id,' + 'to_hex(c.ip) AS ip,' + 'c.symbol_id,' + '(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,' + '(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,' + '(SELECT dso FROM symbols_view WHERE id = c.symbol_id) AS dso_short_name,' + 'c.parent_id,' + 'to_hex(p.ip) AS parent_ip,' + 'p.symbol_id AS parent_symbol_id,' + '(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,' + '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,' + '(SELECT dso FROM symbols_view WHERE id = p.symbol_id) AS parent_dso_short_name' + ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id') +if perf_db_export_calls: + do_query(query, 'CREATE VIEW calls_view AS ' + 'SELECT ' + 'calls.id,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'call_path_id,' + 'to_hex(ip) AS ip,' + 'symbol_id,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'call_time,' + 'return_time,' + 'return_time - call_time AS elapsed_time,' + 'branch_count,' + 'insn_count,' + 'cyc_count,' + 'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC,' + 'call_id,' + 'return_id,' + 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE CAST ( flags AS VARCHAR(6) ) END AS flags,' + 'parent_call_path_id,' + 'calls.parent_id' + ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') + +do_query(query, 'CREATE VIEW samples_view AS ' + 'SELECT ' + 'id,' + 'time,' + 'cpu,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,' + 'to_hex(ip) AS ip_hex,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'sym_offset,' + '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,' + 'to_hex(to_ip) AS to_ip_hex,' + '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,' + 'to_sym_offset,' + '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,' + '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,' + 'in_tx,' + 'insn_count,' + 'cyc_count,' + 'CASE WHEN cyc_count=0 THEN CAST(0 AS NUMERIC(20, 2)) ELSE CAST((CAST(insn_count AS FLOAT) / cyc_count) AS NUMERIC(20, 2)) END AS IPC,' + 'flags' + ' FROM samples') + +do_query(query, 'CREATE VIEW ptwrite_view AS ' + 'SELECT ' + 'ptwrite.id,' + 'time,' + 'cpu,' + 'to_hex(payload) AS payload_hex,' + 'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip' + ' FROM ptwrite' + ' INNER JOIN samples ON samples.id = ptwrite.id') + +do_query(query, 'CREATE VIEW cbr_view AS ' + 'SELECT ' + 'cbr.id,' + 'time,' + 'cpu,' + 'cbr,' + 'mhz,' + 'percent' + ' FROM cbr' + ' INNER JOIN samples ON samples.id = cbr.id') + +do_query(query, 'CREATE VIEW mwait_view AS ' + 'SELECT ' + 'mwait.id,' + 'time,' + 'cpu,' + 'to_hex(hints) AS hints_hex,' + 'to_hex(extensions) AS extensions_hex' + ' FROM mwait' + ' INNER JOIN samples ON samples.id = mwait.id') + +do_query(query, 'CREATE VIEW pwre_view AS ' + 'SELECT ' + 'pwre.id,' + 'time,' + 'cpu,' + 'cstate,' + 'subcstate,' + 'CASE WHEN hw=FALSE THEN \'False\' ELSE \'True\' END AS hw' + ' FROM pwre' + ' INNER JOIN samples ON samples.id = pwre.id') + +do_query(query, 'CREATE VIEW exstop_view AS ' + 'SELECT ' + 'exstop.id,' + 'time,' + 'cpu,' + 'CASE WHEN exact_ip=FALSE THEN \'False\' ELSE \'True\' END AS exact_ip' + ' FROM exstop' + ' INNER JOIN samples ON samples.id = exstop.id') + +do_query(query, 'CREATE VIEW pwrx_view AS ' + 'SELECT ' + 'pwrx.id,' + 'time,' + 'cpu,' + 'deepest_cstate,' + 'last_cstate,' + 'CASE WHEN wake_reason=1 THEN \'Interrupt\'' + ' WHEN wake_reason=2 THEN \'Timer Deadline\'' + ' WHEN wake_reason=4 THEN \'Monitored Address\'' + ' WHEN wake_reason=8 THEN \'HW\'' + ' ELSE CAST ( wake_reason AS VARCHAR(2) )' + 'END AS wake_reason' + ' FROM pwrx' + ' INNER JOIN samples ON samples.id = pwrx.id') + +do_query(query, 'CREATE VIEW power_events_view AS ' + 'SELECT ' + 'samples.id,' + 'samples.time,' + 'samples.cpu,' + 'selected_events.name AS event,' + 'FORMAT(\'%6s\', cbr.cbr) AS cbr,' + 'FORMAT(\'%6s\', cbr.mhz) AS MHz,' + 'FORMAT(\'%5s\', cbr.percent) AS percent,' + 'to_hex(mwait.hints) AS hints_hex,' + 'to_hex(mwait.extensions) AS extensions_hex,' + 'FORMAT(\'%3s\', pwre.cstate) AS cstate,' + 'FORMAT(\'%3s\', pwre.subcstate) AS subcstate,' + 'CASE WHEN pwre.hw=FALSE THEN \'False\' WHEN pwre.hw=TRUE THEN \'True\' ELSE NULL END AS hw,' + 'CASE WHEN exstop.exact_ip=FALSE THEN \'False\' WHEN exstop.exact_ip=TRUE THEN \'True\' ELSE NULL END AS exact_ip,' + 'FORMAT(\'%3s\', pwrx.deepest_cstate) AS deepest_cstate,' + 'FORMAT(\'%3s\', pwrx.last_cstate) AS last_cstate,' + 'CASE WHEN pwrx.wake_reason=1 THEN \'Interrupt\'' + ' WHEN pwrx.wake_reason=2 THEN \'Timer Deadline\'' + ' WHEN pwrx.wake_reason=4 THEN \'Monitored Address\'' + ' WHEN pwrx.wake_reason=8 THEN \'HW\'' + ' ELSE FORMAT(\'%2s\', pwrx.wake_reason)' + 'END AS wake_reason' + ' FROM cbr' + ' FULL JOIN mwait ON mwait.id = cbr.id' + ' FULL JOIN pwre ON pwre.id = cbr.id' + ' FULL JOIN exstop ON exstop.id = cbr.id' + ' FULL JOIN pwrx ON pwrx.id = cbr.id' + ' INNER JOIN samples ON samples.id = coalesce(cbr.id, mwait.id, pwre.id, exstop.id, pwrx.id)' + ' INNER JOIN selected_events ON selected_events.id = samples.evsel_id' + ' ORDER BY samples.id') + +do_query(query, 'CREATE VIEW context_switches_view AS ' + 'SELECT ' + 'context_switches.id,' + 'context_switches.machine_id,' + 'context_switches.time,' + 'context_switches.cpu,' + 'th_out.pid AS pid_out,' + 'th_out.tid AS tid_out,' + 'comm_out.comm AS comm_out,' + 'th_in.pid AS pid_in,' + 'th_in.tid AS tid_in,' + 'comm_in.comm AS comm_in,' + 'CASE WHEN context_switches.flags = 0 THEN \'in\'' + ' WHEN context_switches.flags = 1 THEN \'out\'' + ' WHEN context_switches.flags = 3 THEN \'out preempt\'' + ' ELSE CAST ( context_switches.flags AS VARCHAR(11) )' + 'END AS flags' + ' FROM context_switches' + ' INNER JOIN threads AS th_out ON th_out.id = context_switches.thread_out_id' + ' INNER JOIN threads AS th_in ON th_in.id = context_switches.thread_in_id' + ' INNER JOIN comms AS comm_out ON comm_out.id = context_switches.comm_out_id' + ' INNER JOIN comms AS comm_in ON comm_in.id = context_switches.comm_in_id') + +file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0) +file_trailer = b"\377\377" + +def open_output_file(file_name): + path_name = output_dir_name + "/" + file_name + file = open(path_name, "wb+") + file.write(file_header) + return file + +def close_output_file(file): + file.write(file_trailer) + file.close() + +def copy_output_file_direct(file, table_name): + close_output_file(file) + sql = "COPY " + table_name + " FROM '" + file.name + "' (FORMAT 'binary')" + do_query(query, sql) + +# Use COPY FROM STDIN because security may prevent postgres from accessing the files directly +def copy_output_file(file, table_name): + conn = PQconnectdb(toclientstr("dbname = " + dbname)) + if (PQstatus(conn)): + raise Exception("COPY FROM STDIN PQconnectdb failed") + file.write(file_trailer) + file.seek(0) + sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')" + res = PQexec(conn, toclientstr(sql)) + if (PQresultStatus(res) != 4): + raise Exception("COPY FROM STDIN PQexec failed") + data = file.read(65536) + while (len(data)): + ret = PQputCopyData(conn, data, len(data)) + if (ret != 1): + raise Exception("COPY FROM STDIN PQputCopyData failed, error " + str(ret)) + data = file.read(65536) + ret = PQputCopyEnd(conn, None) + if (ret != 1): + raise Exception("COPY FROM STDIN PQputCopyEnd failed, error " + str(ret)) + PQfinish(conn) + +def remove_output_file(file): + name = file.name + file.close() + os.unlink(name) + +evsel_file = open_output_file("evsel_table.bin") +machine_file = open_output_file("machine_table.bin") +thread_file = open_output_file("thread_table.bin") +comm_file = open_output_file("comm_table.bin") +comm_thread_file = open_output_file("comm_thread_table.bin") +dso_file = open_output_file("dso_table.bin") +symbol_file = open_output_file("symbol_table.bin") +branch_type_file = open_output_file("branch_type_table.bin") +sample_file = open_output_file("sample_table.bin") +if perf_db_export_calls or perf_db_export_callchains: + call_path_file = open_output_file("call_path_table.bin") +if perf_db_export_calls: + call_file = open_output_file("call_table.bin") +ptwrite_file = open_output_file("ptwrite_table.bin") +cbr_file = open_output_file("cbr_table.bin") +mwait_file = open_output_file("mwait_table.bin") +pwre_file = open_output_file("pwre_table.bin") +exstop_file = open_output_file("exstop_table.bin") +pwrx_file = open_output_file("pwrx_table.bin") +context_switches_file = open_output_file("context_switches_table.bin") + +def trace_begin(): + printdate("Writing to intermediate files...") + # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs + evsel_table(0, "unknown") + machine_table(0, 0, "unknown") + thread_table(0, 0, 0, -1, -1) + comm_table(0, "unknown", 0, 0, 0) + dso_table(0, 0, "unknown", "unknown", "") + symbol_table(0, 0, 0, 0, 0, "unknown") + sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + if perf_db_export_calls or perf_db_export_callchains: + call_path_table(0, 0, 0, 0) + call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + +unhandled_count = 0 + +def is_table_empty(table_name): + do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1'); + if query.next(): + return False + return True + +def drop(table_name): + do_query(query, 'DROP VIEW ' + table_name + '_view'); + do_query(query, 'DROP TABLE ' + table_name); + +def trace_end(): + printdate("Copying to database...") + copy_output_file(evsel_file, "selected_events") + copy_output_file(machine_file, "machines") + copy_output_file(thread_file, "threads") + copy_output_file(comm_file, "comms") + copy_output_file(comm_thread_file, "comm_threads") + copy_output_file(dso_file, "dsos") + copy_output_file(symbol_file, "symbols") + copy_output_file(branch_type_file, "branch_types") + copy_output_file(sample_file, "samples") + if perf_db_export_calls or perf_db_export_callchains: + copy_output_file(call_path_file, "call_paths") + if perf_db_export_calls: + copy_output_file(call_file, "calls") + copy_output_file(ptwrite_file, "ptwrite") + copy_output_file(cbr_file, "cbr") + copy_output_file(mwait_file, "mwait") + copy_output_file(pwre_file, "pwre") + copy_output_file(exstop_file, "exstop") + copy_output_file(pwrx_file, "pwrx") + copy_output_file(context_switches_file, "context_switches") + + printdate("Removing intermediate files...") + remove_output_file(evsel_file) + remove_output_file(machine_file) + remove_output_file(thread_file) + remove_output_file(comm_file) + remove_output_file(comm_thread_file) + remove_output_file(dso_file) + remove_output_file(symbol_file) + remove_output_file(branch_type_file) + remove_output_file(sample_file) + if perf_db_export_calls or perf_db_export_callchains: + remove_output_file(call_path_file) + if perf_db_export_calls: + remove_output_file(call_file) + remove_output_file(ptwrite_file) + remove_output_file(cbr_file) + remove_output_file(mwait_file) + remove_output_file(pwre_file) + remove_output_file(exstop_file) + remove_output_file(pwrx_file) + remove_output_file(context_switches_file) + os.rmdir(output_dir_name) + printdate("Adding primary keys") + do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE comms ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE comm_threads ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE dsos ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)') + if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)') + if perf_db_export_calls: + do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE ptwrite ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE cbr ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE mwait ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE pwre ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE exstop ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE pwrx ADD PRIMARY KEY (id)') + do_query(query, 'ALTER TABLE context_switches ADD PRIMARY KEY (id)') + + printdate("Adding foreign keys") + do_query(query, 'ALTER TABLE threads ' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' + 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)') + do_query(query, 'ALTER TABLE comms ' + 'ADD CONSTRAINT threadfk FOREIGN KEY (c_thread_id) REFERENCES threads (id)') + do_query(query, 'ALTER TABLE comm_threads ' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id)') + do_query(query, 'ALTER TABLE dsos ' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id)') + do_query(query, 'ALTER TABLE symbols ' + 'ADD CONSTRAINT dsofk FOREIGN KEY (dso_id) REFERENCES dsos (id)') + do_query(query, 'ALTER TABLE samples ' + 'ADD CONSTRAINT evselfk FOREIGN KEY (evsel_id) REFERENCES selected_events (id),' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT dsofk FOREIGN KEY (dso_id) REFERENCES dsos (id),' + 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),' + 'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),' + 'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)') + if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'ALTER TABLE call_paths ' + 'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),' + 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)') + if perf_db_export_calls: + do_query(query, 'ALTER TABLE calls ' + 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),' + 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),' + 'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),' + 'ADD CONSTRAINT callfk FOREIGN KEY (call_id) REFERENCES samples (id),' + 'ADD CONSTRAINT returnfk FOREIGN KEY (return_id) REFERENCES samples (id),' + 'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)') + do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') + do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') + do_query(query, 'ALTER TABLE comms ADD has_calls boolean') + do_query(query, 'UPDATE comms SET has_calls = TRUE WHERE comms.id IN (SELECT DISTINCT comm_id FROM calls)') + do_query(query, 'ALTER TABLE ptwrite ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE cbr ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE mwait ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE pwre ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE exstop ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE pwrx ' + 'ADD CONSTRAINT idfk FOREIGN KEY (id) REFERENCES samples (id)') + do_query(query, 'ALTER TABLE context_switches ' + 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' + 'ADD CONSTRAINT toutfk FOREIGN KEY (thread_out_id) REFERENCES threads (id),' + 'ADD CONSTRAINT tinfk FOREIGN KEY (thread_in_id) REFERENCES threads (id),' + 'ADD CONSTRAINT coutfk FOREIGN KEY (comm_out_id) REFERENCES comms (id),' + 'ADD CONSTRAINT cinfk FOREIGN KEY (comm_in_id) REFERENCES comms (id)') + + printdate("Dropping unused tables") + if is_table_empty("ptwrite"): + drop("ptwrite") + if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"): + do_query(query, 'DROP VIEW power_events_view'); + drop("mwait") + drop("pwre") + drop("exstop") + drop("pwrx") + if is_table_empty("cbr"): + drop("cbr") + if is_table_empty("context_switches"): + drop("context_switches") + + if (unhandled_count): + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") + +def trace_unhandled(event_name, context, event_fields_dict): + global unhandled_count + unhandled_count += 1 + +def sched__sched_switch(*x): + pass + +def evsel_table(evsel_id, evsel_name, *x): + evsel_name = toserverstr(evsel_name) + n = len(evsel_name) + fmt = "!hiqi" + str(n) + "s" + value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name) + evsel_file.write(value) + +def machine_table(machine_id, pid, root_dir, *x): + root_dir = toserverstr(root_dir) + n = len(root_dir) + fmt = "!hiqiii" + str(n) + "s" + value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir) + machine_file.write(value) + +def thread_table(thread_id, machine_id, process_id, pid, tid, *x): + value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid) + thread_file.write(value) + +def comm_table(comm_id, comm_str, thread_id, time, exec_flag, *x): + comm_str = toserverstr(comm_str) + n = len(comm_str) + fmt = "!hiqi" + str(n) + "s" + "iqiqiB" + value = struct.pack(fmt, 5, 8, comm_id, n, comm_str, 8, thread_id, 8, time, 1, exec_flag) + comm_file.write(value) + +def comm_thread_table(comm_thread_id, comm_id, thread_id, *x): + fmt = "!hiqiqiq" + value = struct.pack(fmt, 3, 8, comm_thread_id, 8, comm_id, 8, thread_id) + comm_thread_file.write(value) + +def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): + short_name = toserverstr(short_name) + long_name = toserverstr(long_name) + build_id = toserverstr(build_id) + n1 = len(short_name) + n2 = len(long_name) + n3 = len(build_id) + fmt = "!hiqiqi" + str(n1) + "si" + str(n2) + "si" + str(n3) + "s" + value = struct.pack(fmt, 5, 8, dso_id, 8, machine_id, n1, short_name, n2, long_name, n3, build_id) + dso_file.write(value) + +def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x): + symbol_name = toserverstr(symbol_name) + n = len(symbol_name) + fmt = "!hiqiqiqiqiii" + str(n) + "s" + value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name) + symbol_file.write(value) + +def branch_type_table(branch_type, name, *x): + name = toserverstr(name) + n = len(name) + fmt = "!hiii" + str(n) + "s" + value = struct.pack(fmt, 2, 4, branch_type, n, name) + branch_type_file.write(value) + +def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, call_path_id, insn_cnt, cyc_cnt, flags, *x): + if branches: + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiBiqiqiqii", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt, 4, flags) + else: + value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiBiqiqiqii", 25, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx, 8, call_path_id, 8, insn_cnt, 8, cyc_cnt, 4, flags) + sample_file.write(value) + +def call_path_table(cp_id, parent_id, symbol_id, ip, *x): + fmt = "!hiqiqiqiq" + value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip) + call_path_file.write(value) + +def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, parent_id, insn_cnt, cyc_cnt, *x): + fmt = "!hiqiqiqiqiqiqiqiqiqiqiiiqiqiq" + value = struct.pack(fmt, 14, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags, 8, parent_id, 8, insn_cnt, 8, cyc_cnt) + call_file.write(value) + +def ptwrite(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + value = struct.pack("!hiqiqiB", 3, 8, id, 8, payload, 1, exact_ip) + ptwrite_file.write(value) + +def cbr(id, raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + MHz = (data[4] + 500) / 1000 + percent = ((cbr * 1000 / data[2]) + 5) / 10 + value = struct.pack("!hiqiiiiii", 4, 8, id, 4, cbr, 4, int(MHz), 4, int(percent)) + cbr_file.write(value) + +def mwait(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + value = struct.pack("!hiqiiii", 3, 8, id, 4, hints, 4, extensions) + mwait_file.write(value) + +def pwre(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + value = struct.pack("!hiqiiiiiB", 4, 8, id, 4, cstate, 4, subcstate, 1, hw) + pwre_file.write(value) + +def exstop(id, raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + value = struct.pack("!hiqiB", 2, 8, id, 1, exact_ip) + exstop_file.write(value) + +def pwrx(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + value = struct.pack("!hiqiiiiii", 4, 8, id, 4, deepest_cstate, 4, last_cstate, 4, wake_reason) + pwrx_file.write(value) + +def synth_data(id, config, raw_buf, *x): + if config == 0: + ptwrite(id, raw_buf) + elif config == 1: + mwait(id, raw_buf) + elif config == 2: + pwre(id, raw_buf) + elif config == 3: + exstop(id, raw_buf) + elif config == 4: + pwrx(id, raw_buf) + elif config == 5: + cbr(id, raw_buf) + +def context_switch_table(id, machine_id, time, cpu, thread_out_id, comm_out_id, thread_in_id, comm_in_id, flags, *x): + fmt = "!hiqiqiqiiiqiqiqiqii" + value = struct.pack(fmt, 9, 8, id, 8, machine_id, 8, time, 4, cpu, 8, thread_out_id, 8, comm_out_id, 8, thread_in_id, 8, comm_in_id, 4, flags) + context_switches_file.write(value) diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py new file mode 100644 index 000000000..73c992feb --- /dev/null +++ b/tools/perf/scripts/python/export-to-sqlite.py @@ -0,0 +1,799 @@ +# export-to-sqlite.py: export perf data to a sqlite3 database +# Copyright (c) 2017, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +from __future__ import print_function + +import os +import sys +import struct +import datetime + +# To use this script you will need to have installed package python-pyside which +# provides LGPL-licensed Python bindings for Qt. You will also need the package +# libqt4-sql-sqlite for Qt sqlite3 support. +# +# Examples of installing pyside: +# +# ubuntu: +# +# $ sudo apt-get install python-pyside.qtsql libqt4-sql-psql +# +# Alternately, to use Python3 and/or pyside 2, one of the following: +# +# $ sudo apt-get install python3-pyside.qtsql libqt4-sql-psql +# $ sudo apt-get install python-pyside2.qtsql libqt5sql5-psql +# $ sudo apt-get install python3-pyside2.qtsql libqt5sql5-psql +# fedora: +# +# $ sudo yum install python-pyside +# +# Alternately, to use Python3 and/or pyside 2, one of the following: +# $ sudo yum install python3-pyside +# $ pip install --user PySide2 +# $ pip3 install --user PySide2 +# +# An example of using this script with Intel PT: +# +# $ perf record -e intel_pt//u ls +# $ perf script -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py pt_example branches calls +# 2017-07-31 14:26:07.326913 Creating database... +# 2017-07-31 14:26:07.538097 Writing records... +# 2017-07-31 14:26:09.889292 Adding indexes +# 2017-07-31 14:26:09.958746 Done +# +# To browse the database, sqlite3 can be used e.g. +# +# $ sqlite3 pt_example +# sqlite> .header on +# sqlite> select * from samples_view where id < 10; +# sqlite> .mode column +# sqlite> select * from samples_view where id < 10; +# sqlite> .tables +# sqlite> .schema samples_view +# sqlite> .quit +# +# An example of using the database is provided by the script +# exported-sql-viewer.py. Refer to that script for details. +# +# The database structure is practically the same as created by the script +# export-to-postgresql.py. Refer to that script for details. A notable +# difference is the 'transaction' column of the 'samples' table which is +# renamed 'transaction_' in sqlite because 'transaction' is a reserved word. + +pyside_version_1 = True +if not "pyside-version-1" in sys.argv: + try: + from PySide2.QtSql import * + pyside_version_1 = False + except: + pass + +if pyside_version_1: + from PySide.QtSql import * + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +# These perf imports are not used at present +#from perf_trace_context import * +#from Core import * + +perf_db_export_mode = True +perf_db_export_calls = False +perf_db_export_callchains = False + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + +def usage(): + printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>] [<pyside-version-1>]"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); + printerr(" pyside-version-1 'pyside-version-1' => use pyside version 1"); + raise Exception("Too few or bad arguments") + +if (len(sys.argv) < 2): + usage() + +dbname = sys.argv[1] + +if (len(sys.argv) >= 3): + columns = sys.argv[2] +else: + columns = "all" + +if columns not in ("all", "branches"): + usage() + +branches = (columns == "branches") + +for i in range(3,len(sys.argv)): + if (sys.argv[i] == "calls"): + perf_db_export_calls = True + elif (sys.argv[i] == "callchains"): + perf_db_export_callchains = True + elif (sys.argv[i] == "pyside-version-1"): + pass + else: + usage() + +def do_query(q, s): + if (q.exec_(s)): + return + raise Exception("Query failed: " + q.lastError().text()) + +def do_query_(q): + if (q.exec_()): + return + raise Exception("Query failed: " + q.lastError().text()) + +printdate("Creating database ...") + +db_exists = False +try: + f = open(dbname) + f.close() + db_exists = True +except: + pass + +if db_exists: + raise Exception(dbname + " already exists") + +db = QSqlDatabase.addDatabase('QSQLITE') +db.setDatabaseName(dbname) +db.open() + +query = QSqlQuery(db) + +do_query(query, 'PRAGMA journal_mode = OFF') +do_query(query, 'BEGIN TRANSACTION') + +do_query(query, 'CREATE TABLE selected_events (' + 'id integer NOT NULL PRIMARY KEY,' + 'name varchar(80))') +do_query(query, 'CREATE TABLE machines (' + 'id integer NOT NULL PRIMARY KEY,' + 'pid integer,' + 'root_dir varchar(4096))') +do_query(query, 'CREATE TABLE threads (' + 'id integer NOT NULL PRIMARY KEY,' + 'machine_id bigint,' + 'process_id bigint,' + 'pid integer,' + 'tid integer)') +do_query(query, 'CREATE TABLE comms (' + 'id integer NOT NULL PRIMARY KEY,' + 'comm varchar(16),' + 'c_thread_id bigint,' + 'c_time bigint,' + 'exec_flag boolean)') +do_query(query, 'CREATE TABLE comm_threads (' + 'id integer NOT NULL PRIMARY KEY,' + 'comm_id bigint,' + 'thread_id bigint)') +do_query(query, 'CREATE TABLE dsos (' + 'id integer NOT NULL PRIMARY KEY,' + 'machine_id bigint,' + 'short_name varchar(256),' + 'long_name varchar(4096),' + 'build_id varchar(64))') +do_query(query, 'CREATE TABLE symbols (' + 'id integer NOT NULL PRIMARY KEY,' + 'dso_id bigint,' + 'sym_start bigint,' + 'sym_end bigint,' + 'binding integer,' + 'name varchar(2048))') +do_query(query, 'CREATE TABLE branch_types (' + 'id integer NOT NULL PRIMARY KEY,' + 'name varchar(80))') + +if branches: + do_query(query, 'CREATE TABLE samples (' + 'id integer NOT NULL PRIMARY KEY,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint,' + 'flags integer)') +else: + do_query(query, 'CREATE TABLE samples (' + 'id integer NOT NULL PRIMARY KEY,' + 'evsel_id bigint,' + 'machine_id bigint,' + 'thread_id bigint,' + 'comm_id bigint,' + 'dso_id bigint,' + 'symbol_id bigint,' + 'sym_offset bigint,' + 'ip bigint,' + 'time bigint,' + 'cpu integer,' + 'to_dso_id bigint,' + 'to_symbol_id bigint,' + 'to_sym_offset bigint,' + 'to_ip bigint,' + 'period bigint,' + 'weight bigint,' + 'transaction_ bigint,' + 'data_src bigint,' + 'branch_type integer,' + 'in_tx boolean,' + 'call_path_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint,' + 'flags integer)') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE TABLE call_paths (' + 'id integer NOT NULL PRIMARY KEY,' + 'parent_id bigint,' + 'symbol_id bigint,' + 'ip bigint)') +if perf_db_export_calls: + do_query(query, 'CREATE TABLE calls (' + 'id integer NOT NULL PRIMARY KEY,' + 'thread_id bigint,' + 'comm_id bigint,' + 'call_path_id bigint,' + 'call_time bigint,' + 'return_time bigint,' + 'branch_count bigint,' + 'call_id bigint,' + 'return_id bigint,' + 'parent_call_path_id bigint,' + 'flags integer,' + 'parent_id bigint,' + 'insn_count bigint,' + 'cyc_count bigint)') + +do_query(query, 'CREATE TABLE ptwrite (' + 'id integer NOT NULL PRIMARY KEY,' + 'payload bigint,' + 'exact_ip integer)') + +do_query(query, 'CREATE TABLE cbr (' + 'id integer NOT NULL PRIMARY KEY,' + 'cbr integer,' + 'mhz integer,' + 'percent integer)') + +do_query(query, 'CREATE TABLE mwait (' + 'id integer NOT NULL PRIMARY KEY,' + 'hints integer,' + 'extensions integer)') + +do_query(query, 'CREATE TABLE pwre (' + 'id integer NOT NULL PRIMARY KEY,' + 'cstate integer,' + 'subcstate integer,' + 'hw integer)') + +do_query(query, 'CREATE TABLE exstop (' + 'id integer NOT NULL PRIMARY KEY,' + 'exact_ip integer)') + +do_query(query, 'CREATE TABLE pwrx (' + 'id integer NOT NULL PRIMARY KEY,' + 'deepest_cstate integer,' + 'last_cstate integer,' + 'wake_reason integer)') + +do_query(query, 'CREATE TABLE context_switches (' + 'id integer NOT NULL PRIMARY KEY,' + 'machine_id bigint,' + 'time bigint,' + 'cpu integer,' + 'thread_out_id bigint,' + 'comm_out_id bigint,' + 'thread_in_id bigint,' + 'comm_in_id bigint,' + 'flags integer)') + +# printf was added to sqlite in version 3.8.3 +sqlite_has_printf = False +try: + do_query(query, 'SELECT printf("") FROM machines') + sqlite_has_printf = True +except: + pass + +def emit_to_hex(x): + if sqlite_has_printf: + return 'printf("%x", ' + x + ')' + else: + return x + +do_query(query, 'CREATE VIEW machines_view AS ' + 'SELECT ' + 'id,' + 'pid,' + 'root_dir,' + 'CASE WHEN id=0 THEN \'unknown\' WHEN pid=-1 THEN \'host\' ELSE \'guest\' END AS host_or_guest' + ' FROM machines') + +do_query(query, 'CREATE VIEW dsos_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'short_name,' + 'long_name,' + 'build_id' + ' FROM dsos') + +do_query(query, 'CREATE VIEW symbols_view AS ' + 'SELECT ' + 'id,' + 'name,' + '(SELECT short_name FROM dsos WHERE id=dso_id) AS dso,' + 'dso_id,' + 'sym_start,' + 'sym_end,' + 'CASE WHEN binding=0 THEN \'local\' WHEN binding=1 THEN \'global\' ELSE \'weak\' END AS binding' + ' FROM symbols') + +do_query(query, 'CREATE VIEW threads_view AS ' + 'SELECT ' + 'id,' + 'machine_id,' + '(SELECT host_or_guest FROM machines_view WHERE id = machine_id) AS host_or_guest,' + 'process_id,' + 'pid,' + 'tid' + ' FROM threads') + +do_query(query, 'CREATE VIEW comm_threads_view AS ' + 'SELECT ' + 'comm_id,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid' + ' FROM comm_threads') + +if perf_db_export_calls or perf_db_export_callchains: + do_query(query, 'CREATE VIEW call_paths_view AS ' + 'SELECT ' + 'c.id,' + + emit_to_hex('c.ip') + ' AS ip,' + 'c.symbol_id,' + '(SELECT name FROM symbols WHERE id = c.symbol_id) AS symbol,' + '(SELECT dso_id FROM symbols WHERE id = c.symbol_id) AS dso_id,' + '(SELECT dso FROM symbols_view WHERE id = c.symbol_id) AS dso_short_name,' + 'c.parent_id,' + + emit_to_hex('p.ip') + ' AS parent_ip,' + 'p.symbol_id AS parent_symbol_id,' + '(SELECT name FROM symbols WHERE id = p.symbol_id) AS parent_symbol,' + '(SELECT dso_id FROM symbols WHERE id = p.symbol_id) AS parent_dso_id,' + '(SELECT dso FROM symbols_view WHERE id = p.symbol_id) AS parent_dso_short_name' + ' FROM call_paths c INNER JOIN call_paths p ON p.id = c.parent_id') +if perf_db_export_calls: + do_query(query, 'CREATE VIEW calls_view AS ' + 'SELECT ' + 'calls.id,' + 'thread_id,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + 'call_path_id,' + + emit_to_hex('ip') + ' AS ip,' + 'symbol_id,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'call_time,' + 'return_time,' + 'return_time - call_time AS elapsed_time,' + 'branch_count,' + 'insn_count,' + 'cyc_count,' + 'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,' + 'call_id,' + 'return_id,' + 'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,' + 'parent_call_path_id,' + 'calls.parent_id' + ' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id') + +do_query(query, 'CREATE VIEW samples_view AS ' + 'SELECT ' + 'id,' + 'time,' + 'cpu,' + '(SELECT pid FROM threads WHERE id = thread_id) AS pid,' + '(SELECT tid FROM threads WHERE id = thread_id) AS tid,' + '(SELECT comm FROM comms WHERE id = comm_id) AS command,' + '(SELECT name FROM selected_events WHERE id = evsel_id) AS event,' + + emit_to_hex('ip') + ' AS ip_hex,' + '(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,' + 'sym_offset,' + '(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,' + + emit_to_hex('to_ip') + ' AS to_ip_hex,' + '(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,' + 'to_sym_offset,' + '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,' + '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,' + 'in_tx,' + 'insn_count,' + 'cyc_count,' + 'CASE WHEN cyc_count=0 THEN CAST(0 AS FLOAT) ELSE ROUND(CAST(insn_count AS FLOAT) / cyc_count, 2) END AS IPC,' + 'flags' + ' FROM samples') + +do_query(query, 'CREATE VIEW ptwrite_view AS ' + 'SELECT ' + 'ptwrite.id,' + 'time,' + 'cpu,' + + emit_to_hex('payload') + ' AS payload_hex,' + 'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip' + ' FROM ptwrite' + ' INNER JOIN samples ON samples.id = ptwrite.id') + +do_query(query, 'CREATE VIEW cbr_view AS ' + 'SELECT ' + 'cbr.id,' + 'time,' + 'cpu,' + 'cbr,' + 'mhz,' + 'percent' + ' FROM cbr' + ' INNER JOIN samples ON samples.id = cbr.id') + +do_query(query, 'CREATE VIEW mwait_view AS ' + 'SELECT ' + 'mwait.id,' + 'time,' + 'cpu,' + + emit_to_hex('hints') + ' AS hints_hex,' + + emit_to_hex('extensions') + ' AS extensions_hex' + ' FROM mwait' + ' INNER JOIN samples ON samples.id = mwait.id') + +do_query(query, 'CREATE VIEW pwre_view AS ' + 'SELECT ' + 'pwre.id,' + 'time,' + 'cpu,' + 'cstate,' + 'subcstate,' + 'CASE WHEN hw=0 THEN \'False\' ELSE \'True\' END AS hw' + ' FROM pwre' + ' INNER JOIN samples ON samples.id = pwre.id') + +do_query(query, 'CREATE VIEW exstop_view AS ' + 'SELECT ' + 'exstop.id,' + 'time,' + 'cpu,' + 'CASE WHEN exact_ip=0 THEN \'False\' ELSE \'True\' END AS exact_ip' + ' FROM exstop' + ' INNER JOIN samples ON samples.id = exstop.id') + +do_query(query, 'CREATE VIEW pwrx_view AS ' + 'SELECT ' + 'pwrx.id,' + 'time,' + 'cpu,' + 'deepest_cstate,' + 'last_cstate,' + 'CASE WHEN wake_reason=1 THEN \'Interrupt\'' + ' WHEN wake_reason=2 THEN \'Timer Deadline\'' + ' WHEN wake_reason=4 THEN \'Monitored Address\'' + ' WHEN wake_reason=8 THEN \'HW\'' + ' ELSE wake_reason ' + 'END AS wake_reason' + ' FROM pwrx' + ' INNER JOIN samples ON samples.id = pwrx.id') + +do_query(query, 'CREATE VIEW power_events_view AS ' + 'SELECT ' + 'samples.id,' + 'time,' + 'cpu,' + 'selected_events.name AS event,' + 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT cbr FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS cbr,' + 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT mhz FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS mhz,' + 'CASE WHEN selected_events.name=\'cbr\' THEN (SELECT percent FROM cbr WHERE cbr.id = samples.id) ELSE "" END AS percent,' + 'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('hints') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS hints_hex,' + 'CASE WHEN selected_events.name=\'mwait\' THEN (SELECT ' + emit_to_hex('extensions') + ' FROM mwait WHERE mwait.id = samples.id) ELSE "" END AS extensions_hex,' + 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT cstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS cstate,' + 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT subcstate FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS subcstate,' + 'CASE WHEN selected_events.name=\'pwre\' THEN (SELECT hw FROM pwre WHERE pwre.id = samples.id) ELSE "" END AS hw,' + 'CASE WHEN selected_events.name=\'exstop\' THEN (SELECT exact_ip FROM exstop WHERE exstop.id = samples.id) ELSE "" END AS exact_ip,' + 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT deepest_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS deepest_cstate,' + 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT last_cstate FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS last_cstate,' + 'CASE WHEN selected_events.name=\'pwrx\' THEN (SELECT ' + 'CASE WHEN wake_reason=1 THEN \'Interrupt\'' + ' WHEN wake_reason=2 THEN \'Timer Deadline\'' + ' WHEN wake_reason=4 THEN \'Monitored Address\'' + ' WHEN wake_reason=8 THEN \'HW\'' + ' ELSE wake_reason ' + 'END' + ' FROM pwrx WHERE pwrx.id = samples.id) ELSE "" END AS wake_reason' + ' FROM samples' + ' INNER JOIN selected_events ON selected_events.id = evsel_id' + ' WHERE selected_events.name IN (\'cbr\',\'mwait\',\'exstop\',\'pwre\',\'pwrx\')') + +do_query(query, 'CREATE VIEW context_switches_view AS ' + 'SELECT ' + 'context_switches.id,' + 'context_switches.machine_id,' + 'context_switches.time,' + 'context_switches.cpu,' + 'th_out.pid AS pid_out,' + 'th_out.tid AS tid_out,' + 'comm_out.comm AS comm_out,' + 'th_in.pid AS pid_in,' + 'th_in.tid AS tid_in,' + 'comm_in.comm AS comm_in,' + 'CASE WHEN context_switches.flags = 0 THEN \'in\'' + ' WHEN context_switches.flags = 1 THEN \'out\'' + ' WHEN context_switches.flags = 3 THEN \'out preempt\'' + ' ELSE context_switches.flags ' + 'END AS flags' + ' FROM context_switches' + ' INNER JOIN threads AS th_out ON th_out.id = context_switches.thread_out_id' + ' INNER JOIN threads AS th_in ON th_in.id = context_switches.thread_in_id' + ' INNER JOIN comms AS comm_out ON comm_out.id = context_switches.comm_out_id' + ' INNER JOIN comms AS comm_in ON comm_in.id = context_switches.comm_in_id') + +do_query(query, 'END TRANSACTION') + +evsel_query = QSqlQuery(db) +evsel_query.prepare("INSERT INTO selected_events VALUES (?, ?)") +machine_query = QSqlQuery(db) +machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)") +thread_query = QSqlQuery(db) +thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)") +comm_query = QSqlQuery(db) +comm_query.prepare("INSERT INTO comms VALUES (?, ?, ?, ?, ?)") +comm_thread_query = QSqlQuery(db) +comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)") +dso_query = QSqlQuery(db) +dso_query.prepare("INSERT INTO dsos VALUES (?, ?, ?, ?, ?)") +symbol_query = QSqlQuery(db) +symbol_query.prepare("INSERT INTO symbols VALUES (?, ?, ?, ?, ?, ?)") +branch_type_query = QSqlQuery(db) +branch_type_query.prepare("INSERT INTO branch_types VALUES (?, ?)") +sample_query = QSqlQuery(db) +if branches: + sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") +else: + sample_query.prepare("INSERT INTO samples VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") +if perf_db_export_calls or perf_db_export_callchains: + call_path_query = QSqlQuery(db) + call_path_query.prepare("INSERT INTO call_paths VALUES (?, ?, ?, ?)") +if perf_db_export_calls: + call_query = QSqlQuery(db) + call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") +ptwrite_query = QSqlQuery(db) +ptwrite_query.prepare("INSERT INTO ptwrite VALUES (?, ?, ?)") +cbr_query = QSqlQuery(db) +cbr_query.prepare("INSERT INTO cbr VALUES (?, ?, ?, ?)") +mwait_query = QSqlQuery(db) +mwait_query.prepare("INSERT INTO mwait VALUES (?, ?, ?)") +pwre_query = QSqlQuery(db) +pwre_query.prepare("INSERT INTO pwre VALUES (?, ?, ?, ?)") +exstop_query = QSqlQuery(db) +exstop_query.prepare("INSERT INTO exstop VALUES (?, ?)") +pwrx_query = QSqlQuery(db) +pwrx_query.prepare("INSERT INTO pwrx VALUES (?, ?, ?, ?)") +context_switch_query = QSqlQuery(db) +context_switch_query.prepare("INSERT INTO context_switches VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)") + +def trace_begin(): + printdate("Writing records...") + do_query(query, 'BEGIN TRANSACTION') + # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs + evsel_table(0, "unknown") + machine_table(0, 0, "unknown") + thread_table(0, 0, 0, -1, -1) + comm_table(0, "unknown", 0, 0, 0) + dso_table(0, 0, "unknown", "unknown", "") + symbol_table(0, 0, 0, 0, 0, "unknown") + sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + if perf_db_export_calls or perf_db_export_callchains: + call_path_table(0, 0, 0, 0) + call_return_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) + +unhandled_count = 0 + +def is_table_empty(table_name): + do_query(query, 'SELECT * FROM ' + table_name + ' LIMIT 1'); + if query.next(): + return False + return True + +def drop(table_name): + do_query(query, 'DROP VIEW ' + table_name + '_view'); + do_query(query, 'DROP TABLE ' + table_name); + +def trace_end(): + do_query(query, 'END TRANSACTION') + + printdate("Adding indexes") + if perf_db_export_calls: + do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') + do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') + do_query(query, 'ALTER TABLE comms ADD has_calls boolean') + do_query(query, 'UPDATE comms SET has_calls = 1 WHERE comms.id IN (SELECT DISTINCT comm_id FROM calls)') + + printdate("Dropping unused tables") + if is_table_empty("ptwrite"): + drop("ptwrite") + if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"): + do_query(query, 'DROP VIEW power_events_view'); + drop("mwait") + drop("pwre") + drop("exstop") + drop("pwrx") + if is_table_empty("cbr"): + drop("cbr") + if is_table_empty("context_switches"): + drop("context_switches") + + if (unhandled_count): + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") + +def trace_unhandled(event_name, context, event_fields_dict): + global unhandled_count + unhandled_count += 1 + +def sched__sched_switch(*x): + pass + +def bind_exec(q, n, x): + for xx in x[0:n]: + q.addBindValue(str(xx)) + do_query_(q) + +def evsel_table(*x): + bind_exec(evsel_query, 2, x) + +def machine_table(*x): + bind_exec(machine_query, 3, x) + +def thread_table(*x): + bind_exec(thread_query, 5, x) + +def comm_table(*x): + bind_exec(comm_query, 5, x) + +def comm_thread_table(*x): + bind_exec(comm_thread_query, 3, x) + +def dso_table(*x): + bind_exec(dso_query, 5, x) + +def symbol_table(*x): + bind_exec(symbol_query, 6, x) + +def branch_type_table(*x): + bind_exec(branch_type_query, 2, x) + +def sample_table(*x): + if branches: + for xx in x[0:15]: + sample_query.addBindValue(str(xx)) + for xx in x[19:25]: + sample_query.addBindValue(str(xx)) + do_query_(sample_query) + else: + bind_exec(sample_query, 25, x) + +def call_path_table(*x): + bind_exec(call_path_query, 4, x) + +def call_return_table(*x): + bind_exec(call_query, 14, x) + +def ptwrite(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + ptwrite_query.addBindValue(str(id)) + ptwrite_query.addBindValue(str(payload)) + ptwrite_query.addBindValue(str(exact_ip)) + do_query_(ptwrite_query) + +def cbr(id, raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + MHz = (data[4] + 500) / 1000 + percent = ((cbr * 1000 / data[2]) + 5) / 10 + cbr_query.addBindValue(str(id)) + cbr_query.addBindValue(str(cbr)) + cbr_query.addBindValue(str(MHz)) + cbr_query.addBindValue(str(percent)) + do_query_(cbr_query) + +def mwait(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + mwait_query.addBindValue(str(id)) + mwait_query.addBindValue(str(hints)) + mwait_query.addBindValue(str(extensions)) + do_query_(mwait_query) + +def pwre(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + pwre_query.addBindValue(str(id)) + pwre_query.addBindValue(str(cstate)) + pwre_query.addBindValue(str(subcstate)) + pwre_query.addBindValue(str(hw)) + do_query_(pwre_query) + +def exstop(id, raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + exstop_query.addBindValue(str(id)) + exstop_query.addBindValue(str(exact_ip)) + do_query_(exstop_query) + +def pwrx(id, raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + pwrx_query.addBindValue(str(id)) + pwrx_query.addBindValue(str(deepest_cstate)) + pwrx_query.addBindValue(str(last_cstate)) + pwrx_query.addBindValue(str(wake_reason)) + do_query_(pwrx_query) + +def synth_data(id, config, raw_buf, *x): + if config == 0: + ptwrite(id, raw_buf) + elif config == 1: + mwait(id, raw_buf) + elif config == 2: + pwre(id, raw_buf) + elif config == 3: + exstop(id, raw_buf) + elif config == 4: + pwrx(id, raw_buf) + elif config == 5: + cbr(id, raw_buf) + +def context_switch_table(*x): + bind_exec(context_switch_query, 9, x) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py new file mode 100755 index 000000000..13f2d8a81 --- /dev/null +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -0,0 +1,5027 @@ +#!/usr/bin/env python +# SPDX-License-Identifier: GPL-2.0 +# exported-sql-viewer.py: view data from sql database +# Copyright (c) 2014-2018, Intel Corporation. + +# To use this script you will need to have exported data using either the +# export-to-sqlite.py or the export-to-postgresql.py script. Refer to those +# scripts for details. +# +# Following on from the example in the export scripts, a +# call-graph can be displayed for the pt_example database like this: +# +# python tools/perf/scripts/python/exported-sql-viewer.py pt_example +# +# Note that for PostgreSQL, this script supports connecting to remote databases +# by setting hostname, port, username, password, and dbname e.g. +# +# python tools/perf/scripts/python/exported-sql-viewer.py "hostname=myhost username=myuser password=mypassword dbname=pt_example" +# +# The result is a GUI window with a tree representing a context-sensitive +# call-graph. Expanding a couple of levels of the tree and adjusting column +# widths to suit will display something like: +# +# Call Graph: pt_example +# Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +# v- ls +# v- 2638:2638 +# v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 +# |- unknown unknown 1 13198 0.1 1 0.0 +# >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 +# >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 +# v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 +# >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 +# >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 +# >- __libc_csu_init ls 1 10354 0.1 10 0.0 +# |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 +# v- main ls 1 8182043 99.6 180254 99.9 +# +# Points to note: +# The top level is a command name (comm) +# The next level is a thread (pid:tid) +# Subsequent levels are functions +# 'Count' is the number of calls +# 'Time' is the elapsed time until the function returns +# Percentages are relative to the level above +# 'Branch Count' is the total number of branches for that function and all +# functions that it calls + +# There is also a "All branches" report, which displays branches and +# possibly disassembly. However, presently, the only supported disassembler is +# Intel XED, and additionally the object code must be present in perf build ID +# cache. To use Intel XED, libxed.so must be present. To build and install +# libxed.so: +# git clone https://github.com/intelxed/mbuild.git mbuild +# git clone https://github.com/intelxed/xed +# cd xed +# ./mfile.py --share +# sudo ./mfile.py --prefix=/usr/local install +# sudo ldconfig +# +# Example report: +# +# Time CPU Command PID TID Branch Type In Tx Branch +# 8107675239590 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so) +# 7fab593ea260 48 89 e7 mov %rsp, %rdi +# 8107675239899 2 ls 22011 22011 hardware interrupt No 7fab593ea260 _start (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +# 8107675241900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea260 _start (ld-2.19.so) +# 7fab593ea260 48 89 e7 mov %rsp, %rdi +# 7fab593ea263 e8 c8 06 00 00 callq 0x7fab593ea930 +# 8107675241900 2 ls 22011 22011 call No 7fab593ea263 _start+0x3 (ld-2.19.so) -> 7fab593ea930 _dl_start (ld-2.19.so) +# 7fab593ea930 55 pushq %rbp +# 7fab593ea931 48 89 e5 mov %rsp, %rbp +# 7fab593ea934 41 57 pushq %r15 +# 7fab593ea936 41 56 pushq %r14 +# 7fab593ea938 41 55 pushq %r13 +# 7fab593ea93a 41 54 pushq %r12 +# 7fab593ea93c 53 pushq %rbx +# 7fab593ea93d 48 89 fb mov %rdi, %rbx +# 7fab593ea940 48 83 ec 68 sub $0x68, %rsp +# 7fab593ea944 0f 31 rdtsc +# 7fab593ea946 48 c1 e2 20 shl $0x20, %rdx +# 7fab593ea94a 89 c0 mov %eax, %eax +# 7fab593ea94c 48 09 c2 or %rax, %rdx +# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax +# 8107675242232 2 ls 22011 22011 hardware interrupt No 7fab593ea94f _dl_start+0x1f (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +# 8107675242900 2 ls 22011 22011 return from interrupt No ffffffff86a00a67 native_irq_return_iret ([kernel]) -> 7fab593ea94f _dl_start+0x1f (ld-2.19.so) +# 7fab593ea94f 48 8b 05 1a 15 22 00 movq 0x22151a(%rip), %rax +# 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip) +# 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) + +from __future__ import print_function + +import sys +# Only change warnings if the python -W option was not used +if not sys.warnoptions: + import warnings + # PySide2 causes deprecation warnings, ignore them. + warnings.filterwarnings("ignore", category=DeprecationWarning) +import argparse +import weakref +import threading +import string +try: + # Python2 + import cPickle as pickle + # size of pickled integer big enough for record size + glb_nsz = 8 +except ImportError: + import pickle + glb_nsz = 16 +import re +import os +import random +import copy +import math +from libxed import LibXED + +pyside_version_1 = True +if not "--pyside-version-1" in sys.argv: + try: + from PySide2.QtCore import * + from PySide2.QtGui import * + from PySide2.QtSql import * + from PySide2.QtWidgets import * + pyside_version_1 = False + except: + pass + +if pyside_version_1: + from PySide.QtCore import * + from PySide.QtGui import * + from PySide.QtSql import * + +from decimal import Decimal, ROUND_HALF_UP +from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong +from multiprocessing import Process, Array, Value, Event + +# xrange is range in Python3 +try: + xrange +except NameError: + xrange = range + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + +# Data formatting helpers + +def tohex(ip): + if ip < 0: + ip += 1 << 64 + return "%x" % ip + +def offstr(offset): + if offset: + return "+0x%x" % offset + return "" + +def dsoname(name): + if name == "[kernel.kallsyms]": + return "[kernel]" + return name + +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + +# Percent to one decimal place + +def PercentToOneDP(n, d): + if not d: + return "0.0" + x = (n * Decimal(100)) / d + return str(x.quantize(Decimal(".1"), rounding=ROUND_HALF_UP)) + +# Helper for queries that must not fail + +def QueryExec(query, stmt): + ret = query.exec_(stmt) + if not ret: + raise Exception("Query failed: " + query.lastError().text()) + +# Background thread + +class Thread(QThread): + + done = Signal(object) + + def __init__(self, task, param=None, parent=None): + super(Thread, self).__init__(parent) + self.task = task + self.param = param + + def run(self): + while True: + if self.param is None: + done, result = self.task() + else: + done, result = self.task(self.param) + self.done.emit(result) + if done: + break + +# Tree data model + +class TreeModel(QAbstractItemModel): + + def __init__(self, glb, params, parent=None): + super(TreeModel, self).__init__(parent) + self.glb = glb + self.params = params + self.root = self.GetRoot() + self.last_row_read = 0 + + def Item(self, parent): + if parent.isValid(): + return parent.internalPointer() + else: + return self.root + + def rowCount(self, parent): + result = self.Item(parent).childCount() + if result < 0: + result = 0 + self.dataChanged.emit(parent, parent) + return result + + def hasChildren(self, parent): + return self.Item(parent).hasChildren() + + def headerData(self, section, orientation, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(section) + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def parent(self, child): + child_item = child.internalPointer() + if child_item is self.root: + return QModelIndex() + parent_item = child_item.getParentItem() + return self.createIndex(parent_item.getRow(), 0, parent_item) + + def index(self, row, column, parent): + child_item = self.Item(parent).getChildItem(row) + return self.createIndex(row, column, child_item) + + def DisplayData(self, item, index): + return item.getData(index.column()) + + def FetchIfNeeded(self, row): + if row > self.last_row_read: + self.last_row_read = row + if row + 10 >= self.root.child_count: + self.fetcher.Fetch(glb_chunk_sz) + + def columnAlignment(self, column): + return Qt.AlignLeft + + def columnFont(self, column): + return None + + def data(self, index, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(index.column()) + if role == Qt.FontRole: + return self.columnFont(index.column()) + if role != Qt.DisplayRole: + return None + item = index.internalPointer() + return self.DisplayData(item, index) + +# Table data model + +class TableModel(QAbstractTableModel): + + def __init__(self, parent=None): + super(TableModel, self).__init__(parent) + self.child_count = 0 + self.child_items = [] + self.last_row_read = 0 + + def Item(self, parent): + if parent.isValid(): + return parent.internalPointer() + else: + return self + + def rowCount(self, parent): + return self.child_count + + def headerData(self, section, orientation, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(section) + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def index(self, row, column, parent): + return self.createIndex(row, column, self.child_items[row]) + + def DisplayData(self, item, index): + return item.getData(index.column()) + + def FetchIfNeeded(self, row): + if row > self.last_row_read: + self.last_row_read = row + if row + 10 >= self.child_count: + self.fetcher.Fetch(glb_chunk_sz) + + def columnAlignment(self, column): + return Qt.AlignLeft + + def columnFont(self, column): + return None + + def data(self, index, role): + if role == Qt.TextAlignmentRole: + return self.columnAlignment(index.column()) + if role == Qt.FontRole: + return self.columnFont(index.column()) + if role != Qt.DisplayRole: + return None + item = index.internalPointer() + return self.DisplayData(item, index) + +# Model cache + +model_cache = weakref.WeakValueDictionary() +model_cache_lock = threading.Lock() + +def LookupCreateModel(model_name, create_fn): + model_cache_lock.acquire() + try: + model = model_cache[model_name] + except: + model = None + if model is None: + model = create_fn() + model_cache[model_name] = model + model_cache_lock.release() + return model + +def LookupModel(model_name): + model_cache_lock.acquire() + try: + model = model_cache[model_name] + except: + model = None + model_cache_lock.release() + return model + +# Find bar + +class FindBar(): + + def __init__(self, parent, finder, is_reg_expr=False): + self.finder = finder + self.context = [] + self.last_value = None + self.last_pattern = None + + label = QLabel("Find:") + label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.textbox = QComboBox() + self.textbox.setEditable(True) + self.textbox.currentIndexChanged.connect(self.ValueChanged) + + self.progress = QProgressBar() + self.progress.setRange(0, 0) + self.progress.hide() + + if is_reg_expr: + self.pattern = QCheckBox("Regular Expression") + else: + self.pattern = QCheckBox("Pattern") + self.pattern.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.next_button = QToolButton() + self.next_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowDown)) + self.next_button.released.connect(lambda: self.NextPrev(1)) + + self.prev_button = QToolButton() + self.prev_button.setIcon(parent.style().standardIcon(QStyle.SP_ArrowUp)) + self.prev_button.released.connect(lambda: self.NextPrev(-1)) + + self.close_button = QToolButton() + self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton)) + self.close_button.released.connect(self.Deactivate) + + self.hbox = QHBoxLayout() + self.hbox.setContentsMargins(0, 0, 0, 0) + + self.hbox.addWidget(label) + self.hbox.addWidget(self.textbox) + self.hbox.addWidget(self.progress) + self.hbox.addWidget(self.pattern) + self.hbox.addWidget(self.next_button) + self.hbox.addWidget(self.prev_button) + self.hbox.addWidget(self.close_button) + + self.bar = QWidget() + self.bar.setLayout(self.hbox) + self.bar.hide() + + def Widget(self): + return self.bar + + def Activate(self): + self.bar.show() + self.textbox.lineEdit().selectAll() + self.textbox.setFocus() + + def Deactivate(self): + self.bar.hide() + + def Busy(self): + self.textbox.setEnabled(False) + self.pattern.hide() + self.next_button.hide() + self.prev_button.hide() + self.progress.show() + + def Idle(self): + self.textbox.setEnabled(True) + self.progress.hide() + self.pattern.show() + self.next_button.show() + self.prev_button.show() + + def Find(self, direction): + value = self.textbox.currentText() + pattern = self.pattern.isChecked() + self.last_value = value + self.last_pattern = pattern + self.finder.Find(value, direction, pattern, self.context) + + def ValueChanged(self): + value = self.textbox.currentText() + pattern = self.pattern.isChecked() + index = self.textbox.currentIndex() + data = self.textbox.itemData(index) + # Store the pattern in the combo box to keep it with the text value + if data == None: + self.textbox.setItemData(index, pattern) + else: + self.pattern.setChecked(data) + self.Find(0) + + def NextPrev(self, direction): + value = self.textbox.currentText() + pattern = self.pattern.isChecked() + if value != self.last_value: + index = self.textbox.findText(value) + # Allow for a button press before the value has been added to the combo box + if index < 0: + index = self.textbox.count() + self.textbox.addItem(value, pattern) + self.textbox.setCurrentIndex(index) + return + else: + self.textbox.setItemData(index, pattern) + elif pattern != self.last_pattern: + # Keep the pattern recorded in the combo box up to date + index = self.textbox.currentIndex() + self.textbox.setItemData(index, pattern) + self.Find(direction) + + def NotFound(self): + QMessageBox.information(self.bar, "Find", "'" + self.textbox.currentText() + "' not found") + +# Context-sensitive call graph data model item base + +class CallGraphLevelItemBase(object): + + def __init__(self, glb, params, row, parent_item): + self.glb = glb + self.params = params + self.row = row + self.parent_item = parent_item + self.query_done = False + self.child_count = 0 + self.child_items = [] + if parent_item: + self.level = parent_item.level + 1 + else: + self.level = 0 + + def getChildItem(self, row): + return self.child_items[row] + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def childCount(self): + if not self.query_done: + self.Select() + if not self.child_count: + return -1 + return self.child_count + + def hasChildren(self): + if not self.query_done: + return True + return self.child_count > 0 + + def getData(self, column): + return self.data[column] + +# Context-sensitive call graph data model level 2+ item base + +class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallGraphLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item) + self.comm_id = comm_id + self.thread_id = thread_id + self.call_path_id = call_path_id + self.insn_cnt = insn_cnt + self.cyc_cnt = cyc_cnt + self.branch_count = branch_count + self.time = time + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + if self.params.have_ipc: + ipc_str = ", SUM(insn_count), SUM(cyc_count)" + else: + ipc_str = "" + QueryExec(query, "SELECT call_path_id, name, short_name, COUNT(calls.id), SUM(return_time - call_time)" + ipc_str + ", SUM(branch_count)" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " INNER JOIN dsos ON symbols.dso_id = dsos.id" + " WHERE parent_call_path_id = " + str(self.call_path_id) + + " AND comm_id = " + str(self.comm_id) + + " AND thread_id = " + str(self.thread_id) + + " GROUP BY call_path_id, name, short_name" + " ORDER BY call_path_id") + while query.next(): + if self.params.have_ipc: + insn_cnt = int(query.value(5)) + cyc_cnt = int(query.value(6)) + branch_count = int(query.value(7)) + else: + insn_cnt = 0 + cyc_cnt = 0 + branch_count = int(query.value(5)) + child_item = CallGraphLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self) + self.child_items.append(child_item) + self.child_count += 1 + +# Context-sensitive call graph data model level three item + +class CallGraphLevelThreeItem(CallGraphLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, call_path_id, name, dso, count, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallGraphLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, call_path_id, time, insn_cnt, cyc_cnt, branch_count, parent_item) + dso = dsoname(dso) + if self.params.have_ipc: + insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt) + cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt) + br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count) + ipc = CalcIPC(cyc_cnt, insn_cnt) + self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ] + else: + self.data = [ name, dso, str(count), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ] + self.dbid = call_path_id + +# Context-sensitive call graph data model level two item + +class CallGraphLevelTwoItem(CallGraphLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item): + super(CallGraphLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 1, 0, 0, 0, 0, parent_item) + if self.params.have_ipc: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""] + self.dbid = thread_id + + def Select(self): + super(CallGraphLevelTwoItem, self).Select() + for child_item in self.child_items: + self.time += child_item.time + self.insn_cnt += child_item.insn_cnt + self.cyc_cnt += child_item.cyc_cnt + self.branch_count += child_item.branch_count + for child_item in self.child_items: + child_item.data[4] = PercentToOneDP(child_item.time, self.time) + if self.params.have_ipc: + child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt) + child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt) + child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count) + else: + child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count) + +# Context-sensitive call graph data model level one item + +class CallGraphLevelOneItem(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, comm, parent_item): + super(CallGraphLevelOneItem, self).__init__(glb, params, row, parent_item) + if self.params.have_ipc: + self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [comm, "", "", "", "", "", ""] + self.dbid = comm_id + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT thread_id, pid, tid" + " FROM comm_threads" + " INNER JOIN threads ON thread_id = threads.id" + " WHERE comm_id = " + str(self.dbid)) + while query.next(): + child_item = CallGraphLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Context-sensitive call graph data model root item + +class CallGraphRootItem(CallGraphLevelItemBase): + + def __init__(self, glb, params): + super(CallGraphRootItem, self).__init__(glb, params, 0, None) + self.dbid = 0 + self.query_done = True + if_has_calls = "" + if IsSelectable(glb.db, "comms", columns = "has_calls"): + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE + query = QSqlQuery(glb.db) + QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) + while query.next(): + if not query.value(0): + continue + child_item = CallGraphLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call graph model parameters + +class CallGraphModelParams(): + + def __init__(self, glb, parent=None): + self.have_ipc = IsSelectable(glb.db, "calls", columns = "insn_count, cyc_count") + +# Context-sensitive call graph data model base + +class CallGraphModelBase(TreeModel): + + def __init__(self, glb, parent=None): + super(CallGraphModelBase, self).__init__(glb, CallGraphModelParams(glb), parent) + + def FindSelect(self, value, pattern, query): + if pattern: + # postgresql and sqlite pattern patching differences: + # postgresql LIKE is case sensitive but sqlite LIKE is not + # postgresql LIKE allows % and _ to be escaped with \ but sqlite LIKE does not + # postgresql supports ILIKE which is case insensitive + # sqlite supports GLOB (text only) which uses * and ? and is case sensitive + if not self.glb.dbref.is_sqlite3: + # Escape % and _ + s = value.replace("%", "\%") + s = s.replace("_", "\_") + # Translate * and ? into SQL LIKE pattern characters % and _ + trans = string.maketrans("*?", "%_") + match = " LIKE '" + str(s).translate(trans) + "'" + else: + match = " GLOB '" + str(value) + "'" + else: + match = " = '" + str(value) + "'" + self.DoFindSelect(query, match) + + def Found(self, query, found): + if found: + return self.FindPath(query) + return [] + + def FindValue(self, value, pattern, query, last_value, last_pattern): + if last_value == value and pattern == last_pattern: + found = query.first() + else: + self.FindSelect(value, pattern, query) + found = query.next() + return self.Found(query, found) + + def FindNext(self, query): + found = query.next() + if not found: + found = query.first() + return self.Found(query, found) + + def FindPrev(self, query): + found = query.previous() + if not found: + found = query.last() + return self.Found(query, found) + + def FindThread(self, c): + if c.direction == 0 or c.value != c.last_value or c.pattern != c.last_pattern: + ids = self.FindValue(c.value, c.pattern, c.query, c.last_value, c.last_pattern) + elif c.direction > 0: + ids = self.FindNext(c.query) + else: + ids = self.FindPrev(c.query) + return (True, ids) + + def Find(self, value, direction, pattern, context, callback): + class Context(): + def __init__(self, *x): + self.value, self.direction, self.pattern, self.query, self.last_value, self.last_pattern = x + def Update(self, *x): + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = x + (self.value, self.pattern) + if len(context): + context[0].Update(value, direction, pattern) + else: + context.append(Context(value, direction, pattern, QSqlQuery(self.glb.db), None, None)) + # Use a thread so the UI is not blocked during the SELECT + thread = Thread(self.FindThread, context[0]) + thread.done.connect(lambda ids, t=thread, c=callback: self.FindDone(t, c, ids), Qt.QueuedConnection) + thread.start() + + def FindDone(self, thread, callback, ids): + callback(ids) + +# Context-sensitive call graph data model + +class CallGraphModel(CallGraphModelBase): + + def __init__(self, glb, parent=None): + super(CallGraphModel, self).__init__(glb, parent) + + def GetRoot(self): + return CallGraphRootItem(self.glb, self.params) + + def columnCount(self, parent=None): + if self.params.have_ipc: + return 12 + else: + return 7 + + def columnHeader(self, column): + if self.params.have_ipc: + headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "] + else: + headers = ["Call Path", "Object", "Count ", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "] + return headers[column] + + def columnAlignment(self, column): + if self.params.have_ipc: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + else: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + return alignment[column] + + def DoFindSelect(self, query, match): + QueryExec(query, "SELECT call_path_id, comm_id, thread_id" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " WHERE calls.id <> 0" + " AND symbols.name" + match + + " GROUP BY comm_id, thread_id, call_path_id" + " ORDER BY comm_id, thread_id, call_path_id") + + def FindPath(self, query): + # Turn the query result into a list of ids that the tree view can walk + # to open the tree at the right place. + ids = [] + parent_id = query.value(0) + while parent_id: + ids.insert(0, parent_id) + q2 = QSqlQuery(self.glb.db) + QueryExec(q2, "SELECT parent_id" + " FROM call_paths" + " WHERE id = " + str(parent_id)) + if not q2.next(): + break + parent_id = q2.value(0) + # The call path root is not used + if ids[0] == 1: + del ids[0] + ids.insert(0, query.value(2)) + ids.insert(0, query.value(1)) + return ids + +# Call tree data model level 2+ item base + +class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, calls_id, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallTreeLevelTwoPlusItemBase, self).__init__(glb, params, row, parent_item) + self.comm_id = comm_id + self.thread_id = thread_id + self.calls_id = calls_id + self.call_time = call_time + self.time = time + self.insn_cnt = insn_cnt + self.cyc_cnt = cyc_cnt + self.branch_count = branch_count + + def Select(self): + self.query_done = True + if self.calls_id == 0: + comm_thread = " AND comm_id = " + str(self.comm_id) + " AND thread_id = " + str(self.thread_id) + else: + comm_thread = "" + if self.params.have_ipc: + ipc_str = ", insn_count, cyc_count" + else: + ipc_str = "" + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT calls.id, name, short_name, call_time, return_time - call_time" + ipc_str + ", branch_count" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " INNER JOIN dsos ON symbols.dso_id = dsos.id" + " WHERE calls.parent_id = " + str(self.calls_id) + comm_thread + + " ORDER BY call_time, calls.id") + while query.next(): + if self.params.have_ipc: + insn_cnt = int(query.value(5)) + cyc_cnt = int(query.value(6)) + branch_count = int(query.value(7)) + else: + insn_cnt = 0 + cyc_cnt = 0 + branch_count = int(query.value(5)) + child_item = CallTreeLevelThreeItem(self.glb, self.params, self.child_count, self.comm_id, self.thread_id, query.value(0), query.value(1), query.value(2), query.value(3), int(query.value(4)), insn_cnt, cyc_cnt, branch_count, self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call tree data model level three item + +class CallTreeLevelThreeItem(CallTreeLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, calls_id, name, dso, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item): + super(CallTreeLevelThreeItem, self).__init__(glb, params, row, comm_id, thread_id, calls_id, call_time, time, insn_cnt, cyc_cnt, branch_count, parent_item) + dso = dsoname(dso) + if self.params.have_ipc: + insn_pcnt = PercentToOneDP(insn_cnt, parent_item.insn_cnt) + cyc_pcnt = PercentToOneDP(cyc_cnt, parent_item.cyc_cnt) + br_pcnt = PercentToOneDP(branch_count, parent_item.branch_count) + ipc = CalcIPC(cyc_cnt, insn_cnt) + self.data = [ name, dso, str(call_time), str(time), PercentToOneDP(time, parent_item.time), str(insn_cnt), insn_pcnt, str(cyc_cnt), cyc_pcnt, ipc, str(branch_count), br_pcnt ] + else: + self.data = [ name, dso, str(call_time), str(time), PercentToOneDP(time, parent_item.time), str(branch_count), PercentToOneDP(branch_count, parent_item.branch_count) ] + self.dbid = calls_id + +# Call tree data model level two item + +class CallTreeLevelTwoItem(CallTreeLevelTwoPlusItemBase): + + def __init__(self, glb, params, row, comm_id, thread_id, pid, tid, parent_item): + super(CallTreeLevelTwoItem, self).__init__(glb, params, row, comm_id, thread_id, 0, 0, 0, 0, 0, 0, parent_item) + if self.params.have_ipc: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [str(pid) + ":" + str(tid), "", "", "", "", "", ""] + self.dbid = thread_id + + def Select(self): + super(CallTreeLevelTwoItem, self).Select() + for child_item in self.child_items: + self.time += child_item.time + self.insn_cnt += child_item.insn_cnt + self.cyc_cnt += child_item.cyc_cnt + self.branch_count += child_item.branch_count + for child_item in self.child_items: + child_item.data[4] = PercentToOneDP(child_item.time, self.time) + if self.params.have_ipc: + child_item.data[6] = PercentToOneDP(child_item.insn_cnt, self.insn_cnt) + child_item.data[8] = PercentToOneDP(child_item.cyc_cnt, self.cyc_cnt) + child_item.data[11] = PercentToOneDP(child_item.branch_count, self.branch_count) + else: + child_item.data[6] = PercentToOneDP(child_item.branch_count, self.branch_count) + +# Call tree data model level one item + +class CallTreeLevelOneItem(CallGraphLevelItemBase): + + def __init__(self, glb, params, row, comm_id, comm, parent_item): + super(CallTreeLevelOneItem, self).__init__(glb, params, row, parent_item) + if self.params.have_ipc: + self.data = [comm, "", "", "", "", "", "", "", "", "", "", ""] + else: + self.data = [comm, "", "", "", "", "", ""] + self.dbid = comm_id + + def Select(self): + self.query_done = True + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT thread_id, pid, tid" + " FROM comm_threads" + " INNER JOIN threads ON thread_id = threads.id" + " WHERE comm_id = " + str(self.dbid)) + while query.next(): + child_item = CallTreeLevelTwoItem(self.glb, self.params, self.child_count, self.dbid, query.value(0), query.value(1), query.value(2), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call tree data model root item + +class CallTreeRootItem(CallGraphLevelItemBase): + + def __init__(self, glb, params): + super(CallTreeRootItem, self).__init__(glb, params, 0, None) + self.dbid = 0 + self.query_done = True + if_has_calls = "" + if IsSelectable(glb.db, "comms", columns = "has_calls"): + if_has_calls = " WHERE has_calls = " + glb.dbref.TRUE + query = QSqlQuery(glb.db) + QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls) + while query.next(): + if not query.value(0): + continue + child_item = CallTreeLevelOneItem(glb, params, self.child_count, query.value(0), query.value(1), self) + self.child_items.append(child_item) + self.child_count += 1 + +# Call Tree data model + +class CallTreeModel(CallGraphModelBase): + + def __init__(self, glb, parent=None): + super(CallTreeModel, self).__init__(glb, parent) + + def GetRoot(self): + return CallTreeRootItem(self.glb, self.params) + + def columnCount(self, parent=None): + if self.params.have_ipc: + return 12 + else: + return 7 + + def columnHeader(self, column): + if self.params.have_ipc: + headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Insn Cnt", "Insn Cnt (%)", "Cyc Cnt", "Cyc Cnt (%)", "IPC", "Branch Count ", "Branch Count (%) "] + else: + headers = ["Call Path", "Object", "Call Time", "Time (ns) ", "Time (%) ", "Branch Count ", "Branch Count (%) "] + return headers[column] + + def columnAlignment(self, column): + if self.params.have_ipc: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + else: + alignment = [ Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight, Qt.AlignRight ] + return alignment[column] + + def DoFindSelect(self, query, match): + QueryExec(query, "SELECT calls.id, comm_id, thread_id" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " WHERE calls.id <> 0" + " AND symbols.name" + match + + " ORDER BY comm_id, thread_id, call_time, calls.id") + + def FindPath(self, query): + # Turn the query result into a list of ids that the tree view can walk + # to open the tree at the right place. + ids = [] + parent_id = query.value(0) + while parent_id: + ids.insert(0, parent_id) + q2 = QSqlQuery(self.glb.db) + QueryExec(q2, "SELECT parent_id" + " FROM calls" + " WHERE id = " + str(parent_id)) + if not q2.next(): + break + parent_id = q2.value(0) + ids.insert(0, query.value(2)) + ids.insert(0, query.value(1)) + return ids + +# Vertical layout + +class HBoxLayout(QHBoxLayout): + + def __init__(self, *children): + super(HBoxLayout, self).__init__() + + self.layout().setContentsMargins(0, 0, 0, 0) + for child in children: + if child.isWidgetType(): + self.layout().addWidget(child) + else: + self.layout().addLayout(child) + +# Horizontal layout + +class VBoxLayout(QVBoxLayout): + + def __init__(self, *children): + super(VBoxLayout, self).__init__() + + self.layout().setContentsMargins(0, 0, 0, 0) + for child in children: + if child.isWidgetType(): + self.layout().addWidget(child) + else: + self.layout().addLayout(child) + +# Vertical layout widget + +class VBox(): + + def __init__(self, *children): + self.vbox = QWidget() + self.vbox.setLayout(VBoxLayout(*children)) + + def Widget(self): + return self.vbox + +# Tree window base + +class TreeWindowBase(QMdiSubWindow): + + def __init__(self, parent=None): + super(TreeWindowBase, self).__init__(parent) + + self.model = None + self.find_bar = None + + self.view = QTreeView() + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTreeCellsToClipboard + + self.context_menu = TreeContextMenu(self.view) + + def DisplayFound(self, ids): + if not len(ids): + return False + parent = QModelIndex() + for dbid in ids: + found = False + n = self.model.rowCount(parent) + for row in xrange(n): + child = self.model.index(row, 0, parent) + if child.internalPointer().dbid == dbid: + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + parent = child + break + if not found: + break + return found + + def Find(self, value, direction, pattern, context): + self.view.setFocus() + self.find_bar.Busy() + self.model.Find(value, direction, pattern, context, self.FindDone) + + def FindDone(self, ids): + found = True + if not self.DisplayFound(ids): + found = False + self.find_bar.Idle() + if not found: + self.find_bar.NotFound() + + +# Context-sensitive call graph window + +class CallGraphWindow(TreeWindowBase): + + def __init__(self, glb, parent=None): + super(CallGraphWindow, self).__init__(parent) + + self.model = LookupCreateModel("Context-Sensitive Call Graph", lambda x=glb: CallGraphModel(x)) + + self.view.setModel(self.model) + + for c, w in ((0, 250), (1, 100), (2, 60), (3, 70), (4, 70), (5, 100)): + self.view.setColumnWidth(c, w) + + self.find_bar = FindBar(self, self) + + self.vbox = VBox(self.view, self.find_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Context-Sensitive Call Graph") + +# Call tree window + +class CallTreeWindow(TreeWindowBase): + + def __init__(self, glb, parent=None, thread_at_time=None): + super(CallTreeWindow, self).__init__(parent) + + self.model = LookupCreateModel("Call Tree", lambda x=glb: CallTreeModel(x)) + + self.view.setModel(self.model) + + for c, w in ((0, 230), (1, 100), (2, 100), (3, 70), (4, 70), (5, 100)): + self.view.setColumnWidth(c, w) + + self.find_bar = FindBar(self, self) + + self.vbox = VBox(self.view, self.find_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Call Tree") + + if thread_at_time: + self.DisplayThreadAtTime(*thread_at_time) + + def DisplayThreadAtTime(self, comm_id, thread_id, time): + parent = QModelIndex() + for dbid in (comm_id, thread_id): + found = False + n = self.model.rowCount(parent) + for row in xrange(n): + child = self.model.index(row, 0, parent) + if child.internalPointer().dbid == dbid: + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + parent = child + break + if not found: + return + found = False + while True: + n = self.model.rowCount(parent) + if not n: + return + last_child = None + for row in xrange(n): + self.view.setExpanded(parent, True) + child = self.model.index(row, 0, parent) + child_call_time = child.internalPointer().call_time + if child_call_time < time: + last_child = child + elif child_call_time == time: + self.view.setCurrentIndex(child) + return + elif child_call_time > time: + break + if not last_child: + if not found: + child = self.model.index(0, 0, parent) + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(child) + return + found = True + self.view.setExpanded(parent, True) + self.view.setCurrentIndex(last_child) + parent = last_child + +# ExecComm() gets the comm_id of the command string that was set when the process exec'd i.e. the program name + +def ExecComm(db, thread_id, time): + query = QSqlQuery(db) + QueryExec(query, "SELECT comm_threads.comm_id, comms.c_time, comms.exec_flag" + " FROM comm_threads" + " INNER JOIN comms ON comms.id = comm_threads.comm_id" + " WHERE comm_threads.thread_id = " + str(thread_id) + + " ORDER BY comms.c_time, comms.id") + first = None + last = None + while query.next(): + if first is None: + first = query.value(0) + if query.value(2) and Decimal(query.value(1)) <= Decimal(time): + last = query.value(0) + if not(last is None): + return last + return first + +# Container for (x, y) data + +class XY(): + def __init__(self, x=0, y=0): + self.x = x + self.y = y + + def __str__(self): + return "XY({}, {})".format(str(self.x), str(self.y)) + +# Container for sub-range data + +class Subrange(): + def __init__(self, lo=0, hi=0): + self.lo = lo + self.hi = hi + + def __str__(self): + return "Subrange({}, {})".format(str(self.lo), str(self.hi)) + +# Graph data region base class + +class GraphDataRegion(object): + + def __init__(self, key, title = "", ordinal = ""): + self.key = key + self.title = title + self.ordinal = ordinal + +# Function to sort GraphDataRegion + +def GraphDataRegionOrdinal(data_region): + return data_region.ordinal + +# Attributes for a graph region + +class GraphRegionAttribute(): + + def __init__(self, colour): + self.colour = colour + +# Switch graph data region represents a task + +class SwitchGraphDataRegion(GraphDataRegion): + + def __init__(self, key, exec_comm_id, pid, tid, comm, thread_id, comm_id): + super(SwitchGraphDataRegion, self).__init__(key) + + self.title = str(pid) + " / " + str(tid) + " " + comm + # Order graph legend within exec comm by pid / tid / time + self.ordinal = str(pid).rjust(16) + str(exec_comm_id).rjust(8) + str(tid).rjust(16) + self.exec_comm_id = exec_comm_id + self.pid = pid + self.tid = tid + self.comm = comm + self.thread_id = thread_id + self.comm_id = comm_id + +# Graph data point + +class GraphDataPoint(): + + def __init__(self, data, index, x, y, altx=None, alty=None, hregion=None, vregion=None): + self.data = data + self.index = index + self.x = x + self.y = y + self.altx = altx + self.alty = alty + self.hregion = hregion + self.vregion = vregion + +# Graph data (single graph) base class + +class GraphData(object): + + def __init__(self, collection, xbase=Decimal(0), ybase=Decimal(0)): + self.collection = collection + self.points = [] + self.xbase = xbase + self.ybase = ybase + self.title = "" + + def AddPoint(self, x, y, altx=None, alty=None, hregion=None, vregion=None): + index = len(self.points) + + x = float(Decimal(x) - self.xbase) + y = float(Decimal(y) - self.ybase) + + self.points.append(GraphDataPoint(self, index, x, y, altx, alty, hregion, vregion)) + + def XToData(self, x): + return Decimal(x) + self.xbase + + def YToData(self, y): + return Decimal(y) + self.ybase + +# Switch graph data (for one CPU) + +class SwitchGraphData(GraphData): + + def __init__(self, db, collection, cpu, xbase): + super(SwitchGraphData, self).__init__(collection, xbase) + + self.cpu = cpu + self.title = "CPU " + str(cpu) + self.SelectSwitches(db) + + def SelectComms(self, db, thread_id, last_comm_id, start_time, end_time): + query = QSqlQuery(db) + QueryExec(query, "SELECT id, c_time" + " FROM comms" + " WHERE c_thread_id = " + str(thread_id) + + " AND exec_flag = " + self.collection.glb.dbref.TRUE + + " AND c_time >= " + str(start_time) + + " AND c_time <= " + str(end_time) + + " ORDER BY c_time, id") + while query.next(): + comm_id = query.value(0) + if comm_id == last_comm_id: + continue + time = query.value(1) + hregion = self.HRegion(db, thread_id, comm_id, time) + self.AddPoint(time, 1000, None, None, hregion) + + def SelectSwitches(self, db): + last_time = None + last_comm_id = None + last_thread_id = None + query = QSqlQuery(db) + QueryExec(query, "SELECT time, thread_out_id, thread_in_id, comm_out_id, comm_in_id, flags" + " FROM context_switches" + " WHERE machine_id = " + str(self.collection.machine_id) + + " AND cpu = " + str(self.cpu) + + " ORDER BY time, id") + while query.next(): + flags = int(query.value(5)) + if flags & 1: + # Schedule-out: detect and add exec's + if last_thread_id == query.value(1) and last_comm_id is not None and last_comm_id != query.value(3): + self.SelectComms(db, last_thread_id, last_comm_id, last_time, query.value(0)) + continue + # Schedule-in: add data point + if len(self.points) == 0: + start_time = self.collection.glb.StartTime(self.collection.machine_id) + hregion = self.HRegion(db, query.value(1), query.value(3), start_time) + self.AddPoint(start_time, 1000, None, None, hregion) + time = query.value(0) + comm_id = query.value(4) + thread_id = query.value(2) + hregion = self.HRegion(db, thread_id, comm_id, time) + self.AddPoint(time, 1000, None, None, hregion) + last_time = time + last_comm_id = comm_id + last_thread_id = thread_id + + def NewHRegion(self, db, key, thread_id, comm_id, time): + exec_comm_id = ExecComm(db, thread_id, time) + query = QSqlQuery(db) + QueryExec(query, "SELECT pid, tid FROM threads WHERE id = " + str(thread_id)) + if query.next(): + pid = query.value(0) + tid = query.value(1) + else: + pid = -1 + tid = -1 + query = QSqlQuery(db) + QueryExec(query, "SELECT comm FROM comms WHERE id = " + str(comm_id)) + if query.next(): + comm = query.value(0) + else: + comm = "" + return SwitchGraphDataRegion(key, exec_comm_id, pid, tid, comm, thread_id, comm_id) + + def HRegion(self, db, thread_id, comm_id, time): + key = str(thread_id) + ":" + str(comm_id) + hregion = self.collection.LookupHRegion(key) + if hregion is None: + hregion = self.NewHRegion(db, key, thread_id, comm_id, time) + self.collection.AddHRegion(key, hregion) + return hregion + +# Graph data collection (multiple related graphs) base class + +class GraphDataCollection(object): + + def __init__(self, glb): + self.glb = glb + self.data = [] + self.hregions = {} + self.xrangelo = None + self.xrangehi = None + self.yrangelo = None + self.yrangehi = None + self.dp = XY(0, 0) + + def AddGraphData(self, data): + self.data.append(data) + + def LookupHRegion(self, key): + if key in self.hregions: + return self.hregions[key] + return None + + def AddHRegion(self, key, hregion): + self.hregions[key] = hregion + +# Switch graph data collection (SwitchGraphData for each CPU) + +class SwitchGraphDataCollection(GraphDataCollection): + + def __init__(self, glb, db, machine_id): + super(SwitchGraphDataCollection, self).__init__(glb) + + self.machine_id = machine_id + self.cpus = self.SelectCPUs(db) + + self.xrangelo = glb.StartTime(machine_id) + self.xrangehi = glb.FinishTime(machine_id) + + self.yrangelo = Decimal(0) + self.yrangehi = Decimal(1000) + + for cpu in self.cpus: + self.AddGraphData(SwitchGraphData(db, self, cpu, self.xrangelo)) + + def SelectCPUs(self, db): + cpus = [] + query = QSqlQuery(db) + QueryExec(query, "SELECT DISTINCT cpu" + " FROM context_switches" + " WHERE machine_id = " + str(self.machine_id)) + while query.next(): + cpus.append(int(query.value(0))) + return sorted(cpus) + +# Switch graph data graphics item displays the graphed data + +class SwitchGraphDataGraphicsItem(QGraphicsItem): + + def __init__(self, data, graph_width, graph_height, attrs, event_handler, parent=None): + super(SwitchGraphDataGraphicsItem, self).__init__(parent) + + self.data = data + self.graph_width = graph_width + self.graph_height = graph_height + self.attrs = attrs + self.event_handler = event_handler + self.setAcceptHoverEvents(True) + + def boundingRect(self): + return QRectF(0, 0, self.graph_width, self.graph_height) + + def PaintPoint(self, painter, last, x): + if not(last is None or last.hregion.pid == 0 or x < self.attrs.subrange.x.lo): + if last.x < self.attrs.subrange.x.lo: + x0 = self.attrs.subrange.x.lo + else: + x0 = last.x + if x > self.attrs.subrange.x.hi: + x1 = self.attrs.subrange.x.hi + else: + x1 = x - 1 + x0 = self.attrs.XToPixel(x0) + x1 = self.attrs.XToPixel(x1) + + y0 = self.attrs.YToPixel(last.y) + + colour = self.attrs.region_attributes[last.hregion.key].colour + + width = x1 - x0 + 1 + if width < 2: + painter.setPen(colour) + painter.drawLine(x0, self.graph_height - y0, x0, self.graph_height) + else: + painter.fillRect(x0, self.graph_height - y0, width, self.graph_height - 1, colour) + + def paint(self, painter, option, widget): + last = None + for point in self.data.points: + self.PaintPoint(painter, last, point.x) + if point.x > self.attrs.subrange.x.hi: + break; + last = point + self.PaintPoint(painter, last, self.attrs.subrange.x.hi + 1) + + def BinarySearchPoint(self, target): + lower_pos = 0 + higher_pos = len(self.data.points) + while True: + pos = int((lower_pos + higher_pos) / 2) + val = self.data.points[pos].x + if target >= val: + lower_pos = pos + else: + higher_pos = pos + if higher_pos <= lower_pos + 1: + return lower_pos + + def XPixelToData(self, x): + x = self.attrs.PixelToX(x) + if x < self.data.points[0].x: + x = 0 + pos = 0 + low = True + else: + pos = self.BinarySearchPoint(x) + low = False + return (low, pos, self.data.XToData(x)) + + def EventToData(self, event): + no_data = (None,) * 4 + if len(self.data.points) < 1: + return no_data + x = event.pos().x() + if x < 0: + return no_data + low0, pos0, time_from = self.XPixelToData(x) + low1, pos1, time_to = self.XPixelToData(x + 1) + hregions = set() + hregion_times = [] + if not low1: + for i in xrange(pos0, pos1 + 1): + hregion = self.data.points[i].hregion + hregions.add(hregion) + if i == pos0: + time = time_from + else: + time = self.data.XToData(self.data.points[i].x) + hregion_times.append((hregion, time)) + return (time_from, time_to, hregions, hregion_times) + + def hoverMoveEvent(self, event): + time_from, time_to, hregions, hregion_times = self.EventToData(event) + if time_from is not None: + self.event_handler.PointEvent(self.data.cpu, time_from, time_to, hregions) + + def hoverLeaveEvent(self, event): + self.event_handler.NoPointEvent() + + def mousePressEvent(self, event): + if event.button() != Qt.RightButton: + super(SwitchGraphDataGraphicsItem, self).mousePressEvent(event) + return + time_from, time_to, hregions, hregion_times = self.EventToData(event) + if hregion_times: + self.event_handler.RightClickEvent(self.data.cpu, hregion_times, event.screenPos()) + +# X-axis graphics item + +class XAxisGraphicsItem(QGraphicsItem): + + def __init__(self, width, parent=None): + super(XAxisGraphicsItem, self).__init__(parent) + + self.width = width + self.max_mark_sz = 4 + self.height = self.max_mark_sz + 1 + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def Step(self): + attrs = self.parentItem().attrs + subrange = attrs.subrange.x + t = subrange.hi - subrange.lo + s = (3.0 * t) / self.width + n = 1.0 + while s > n: + n = n * 10.0 + return n + + def PaintMarks(self, painter, at_y, lo, hi, step, i): + attrs = self.parentItem().attrs + x = lo + while x <= hi: + xp = attrs.XToPixel(x) + if i % 10: + if i % 5: + sz = 1 + else: + sz = 2 + else: + sz = self.max_mark_sz + i = 0 + painter.drawLine(xp, at_y, xp, at_y + sz) + x += step + i += 1 + + def paint(self, painter, option, widget): + # Using QPainter::drawLine(int x1, int y1, int x2, int y2) so x2 = width -1 + painter.drawLine(0, 0, self.width - 1, 0) + n = self.Step() + attrs = self.parentItem().attrs + subrange = attrs.subrange.x + if subrange.lo: + x_offset = n - (subrange.lo % n) + else: + x_offset = 0.0 + x = subrange.lo + x_offset + i = (x / n) % 10 + self.PaintMarks(painter, 0, x, subrange.hi, n, i) + + def ScaleDimensions(self): + n = self.Step() + attrs = self.parentItem().attrs + lo = attrs.subrange.x.lo + hi = (n * 10.0) + lo + width = attrs.XToPixel(hi) + if width > 500: + width = 0 + return (n, lo, hi, width) + + def PaintScale(self, painter, at_x, at_y): + n, lo, hi, width = self.ScaleDimensions() + if not width: + return + painter.drawLine(at_x, at_y, at_x + width, at_y) + self.PaintMarks(painter, at_y, lo, hi, n, 0) + + def ScaleWidth(self): + n, lo, hi, width = self.ScaleDimensions() + return width + + def ScaleHeight(self): + return self.height + + def ScaleUnit(self): + return self.Step() * 10 + +# Scale graphics item base class + +class ScaleGraphicsItem(QGraphicsItem): + + def __init__(self, axis, parent=None): + super(ScaleGraphicsItem, self).__init__(parent) + self.axis = axis + + def boundingRect(self): + scale_width = self.axis.ScaleWidth() + if not scale_width: + return QRectF() + return QRectF(0, 0, self.axis.ScaleWidth() + 100, self.axis.ScaleHeight()) + + def paint(self, painter, option, widget): + scale_width = self.axis.ScaleWidth() + if not scale_width: + return + self.axis.PaintScale(painter, 0, 5) + x = scale_width + 4 + painter.drawText(QPointF(x, 10), self.Text()) + + def Unit(self): + return self.axis.ScaleUnit() + + def Text(self): + return "" + +# Switch graph scale graphics item + +class SwitchScaleGraphicsItem(ScaleGraphicsItem): + + def __init__(self, axis, parent=None): + super(SwitchScaleGraphicsItem, self).__init__(axis, parent) + + def Text(self): + unit = self.Unit() + if unit >= 1000000000: + unit = int(unit / 1000000000) + us = "s" + elif unit >= 1000000: + unit = int(unit / 1000000) + us = "ms" + elif unit >= 1000: + unit = int(unit / 1000) + us = "us" + else: + unit = int(unit) + us = "ns" + return " = " + str(unit) + " " + us + +# Switch graph graphics item contains graph title, scale, x/y-axis, and the graphed data + +class SwitchGraphGraphicsItem(QGraphicsItem): + + def __init__(self, collection, data, attrs, event_handler, first, parent=None): + super(SwitchGraphGraphicsItem, self).__init__(parent) + self.collection = collection + self.data = data + self.attrs = attrs + self.event_handler = event_handler + + margin = 20 + title_width = 50 + + self.title_graphics = QGraphicsSimpleTextItem(data.title, self) + + self.title_graphics.setPos(margin, margin) + graph_width = attrs.XToPixel(attrs.subrange.x.hi) + 1 + graph_height = attrs.YToPixel(attrs.subrange.y.hi) + 1 + + self.graph_origin_x = margin + title_width + margin + self.graph_origin_y = graph_height + margin + + x_axis_size = 1 + y_axis_size = 1 + self.yline = QGraphicsLineItem(0, 0, 0, graph_height, self) + + self.x_axis = XAxisGraphicsItem(graph_width, self) + self.x_axis.setPos(self.graph_origin_x, self.graph_origin_y + 1) + + if first: + self.scale_item = SwitchScaleGraphicsItem(self.x_axis, self) + self.scale_item.setPos(self.graph_origin_x, self.graph_origin_y + 10) + + self.yline.setPos(self.graph_origin_x - y_axis_size, self.graph_origin_y - graph_height) + + self.axis_point = QGraphicsLineItem(0, 0, 0, 0, self) + self.axis_point.setPos(self.graph_origin_x - 1, self.graph_origin_y +1) + + self.width = self.graph_origin_x + graph_width + margin + self.height = self.graph_origin_y + margin + + self.graph = SwitchGraphDataGraphicsItem(data, graph_width, graph_height, attrs, event_handler, self) + self.graph.setPos(self.graph_origin_x, self.graph_origin_y - graph_height) + + if parent and 'EnableRubberBand' in dir(parent): + parent.EnableRubberBand(self.graph_origin_x, self.graph_origin_x + graph_width - 1, self) + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, option, widget): + pass + + def RBXToPixel(self, x): + return self.attrs.PixelToX(x - self.graph_origin_x) + + def RBXRangeToPixel(self, x0, x1): + return (self.RBXToPixel(x0), self.RBXToPixel(x1 + 1)) + + def RBPixelToTime(self, x): + if x < self.data.points[0].x: + return self.data.XToData(0) + return self.data.XToData(x) + + def RBEventTimes(self, x0, x1): + x0, x1 = self.RBXRangeToPixel(x0, x1) + time_from = self.RBPixelToTime(x0) + time_to = self.RBPixelToTime(x1) + return (time_from, time_to) + + def RBEvent(self, x0, x1): + time_from, time_to = self.RBEventTimes(x0, x1) + self.event_handler.RangeEvent(time_from, time_to) + + def RBMoveEvent(self, x0, x1): + if x1 < x0: + x0, x1 = x1, x0 + self.RBEvent(x0, x1) + + def RBReleaseEvent(self, x0, x1, selection_state): + if x1 < x0: + x0, x1 = x1, x0 + x0, x1 = self.RBXRangeToPixel(x0, x1) + self.event_handler.SelectEvent(x0, x1, selection_state) + +# Graphics item to draw a vertical bracket (used to highlight "forward" sub-range) + +class VerticalBracketGraphicsItem(QGraphicsItem): + + def __init__(self, parent=None): + super(VerticalBracketGraphicsItem, self).__init__(parent) + + self.width = 0 + self.height = 0 + self.hide() + + def SetSize(self, width, height): + self.width = width + 1 + self.height = height + 1 + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, option, widget): + colour = QColor(255, 255, 0, 32) + painter.fillRect(0, 0, self.width, self.height, colour) + x1 = self.width - 1 + y1 = self.height - 1 + painter.drawLine(0, 0, x1, 0) + painter.drawLine(0, 0, 0, 3) + painter.drawLine(x1, 0, x1, 3) + painter.drawLine(0, y1, x1, y1) + painter.drawLine(0, y1, 0, y1 - 3) + painter.drawLine(x1, y1, x1, y1 - 3) + +# Graphics item to contain graphs arranged vertically + +class VertcalGraphSetGraphicsItem(QGraphicsItem): + + def __init__(self, collection, attrs, event_handler, child_class, parent=None): + super(VertcalGraphSetGraphicsItem, self).__init__(parent) + + self.collection = collection + + self.top = 10 + + self.width = 0 + self.height = self.top + + self.rubber_band = None + self.rb_enabled = False + + first = True + for data in collection.data: + child = child_class(collection, data, attrs, event_handler, first, self) + child.setPos(0, self.height + 1) + rect = child.boundingRect() + if rect.right() > self.width: + self.width = rect.right() + self.height = self.height + rect.bottom() + 1 + first = False + + self.bracket = VerticalBracketGraphicsItem(self) + + def EnableRubberBand(self, xlo, xhi, rb_event_handler): + if self.rb_enabled: + return + self.rb_enabled = True + self.rb_in_view = False + self.setAcceptedMouseButtons(Qt.LeftButton) + self.rb_xlo = xlo + self.rb_xhi = xhi + self.rb_event_handler = rb_event_handler + self.mousePressEvent = self.MousePressEvent + self.mouseMoveEvent = self.MouseMoveEvent + self.mouseReleaseEvent = self.MouseReleaseEvent + + def boundingRect(self): + return QRectF(0, 0, self.width, self.height) + + def paint(self, painter, option, widget): + pass + + def RubberBandParent(self): + scene = self.scene() + view = scene.views()[0] + viewport = view.viewport() + return viewport + + def RubberBandSetGeometry(self, rect): + scene_rectf = self.mapRectToScene(QRectF(rect)) + scene = self.scene() + view = scene.views()[0] + poly = view.mapFromScene(scene_rectf) + self.rubber_band.setGeometry(poly.boundingRect()) + + def SetSelection(self, selection_state): + if self.rubber_band: + if selection_state: + self.RubberBandSetGeometry(selection_state) + self.rubber_band.show() + else: + self.rubber_band.hide() + + def SetBracket(self, rect): + if rect: + x, y, width, height = rect.x(), rect.y(), rect.width(), rect.height() + self.bracket.setPos(x, y) + self.bracket.SetSize(width, height) + self.bracket.show() + else: + self.bracket.hide() + + def RubberBandX(self, event): + x = event.pos().toPoint().x() + if x < self.rb_xlo: + x = self.rb_xlo + elif x > self.rb_xhi: + x = self.rb_xhi + else: + self.rb_in_view = True + return x + + def RubberBandRect(self, x): + if self.rb_origin.x() <= x: + width = x - self.rb_origin.x() + rect = QRect(self.rb_origin, QSize(width, self.height)) + else: + width = self.rb_origin.x() - x + top_left = QPoint(self.rb_origin.x() - width, self.rb_origin.y()) + rect = QRect(top_left, QSize(width, self.height)) + return rect + + def MousePressEvent(self, event): + self.rb_in_view = False + x = self.RubberBandX(event) + self.rb_origin = QPoint(x, self.top) + if self.rubber_band is None: + self.rubber_band = QRubberBand(QRubberBand.Rectangle, self.RubberBandParent()) + self.RubberBandSetGeometry(QRect(self.rb_origin, QSize(0, self.height))) + if self.rb_in_view: + self.rubber_band.show() + self.rb_event_handler.RBMoveEvent(x, x) + else: + self.rubber_band.hide() + + def MouseMoveEvent(self, event): + x = self.RubberBandX(event) + rect = self.RubberBandRect(x) + self.RubberBandSetGeometry(rect) + if self.rb_in_view: + self.rubber_band.show() + self.rb_event_handler.RBMoveEvent(self.rb_origin.x(), x) + + def MouseReleaseEvent(self, event): + x = self.RubberBandX(event) + if self.rb_in_view: + selection_state = self.RubberBandRect(x) + else: + selection_state = None + self.rb_event_handler.RBReleaseEvent(self.rb_origin.x(), x, selection_state) + +# Switch graph legend data model + +class SwitchGraphLegendModel(QAbstractTableModel): + + def __init__(self, collection, region_attributes, parent=None): + super(SwitchGraphLegendModel, self).__init__(parent) + + self.region_attributes = region_attributes + + self.child_items = sorted(collection.hregions.values(), key=GraphDataRegionOrdinal) + self.child_count = len(self.child_items) + + self.highlight_set = set() + + self.column_headers = ("pid", "tid", "comm") + + def rowCount(self, parent): + return self.child_count + + def headerData(self, section, orientation, role): + if role != Qt.DisplayRole: + return None + if orientation != Qt.Horizontal: + return None + return self.columnHeader(section) + + def index(self, row, column, parent): + return self.createIndex(row, column, self.child_items[row]) + + def columnCount(self, parent=None): + return len(self.column_headers) + + def columnHeader(self, column): + return self.column_headers[column] + + def data(self, index, role): + if role == Qt.BackgroundRole: + child = self.child_items[index.row()] + if child in self.highlight_set: + return self.region_attributes[child.key].colour + return None + if role == Qt.ForegroundRole: + child = self.child_items[index.row()] + if child in self.highlight_set: + return QColor(255, 255, 255) + return self.region_attributes[child.key].colour + if role != Qt.DisplayRole: + return None + hregion = self.child_items[index.row()] + col = index.column() + if col == 0: + return hregion.pid + if col == 1: + return hregion.tid + if col == 2: + return hregion.comm + return None + + def SetHighlight(self, row, set_highlight): + child = self.child_items[row] + top_left = self.createIndex(row, 0, child) + bottom_right = self.createIndex(row, len(self.column_headers) - 1, child) + self.dataChanged.emit(top_left, bottom_right) + + def Highlight(self, highlight_set): + for row in xrange(self.child_count): + child = self.child_items[row] + if child in self.highlight_set: + if child not in highlight_set: + self.SetHighlight(row, False) + elif child in highlight_set: + self.SetHighlight(row, True) + self.highlight_set = highlight_set + +# Switch graph legend is a table + +class SwitchGraphLegend(QWidget): + + def __init__(self, collection, region_attributes, parent=None): + super(SwitchGraphLegend, self).__init__(parent) + + self.data_model = SwitchGraphLegendModel(collection, region_attributes) + + self.model = QSortFilterProxyModel() + self.model.setSourceModel(self.data_model) + + self.view = QTableView() + self.view.setModel(self.model) + self.view.setEditTriggers(QAbstractItemView.NoEditTriggers) + self.view.verticalHeader().setVisible(False) + self.view.sortByColumn(-1, Qt.AscendingOrder) + self.view.setSortingEnabled(True) + self.view.resizeColumnsToContents() + self.view.resizeRowsToContents() + + self.vbox = VBoxLayout(self.view) + self.setLayout(self.vbox) + + sz1 = self.view.columnWidth(0) + self.view.columnWidth(1) + self.view.columnWidth(2) + 2 + sz1 = sz1 + self.view.verticalScrollBar().sizeHint().width() + self.saved_size = sz1 + + def resizeEvent(self, event): + self.saved_size = self.size().width() + super(SwitchGraphLegend, self).resizeEvent(event) + + def Highlight(self, highlight_set): + self.data_model.Highlight(highlight_set) + self.update() + + def changeEvent(self, event): + if event.type() == QEvent.FontChange: + self.view.resizeRowsToContents() + self.view.resizeColumnsToContents() + # Need to resize rows again after column resize + self.view.resizeRowsToContents() + super(SwitchGraphLegend, self).changeEvent(event) + +# Random colour generation + +def RGBColourTooLight(r, g, b): + if g > 230: + return True + if g <= 160: + return False + if r <= 180 and g <= 180: + return False + if r < 60: + return False + return True + +def GenerateColours(x): + cs = [0] + for i in xrange(1, x): + cs.append(int((255.0 / i) + 0.5)) + colours = [] + for r in cs: + for g in cs: + for b in cs: + # Exclude black and colours that look too light against a white background + if (r, g, b) == (0, 0, 0) or RGBColourTooLight(r, g, b): + continue + colours.append(QColor(r, g, b)) + return colours + +def GenerateNColours(n): + for x in xrange(2, n + 2): + colours = GenerateColours(x) + if len(colours) >= n: + return colours + return [] + +def GenerateNRandomColours(n, seed): + colours = GenerateNColours(n) + random.seed(seed) + random.shuffle(colours) + return colours + +# Graph attributes, in particular the scale and subrange that change when zooming + +class GraphAttributes(): + + def __init__(self, scale, subrange, region_attributes, dp): + self.scale = scale + self.subrange = subrange + self.region_attributes = region_attributes + # Rounding avoids errors due to finite floating point precision + self.dp = dp # data decimal places + self.Update() + + def XToPixel(self, x): + return int(round((x - self.subrange.x.lo) * self.scale.x, self.pdp.x)) + + def YToPixel(self, y): + return int(round((y - self.subrange.y.lo) * self.scale.y, self.pdp.y)) + + def PixelToXRounded(self, px): + return round((round(px, 0) / self.scale.x), self.dp.x) + self.subrange.x.lo + + def PixelToYRounded(self, py): + return round((round(py, 0) / self.scale.y), self.dp.y) + self.subrange.y.lo + + def PixelToX(self, px): + x = self.PixelToXRounded(px) + if self.pdp.x == 0: + rt = self.XToPixel(x) + if rt > px: + return x - 1 + return x + + def PixelToY(self, py): + y = self.PixelToYRounded(py) + if self.pdp.y == 0: + rt = self.YToPixel(y) + if rt > py: + return y - 1 + return y + + def ToPDP(self, dp, scale): + # Calculate pixel decimal places: + # (10 ** dp) is the minimum delta in the data + # scale it to get the minimum delta in pixels + # log10 gives the number of decimals places negatively + # subtrace 1 to divide by 10 + # round to the lower negative number + # change the sign to get the number of decimals positively + x = math.log10((10 ** dp) * scale) + if x < 0: + x -= 1 + x = -int(math.floor(x) - 0.1) + else: + x = 0 + return x + + def Update(self): + x = self.ToPDP(self.dp.x, self.scale.x) + y = self.ToPDP(self.dp.y, self.scale.y) + self.pdp = XY(x, y) # pixel decimal places + +# Switch graph splitter which divides the CPU graphs from the legend + +class SwitchGraphSplitter(QSplitter): + + def __init__(self, parent=None): + super(SwitchGraphSplitter, self).__init__(parent) + + self.first_time = False + + def resizeEvent(self, ev): + if self.first_time: + self.first_time = False + sz1 = self.widget(1).view.columnWidth(0) + self.widget(1).view.columnWidth(1) + self.widget(1).view.columnWidth(2) + 2 + sz1 = sz1 + self.widget(1).view.verticalScrollBar().sizeHint().width() + sz0 = self.size().width() - self.handleWidth() - sz1 + self.setSizes([sz0, sz1]) + elif not(self.widget(1).saved_size is None): + sz1 = self.widget(1).saved_size + sz0 = self.size().width() - self.handleWidth() - sz1 + self.setSizes([sz0, sz1]) + super(SwitchGraphSplitter, self).resizeEvent(ev) + +# Graph widget base class + +class GraphWidget(QWidget): + + graph_title_changed = Signal(object) + + def __init__(self, parent=None): + super(GraphWidget, self).__init__(parent) + + def GraphTitleChanged(self, title): + self.graph_title_changed.emit(title) + + def Title(self): + return "" + +# Display time in s, ms, us or ns + +def ToTimeStr(val): + val = Decimal(val) + if val >= 1000000000: + return "{} s".format((val / 1000000000).quantize(Decimal("0.000000001"))) + if val >= 1000000: + return "{} ms".format((val / 1000000).quantize(Decimal("0.000001"))) + if val >= 1000: + return "{} us".format((val / 1000).quantize(Decimal("0.001"))) + return "{} ns".format(val.quantize(Decimal("1"))) + +# Switch (i.e. context switch i.e. Time Chart by CPU) graph widget which contains the CPU graphs and the legend and control buttons + +class SwitchGraphWidget(GraphWidget): + + def __init__(self, glb, collection, parent=None): + super(SwitchGraphWidget, self).__init__(parent) + + self.glb = glb + self.collection = collection + + self.back_state = [] + self.forward_state = [] + self.selection_state = (None, None) + self.fwd_rect = None + self.start_time = self.glb.StartTime(collection.machine_id) + + i = 0 + hregions = collection.hregions.values() + colours = GenerateNRandomColours(len(hregions), 1013) + region_attributes = {} + for hregion in hregions: + if hregion.pid == 0 and hregion.tid == 0: + region_attributes[hregion.key] = GraphRegionAttribute(QColor(0, 0, 0)) + else: + region_attributes[hregion.key] = GraphRegionAttribute(colours[i]) + i = i + 1 + + # Default to entire range + xsubrange = Subrange(0.0, float(collection.xrangehi - collection.xrangelo) + 1.0) + ysubrange = Subrange(0.0, float(collection.yrangehi - collection.yrangelo) + 1.0) + subrange = XY(xsubrange, ysubrange) + + scale = self.GetScaleForRange(subrange) + + self.attrs = GraphAttributes(scale, subrange, region_attributes, collection.dp) + + self.item = VertcalGraphSetGraphicsItem(collection, self.attrs, self, SwitchGraphGraphicsItem) + + self.scene = QGraphicsScene() + self.scene.addItem(self.item) + + self.view = QGraphicsView(self.scene) + self.view.centerOn(0, 0) + self.view.setAlignment(Qt.AlignLeft | Qt.AlignTop) + + self.legend = SwitchGraphLegend(collection, region_attributes) + + self.splitter = SwitchGraphSplitter() + self.splitter.addWidget(self.view) + self.splitter.addWidget(self.legend) + + self.point_label = QLabel("") + self.point_label.setSizePolicy(QSizePolicy.Preferred, QSizePolicy.Fixed) + + self.back_button = QToolButton() + self.back_button.setIcon(self.style().standardIcon(QStyle.SP_ArrowLeft)) + self.back_button.setDisabled(True) + self.back_button.released.connect(lambda: self.Back()) + + self.forward_button = QToolButton() + self.forward_button.setIcon(self.style().standardIcon(QStyle.SP_ArrowRight)) + self.forward_button.setDisabled(True) + self.forward_button.released.connect(lambda: self.Forward()) + + self.zoom_button = QToolButton() + self.zoom_button.setText("Zoom") + self.zoom_button.setDisabled(True) + self.zoom_button.released.connect(lambda: self.Zoom()) + + self.hbox = HBoxLayout(self.back_button, self.forward_button, self.zoom_button, self.point_label) + + self.vbox = VBoxLayout(self.splitter, self.hbox) + + self.setLayout(self.vbox) + + def GetScaleForRangeX(self, xsubrange): + # Default graph 1000 pixels wide + dflt = 1000.0 + r = xsubrange.hi - xsubrange.lo + return dflt / r + + def GetScaleForRangeY(self, ysubrange): + # Default graph 50 pixels high + dflt = 50.0 + r = ysubrange.hi - ysubrange.lo + return dflt / r + + def GetScaleForRange(self, subrange): + # Default graph 1000 pixels wide, 50 pixels high + xscale = self.GetScaleForRangeX(subrange.x) + yscale = self.GetScaleForRangeY(subrange.y) + return XY(xscale, yscale) + + def PointEvent(self, cpu, time_from, time_to, hregions): + text = "CPU: " + str(cpu) + time_from = time_from.quantize(Decimal(1)) + rel_time_from = time_from - self.glb.StartTime(self.collection.machine_id) + text = text + " Time: " + str(time_from) + " (+" + ToTimeStr(rel_time_from) + ")" + self.point_label.setText(text) + self.legend.Highlight(hregions) + + def RightClickEvent(self, cpu, hregion_times, pos): + if not IsSelectable(self.glb.db, "calls", "WHERE parent_id >= 0"): + return + menu = QMenu(self.view) + for hregion, time in hregion_times: + thread_at_time = (hregion.exec_comm_id, hregion.thread_id, time) + menu_text = "Show Call Tree for {} {}:{} at {}".format(hregion.comm, hregion.pid, hregion.tid, time) + menu.addAction(CreateAction(menu_text, "Show Call Tree", lambda a=None, args=thread_at_time: self.RightClickSelect(args), self.view)) + menu.exec_(pos) + + def RightClickSelect(self, args): + CallTreeWindow(self.glb, self.glb.mainwindow, thread_at_time=args) + + def NoPointEvent(self): + self.point_label.setText("") + self.legend.Highlight({}) + + def RangeEvent(self, time_from, time_to): + time_from = time_from.quantize(Decimal(1)) + time_to = time_to.quantize(Decimal(1)) + if time_to <= time_from: + self.point_label.setText("") + return + rel_time_from = time_from - self.start_time + rel_time_to = time_to - self.start_time + text = " Time: " + str(time_from) + " (+" + ToTimeStr(rel_time_from) + ") to: " + str(time_to) + " (+" + ToTimeStr(rel_time_to) + ")" + text = text + " duration: " + ToTimeStr(time_to - time_from) + self.point_label.setText(text) + + def BackState(self): + return (self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect) + + def PushBackState(self): + state = copy.deepcopy(self.BackState()) + self.back_state.append(state) + self.back_button.setEnabled(True) + + def PopBackState(self): + self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect = self.back_state.pop() + self.attrs.Update() + if not self.back_state: + self.back_button.setDisabled(True) + + def PushForwardState(self): + state = copy.deepcopy(self.BackState()) + self.forward_state.append(state) + self.forward_button.setEnabled(True) + + def PopForwardState(self): + self.attrs.subrange, self.attrs.scale, self.selection_state, self.fwd_rect = self.forward_state.pop() + self.attrs.Update() + if not self.forward_state: + self.forward_button.setDisabled(True) + + def Title(self): + time_from = self.collection.xrangelo + Decimal(self.attrs.subrange.x.lo) + time_to = self.collection.xrangelo + Decimal(self.attrs.subrange.x.hi) + rel_time_from = time_from - self.start_time + rel_time_to = time_to - self.start_time + title = "+" + ToTimeStr(rel_time_from) + " to +" + ToTimeStr(rel_time_to) + title = title + " (" + ToTimeStr(time_to - time_from) + ")" + return title + + def Update(self): + selected_subrange, selection_state = self.selection_state + self.item.SetSelection(selection_state) + self.item.SetBracket(self.fwd_rect) + self.zoom_button.setDisabled(selected_subrange is None) + self.GraphTitleChanged(self.Title()) + self.item.update(self.item.boundingRect()) + + def Back(self): + if not self.back_state: + return + self.PushForwardState() + self.PopBackState() + self.Update() + + def Forward(self): + if not self.forward_state: + return + self.PushBackState() + self.PopForwardState() + self.Update() + + def SelectEvent(self, x0, x1, selection_state): + if selection_state is None: + selected_subrange = None + else: + if x1 - x0 < 1.0: + x1 += 1.0 + selected_subrange = Subrange(x0, x1) + self.selection_state = (selected_subrange, selection_state) + self.zoom_button.setDisabled(selected_subrange is None) + + def Zoom(self): + selected_subrange, selection_state = self.selection_state + if selected_subrange is None: + return + self.fwd_rect = selection_state + self.item.SetSelection(None) + self.PushBackState() + self.attrs.subrange.x = selected_subrange + self.forward_state = [] + self.forward_button.setDisabled(True) + self.selection_state = (None, None) + self.fwd_rect = None + self.attrs.scale.x = self.GetScaleForRangeX(self.attrs.subrange.x) + self.attrs.Update() + self.Update() + +# Slow initialization - perform non-GUI initialization in a separate thread and put up a modal message box while waiting + +class SlowInitClass(): + + def __init__(self, glb, title, init_fn): + self.init_fn = init_fn + self.done = False + self.result = None + + self.msg_box = QMessageBox(glb.mainwindow) + self.msg_box.setText("Initializing " + title + ". Please wait.") + self.msg_box.setWindowTitle("Initializing " + title) + self.msg_box.setWindowIcon(glb.mainwindow.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.init_thread = Thread(self.ThreadFn, glb) + self.init_thread.done.connect(lambda: self.Done(), Qt.QueuedConnection) + + self.init_thread.start() + + def Done(self): + self.msg_box.done(0) + + def ThreadFn(self, glb): + conn_name = "SlowInitClass" + str(os.getpid()) + db, dbname = glb.dbref.Open(conn_name) + self.result = self.init_fn(db) + self.done = True + return (True, 0) + + def Result(self): + while not self.done: + self.msg_box.exec_() + self.init_thread.wait() + return self.result + +def SlowInit(glb, title, init_fn): + init = SlowInitClass(glb, title, init_fn) + return init.Result() + +# Time chart by CPU window + +class TimeChartByCPUWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(TimeChartByCPUWindow, self).__init__(parent) + + self.glb = glb + self.machine_id = glb.HostMachineId() + self.collection_name = "SwitchGraphDataCollection " + str(self.machine_id) + + collection = LookupModel(self.collection_name) + if collection is None: + collection = SlowInit(glb, "Time Chart", self.Init) + + self.widget = SwitchGraphWidget(glb, collection, self) + self.view = self.widget + + self.base_title = "Time Chart by CPU" + self.setWindowTitle(self.base_title + self.widget.Title()) + self.widget.graph_title_changed.connect(self.GraphTitleChanged) + + self.setWidget(self.widget) + + AddSubWindow(glb.mainwindow.mdi_area, self, self.windowTitle()) + + def Init(self, db): + return LookupCreateModel(self.collection_name, lambda : SwitchGraphDataCollection(self.glb, db, self.machine_id)) + + def GraphTitleChanged(self, title): + self.setWindowTitle(self.base_title + " : " + title) + +# Child data item finder + +class ChildDataItemFinder(): + + def __init__(self, root): + self.root = root + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (None,) * 5 + self.rows = [] + self.pos = 0 + + def FindSelect(self): + self.rows = [] + if self.pattern: + pattern = re.compile(self.value) + for child in self.root.child_items: + for column_data in child.data: + if re.search(pattern, str(column_data)) is not None: + self.rows.append(child.row) + break + else: + for child in self.root.child_items: + for column_data in child.data: + if self.value in str(column_data): + self.rows.append(child.row) + break + + def FindValue(self): + self.pos = 0 + if self.last_value != self.value or self.pattern != self.last_pattern: + self.FindSelect() + if not len(self.rows): + return -1 + return self.rows[self.pos] + + def FindThread(self): + if self.direction == 0 or self.value != self.last_value or self.pattern != self.last_pattern: + row = self.FindValue() + elif len(self.rows): + if self.direction > 0: + self.pos += 1 + if self.pos >= len(self.rows): + self.pos = 0 + else: + self.pos -= 1 + if self.pos < 0: + self.pos = len(self.rows) - 1 + row = self.rows[self.pos] + else: + row = -1 + return (True, row) + + def Find(self, value, direction, pattern, context, callback): + self.value, self.direction, self.pattern, self.last_value, self.last_pattern = (value, direction,pattern, self.value, self.pattern) + # Use a thread so the UI is not blocked + thread = Thread(self.FindThread) + thread.done.connect(lambda row, t=thread, c=callback: self.FindDone(t, c, row), Qt.QueuedConnection) + thread.start() + + def FindDone(self, thread, callback, row): + callback(row) + +# Number of database records to fetch in one go + +glb_chunk_sz = 10000 + +# Background process for SQL data fetcher + +class SQLFetcherProcess(): + + def __init__(self, dbref, sql, buffer, head, tail, fetch_count, fetching_done, process_target, wait_event, fetched_event, prep): + # Need a unique connection name + conn_name = "SQLFetcher" + str(os.getpid()) + self.db, dbname = dbref.Open(conn_name) + self.sql = sql + self.buffer = buffer + self.head = head + self.tail = tail + self.fetch_count = fetch_count + self.fetching_done = fetching_done + self.process_target = process_target + self.wait_event = wait_event + self.fetched_event = fetched_event + self.prep = prep + self.query = QSqlQuery(self.db) + self.query_limit = 0 if "$$last_id$$" in sql else 2 + self.last_id = -1 + self.fetched = 0 + self.more = True + self.local_head = self.head.value + self.local_tail = self.tail.value + + def Select(self): + if self.query_limit: + if self.query_limit == 1: + return + self.query_limit -= 1 + stmt = self.sql.replace("$$last_id$$", str(self.last_id)) + QueryExec(self.query, stmt) + + def Next(self): + if not self.query.next(): + self.Select() + if not self.query.next(): + return None + self.last_id = self.query.value(0) + return self.prep(self.query) + + def WaitForTarget(self): + while True: + self.wait_event.clear() + target = self.process_target.value + if target > self.fetched or target < 0: + break + self.wait_event.wait() + return target + + def HasSpace(self, sz): + if self.local_tail <= self.local_head: + space = len(self.buffer) - self.local_head + if space > sz: + return True + if space >= glb_nsz: + # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer + nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL) + self.buffer[self.local_head : self.local_head + len(nd)] = nd + self.local_head = 0 + if self.local_tail - self.local_head > sz: + return True + return False + + def WaitForSpace(self, sz): + if self.HasSpace(sz): + return + while True: + self.wait_event.clear() + self.local_tail = self.tail.value + if self.HasSpace(sz): + return + self.wait_event.wait() + + def AddToBuffer(self, obj): + d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL) + n = len(d) + nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL) + sz = n + glb_nsz + self.WaitForSpace(sz) + pos = self.local_head + self.buffer[pos : pos + len(nd)] = nd + self.buffer[pos + glb_nsz : pos + sz] = d + self.local_head += sz + + def FetchBatch(self, batch_size): + fetched = 0 + while batch_size > fetched: + obj = self.Next() + if obj is None: + self.more = False + break + self.AddToBuffer(obj) + fetched += 1 + if fetched: + self.fetched += fetched + with self.fetch_count.get_lock(): + self.fetch_count.value += fetched + self.head.value = self.local_head + self.fetched_event.set() + + def Run(self): + while self.more: + target = self.WaitForTarget() + if target < 0: + break + batch_size = min(glb_chunk_sz, target - self.fetched) + self.FetchBatch(batch_size) + self.fetching_done.value = True + self.fetched_event.set() + +def SQLFetcherFn(*x): + process = SQLFetcherProcess(*x) + process.Run() + +# SQL data fetcher + +class SQLFetcher(QObject): + + done = Signal(object) + + def __init__(self, glb, sql, prep, process_data, parent=None): + super(SQLFetcher, self).__init__(parent) + self.process_data = process_data + self.more = True + self.target = 0 + self.last_target = 0 + self.fetched = 0 + self.buffer_size = 16 * 1024 * 1024 + self.buffer = Array(c_char, self.buffer_size, lock=False) + self.head = Value(c_longlong) + self.tail = Value(c_longlong) + self.local_tail = 0 + self.fetch_count = Value(c_longlong) + self.fetching_done = Value(c_bool) + self.last_count = 0 + self.process_target = Value(c_longlong) + self.wait_event = Event() + self.fetched_event = Event() + glb.AddInstanceToShutdownOnExit(self) + self.process = Process(target=SQLFetcherFn, args=(glb.dbref, sql, self.buffer, self.head, self.tail, self.fetch_count, self.fetching_done, self.process_target, self.wait_event, self.fetched_event, prep)) + self.process.start() + self.thread = Thread(self.Thread) + self.thread.done.connect(self.ProcessData, Qt.QueuedConnection) + self.thread.start() + + def Shutdown(self): + # Tell the thread and process to exit + self.process_target.value = -1 + self.wait_event.set() + self.more = False + self.fetching_done.value = True + self.fetched_event.set() + + def Thread(self): + if not self.more: + return True, 0 + while True: + self.fetched_event.clear() + fetch_count = self.fetch_count.value + if fetch_count != self.last_count: + break + if self.fetching_done.value: + self.more = False + return True, 0 + self.fetched_event.wait() + count = fetch_count - self.last_count + self.last_count = fetch_count + self.fetched += count + return False, count + + def Fetch(self, nr): + if not self.more: + # -1 inidcates there are no more + return -1 + result = self.fetched + extra = result + nr - self.target + if extra > 0: + self.target += extra + # process_target < 0 indicates shutting down + if self.process_target.value >= 0: + self.process_target.value = self.target + self.wait_event.set() + return result + + def RemoveFromBuffer(self): + pos = self.local_tail + if len(self.buffer) - pos < glb_nsz: + pos = 0 + n = pickle.loads(self.buffer[pos : pos + glb_nsz]) + if n == 0: + pos = 0 + n = pickle.loads(self.buffer[0 : glb_nsz]) + pos += glb_nsz + obj = pickle.loads(self.buffer[pos : pos + n]) + self.local_tail = pos + n + return obj + + def ProcessData(self, count): + for i in xrange(count): + obj = self.RemoveFromBuffer() + self.process_data(obj) + self.tail.value = self.local_tail + self.wait_event.set() + self.done.emit(count) + +# Fetch more records bar + +class FetchMoreRecordsBar(): + + def __init__(self, model, parent): + self.model = model + + self.label = QLabel("Number of records (x " + "{:,}".format(glb_chunk_sz) + ") to fetch:") + self.label.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.fetch_count = QSpinBox() + self.fetch_count.setRange(1, 1000000) + self.fetch_count.setValue(10) + self.fetch_count.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.fetch = QPushButton("Go!") + self.fetch.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + self.fetch.released.connect(self.FetchMoreRecords) + + self.progress = QProgressBar() + self.progress.setRange(0, 100) + self.progress.hide() + + self.done_label = QLabel("All records fetched") + self.done_label.hide() + + self.spacer = QLabel("") + + self.close_button = QToolButton() + self.close_button.setIcon(parent.style().standardIcon(QStyle.SP_DockWidgetCloseButton)) + self.close_button.released.connect(self.Deactivate) + + self.hbox = QHBoxLayout() + self.hbox.setContentsMargins(0, 0, 0, 0) + + self.hbox.addWidget(self.label) + self.hbox.addWidget(self.fetch_count) + self.hbox.addWidget(self.fetch) + self.hbox.addWidget(self.spacer) + self.hbox.addWidget(self.progress) + self.hbox.addWidget(self.done_label) + self.hbox.addWidget(self.close_button) + + self.bar = QWidget() + self.bar.setLayout(self.hbox) + self.bar.show() + + self.in_progress = False + self.model.progress.connect(self.Progress) + + self.done = False + + if not model.HasMoreRecords(): + self.Done() + + def Widget(self): + return self.bar + + def Activate(self): + self.bar.show() + self.fetch.setFocus() + + def Deactivate(self): + self.bar.hide() + + def Enable(self, enable): + self.fetch.setEnabled(enable) + self.fetch_count.setEnabled(enable) + + def Busy(self): + self.Enable(False) + self.fetch.hide() + self.spacer.hide() + self.progress.show() + + def Idle(self): + self.in_progress = False + self.Enable(True) + self.progress.hide() + self.fetch.show() + self.spacer.show() + + def Target(self): + return self.fetch_count.value() * glb_chunk_sz + + def Done(self): + self.done = True + self.Idle() + self.label.hide() + self.fetch_count.hide() + self.fetch.hide() + self.spacer.hide() + self.done_label.show() + + def Progress(self, count): + if self.in_progress: + if count: + percent = ((count - self.start) * 100) / self.Target() + if percent >= 100: + self.Idle() + else: + self.progress.setValue(percent) + if not count: + # Count value of zero means no more records + self.Done() + + def FetchMoreRecords(self): + if self.done: + return + self.progress.setValue(0) + self.Busy() + self.in_progress = True + self.start = self.model.FetchMoreRecords(self.Target()) + +# Brance data model level two item + +class BranchLevelTwoItem(): + + def __init__(self, row, col, text, parent_item): + self.row = row + self.parent_item = parent_item + self.data = [""] * (col + 1) + self.data[col] = text + self.level = 2 + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def childCount(self): + return 0 + + def hasChildren(self): + return False + + def getData(self, column): + return self.data[column] + +# Brance data model level one item + +class BranchLevelOneItem(): + + def __init__(self, glb, row, data, parent_item): + self.glb = glb + self.row = row + self.parent_item = parent_item + self.child_count = 0 + self.child_items = [] + self.data = data[1:] + self.dbid = data[0] + self.level = 1 + self.query_done = False + self.br_col = len(self.data) - 1 + + def getChildItem(self, row): + return self.child_items[row] + + def getParentItem(self): + return self.parent_item + + def getRow(self): + return self.row + + def Select(self): + self.query_done = True + + if not self.glb.have_disassembler: + return + + query = QSqlQuery(self.glb.db) + + QueryExec(query, "SELECT cpu, to_dso_id, to_symbol_id, to_sym_offset, short_name, long_name, build_id, sym_start, to_ip" + " FROM samples" + " INNER JOIN dsos ON samples.to_dso_id = dsos.id" + " INNER JOIN symbols ON samples.to_symbol_id = symbols.id" + " WHERE samples.id = " + str(self.dbid)) + if not query.next(): + return + cpu = query.value(0) + dso = query.value(1) + sym = query.value(2) + if dso == 0 or sym == 0: + return + off = query.value(3) + short_name = query.value(4) + long_name = query.value(5) + build_id = query.value(6) + sym_start = query.value(7) + ip = query.value(8) + + QueryExec(query, "SELECT samples.dso_id, symbol_id, sym_offset, sym_start" + " FROM samples" + " INNER JOIN symbols ON samples.symbol_id = symbols.id" + " WHERE samples.id > " + str(self.dbid) + " AND cpu = " + str(cpu) + + " ORDER BY samples.id" + " LIMIT 1") + if not query.next(): + return + if query.value(0) != dso: + # Cannot disassemble from one dso to another + return + bsym = query.value(1) + boff = query.value(2) + bsym_start = query.value(3) + if bsym == 0: + return + tot = bsym_start + boff + 1 - sym_start - off + if tot <= 0 or tot > 16384: + return + + inst = self.glb.disassembler.Instruction() + f = self.glb.FileFromNamesAndBuildId(short_name, long_name, build_id) + if not f: + return + mode = 0 if Is64Bit(f) else 1 + self.glb.disassembler.SetMode(inst, mode) + + buf_sz = tot + 16 + buf = create_string_buffer(tot + 16) + f.seek(sym_start + off) + buf.value = f.read(buf_sz) + buf_ptr = addressof(buf) + i = 0 + while tot > 0: + cnt, text = self.glb.disassembler.DisassembleOne(inst, buf_ptr, buf_sz, ip) + if cnt: + byte_str = tohex(ip).rjust(16) + for k in xrange(cnt): + byte_str += " %02x" % ord(buf[i]) + i += 1 + while k < 15: + byte_str += " " + k += 1 + self.child_items.append(BranchLevelTwoItem(0, self.br_col, byte_str + " " + text, self)) + self.child_count += 1 + else: + return + buf_ptr += cnt + tot -= cnt + buf_sz -= cnt + ip += cnt + + def childCount(self): + if not self.query_done: + self.Select() + if not self.child_count: + return -1 + return self.child_count + + def hasChildren(self): + if not self.query_done: + return True + return self.child_count > 0 + + def getData(self, column): + return self.data[column] + +# Brance data model root item + +class BranchRootItem(): + + def __init__(self): + self.child_count = 0 + self.child_items = [] + self.level = 0 + + def getChildItem(self, row): + return self.child_items[row] + + def getParentItem(self): + return None + + def getRow(self): + return 0 + + def childCount(self): + return self.child_count + + def hasChildren(self): + return self.child_count > 0 + + def getData(self, column): + return "" + +# Calculate instructions per cycle + +def CalcIPC(cyc_cnt, insn_cnt): + if cyc_cnt and insn_cnt: + ipc = Decimal(float(insn_cnt) / cyc_cnt) + ipc = str(ipc.quantize(Decimal(".01"), rounding=ROUND_HALF_UP)) + else: + ipc = "0" + return ipc + +# Branch data preparation + +def BranchDataPrepBr(query, data): + data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) + + " (" + dsoname(query.value(11)) + ")" + " -> " + + tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) + + " (" + dsoname(query.value(15)) + ")") + +def BranchDataPrepIPC(query, data): + insn_cnt = query.value(16) + cyc_cnt = query.value(17) + ipc = CalcIPC(cyc_cnt, insn_cnt) + data.append(insn_cnt) + data.append(cyc_cnt) + data.append(ipc) + +def BranchDataPrep(query): + data = [] + for i in xrange(0, 8): + data.append(query.value(i)) + BranchDataPrepBr(query, data) + return data + +def BranchDataPrepWA(query): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, 8): + data.append(query.value(i)) + BranchDataPrepBr(query, data) + return data + +def BranchDataWithIPCPrep(query): + data = [] + for i in xrange(0, 8): + data.append(query.value(i)) + BranchDataPrepIPC(query, data) + BranchDataPrepBr(query, data) + return data + +def BranchDataWithIPCPrepWA(query): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, 8): + data.append(query.value(i)) + BranchDataPrepIPC(query, data) + BranchDataPrepBr(query, data) + return data + +# Branch data model + +class BranchModel(TreeModel): + + progress = Signal(object) + + def __init__(self, glb, event_id, where_clause, parent=None): + super(BranchModel, self).__init__(glb, None, parent) + self.event_id = event_id + self.more = True + self.populated = 0 + self.have_ipc = IsSelectable(glb.db, "samples", columns = "insn_count, cyc_count") + if self.have_ipc: + select_ipc = ", insn_count, cyc_count" + prep_fn = BranchDataWithIPCPrep + prep_wa_fn = BranchDataWithIPCPrepWA + else: + select_ipc = "" + prep_fn = BranchDataPrep + prep_wa_fn = BranchDataPrepWA + sql = ("SELECT samples.id, time, cpu, comm, pid, tid, branch_types.name," + " CASE WHEN in_tx = '0' THEN 'No' ELSE 'Yes' END," + " ip, symbols.name, sym_offset, dsos.short_name," + " to_ip, to_symbols.name, to_sym_offset, to_dsos.short_name" + + select_ipc + + " FROM samples" + " INNER JOIN comms ON comm_id = comms.id" + " INNER JOIN threads ON thread_id = threads.id" + " INNER JOIN branch_types ON branch_type = branch_types.id" + " INNER JOIN symbols ON symbol_id = symbols.id" + " INNER JOIN symbols to_symbols ON to_symbol_id = to_symbols.id" + " INNER JOIN dsos ON samples.dso_id = dsos.id" + " INNER JOIN dsos AS to_dsos ON samples.to_dso_id = to_dsos.id" + " WHERE samples.id > $$last_id$$" + where_clause + + " AND evsel_id = " + str(self.event_id) + + " ORDER BY samples.id" + " LIMIT " + str(glb_chunk_sz)) + if pyside_version_1 and sys.version_info[0] == 3: + prep = prep_fn + else: + prep = prep_wa_fn + self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample) + self.fetcher.done.connect(self.Update) + self.fetcher.Fetch(glb_chunk_sz) + + def GetRoot(self): + return BranchRootItem() + + def columnCount(self, parent=None): + if self.have_ipc: + return 11 + else: + return 8 + + def columnHeader(self, column): + if self.have_ipc: + return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Insn Cnt", "Cyc Cnt", "IPC", "Branch")[column] + else: + return ("Time", "CPU", "Command", "PID", "TID", "Branch Type", "In Tx", "Branch")[column] + + def columnFont(self, column): + if self.have_ipc: + br_col = 10 + else: + br_col = 7 + if column != br_col: + return None + return QFont("Monospace") + + def DisplayData(self, item, index): + if item.level == 1: + self.FetchIfNeeded(item.row) + return item.getData(index.column()) + + def AddSample(self, data): + child = BranchLevelOneItem(self.glb, self.populated, data, self.root) + self.root.child_items.append(child) + self.populated += 1 + + def Update(self, fetched): + if not fetched: + self.more = False + self.progress.emit(0) + child_count = self.root.child_count + count = self.populated - child_count + if count > 0: + parent = QModelIndex() + self.beginInsertRows(parent, child_count, child_count + count - 1) + self.insertRows(child_count, count, parent) + self.root.child_count += count + self.endInsertRows() + self.progress.emit(self.root.child_count) + + def FetchMoreRecords(self, count): + current = self.root.child_count + if self.more: + self.fetcher.Fetch(count) + else: + self.progress.emit(0) + return current + + def HasMoreRecords(self): + return self.more + +# Report Variables + +class ReportVars(): + + def __init__(self, name = "", where_clause = "", limit = ""): + self.name = name + self.where_clause = where_clause + self.limit = limit + + def UniqueId(self): + return str(self.where_clause + ";" + self.limit) + +# Branch window + +class BranchWindow(QMdiSubWindow): + + def __init__(self, glb, event_id, report_vars, parent=None): + super(BranchWindow, self).__init__(parent) + + model_name = "Branch Events " + str(event_id) + " " + report_vars.UniqueId() + + self.model = LookupCreateModel(model_name, lambda: BranchModel(glb, event_id, report_vars.where_clause)) + + self.view = QTreeView() + self.view.setUniformRowHeights(True) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTreeCellsToClipboard + self.view.setModel(self.model) + + self.ResizeColumnsToContents() + + self.context_menu = TreeContextMenu(self.view) + + self.find_bar = FindBar(self, self, True) + + self.finder = ChildDataItemFinder(self.model.root) + + self.fetch_bar = FetchMoreRecordsBar(self.model, self) + + self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, report_vars.name + " Branch Events") + + def ResizeColumnToContents(self, column, n): + # Using the view's resizeColumnToContents() here is extrememly slow + # so implement a crude alternative + mm = "MM" if column else "MMMM" + font = self.view.font() + metrics = QFontMetrics(font) + max = 0 + for row in xrange(n): + val = self.model.root.child_items[row].data[column] + len = metrics.width(str(val) + mm) + max = len if len > max else max + val = self.model.columnHeader(column) + len = metrics.width(str(val) + mm) + max = len if len > max else max + self.view.setColumnWidth(column, max) + + def ResizeColumnsToContents(self): + n = min(self.model.root.child_count, 100) + if n < 1: + # No data yet, so connect a signal to notify when there is + self.model.rowsInserted.connect(self.UpdateColumnWidths) + return + columns = self.model.columnCount() + for i in xrange(columns): + self.ResizeColumnToContents(i, n) + + def UpdateColumnWidths(self, *x): + # This only needs to be done once, so disconnect the signal now + self.model.rowsInserted.disconnect(self.UpdateColumnWidths) + self.ResizeColumnsToContents() + + def Find(self, value, direction, pattern, context): + self.view.setFocus() + self.find_bar.Busy() + self.finder.Find(value, direction, pattern, context, self.FindDone) + + def FindDone(self, row): + self.find_bar.Idle() + if row >= 0: + self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + else: + self.find_bar.NotFound() + +# Line edit data item + +class LineEditDataItem(object): + + def __init__(self, glb, label, placeholder_text, parent, id = "", default = ""): + self.glb = glb + self.label = label + self.placeholder_text = placeholder_text + self.parent = parent + self.id = id + + self.value = default + + self.widget = QLineEdit(default) + self.widget.editingFinished.connect(self.Validate) + self.widget.textChanged.connect(self.Invalidate) + self.red = False + self.error = "" + self.validated = True + + if placeholder_text: + self.widget.setPlaceholderText(placeholder_text) + + def TurnTextRed(self): + if not self.red: + palette = QPalette() + palette.setColor(QPalette.Text,Qt.red) + self.widget.setPalette(palette) + self.red = True + + def TurnTextNormal(self): + if self.red: + palette = QPalette() + self.widget.setPalette(palette) + self.red = False + + def InvalidValue(self, value): + self.value = "" + self.TurnTextRed() + self.error = self.label + " invalid value '" + value + "'" + self.parent.ShowMessage(self.error) + + def Invalidate(self): + self.validated = False + + def DoValidate(self, input_string): + self.value = input_string.strip() + + def Validate(self): + self.validated = True + self.error = "" + self.TurnTextNormal() + self.parent.ClearMessage() + input_string = self.widget.text() + if not len(input_string.strip()): + self.value = "" + return + self.DoValidate(input_string) + + def IsValid(self): + if not self.validated: + self.Validate() + if len(self.error): + self.parent.ShowMessage(self.error) + return False + return True + + def IsNumber(self, value): + try: + x = int(value) + except: + x = 0 + return str(x) == value + +# Non-negative integer ranges dialog data item + +class NonNegativeIntegerRangesDataItem(LineEditDataItem): + + def __init__(self, glb, label, placeholder_text, column_name, parent): + super(NonNegativeIntegerRangesDataItem, self).__init__(glb, label, placeholder_text, parent) + + self.column_name = column_name + + def DoValidate(self, input_string): + singles = [] + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if "-" in value: + vrange = value.split("-") + if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return self.InvalidValue(value) + ranges.append(vrange) + else: + if not self.IsNumber(value): + return self.InvalidValue(value) + singles.append(value) + ranges = [("(" + self.column_name + " >= " + r[0] + " AND " + self.column_name + " <= " + r[1] + ")") for r in ranges] + if len(singles): + ranges.append(self.column_name + " IN (" + ",".join(singles) + ")") + self.value = " OR ".join(ranges) + +# Positive integer dialog data item + +class PositiveIntegerDataItem(LineEditDataItem): + + def __init__(self, glb, label, placeholder_text, parent, id = "", default = ""): + super(PositiveIntegerDataItem, self).__init__(glb, label, placeholder_text, parent, id, default) + + def DoValidate(self, input_string): + if not self.IsNumber(input_string.strip()): + return self.InvalidValue(input_string) + value = int(input_string.strip()) + if value <= 0: + return self.InvalidValue(input_string) + self.value = str(value) + +# Dialog data item converted and validated using a SQL table + +class SQLTableDataItem(LineEditDataItem): + + def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent): + super(SQLTableDataItem, self).__init__(glb, label, placeholder_text, parent) + + self.table_name = table_name + self.match_column = match_column + self.column_name1 = column_name1 + self.column_name2 = column_name2 + + def ValueToIds(self, value): + ids = [] + query = QSqlQuery(self.glb.db) + stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'" + ret = query.exec_(stmt) + if ret: + while query.next(): + ids.append(str(query.value(0))) + return ids + + def DoValidate(self, input_string): + all_ids = [] + for value in [x.strip() for x in input_string.split(",")]: + ids = self.ValueToIds(value) + if len(ids): + all_ids.extend(ids) + else: + return self.InvalidValue(value) + self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")" + if self.column_name2: + self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )" + +# Sample time ranges dialog data item converted and validated using 'samples' SQL table + +class SampleTimeRangesDataItem(LineEditDataItem): + + def __init__(self, glb, label, placeholder_text, column_name, parent): + self.column_name = column_name + + self.last_id = 0 + self.first_time = 0 + self.last_time = 2 ** 64 + + query = QSqlQuery(glb.db) + QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1") + if query.next(): + self.last_id = int(query.value(0)) + self.first_time = int(glb.HostStartTime()) + self.last_time = int(glb.HostFinishTime()) + if placeholder_text: + placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time) + + super(SampleTimeRangesDataItem, self).__init__(glb, label, placeholder_text, parent) + + def IdBetween(self, query, lower_id, higher_id, order): + QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1") + if query.next(): + return True, int(query.value(0)) + else: + return False, 0 + + def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor): + query = QSqlQuery(self.glb.db) + while True: + next_id = int((lower_id + higher_id) / 2) + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + if not query.next(): + ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC") + if not ok: + ok, dbid = self.IdBetween(query, next_id, higher_id, "") + if not ok: + return str(higher_id) + next_id = dbid + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + next_time = int(query.value(0)) + if get_floor: + if target_time > next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(higher_id) + else: + if target_time >= next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(lower_id) + + def ConvertRelativeTime(self, val): + mult = 1 + suffix = val[-2:] + if suffix == "ms": + mult = 1000000 + elif suffix == "us": + mult = 1000 + elif suffix == "ns": + mult = 1 + else: + return val + val = val[:-2].strip() + if not self.IsNumber(val): + return val + val = int(val) * mult + if val >= 0: + val += self.first_time + else: + val += self.last_time + return str(val) + + def ConvertTimeRange(self, vrange): + if vrange[0] == "": + vrange[0] = str(self.first_time) + if vrange[1] == "": + vrange[1] = str(self.last_time) + vrange[0] = self.ConvertRelativeTime(vrange[0]) + vrange[1] = self.ConvertRelativeTime(vrange[1]) + if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return False + beg_range = max(int(vrange[0]), self.first_time) + end_range = min(int(vrange[1]), self.last_time) + if beg_range > self.last_time or end_range < self.first_time: + return False + vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True) + vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False) + return True + + def AddTimeRange(self, value, ranges): + n = value.count("-") + if n == 1: + pass + elif n == 2: + if value.split("-")[1].strip() == "": + n = 1 + elif n == 3: + n = 2 + else: + return False + pos = findnth(value, "-", n) + vrange = [value[:pos].strip() ,value[pos+1:].strip()] + if self.ConvertTimeRange(vrange): + ranges.append(vrange) + return True + return False + + def DoValidate(self, input_string): + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if not self.AddTimeRange(value, ranges): + return self.InvalidValue(value) + ranges = [("(" + self.column_name + " >= " + r[0] + " AND " + self.column_name + " <= " + r[1] + ")") for r in ranges] + self.value = " OR ".join(ranges) + +# Report Dialog Base + +class ReportDialogBase(QDialog): + + def __init__(self, glb, title, items, partial, parent=None): + super(ReportDialogBase, self).__init__(parent) + + self.glb = glb + + self.report_vars = ReportVars() + + self.setWindowTitle(title) + self.setMinimumWidth(600) + + self.data_items = [x(glb, self) for x in items] + + self.partial = partial + + self.grid = QGridLayout() + + for row in xrange(len(self.data_items)): + self.grid.addWidget(QLabel(self.data_items[row].label), row, 0) + self.grid.addWidget(self.data_items[row].widget, row, 1) + + self.status = QLabel() + + self.ok_button = QPushButton("Ok", self) + self.ok_button.setDefault(True) + self.ok_button.released.connect(self.Ok) + self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.cancel_button = QPushButton("Cancel", self) + self.cancel_button.released.connect(self.reject) + self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.hbox = QHBoxLayout() + #self.hbox.addStretch() + self.hbox.addWidget(self.status) + self.hbox.addWidget(self.ok_button) + self.hbox.addWidget(self.cancel_button) + + self.vbox = QVBoxLayout() + self.vbox.addLayout(self.grid) + self.vbox.addLayout(self.hbox) + + self.setLayout(self.vbox) + + def Ok(self): + vars = self.report_vars + for d in self.data_items: + if d.id == "REPORTNAME": + vars.name = d.value + if not vars.name: + self.ShowMessage("Report name is required") + return + for d in self.data_items: + if not d.IsValid(): + return + for d in self.data_items[1:]: + if d.id == "LIMIT": + vars.limit = d.value + elif len(d.value): + if len(vars.where_clause): + vars.where_clause += " AND " + vars.where_clause += d.value + if len(vars.where_clause): + if self.partial: + vars.where_clause = " AND ( " + vars.where_clause + " ) " + else: + vars.where_clause = " WHERE " + vars.where_clause + " " + self.accept() + + def ShowMessage(self, msg): + self.status.setText("<font color=#FF0000>" + msg) + + def ClearMessage(self): + self.status.setText("") + +# Selected branch report creation dialog + +class SelectedBranchDialog(ReportDialogBase): + + def __init__(self, glb, parent=None): + title = "Selected Branches" + items = (lambda g, p: LineEditDataItem(g, "Report name:", "Enter a name to appear in the window title bar", p, "REPORTNAME"), + lambda g, p: SampleTimeRangesDataItem(g, "Time ranges:", "Enter time ranges", "samples.id", p), + lambda g, p: NonNegativeIntegerRangesDataItem(g, "CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "cpu", p), + lambda g, p: SQLTableDataItem(g, "Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", "", p), + lambda g, p: SQLTableDataItem(g, "PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", "", p), + lambda g, p: SQLTableDataItem(g, "TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", "", p), + lambda g, p: SQLTableDataItem(g, "DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id", p), + lambda g, p: SQLTableDataItem(g, "Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id", p), + lambda g, p: LineEditDataItem(g, "Raw SQL clause: ", "Enter a raw SQL WHERE clause", p)) + super(SelectedBranchDialog, self).__init__(glb, title, items, True, parent) + +# Event list + +def GetEventList(db): + events = [] + query = QSqlQuery(db) + QueryExec(query, "SELECT name FROM selected_events WHERE id > 0 ORDER BY id") + while query.next(): + events.append(query.value(0)) + return events + +# Is a table selectable + +def IsSelectable(db, table, sql = "", columns = "*"): + query = QSqlQuery(db) + try: + QueryExec(query, "SELECT " + columns + " FROM " + table + " " + sql + " LIMIT 1") + except: + return False + return True + +# SQL table data model item + +class SQLTableItem(): + + def __init__(self, row, data): + self.row = row + self.data = data + + def getData(self, column): + return self.data[column] + +# SQL table data model + +class SQLTableModel(TableModel): + + progress = Signal(object) + + def __init__(self, glb, sql, column_headers, parent=None): + super(SQLTableModel, self).__init__(parent) + self.glb = glb + self.more = True + self.populated = 0 + self.column_headers = column_headers + self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample) + self.fetcher.done.connect(self.Update) + self.fetcher.Fetch(glb_chunk_sz) + + def DisplayData(self, item, index): + self.FetchIfNeeded(item.row) + return item.getData(index.column()) + + def AddSample(self, data): + child = SQLTableItem(self.populated, data) + self.child_items.append(child) + self.populated += 1 + + def Update(self, fetched): + if not fetched: + self.more = False + self.progress.emit(0) + child_count = self.child_count + count = self.populated - child_count + if count > 0: + parent = QModelIndex() + self.beginInsertRows(parent, child_count, child_count + count - 1) + self.insertRows(child_count, count, parent) + self.child_count += count + self.endInsertRows() + self.progress.emit(self.child_count) + + def FetchMoreRecords(self, count): + current = self.child_count + if self.more: + self.fetcher.Fetch(count) + else: + self.progress.emit(0) + return current + + def HasMoreRecords(self): + return self.more + + def columnCount(self, parent=None): + return len(self.column_headers) + + def columnHeader(self, column): + return self.column_headers[column] + + def SQLTableDataPrep(self, query, count): + data = [] + for i in xrange(count): + data.append(query.value(i)) + return data + +# SQL automatic table data model + +class SQLAutoTableModel(SQLTableModel): + + def __init__(self, glb, table_name, parent=None): + sql = "SELECT * FROM " + table_name + " WHERE id > $$last_id$$ ORDER BY id LIMIT " + str(glb_chunk_sz) + if table_name == "comm_threads_view": + # For now, comm_threads_view has no id column + sql = "SELECT * FROM " + table_name + " WHERE comm_id > $$last_id$$ ORDER BY comm_id LIMIT " + str(glb_chunk_sz) + column_headers = [] + query = QSqlQuery(glb.db) + if glb.dbref.is_sqlite3: + QueryExec(query, "PRAGMA table_info(" + table_name + ")") + while query.next(): + column_headers.append(query.value(1)) + if table_name == "sqlite_master": + sql = "SELECT * FROM " + table_name + else: + if table_name[:19] == "information_schema.": + sql = "SELECT * FROM " + table_name + select_table_name = table_name[19:] + schema = "information_schema" + else: + select_table_name = table_name + schema = "public" + QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'") + while query.next(): + column_headers.append(query.value(0)) + if pyside_version_1 and sys.version_info[0] == 3: + if table_name == "samples_view": + self.SQLTableDataPrep = self.samples_view_DataPrep + if table_name == "samples": + self.SQLTableDataPrep = self.samples_DataPrep + super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent) + + def samples_view_DataPrep(self, query, count): + data = [] + data.append(query.value(0)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(1))) + for i in xrange(2, count): + data.append(query.value(i)) + return data + + def samples_DataPrep(self, query, count): + data = [] + for i in xrange(9): + data.append(query.value(i)) + # Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string + data.append("{:>19}".format(query.value(9))) + for i in xrange(10, count): + data.append(query.value(i)) + return data + +# Base class for custom ResizeColumnsToContents + +class ResizeColumnsToContentsBase(QObject): + + def __init__(self, parent=None): + super(ResizeColumnsToContentsBase, self).__init__(parent) + + def ResizeColumnToContents(self, column, n): + # Using the view's resizeColumnToContents() here is extrememly slow + # so implement a crude alternative + font = self.view.font() + metrics = QFontMetrics(font) + max = 0 + for row in xrange(n): + val = self.data_model.child_items[row].data[column] + len = metrics.width(str(val) + "MM") + max = len if len > max else max + val = self.data_model.columnHeader(column) + len = metrics.width(str(val) + "MM") + max = len if len > max else max + self.view.setColumnWidth(column, max) + + def ResizeColumnsToContents(self): + n = min(self.data_model.child_count, 100) + if n < 1: + # No data yet, so connect a signal to notify when there is + self.data_model.rowsInserted.connect(self.UpdateColumnWidths) + return + columns = self.data_model.columnCount() + for i in xrange(columns): + self.ResizeColumnToContents(i, n) + + def UpdateColumnWidths(self, *x): + # This only needs to be done once, so disconnect the signal now + self.data_model.rowsInserted.disconnect(self.UpdateColumnWidths) + self.ResizeColumnsToContents() + +# Convert value to CSV + +def ToCSValue(val): + if '"' in val: + val = val.replace('"', '""') + if "," in val or '"' in val: + val = '"' + val + '"' + return val + +# Key to sort table model indexes by row / column, assuming fewer than 1000 columns + +glb_max_cols = 1000 + +def RowColumnKey(a): + return a.row() * glb_max_cols + a.column() + +# Copy selected table cells to clipboard + +def CopyTableCellsToClipboard(view, as_csv=False, with_hdr=False): + indexes = sorted(view.selectedIndexes(), key=RowColumnKey) + idx_cnt = len(indexes) + if not idx_cnt: + return + if idx_cnt == 1: + with_hdr=False + min_row = indexes[0].row() + max_row = indexes[0].row() + min_col = indexes[0].column() + max_col = indexes[0].column() + for i in indexes: + min_row = min(min_row, i.row()) + max_row = max(max_row, i.row()) + min_col = min(min_col, i.column()) + max_col = max(max_col, i.column()) + if max_col > glb_max_cols: + raise RuntimeError("glb_max_cols is too low") + max_width = [0] * (1 + max_col - min_col) + for i in indexes: + c = i.column() - min_col + max_width[c] = max(max_width[c], len(str(i.data()))) + text = "" + pad = "" + sep = "" + if with_hdr: + model = indexes[0].model() + for col in range(min_col, max_col + 1): + val = model.headerData(col, Qt.Horizontal, Qt.DisplayRole) + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + c = col - min_col + max_width[c] = max(max_width[c], len(val)) + width = max_width[c] + align = model.headerData(col, Qt.Horizontal, Qt.TextAlignmentRole) + if align & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + text += "\n" + pad = "" + sep = "" + last_row = min_row + for i in indexes: + if i.row() > last_row: + last_row = i.row() + text += "\n" + pad = "" + sep = "" + if as_csv: + text += sep + ToCSValue(str(i.data())) + sep = "," + else: + width = max_width[i.column() - min_col] + if i.data(Qt.TextAlignmentRole) & Qt.AlignRight: + val = str(i.data()).rjust(width) + else: + val = str(i.data()) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + QApplication.clipboard().setText(text) + +def CopyTreeCellsToClipboard(view, as_csv=False, with_hdr=False): + indexes = view.selectedIndexes() + if not len(indexes): + return + + selection = view.selectionModel() + + first = None + for i in indexes: + above = view.indexAbove(i) + if not selection.isSelected(above): + first = i + break + + if first is None: + raise RuntimeError("CopyTreeCellsToClipboard internal error") + + model = first.model() + row_cnt = 0 + col_cnt = model.columnCount(first) + max_width = [0] * col_cnt + + indent_sz = 2 + indent_str = " " * indent_sz + + expanded_mark_sz = 2 + if sys.version_info[0] == 3: + expanded_mark = "\u25BC " + not_expanded_mark = "\u25B6 " + else: + expanded_mark = unicode(chr(0xE2) + chr(0x96) + chr(0xBC) + " ", "utf-8") + not_expanded_mark = unicode(chr(0xE2) + chr(0x96) + chr(0xB6) + " ", "utf-8") + leaf_mark = " " + + if not as_csv: + pos = first + while True: + row_cnt += 1 + row = pos.row() + for c in range(col_cnt): + i = pos.sibling(row, c) + if c: + n = len(str(i.data())) + else: + n = len(str(i.data()).strip()) + n += (i.internalPointer().level - 1) * indent_sz + n += expanded_mark_sz + max_width[c] = max(max_width[c], n) + pos = view.indexBelow(pos) + if not selection.isSelected(pos): + break + + text = "" + pad = "" + sep = "" + if with_hdr: + for c in range(col_cnt): + val = model.headerData(c, Qt.Horizontal, Qt.DisplayRole).strip() + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + max_width[c] = max(max_width[c], len(val)) + width = max_width[c] + align = model.headerData(c, Qt.Horizontal, Qt.TextAlignmentRole) + if align & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + text += "\n" + pad = "" + sep = "" + + pos = first + while True: + row = pos.row() + for c in range(col_cnt): + i = pos.sibling(row, c) + val = str(i.data()) + if not c: + if model.hasChildren(i): + if view.isExpanded(i): + mark = expanded_mark + else: + mark = not_expanded_mark + else: + mark = leaf_mark + val = indent_str * (i.internalPointer().level - 1) + mark + val.strip() + if as_csv: + text += sep + ToCSValue(val) + sep = "," + else: + width = max_width[c] + if c and i.data(Qt.TextAlignmentRole) & Qt.AlignRight: + val = val.rjust(width) + text += pad + sep + val + pad = " " * (width - len(val)) + sep = " " + pos = view.indexBelow(pos) + if not selection.isSelected(pos): + break + text = text.rstrip() + "\n" + pad = "" + sep = "" + + QApplication.clipboard().setText(text) + +def CopyCellsToClipboard(view, as_csv=False, with_hdr=False): + view.CopyCellsToClipboard(view, as_csv, with_hdr) + +def CopyCellsToClipboardHdr(view): + CopyCellsToClipboard(view, False, True) + +def CopyCellsToClipboardCSV(view): + CopyCellsToClipboard(view, True, True) + +# Context menu + +class ContextMenu(object): + + def __init__(self, view): + self.view = view + self.view.setContextMenuPolicy(Qt.CustomContextMenu) + self.view.customContextMenuRequested.connect(self.ShowContextMenu) + + def ShowContextMenu(self, pos): + menu = QMenu(self.view) + self.AddActions(menu) + menu.exec_(self.view.mapToGlobal(pos)) + + def AddCopy(self, menu): + menu.addAction(CreateAction("&Copy selection", "Copy to clipboard", lambda: CopyCellsToClipboardHdr(self.view), self.view)) + menu.addAction(CreateAction("Copy selection as CS&V", "Copy to clipboard as CSV", lambda: CopyCellsToClipboardCSV(self.view), self.view)) + + def AddActions(self, menu): + self.AddCopy(menu) + +class TreeContextMenu(ContextMenu): + + def __init__(self, view): + super(TreeContextMenu, self).__init__(view) + + def AddActions(self, menu): + i = self.view.currentIndex() + text = str(i.data()).strip() + if len(text): + menu.addAction(CreateAction('Copy "' + text + '"', "Copy to clipboard", lambda: QApplication.clipboard().setText(text), self.view)) + self.AddCopy(menu) + +# Table window + +class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): + + def __init__(self, glb, table_name, parent=None): + super(TableWindow, self).__init__(parent) + + self.data_model = LookupCreateModel(table_name + " Table", lambda: SQLAutoTableModel(glb, table_name)) + + self.model = QSortFilterProxyModel() + self.model.setSourceModel(self.data_model) + + self.view = QTableView() + self.view.setModel(self.model) + self.view.setEditTriggers(QAbstractItemView.NoEditTriggers) + self.view.verticalHeader().setVisible(False) + self.view.sortByColumn(-1, Qt.AscendingOrder) + self.view.setSortingEnabled(True) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTableCellsToClipboard + + self.ResizeColumnsToContents() + + self.context_menu = ContextMenu(self.view) + + self.find_bar = FindBar(self, self, True) + + self.finder = ChildDataItemFinder(self.data_model) + + self.fetch_bar = FetchMoreRecordsBar(self.data_model, self) + + self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, table_name + " Table") + + def Find(self, value, direction, pattern, context): + self.view.setFocus() + self.find_bar.Busy() + self.finder.Find(value, direction, pattern, context, self.FindDone) + + def FindDone(self, row): + self.find_bar.Idle() + if row >= 0: + self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex()))) + else: + self.find_bar.NotFound() + +# Table list + +def GetTableList(glb): + tables = [] + query = QSqlQuery(glb.db) + if glb.dbref.is_sqlite3: + QueryExec(query, "SELECT name FROM sqlite_master WHERE type IN ( 'table' , 'view' ) ORDER BY name") + else: + QueryExec(query, "SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type IN ( 'BASE TABLE' , 'VIEW' ) ORDER BY table_name") + while query.next(): + tables.append(query.value(0)) + if glb.dbref.is_sqlite3: + tables.append("sqlite_master") + else: + tables.append("information_schema.tables") + tables.append("information_schema.views") + tables.append("information_schema.columns") + return tables + +# Top Calls data model + +class TopCallsModel(SQLTableModel): + + def __init__(self, glb, report_vars, parent=None): + text = "" + if not glb.dbref.is_sqlite3: + text = "::text" + limit = "" + if len(report_vars.limit): + limit = " LIMIT " + report_vars.limit + sql = ("SELECT comm, pid, tid, name," + " CASE" + " WHEN (short_name = '[kernel.kallsyms]') THEN '[kernel]'" + text + + " ELSE short_name" + " END AS dso," + " call_time, return_time, (return_time - call_time) AS elapsed_time, branch_count, " + " CASE" + " WHEN (calls.flags = 1) THEN 'no call'" + text + + " WHEN (calls.flags = 2) THEN 'no return'" + text + + " WHEN (calls.flags = 3) THEN 'no call/return'" + text + + " ELSE ''" + text + + " END AS flags" + " FROM calls" + " INNER JOIN call_paths ON calls.call_path_id = call_paths.id" + " INNER JOIN symbols ON call_paths.symbol_id = symbols.id" + " INNER JOIN dsos ON symbols.dso_id = dsos.id" + " INNER JOIN comms ON calls.comm_id = comms.id" + " INNER JOIN threads ON calls.thread_id = threads.id" + + report_vars.where_clause + + " ORDER BY elapsed_time DESC" + + limit + ) + column_headers = ("Command", "PID", "TID", "Symbol", "Object", "Call Time", "Return Time", "Elapsed Time (ns)", "Branch Count", "Flags") + self.alignment = (Qt.AlignLeft, Qt.AlignLeft, Qt.AlignLeft, Qt.AlignLeft, Qt.AlignLeft, Qt.AlignLeft, Qt.AlignLeft, Qt.AlignRight, Qt.AlignRight, Qt.AlignLeft) + super(TopCallsModel, self).__init__(glb, sql, column_headers, parent) + + def columnAlignment(self, column): + return self.alignment[column] + +# Top Calls report creation dialog + +class TopCallsDialog(ReportDialogBase): + + def __init__(self, glb, parent=None): + title = "Top Calls by Elapsed Time" + items = (lambda g, p: LineEditDataItem(g, "Report name:", "Enter a name to appear in the window title bar", p, "REPORTNAME"), + lambda g, p: SQLTableDataItem(g, "Commands:", "Only calls with these commands will be included", "comms", "comm", "comm_id", "", p), + lambda g, p: SQLTableDataItem(g, "PIDs:", "Only calls with these process IDs will be included", "threads", "pid", "thread_id", "", p), + lambda g, p: SQLTableDataItem(g, "TIDs:", "Only calls with these thread IDs will be included", "threads", "tid", "thread_id", "", p), + lambda g, p: SQLTableDataItem(g, "DSOs:", "Only calls with these DSOs will be included", "dsos", "short_name", "dso_id", "", p), + lambda g, p: SQLTableDataItem(g, "Symbols:", "Only calls with these symbols will be included", "symbols", "name", "symbol_id", "", p), + lambda g, p: LineEditDataItem(g, "Raw SQL clause: ", "Enter a raw SQL WHERE clause", p), + lambda g, p: PositiveIntegerDataItem(g, "Record limit:", "Limit selection to this number of records", p, "LIMIT", "100")) + super(TopCallsDialog, self).__init__(glb, title, items, False, parent) + +# Top Calls window + +class TopCallsWindow(QMdiSubWindow, ResizeColumnsToContentsBase): + + def __init__(self, glb, report_vars, parent=None): + super(TopCallsWindow, self).__init__(parent) + + self.data_model = LookupCreateModel("Top Calls " + report_vars.UniqueId(), lambda: TopCallsModel(glb, report_vars)) + self.model = self.data_model + + self.view = QTableView() + self.view.setModel(self.model) + self.view.setEditTriggers(QAbstractItemView.NoEditTriggers) + self.view.verticalHeader().setVisible(False) + self.view.setSelectionMode(QAbstractItemView.ContiguousSelection) + self.view.CopyCellsToClipboard = CopyTableCellsToClipboard + + self.context_menu = ContextMenu(self.view) + + self.ResizeColumnsToContents() + + self.find_bar = FindBar(self, self, True) + + self.finder = ChildDataItemFinder(self.model) + + self.fetch_bar = FetchMoreRecordsBar(self.data_model, self) + + self.vbox = VBox(self.view, self.find_bar.Widget(), self.fetch_bar.Widget()) + + self.setWidget(self.vbox.Widget()) + + AddSubWindow(glb.mainwindow.mdi_area, self, report_vars.name) + + def Find(self, value, direction, pattern, context): + self.view.setFocus() + self.find_bar.Busy() + self.finder.Find(value, direction, pattern, context, self.FindDone) + + def FindDone(self, row): + self.find_bar.Idle() + if row >= 0: + self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + else: + self.find_bar.NotFound() + +# Action Definition + +def CreateAction(label, tip, callback, parent=None, shortcut=None): + action = QAction(label, parent) + if shortcut != None: + action.setShortcuts(shortcut) + action.setStatusTip(tip) + action.triggered.connect(callback) + return action + +# Typical application actions + +def CreateExitAction(app, parent=None): + return CreateAction("&Quit", "Exit the application", app.closeAllWindows, parent, QKeySequence.Quit) + +# Typical MDI actions + +def CreateCloseActiveWindowAction(mdi_area): + return CreateAction("Cl&ose", "Close the active window", mdi_area.closeActiveSubWindow, mdi_area) + +def CreateCloseAllWindowsAction(mdi_area): + return CreateAction("Close &All", "Close all the windows", mdi_area.closeAllSubWindows, mdi_area) + +def CreateTileWindowsAction(mdi_area): + return CreateAction("&Tile", "Tile the windows", mdi_area.tileSubWindows, mdi_area) + +def CreateCascadeWindowsAction(mdi_area): + return CreateAction("&Cascade", "Cascade the windows", mdi_area.cascadeSubWindows, mdi_area) + +def CreateNextWindowAction(mdi_area): + return CreateAction("Ne&xt", "Move the focus to the next window", mdi_area.activateNextSubWindow, mdi_area, QKeySequence.NextChild) + +def CreatePreviousWindowAction(mdi_area): + return CreateAction("Pre&vious", "Move the focus to the previous window", mdi_area.activatePreviousSubWindow, mdi_area, QKeySequence.PreviousChild) + +# Typical MDI window menu + +class WindowMenu(): + + def __init__(self, mdi_area, menu): + self.mdi_area = mdi_area + self.window_menu = menu.addMenu("&Windows") + self.close_active_window = CreateCloseActiveWindowAction(mdi_area) + self.close_all_windows = CreateCloseAllWindowsAction(mdi_area) + self.tile_windows = CreateTileWindowsAction(mdi_area) + self.cascade_windows = CreateCascadeWindowsAction(mdi_area) + self.next_window = CreateNextWindowAction(mdi_area) + self.previous_window = CreatePreviousWindowAction(mdi_area) + self.window_menu.aboutToShow.connect(self.Update) + + def Update(self): + self.window_menu.clear() + sub_window_count = len(self.mdi_area.subWindowList()) + have_sub_windows = sub_window_count != 0 + self.close_active_window.setEnabled(have_sub_windows) + self.close_all_windows.setEnabled(have_sub_windows) + self.tile_windows.setEnabled(have_sub_windows) + self.cascade_windows.setEnabled(have_sub_windows) + self.next_window.setEnabled(have_sub_windows) + self.previous_window.setEnabled(have_sub_windows) + self.window_menu.addAction(self.close_active_window) + self.window_menu.addAction(self.close_all_windows) + self.window_menu.addSeparator() + self.window_menu.addAction(self.tile_windows) + self.window_menu.addAction(self.cascade_windows) + self.window_menu.addSeparator() + self.window_menu.addAction(self.next_window) + self.window_menu.addAction(self.previous_window) + if sub_window_count == 0: + return + self.window_menu.addSeparator() + nr = 1 + for sub_window in self.mdi_area.subWindowList(): + label = str(nr) + " " + sub_window.name + if nr < 10: + label = "&" + label + action = self.window_menu.addAction(label) + action.setCheckable(True) + action.setChecked(sub_window == self.mdi_area.activeSubWindow()) + action.triggered.connect(lambda a=None,x=nr: self.setActiveSubWindow(x)) + self.window_menu.addAction(action) + nr += 1 + + def setActiveSubWindow(self, nr): + self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1]) + +# Help text + +glb_help_text = """ +<h1>Contents</h1> +<style> +p.c1 { + text-indent: 40px; +} +p.c2 { + text-indent: 80px; +} +} +</style> +<p class=c1><a href=#reports>1. Reports</a></p> +<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p> +<p class=c2><a href=#calltree>1.2 Call Tree</a></p> +<p class=c2><a href=#allbranches>1.3 All branches</a></p> +<p class=c2><a href=#selectedbranches>1.4 Selected branches</a></p> +<p class=c2><a href=#topcallsbyelapsedtime>1.5 Top calls by elapsed time</a></p> +<p class=c1><a href=#charts>2. Charts</a></p> +<p class=c2><a href=#timechartbycpu>2.1 Time chart by CPU</a></p> +<p class=c1><a href=#tables>3. Tables</a></p> +<h1 id=reports>1. Reports</h1> +<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2> +The result is a GUI window with a tree representing a context-sensitive +call-graph. Expanding a couple of levels of the tree and adjusting column +widths to suit will display something like: +<pre> + Call Graph: pt_example +Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +v- ls + v- 2638:2638 + v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 + |- unknown unknown 1 13198 0.1 1 0.0 + >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 + >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 + v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 + >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 + >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 + >- __libc_csu_init ls 1 10354 0.1 10 0.0 + |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 + v- main ls 1 8182043 99.6 180254 99.9 +</pre> +<h3>Points to note:</h3> +<ul> +<li>The top level is a command name (comm)</li> +<li>The next level is a thread (pid:tid)</li> +<li>Subsequent levels are functions</li> +<li>'Count' is the number of calls</li> +<li>'Time' is the elapsed time until the function returns</li> +<li>Percentages are relative to the level above</li> +<li>'Branch Count' is the total number of branches for that function and all functions that it calls +</ul> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match. +The pattern matching symbols are ? for any character and * for zero or more characters. +<h2 id=calltree>1.2 Call Tree</h2> +The Call Tree report is very similar to the Context-Sensitive Call Graph, but the data is not aggregated. +Also the 'Count' column, which would be always 1, is replaced by the 'Call Time'. +<h2 id=allbranches>1.3 All branches</h2> +The All branches report displays all branches in chronological order. +Not all data is fetched immediately. More records can be fetched using the Fetch bar provided. +<h3>Disassembly</h3> +Open a branch to display disassembly. This only works if: +<ol> +<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li> +<li>The object code is available. Currently, only the perf build ID cache is searched for object code. +The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR. +One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu), +or alternatively, set environment variable PERF_KCORE to the kcore file name.</li> +</ol> +<h4 id=xed>Intel XED Setup</h4> +To use Intel XED, libxed.so must be present. To build and install libxed.so: +<pre> +git clone https://github.com/intelxed/mbuild.git mbuild +git clone https://github.com/intelxed/xed +cd xed +./mfile.py --share +sudo ./mfile.py --prefix=/usr/local install +sudo ldconfig +</pre> +<h3>Instructions per Cycle (IPC)</h3> +If available, IPC information is displayed in columns 'insn_cnt', 'cyc_cnt' and 'IPC'. +<p><b>Intel PT note:</b> The information applies to the blocks of code ending with, and including, that branch. +Due to the granularity of timing information, the number of cycles for some code blocks will not be known. +In that case, 'insn_cnt', 'cyc_cnt' and 'IPC' are zero, but when 'IPC' is displayed it covers the period +since the previous displayed 'IPC'. +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<h2 id=selectedbranches>1.4 Selected branches</h2> +This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced +by various selection criteria. A dialog box displays available criteria which are AND'ed together. +<h3>1.4.1 Time ranges</h3> +The time ranges hint text shows the total time range. Relative time ranges can also be entered in +ms, us or ns. Also, negative values are relative to the end of trace. Examples: +<pre> + 81073085947329-81073085958238 From 81073085947329 to 81073085958238 + 100us-200us From 100us to 200us + 10ms- From 10ms to the end + -100ns The first 100ns + -10ms- The last 10ms +</pre> +N.B. Due to the granularity of timestamps, there could be no branches in any given time range. +<h2 id=topcallsbyelapsedtime>1.5 Top calls by elapsed time</h2> +The Top calls by elapsed time report displays calls in descending order of time elapsed between when the function was called and when it returned. +The data is reduced by various selection criteria. A dialog box displays available criteria which are AND'ed together. +If not all data is fetched, a Fetch bar is provided. Ctrl-F displays a Find bar. +<h1 id=charts>2. Charts</h1> +<h2 id=timechartbycpu>2.1 Time chart by CPU</h2> +This chart displays context switch information when that data is available. Refer to context_switches_view on the Tables menu. +<h3>Features</h3> +<ol> +<li>Mouse over to highight the task and show the time</li> +<li>Drag the mouse to select a region and zoom by pushing the Zoom button</li> +<li>Go back and forward by pressing the arrow buttons</li> +<li>If call information is available, right-click to show a call tree opened to that task and time. +Note, the call tree may take some time to appear, and there may not be call information for the task or time selected. +</li> +</ol> +<h3>Important</h3> +The graph can be misleading in the following respects: +<ol> +<li>The graph shows the first task on each CPU as running from the beginning of the time range. +Because tracing might start on different CPUs at different times, that is not necessarily the case. +Refer to context_switches_view on the Tables menu to understand what data the graph is based upon.</li> +<li>Similarly, the last task on each CPU can be showing running longer than it really was. +Again, refer to context_switches_view on the Tables menu to understand what data the graph is based upon.</li> +<li>When the mouse is over a task, the highlighted task might not be visible on the legend without scrolling if the legend does not fit fully in the window</li> +</ol> +<h1 id=tables>3. Tables</h1> +The Tables menu shows all tables and views in the database. Most tables have an associated view +which displays the information in a more friendly way. Not all data for large tables is fetched +immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted, +but that can be slow for large tables. +<p>There are also tables of database meta-information. +For SQLite3 databases, the sqlite_master table is included. +For PostgreSQL databases, information_schema.tables/views/columns are included. +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous +will go to the next/previous result in id order, instead of display order. +""" + +# Help window + +class HelpWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(HelpWindow, self).__init__(parent) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setWidget(self.text) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help") + +# Main window that only displays the help text + +class HelpOnlyWindow(QMainWindow): + + def __init__(self, parent=None): + super(HelpOnlyWindow, self).__init__(parent) + + self.setMinimumSize(200, 100) + self.resize(800, 600) + self.setWindowTitle("Exported SQL Viewer Help") + self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setCentralWidget(self.text) + +# PostqreSQL server version + +def PostqreSQLServerVersion(db): + query = QSqlQuery(db) + QueryExec(query, "SELECT VERSION()") + if query.next(): + v_str = query.value(0) + v_list = v_str.strip().split(" ") + if v_list[0] == "PostgreSQL" and v_list[2] == "on": + return v_list[1] + return v_str + return "Unknown" + +# SQLite version + +def SQLiteVersion(db): + query = QSqlQuery(db) + QueryExec(query, "SELECT sqlite_version()") + if query.next(): + return query.value(0) + return "Unknown" + +# About dialog + +class AboutDialog(QDialog): + + def __init__(self, glb, parent=None): + super(AboutDialog, self).__init__(parent) + + self.setWindowTitle("About Exported SQL Viewer") + self.setMinimumWidth(300) + + pyside_version = "1" if pyside_version_1 else "2" + + text = "<pre>" + text += "Python version: " + sys.version.split(" ")[0] + "\n" + text += "PySide version: " + pyside_version + "\n" + text += "Qt version: " + qVersion() + "\n" + if glb.dbref.is_sqlite3: + text += "SQLite version: " + SQLiteVersion(glb.db) + "\n" + else: + text += "PostqreSQL version: " + PostqreSQLServerVersion(glb.db) + "\n" + text += "</pre>" + + self.text = QTextBrowser() + self.text.setHtml(text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.vbox = QVBoxLayout() + self.vbox.addWidget(self.text) + + self.setLayout(self.vbox) + +# Font resize + +def ResizeFont(widget, diff): + font = widget.font() + sz = font.pointSize() + font.setPointSize(sz + diff) + widget.setFont(font) + +def ShrinkFont(widget): + ResizeFont(widget, -1) + +def EnlargeFont(widget): + ResizeFont(widget, 1) + +# Unique name for sub-windows + +def NumberedWindowName(name, nr): + if nr > 1: + name += " <" + str(nr) + ">" + return name + +def UniqueSubWindowName(mdi_area, name): + nr = 1 + while True: + unique_name = NumberedWindowName(name, nr) + ok = True + for sub_window in mdi_area.subWindowList(): + if sub_window.name == unique_name: + ok = False + break + if ok: + return unique_name + nr += 1 + +# Add a sub-window + +def AddSubWindow(mdi_area, sub_window, name): + unique_name = UniqueSubWindowName(mdi_area, name) + sub_window.setMinimumSize(200, 100) + sub_window.resize(800, 600) + sub_window.setWindowTitle(unique_name) + sub_window.setAttribute(Qt.WA_DeleteOnClose) + sub_window.setWindowIcon(sub_window.style().standardIcon(QStyle.SP_FileIcon)) + sub_window.name = unique_name + mdi_area.addSubWindow(sub_window) + sub_window.show() + +# Main window + +class MainWindow(QMainWindow): + + def __init__(self, glb, parent=None): + super(MainWindow, self).__init__(parent) + + self.glb = glb + + self.setWindowTitle("Exported SQL Viewer: " + glb.dbname) + self.setWindowIcon(self.style().standardIcon(QStyle.SP_ComputerIcon)) + self.setMinimumSize(200, 100) + + self.mdi_area = QMdiArea() + self.mdi_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded) + self.mdi_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded) + + self.setCentralWidget(self.mdi_area) + + menu = self.menuBar() + + file_menu = menu.addMenu("&File") + file_menu.addAction(CreateExitAction(glb.app, self)) + + edit_menu = menu.addMenu("&Edit") + edit_menu.addAction(CreateAction("&Copy", "Copy to clipboard", self.CopyToClipboard, self, QKeySequence.Copy)) + edit_menu.addAction(CreateAction("Copy as CS&V", "Copy to clipboard as CSV", self.CopyToClipboardCSV, self)) + edit_menu.addAction(CreateAction("&Find...", "Find items", self.Find, self, QKeySequence.Find)) + edit_menu.addAction(CreateAction("Fetch &more records...", "Fetch more records", self.FetchMoreRecords, self, [QKeySequence(Qt.Key_F8)])) + edit_menu.addAction(CreateAction("&Shrink Font", "Make text smaller", self.ShrinkFont, self, [QKeySequence("Ctrl+-")])) + edit_menu.addAction(CreateAction("&Enlarge Font", "Make text bigger", self.EnlargeFont, self, [QKeySequence("Ctrl++")])) + + reports_menu = menu.addMenu("&Reports") + if IsSelectable(glb.db, "calls"): + reports_menu.addAction(CreateAction("Context-Sensitive Call &Graph", "Create a new window containing a context-sensitive call graph", self.NewCallGraph, self)) + + if IsSelectable(glb.db, "calls", "WHERE parent_id >= 0"): + reports_menu.addAction(CreateAction("Call &Tree", "Create a new window containing a call tree", self.NewCallTree, self)) + + self.EventMenu(GetEventList(glb.db), reports_menu) + + if IsSelectable(glb.db, "calls"): + reports_menu.addAction(CreateAction("&Top calls by elapsed time", "Create a new window displaying top calls by elapsed time", self.NewTopCalls, self)) + + if IsSelectable(glb.db, "context_switches"): + charts_menu = menu.addMenu("&Charts") + charts_menu.addAction(CreateAction("&Time chart by CPU", "Create a new window displaying time charts by CPU", self.TimeChartByCPU, self)) + + self.TableMenu(GetTableList(glb), menu) + + self.window_menu = WindowMenu(self.mdi_area, menu) + + help_menu = menu.addMenu("&Help") + help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + help_menu.addAction(CreateAction("&About Exported SQL Viewer", "About this application", self.About, self)) + + def Try(self, fn): + win = self.mdi_area.activeSubWindow() + if win: + try: + fn(win.view) + except: + pass + + def CopyToClipboard(self): + self.Try(CopyCellsToClipboardHdr) + + def CopyToClipboardCSV(self): + self.Try(CopyCellsToClipboardCSV) + + def Find(self): + win = self.mdi_area.activeSubWindow() + if win: + try: + win.find_bar.Activate() + except: + pass + + def FetchMoreRecords(self): + win = self.mdi_area.activeSubWindow() + if win: + try: + win.fetch_bar.Activate() + except: + pass + + def ShrinkFont(self): + self.Try(ShrinkFont) + + def EnlargeFont(self): + self.Try(EnlargeFont) + + def EventMenu(self, events, reports_menu): + branches_events = 0 + for event in events: + event = event.split(":")[0] + if event == "branches": + branches_events += 1 + dbid = 0 + for event in events: + dbid += 1 + event = event.split(":")[0] + if event == "branches": + label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewBranchView(x), self)) + label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda a=None,x=dbid: self.NewSelectedBranchView(x), self)) + + def TimeChartByCPU(self): + TimeChartByCPUWindow(self.glb, self) + + def TableMenu(self, tables, menu): + table_menu = menu.addMenu("&Tables") + for table in tables: + table_menu.addAction(CreateAction(table, "Create a new window containing a table view", lambda a=None,t=table: self.NewTableView(t), self)) + + def NewCallGraph(self): + CallGraphWindow(self.glb, self) + + def NewCallTree(self): + CallTreeWindow(self.glb, self) + + def NewTopCalls(self): + dialog = TopCallsDialog(self.glb, self) + ret = dialog.exec_() + if ret: + TopCallsWindow(self.glb, dialog.report_vars, self) + + def NewBranchView(self, event_id): + BranchWindow(self.glb, event_id, ReportVars(), self) + + def NewSelectedBranchView(self, event_id): + dialog = SelectedBranchDialog(self.glb, self) + ret = dialog.exec_() + if ret: + BranchWindow(self.glb, event_id, dialog.report_vars, self) + + def NewTableView(self, table_name): + TableWindow(self.glb, table_name, self) + + def Help(self): + HelpWindow(self.glb, self) + + def About(self): + dialog = AboutDialog(self.glb, self) + dialog.exec_() + +def TryOpen(file_name): + try: + return open(file_name, "rb") + except: + return None + +def Is64Bit(f): + result = sizeof(c_void_p) + # ELF support only + pos = f.tell() + f.seek(0) + header = f.read(7) + f.seek(pos) + magic = header[0:4] + if sys.version_info[0] == 2: + eclass = ord(header[4]) + encoding = ord(header[5]) + version = ord(header[6]) + else: + eclass = header[4] + encoding = header[5] + version = header[6] + if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1: + result = True if eclass == 2 else False + return result + +# Global data + +class Glb(): + + def __init__(self, dbref, db, dbname): + self.dbref = dbref + self.db = db + self.dbname = dbname + self.home_dir = os.path.expanduser("~") + self.buildid_dir = os.getenv("PERF_BUILDID_DIR") + if self.buildid_dir: + self.buildid_dir += "/.build-id/" + else: + self.buildid_dir = self.home_dir + "/.debug/.build-id/" + self.app = None + self.mainwindow = None + self.instances_to_shutdown_on_exit = weakref.WeakSet() + try: + self.disassembler = LibXED() + self.have_disassembler = True + except: + self.have_disassembler = False + self.host_machine_id = 0 + self.host_start_time = 0 + self.host_finish_time = 0 + + def FileFromBuildId(self, build_id): + file_name = self.buildid_dir + build_id[0:2] + "/" + build_id[2:] + "/elf" + return TryOpen(file_name) + + def FileFromNamesAndBuildId(self, short_name, long_name, build_id): + # Assume current machine i.e. no support for virtualization + if short_name[0:7] == "[kernel" and os.path.basename(long_name) == "kcore": + file_name = os.getenv("PERF_KCORE") + f = TryOpen(file_name) if file_name else None + if f: + return f + # For now, no special handling if long_name is /proc/kcore + f = TryOpen(long_name) + if f: + return f + f = self.FileFromBuildId(build_id) + if f: + return f + return None + + def AddInstanceToShutdownOnExit(self, instance): + self.instances_to_shutdown_on_exit.add(instance) + + # Shutdown any background processes or threads + def ShutdownInstances(self): + for x in self.instances_to_shutdown_on_exit: + try: + x.Shutdown() + except: + pass + + def GetHostMachineId(self): + query = QSqlQuery(self.db) + QueryExec(query, "SELECT id FROM machines WHERE pid = -1") + if query.next(): + self.host_machine_id = query.value(0) + else: + self.host_machine_id = 0 + return self.host_machine_id + + def HostMachineId(self): + if self.host_machine_id: + return self.host_machine_id + return self.GetHostMachineId() + + def SelectValue(self, sql): + query = QSqlQuery(self.db) + try: + QueryExec(query, sql) + except: + return None + if query.next(): + return Decimal(query.value(0)) + return None + + def SwitchesMinTime(self, machine_id): + return self.SelectValue("SELECT time" + " FROM context_switches" + " WHERE time != 0 AND machine_id = " + str(machine_id) + + " ORDER BY id LIMIT 1") + + def SwitchesMaxTime(self, machine_id): + return self.SelectValue("SELECT time" + " FROM context_switches" + " WHERE time != 0 AND machine_id = " + str(machine_id) + + " ORDER BY id DESC LIMIT 1") + + def SamplesMinTime(self, machine_id): + return self.SelectValue("SELECT time" + " FROM samples" + " WHERE time != 0 AND machine_id = " + str(machine_id) + + " ORDER BY id LIMIT 1") + + def SamplesMaxTime(self, machine_id): + return self.SelectValue("SELECT time" + " FROM samples" + " WHERE time != 0 AND machine_id = " + str(machine_id) + + " ORDER BY id DESC LIMIT 1") + + def CallsMinTime(self, machine_id): + return self.SelectValue("SELECT calls.call_time" + " FROM calls" + " INNER JOIN threads ON threads.thread_id = calls.thread_id" + " WHERE calls.call_time != 0 AND threads.machine_id = " + str(machine_id) + + " ORDER BY calls.id LIMIT 1") + + def CallsMaxTime(self, machine_id): + return self.SelectValue("SELECT calls.return_time" + " FROM calls" + " INNER JOIN threads ON threads.thread_id = calls.thread_id" + " WHERE calls.return_time != 0 AND threads.machine_id = " + str(machine_id) + + " ORDER BY calls.return_time DESC LIMIT 1") + + def GetStartTime(self, machine_id): + t0 = self.SwitchesMinTime(machine_id) + t1 = self.SamplesMinTime(machine_id) + t2 = self.CallsMinTime(machine_id) + if t0 is None or (not(t1 is None) and t1 < t0): + t0 = t1 + if t0 is None or (not(t2 is None) and t2 < t0): + t0 = t2 + return t0 + + def GetFinishTime(self, machine_id): + t0 = self.SwitchesMaxTime(machine_id) + t1 = self.SamplesMaxTime(machine_id) + t2 = self.CallsMaxTime(machine_id) + if t0 is None or (not(t1 is None) and t1 > t0): + t0 = t1 + if t0 is None or (not(t2 is None) and t2 > t0): + t0 = t2 + return t0 + + def HostStartTime(self): + if self.host_start_time: + return self.host_start_time + self.host_start_time = self.GetStartTime(self.HostMachineId()) + return self.host_start_time + + def HostFinishTime(self): + if self.host_finish_time: + return self.host_finish_time + self.host_finish_time = self.GetFinishTime(self.HostMachineId()) + return self.host_finish_time + + def StartTime(self, machine_id): + if machine_id == self.HostMachineId(): + return self.HostStartTime() + return self.GetStartTime(machine_id) + + def FinishTime(self, machine_id): + if machine_id == self.HostMachineId(): + return self.HostFinishTime() + return self.GetFinishTime(machine_id) + +# Database reference + +class DBRef(): + + def __init__(self, is_sqlite3, dbname): + self.is_sqlite3 = is_sqlite3 + self.dbname = dbname + self.TRUE = "TRUE" + self.FALSE = "FALSE" + # SQLite prior to version 3.23 does not support TRUE and FALSE + if self.is_sqlite3: + self.TRUE = "1" + self.FALSE = "0" + + def Open(self, connection_name): + dbname = self.dbname + if self.is_sqlite3: + db = QSqlDatabase.addDatabase("QSQLITE", connection_name) + else: + db = QSqlDatabase.addDatabase("QPSQL", connection_name) + opts = dbname.split() + for opt in opts: + if "=" in opt: + opt = opt.split("=") + if opt[0] == "hostname": + db.setHostName(opt[1]) + elif opt[0] == "port": + db.setPort(int(opt[1])) + elif opt[0] == "username": + db.setUserName(opt[1]) + elif opt[0] == "password": + db.setPassword(opt[1]) + elif opt[0] == "dbname": + dbname = opt[1] + else: + dbname = opt + + db.setDatabaseName(dbname) + if not db.open(): + raise Exception("Failed to open database " + dbname + " error: " + db.lastError().text()) + return db, dbname + +# Main + +def Main(): + usage_str = "exported-sql-viewer.py [--pyside-version-1] <database name>\n" \ + " or: exported-sql-viewer.py --help-only" + ap = argparse.ArgumentParser(usage = usage_str, add_help = False) + ap.add_argument("--pyside-version-1", action='store_true') + ap.add_argument("dbname", nargs="?") + ap.add_argument("--help-only", action='store_true') + args = ap.parse_args() + + if args.help_only: + app = QApplication(sys.argv) + mainwindow = HelpOnlyWindow() + mainwindow.show() + err = app.exec_() + sys.exit(err) + + dbname = args.dbname + if dbname is None: + ap.print_usage() + print("Too few arguments") + sys.exit(1) + + is_sqlite3 = False + try: + f = open(dbname, "rb") + if f.read(15) == b'SQLite format 3': + is_sqlite3 = True + f.close() + except: + pass + + dbref = DBRef(is_sqlite3, dbname) + db, dbname = dbref.Open("main") + glb = Glb(dbref, db, dbname) + app = QApplication(sys.argv) + glb.app = app + mainwindow = MainWindow(glb) + glb.mainwindow = mainwindow + mainwindow.show() + err = app.exec_() + glb.ShutdownInstances() + db.close() + sys.exit(err) + +if __name__ == "__main__": + Main() diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py new file mode 100644 index 000000000..310efe5e7 --- /dev/null +++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py @@ -0,0 +1,79 @@ +# failed system call counts, by pid +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Displays system-wide failed system call totals, broken down by pid. +# If a [comm] arg is specified, only syscalls called by [comm] are displayed. + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +usage = "perf script -s syscall-counts-by-pid.py [comm|pid]\n"; + +for_comm = None +for_pid = None + +if len(sys.argv) > 2: + sys.exit(usage) + +if len(sys.argv) > 1: + try: + for_pid = int(sys.argv[1]) + except: + for_comm = sys.argv[1] + +syscalls = autodict() + +def trace_begin(): + print("Press control+C to stop and show the summary") + +def trace_end(): + print_error_totals() + +def raw_syscalls__sys_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, id, ret): + if (for_comm and common_comm != for_comm) or \ + (for_pid and common_pid != for_pid ): + return + + if ret < 0: + try: + syscalls[common_comm][common_pid][id][ret] += 1 + except TypeError: + syscalls[common_comm][common_pid][id][ret] = 1 + +def syscalls__sys_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, ret): + raw_syscalls__sys_exit(**locals()) + +def print_error_totals(): + if for_comm is not None: + print("\nsyscall errors for %s:\n" % (for_comm)) + else: + print("\nsyscall errors:\n") + + print("%-30s %10s" % ("comm [pid]", "count")) + print("%-30s %10s" % ("------------------------------", "----------")) + + comm_keys = syscalls.keys() + for comm in comm_keys: + pid_keys = syscalls[comm].keys() + for pid in pid_keys: + print("\n%s [%d]" % (comm, pid)) + id_keys = syscalls[comm][pid].keys() + for id in id_keys: + print(" syscall: %-16s" % syscall_name(id)) + ret_keys = syscalls[comm][pid][id].keys() + for ret, val in sorted(syscalls[comm][pid][id].items(), key = lambda kv: (kv[1], kv[0]), reverse = True): + print(" err = %-20s %10d" % (strerror(ret), val)) diff --git a/tools/perf/scripts/python/flamegraph.py b/tools/perf/scripts/python/flamegraph.py new file mode 100755 index 000000000..b6af1dd5f --- /dev/null +++ b/tools/perf/scripts/python/flamegraph.py @@ -0,0 +1,180 @@ +# flamegraph.py - create flame graphs from perf samples +# SPDX-License-Identifier: GPL-2.0 +# +# Usage: +# +# perf record -a -g -F 99 sleep 60 +# perf script report flamegraph +# +# Combined: +# +# perf script flamegraph -a -F 99 sleep 60 +# +# Written by Andreas Gerstmayr <agerstmayr@redhat.com> +# Flame Graphs invented by Brendan Gregg <bgregg@netflix.com> +# Works in tandem with d3-flame-graph by Martin Spier <mspier@netflix.com> +# +# pylint: disable=missing-module-docstring +# pylint: disable=missing-class-docstring +# pylint: disable=missing-function-docstring + +from __future__ import print_function +import sys +import os +import io +import argparse +import json +import subprocess + +# pylint: disable=too-few-public-methods +class Node: + def __init__(self, name, libtype): + self.name = name + # "root" | "kernel" | "" + # "" indicates user space + self.libtype = libtype + self.value = 0 + self.children = [] + + def to_json(self): + return { + "n": self.name, + "l": self.libtype, + "v": self.value, + "c": self.children + } + + +class FlameGraphCLI: + def __init__(self, args): + self.args = args + self.stack = Node("all", "root") + + if self.args.format == "html" and \ + not os.path.isfile(self.args.template): + print("Flame Graph template {} does not exist. Please install " + "the js-d3-flame-graph (RPM) or libjs-d3-flame-graph (deb) " + "package, specify an existing flame graph template " + "(--template PATH) or another output format " + "(--format FORMAT).".format(self.args.template), + file=sys.stderr) + sys.exit(1) + + @staticmethod + def get_libtype_from_dso(dso): + """ + when kernel-debuginfo is installed, + dso points to /usr/lib/debug/lib/modules/*/vmlinux + """ + if dso and (dso == "[kernel.kallsyms]" or dso.endswith("/vmlinux")): + return "kernel" + + return "" + + @staticmethod + def find_or_create_node(node, name, libtype): + for child in node.children: + if child.name == name: + return child + + child = Node(name, libtype) + node.children.append(child) + return child + + def process_event(self, event): + pid = event.get("sample", {}).get("pid", 0) + # event["dso"] sometimes contains /usr/lib/debug/lib/modules/*/vmlinux + # for user-space processes; let's use pid for kernel or user-space distinction + if pid == 0: + comm = event["comm"] + libtype = "kernel" + else: + comm = "{} ({})".format(event["comm"], pid) + libtype = "" + node = self.find_or_create_node(self.stack, comm, libtype) + + if "callchain" in event: + for entry in reversed(event["callchain"]): + name = entry.get("sym", {}).get("name", "[unknown]") + libtype = self.get_libtype_from_dso(entry.get("dso")) + node = self.find_or_create_node(node, name, libtype) + else: + name = event.get("symbol", "[unknown]") + libtype = self.get_libtype_from_dso(event.get("dso")) + node = self.find_or_create_node(node, name, libtype) + node.value += 1 + + def get_report_header(self): + if self.args.input == "-": + # when this script is invoked with "perf script flamegraph", + # no perf.data is created and we cannot read the header of it + return "" + + try: + output = subprocess.check_output(["perf", "report", "--header-only"]) + return output.decode("utf-8") + except Exception as err: # pylint: disable=broad-except + print("Error reading report header: {}".format(err), file=sys.stderr) + return "" + + def trace_end(self): + stacks_json = json.dumps(self.stack, default=lambda x: x.to_json()) + + if self.args.format == "html": + report_header = self.get_report_header() + options = { + "colorscheme": self.args.colorscheme, + "context": report_header + } + options_json = json.dumps(options) + + try: + with io.open(self.args.template, encoding="utf-8") as template: + output_str = ( + template.read() + .replace("/** @options_json **/", options_json) + .replace("/** @flamegraph_json **/", stacks_json) + ) + except IOError as err: + print("Error reading template file: {}".format(err), file=sys.stderr) + sys.exit(1) + output_fn = self.args.output or "flamegraph.html" + else: + output_str = stacks_json + output_fn = self.args.output or "stacks.json" + + if output_fn == "-": + with io.open(sys.stdout.fileno(), "w", encoding="utf-8", closefd=False) as out: + out.write(output_str) + else: + print("dumping data to {}".format(output_fn)) + try: + with io.open(output_fn, "w", encoding="utf-8") as out: + out.write(output_str) + except IOError as err: + print("Error writing output file: {}".format(err), file=sys.stderr) + sys.exit(1) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Create flame graphs.") + parser.add_argument("-f", "--format", + default="html", choices=["json", "html"], + help="output file format") + parser.add_argument("-o", "--output", + help="output file name") + parser.add_argument("--template", + default="/usr/share/d3-flame-graph/d3-flamegraph-base.html", + help="path to flame graph HTML template") + parser.add_argument("--colorscheme", + default="blue-green", + help="flame graph color scheme", + choices=["blue-green", "orange"]) + parser.add_argument("-i", "--input", + help=argparse.SUPPRESS) + + cli_args = parser.parse_args() + cli = FlameGraphCLI(cli_args) + + process_event = cli.process_event + trace_end = cli.trace_end diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py new file mode 100644 index 000000000..7e884d46f --- /dev/null +++ b/tools/perf/scripts/python/futex-contention.py @@ -0,0 +1,57 @@ +# futex contention +# (c) 2010, Arnaldo Carvalho de Melo <acme@redhat.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Translation of: +# +# http://sourceware.org/systemtap/wiki/WSFutexContention +# +# to perf python scripting. +# +# Measures futex contention + +from __future__ import print_function + +import os +import sys +sys.path.append(os.environ['PERF_EXEC_PATH'] + + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') +from Util import * + +process_names = {} +thread_thislock = {} +thread_blocktime = {} + +lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time +process_names = {} # long-lived pid-to-execname mapping + + +def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, + nr, uaddr, op, val, utime, uaddr2, val3): + cmd = op & FUTEX_CMD_MASK + if cmd != FUTEX_WAIT: + return # we don't care about originators of WAKE events + + process_names[tid] = comm + thread_thislock[tid] = uaddr + thread_blocktime[tid] = nsecs(s, ns) + + +def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, + nr, ret): + if tid in thread_blocktime: + elapsed = nsecs(s, ns) - thread_blocktime[tid] + add_stats(lock_waits, (tid, thread_thislock[tid]), elapsed) + del thread_blocktime[tid] + del thread_thislock[tid] + + +def trace_begin(): + print("Press control+C to stop and show the summary") + + +def trace_end(): + for (tid, lock) in lock_waits: + min, max, avg, count = lock_waits[tid, lock] + print("%s[%d] lock %x contended %d times, %d avg ns [max: %d ns, min %d ns]" % + (process_names[tid], tid, lock, count, avg, max, min)) diff --git a/tools/perf/scripts/python/intel-pt-events.py b/tools/perf/scripts/python/intel-pt-events.py new file mode 100644 index 000000000..8058b2fc2 --- /dev/null +++ b/tools/perf/scripts/python/intel-pt-events.py @@ -0,0 +1,431 @@ +# SPDX-License-Identifier: GPL-2.0 +# intel-pt-events.py: Print Intel PT Events including Power Events and PTWRITE +# Copyright (c) 2017-2021, Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. + +from __future__ import division, print_function + +import os +import sys +import struct +import argparse + +from libxed import LibXED +from ctypes import create_string_buffer, addressof + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import perf_set_itrace_options, \ + perf_sample_insn, perf_sample_srccode + +try: + broken_pipe_exception = BrokenPipeError +except: + broken_pipe_exception = IOError + +glb_switch_str = {} +glb_insn = False +glb_disassembler = None +glb_src = False +glb_source_file_name = None +glb_line_number = None +glb_dso = None + +def get_optional_null(perf_dict, field): + if field in perf_dict: + return perf_dict[field] + return "" + +def get_optional_zero(perf_dict, field): + if field in perf_dict: + return perf_dict[field] + return 0 + +def get_optional_bytes(perf_dict, field): + if field in perf_dict: + return perf_dict[field] + return bytes() + +def get_optional(perf_dict, field): + if field in perf_dict: + return perf_dict[field] + return "[unknown]" + +def get_offset(perf_dict, field): + if field in perf_dict: + return "+%#x" % perf_dict[field] + return "" + +def trace_begin(): + ap = argparse.ArgumentParser(usage = "", add_help = False) + ap.add_argument("--insn-trace", action='store_true') + ap.add_argument("--src-trace", action='store_true') + ap.add_argument("--all-switch-events", action='store_true') + global glb_args + global glb_insn + global glb_src + glb_args = ap.parse_args() + if glb_args.insn_trace: + print("Intel PT Instruction Trace") + itrace = "i0nsepwxI" + glb_insn = True + elif glb_args.src_trace: + print("Intel PT Source Trace") + itrace = "i0nsepwxI" + glb_insn = True + glb_src = True + else: + print("Intel PT Branch Trace, Power Events, Event Trace and PTWRITE") + itrace = "bepwxI" + global glb_disassembler + try: + glb_disassembler = LibXED() + except: + glb_disassembler = None + perf_set_itrace_options(perf_script_context, itrace) + +def trace_end(): + print("End") + +def trace_unhandled(event_name, context, event_fields_dict): + print(' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])) + +def print_ptwrite(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + flags = data[0] + payload = data[1] + exact_ip = flags & 1 + try: + s = payload.to_bytes(8, "little").decode("ascii").rstrip("\x00") + if not s.isprintable(): + s = "" + except: + s = "" + print("IP: %u payload: %#x" % (exact_ip, payload), s, end=' ') + +def print_cbr(raw_buf): + data = struct.unpack_from("<BBBBII", raw_buf) + cbr = data[0] + f = (data[4] + 500) / 1000 + p = ((cbr * 1000 / data[2]) + 5) / 10 + print("%3u freq: %4u MHz (%3u%%)" % (cbr, f, p), end=' ') + +def print_mwait(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hints = payload & 0xff + extensions = (payload >> 32) & 0x3 + print("hints: %#x extensions: %#x" % (hints, extensions), end=' ') + +def print_pwre(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + hw = (payload >> 7) & 1 + cstate = (payload >> 12) & 0xf + subcstate = (payload >> 8) & 0xf + print("hw: %u cstate: %u sub-cstate: %u" % (hw, cstate, subcstate), + end=' ') + +def print_exstop(raw_buf): + data = struct.unpack_from("<I", raw_buf) + flags = data[0] + exact_ip = flags & 1 + print("IP: %u" % (exact_ip), end=' ') + +def print_pwrx(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + payload = data[1] + deepest_cstate = payload & 0xf + last_cstate = (payload >> 4) & 0xf + wake_reason = (payload >> 8) & 0xf + print("deepest cstate: %u last cstate: %u wake reason: %#x" % + (deepest_cstate, last_cstate, wake_reason), end=' ') + +def print_psb(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + offset = data[1] + print("offset: %#x" % (offset), end=' ') + +glb_cfe = ["", "INTR", "IRET", "SMI", "RSM", "SIPI", "INIT", "VMENTRY", "VMEXIT", + "VMEXIT_INTR", "SHUTDOWN", "", "UINT", "UIRET"] + [""] * 18 +glb_evd = ["", "PFA", "VMXQ", "VMXR"] + [""] * 60 + +def print_evt(raw_buf): + data = struct.unpack_from("<BBH", raw_buf) + typ = data[0] & 0x1f + ip_flag = (data[0] & 0x80) >> 7 + vector = data[1] + evd_cnt = data[2] + s = glb_cfe[typ] + if s: + print(" cfe: %s IP: %u vector: %u" % (s, ip_flag, vector), end=' ') + else: + print(" cfe: %u IP: %u vector: %u" % (typ, ip_flag, vector), end=' ') + pos = 4 + for i in range(evd_cnt): + data = struct.unpack_from("<QQ", raw_buf) + et = data[0] & 0x3f + s = glb_evd[et] + if s: + print("%s: %#x" % (s, data[1]), end=' ') + else: + print("EVD_%u: %#x" % (et, data[1]), end=' ') + +def print_iflag(raw_buf): + data = struct.unpack_from("<IQ", raw_buf) + iflag = data[0] & 1 + old_iflag = iflag ^ 1 + via_branch = data[0] & 2 + branch_ip = data[1] + if via_branch: + s = "via" + else: + s = "non" + print("IFLAG: %u->%u %s branch" % (old_iflag, iflag, s), end=' ') + +def common_start_str(comm, sample): + ts = sample["time"] + cpu = sample["cpu"] + pid = sample["pid"] + tid = sample["tid"] + if "machine_pid" in sample: + machine_pid = sample["machine_pid"] + vcpu = sample["vcpu"] + return "VM:%5d VCPU:%03d %16s %5u/%-5u [%03u] %9u.%09u " % (machine_pid, vcpu, comm, pid, tid, cpu, ts / 1000000000, ts %1000000000) + else: + return "%16s %5u/%-5u [%03u] %9u.%09u " % (comm, pid, tid, cpu, ts / 1000000000, ts %1000000000) + +def print_common_start(comm, sample, name): + flags_disp = get_optional_null(sample, "flags_disp") + # Unused fields: + # period = sample["period"] + # phys_addr = sample["phys_addr"] + # weight = sample["weight"] + # transaction = sample["transaction"] + # cpumode = get_optional_zero(sample, "cpumode") + print(common_start_str(comm, sample) + "%8s %21s" % (name, flags_disp), end=' ') + +def print_instructions_start(comm, sample): + if "x" in get_optional_null(sample, "flags"): + print(common_start_str(comm, sample) + "x", end=' ') + else: + print(common_start_str(comm, sample), end=' ') + +def disassem(insn, ip): + inst = glb_disassembler.Instruction() + glb_disassembler.SetMode(inst, 0) # Assume 64-bit + buf = create_string_buffer(64) + buf.value = insn + return glb_disassembler.DisassembleOne(inst, addressof(buf), len(insn), ip) + +def print_common_ip(param_dict, sample, symbol, dso): + ip = sample["ip"] + offs = get_offset(param_dict, "symoff") + if "cyc_cnt" in sample: + cyc_cnt = sample["cyc_cnt"] + insn_cnt = get_optional_zero(sample, "insn_cnt") + ipc_str = " IPC: %#.2f (%u/%u)" % (insn_cnt / cyc_cnt, insn_cnt, cyc_cnt) + else: + ipc_str = "" + if glb_insn and glb_disassembler is not None: + insn = perf_sample_insn(perf_script_context) + if insn and len(insn): + cnt, text = disassem(insn, ip) + byte_str = ("%x" % ip).rjust(16) + if sys.version_info.major >= 3: + for k in range(cnt): + byte_str += " %02x" % insn[k] + else: + for k in xrange(cnt): + byte_str += " %02x" % ord(insn[k]) + print("%-40s %-30s" % (byte_str, text), end=' ') + print("%s%s (%s)" % (symbol, offs, dso), end=' ') + else: + print("%16x %s%s (%s)" % (ip, symbol, offs, dso), end=' ') + if "addr_correlates_sym" in sample: + addr = sample["addr"] + dso = get_optional(sample, "addr_dso") + symbol = get_optional(sample, "addr_symbol") + offs = get_offset(sample, "addr_symoff") + print("=> %x %s%s (%s)%s" % (addr, symbol, offs, dso, ipc_str)) + else: + print(ipc_str) + +def print_srccode(comm, param_dict, sample, symbol, dso, with_insn): + ip = sample["ip"] + if symbol == "[unknown]": + start_str = common_start_str(comm, sample) + ("%x" % ip).rjust(16).ljust(40) + else: + offs = get_offset(param_dict, "symoff") + start_str = common_start_str(comm, sample) + (symbol + offs).ljust(40) + + if with_insn and glb_insn and glb_disassembler is not None: + insn = perf_sample_insn(perf_script_context) + if insn and len(insn): + cnt, text = disassem(insn, ip) + start_str += text.ljust(30) + + global glb_source_file_name + global glb_line_number + global glb_dso + + source_file_name, line_number, source_line = perf_sample_srccode(perf_script_context) + if source_file_name: + if glb_line_number == line_number and glb_source_file_name == source_file_name: + src_str = "" + else: + if len(source_file_name) > 40: + src_file = ("..." + source_file_name[-37:]) + " " + else: + src_file = source_file_name.ljust(41) + if source_line is None: + src_str = src_file + str(line_number).rjust(4) + " <source not found>" + else: + src_str = src_file + str(line_number).rjust(4) + " " + source_line + glb_dso = None + elif dso == glb_dso: + src_str = "" + else: + src_str = dso + glb_dso = dso + + glb_line_number = line_number + glb_source_file_name = source_file_name + + print(start_str, src_str) + +def do_process_event(param_dict): + event_attr = param_dict["attr"] + sample = param_dict["sample"] + raw_buf = param_dict["raw_buf"] + comm = param_dict["comm"] + name = param_dict["ev_name"] + # Unused fields: + # callchain = param_dict["callchain"] + # brstack = param_dict["brstack"] + # brstacksym = param_dict["brstacksym"] + + # Symbol and dso info are not always resolved + dso = get_optional(param_dict, "dso") + symbol = get_optional(param_dict, "symbol") + + cpu = sample["cpu"] + if cpu in glb_switch_str: + print(glb_switch_str[cpu]) + del glb_switch_str[cpu] + + if name[0:12] == "instructions": + if glb_src: + print_srccode(comm, param_dict, sample, symbol, dso, True) + else: + print_instructions_start(comm, sample) + print_common_ip(param_dict, sample, symbol, dso) + elif name[0:8] == "branches": + if glb_src: + print_srccode(comm, param_dict, sample, symbol, dso, False) + else: + print_common_start(comm, sample, name) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "ptwrite": + print_common_start(comm, sample, name) + print_ptwrite(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "cbr": + print_common_start(comm, sample, name) + print_cbr(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "mwait": + print_common_start(comm, sample, name) + print_mwait(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "pwre": + print_common_start(comm, sample, name) + print_pwre(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "exstop": + print_common_start(comm, sample, name) + print_exstop(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "pwrx": + print_common_start(comm, sample, name) + print_pwrx(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "psb": + print_common_start(comm, sample, name) + print_psb(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "evt": + print_common_start(comm, sample, name) + print_evt(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + elif name == "iflag": + print_common_start(comm, sample, name) + print_iflag(raw_buf) + print_common_ip(param_dict, sample, symbol, dso) + else: + print_common_start(comm, sample, name) + print_common_ip(param_dict, sample, symbol, dso) + +def process_event(param_dict): + try: + do_process_event(param_dict) + except broken_pipe_exception: + # Stop python printing broken pipe errors and traceback + sys.stdout = open(os.devnull, 'w') + sys.exit(1) + +def auxtrace_error(typ, code, cpu, pid, tid, ip, ts, msg, cpumode, *x): + if len(x) >= 2 and x[0]: + machine_pid = x[0] + vcpu = x[1] + else: + machine_pid = 0 + vcpu = -1 + try: + if machine_pid: + print("VM:%5d VCPU:%03d %16s %5u/%-5u [%03u] %9u.%09u error type %u code %u: %s ip 0x%16x" % + (machine_pid, vcpu, "Trace error", pid, tid, cpu, ts / 1000000000, ts %1000000000, typ, code, msg, ip)) + else: + print("%16s %5u/%-5u [%03u] %9u.%09u error type %u code %u: %s ip 0x%16x" % + ("Trace error", pid, tid, cpu, ts / 1000000000, ts %1000000000, typ, code, msg, ip)) + except broken_pipe_exception: + # Stop python printing broken pipe errors and traceback + sys.stdout = open(os.devnull, 'w') + sys.exit(1) + +def context_switch(ts, cpu, pid, tid, np_pid, np_tid, machine_pid, out, out_preempt, *x): + if out: + out_str = "Switch out " + else: + out_str = "Switch In " + if out_preempt: + preempt_str = "preempt" + else: + preempt_str = "" + if len(x) >= 2 and x[0]: + machine_pid = x[0] + vcpu = x[1] + else: + vcpu = None; + if machine_pid == -1: + machine_str = "" + elif vcpu is None: + machine_str = "machine PID %d" % machine_pid + else: + machine_str = "machine PID %d VCPU %d" % (machine_pid, vcpu) + switch_str = "%16s %5d/%-5d [%03u] %9u.%09u %5d/%-5d %s %s" % \ + (out_str, pid, tid, cpu, ts / 1000000000, ts %1000000000, np_pid, np_tid, machine_str, preempt_str) + if glb_args.all_switch_events: + print(switch_str) + else: + global glb_switch_str + glb_switch_str[cpu] = switch_str diff --git a/tools/perf/scripts/python/libxed.py b/tools/perf/scripts/python/libxed.py new file mode 100644 index 000000000..2c70a5a7e --- /dev/null +++ b/tools/perf/scripts/python/libxed.py @@ -0,0 +1,107 @@ +#!/usr/bin/env python +# SPDX-License-Identifier: GPL-2.0 +# libxed.py: Python wrapper for libxed.so +# Copyright (c) 2014-2021, Intel Corporation. + +# To use Intel XED, libxed.so must be present. To build and install +# libxed.so: +# git clone https://github.com/intelxed/mbuild.git mbuild +# git clone https://github.com/intelxed/xed +# cd xed +# ./mfile.py --share +# sudo ./mfile.py --prefix=/usr/local install +# sudo ldconfig +# + +import sys + +from ctypes import CDLL, Structure, create_string_buffer, addressof, sizeof, \ + c_void_p, c_bool, c_byte, c_char, c_int, c_uint, c_longlong, c_ulonglong + +# XED Disassembler + +class xed_state_t(Structure): + + _fields_ = [ + ("mode", c_int), + ("width", c_int) + ] + +class XEDInstruction(): + + def __init__(self, libxed): + # Current xed_decoded_inst_t structure is 192 bytes. Use 512 to allow for future expansion + xedd_t = c_byte * 512 + self.xedd = xedd_t() + self.xedp = addressof(self.xedd) + libxed.xed_decoded_inst_zero(self.xedp) + self.state = xed_state_t() + self.statep = addressof(self.state) + # Buffer for disassembled instruction text + self.buffer = create_string_buffer(256) + self.bufferp = addressof(self.buffer) + +class LibXED(): + + def __init__(self): + try: + self.libxed = CDLL("libxed.so") + except: + self.libxed = None + if not self.libxed: + self.libxed = CDLL("/usr/local/lib/libxed.so") + + self.xed_tables_init = self.libxed.xed_tables_init + self.xed_tables_init.restype = None + self.xed_tables_init.argtypes = [] + + self.xed_decoded_inst_zero = self.libxed.xed_decoded_inst_zero + self.xed_decoded_inst_zero.restype = None + self.xed_decoded_inst_zero.argtypes = [ c_void_p ] + + self.xed_operand_values_set_mode = self.libxed.xed_operand_values_set_mode + self.xed_operand_values_set_mode.restype = None + self.xed_operand_values_set_mode.argtypes = [ c_void_p, c_void_p ] + + self.xed_decoded_inst_zero_keep_mode = self.libxed.xed_decoded_inst_zero_keep_mode + self.xed_decoded_inst_zero_keep_mode.restype = None + self.xed_decoded_inst_zero_keep_mode.argtypes = [ c_void_p ] + + self.xed_decode = self.libxed.xed_decode + self.xed_decode.restype = c_int + self.xed_decode.argtypes = [ c_void_p, c_void_p, c_uint ] + + self.xed_format_context = self.libxed.xed_format_context + self.xed_format_context.restype = c_uint + self.xed_format_context.argtypes = [ c_int, c_void_p, c_void_p, c_int, c_ulonglong, c_void_p, c_void_p ] + + self.xed_tables_init() + + def Instruction(self): + return XEDInstruction(self) + + def SetMode(self, inst, mode): + if mode: + inst.state.mode = 4 # 32-bit + inst.state.width = 4 # 4 bytes + else: + inst.state.mode = 1 # 64-bit + inst.state.width = 8 # 8 bytes + self.xed_operand_values_set_mode(inst.xedp, inst.statep) + + def DisassembleOne(self, inst, bytes_ptr, bytes_cnt, ip): + self.xed_decoded_inst_zero_keep_mode(inst.xedp) + err = self.xed_decode(inst.xedp, bytes_ptr, bytes_cnt) + if err: + return 0, "" + # Use AT&T mode (2), alternative is Intel (3) + ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0) + if not ok: + return 0, "" + if sys.version_info[0] == 2: + result = inst.buffer.value + else: + result = inst.buffer.value.decode() + # Return instruction length and the disassembled instruction text + # For now, assume the length is in byte 166 + return inst.xedd[166], result diff --git a/tools/perf/scripts/python/mem-phys-addr.py b/tools/perf/scripts/python/mem-phys-addr.py new file mode 100644 index 000000000..1f332e72b --- /dev/null +++ b/tools/perf/scripts/python/mem-phys-addr.py @@ -0,0 +1,100 @@ +# mem-phys-addr.py: Resolve physical address samples +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2018, Intel Corporation. + +from __future__ import division +from __future__ import print_function + +import os +import sys +import struct +import re +import bisect +import collections + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +#physical address ranges for System RAM +system_ram = [] +#physical address ranges for Persistent Memory +pmem = [] +#file object for proc iomem +f = None +#Count for each type of memory +load_mem_type_cnt = collections.Counter() +#perf event name +event_name = None + +def parse_iomem(): + global f + f = open('/proc/iomem', 'r') + for i, j in enumerate(f): + m = re.split('-|:',j,2) + if m[2].strip() == 'System RAM': + system_ram.append(int(m[0], 16)) + system_ram.append(int(m[1], 16)) + if m[2].strip() == 'Persistent Memory': + pmem.append(int(m[0], 16)) + pmem.append(int(m[1], 16)) + +def print_memory_type(): + print("Event: %s" % (event_name)) + print("%-40s %10s %10s\n" % ("Memory type", "count", "percentage"), end='') + print("%-40s %10s %10s\n" % ("----------------------------------------", + "-----------", "-----------"), + end=''); + total = sum(load_mem_type_cnt.values()) + for mem_type, count in sorted(load_mem_type_cnt.most_common(), \ + key = lambda kv: (kv[1], kv[0]), reverse = True): + print("%-40s %10d %10.1f%%\n" % + (mem_type, count, 100 * count / total), + end='') + +def trace_begin(): + parse_iomem() + +def trace_end(): + print_memory_type() + f.close() + +def is_system_ram(phys_addr): + #/proc/iomem is sorted + position = bisect.bisect(system_ram, phys_addr) + if position % 2 == 0: + return False + return True + +def is_persistent_mem(phys_addr): + position = bisect.bisect(pmem, phys_addr) + if position % 2 == 0: + return False + return True + +def find_memory_type(phys_addr): + if phys_addr == 0: + return "N/A" + if is_system_ram(phys_addr): + return "System RAM" + + if is_persistent_mem(phys_addr): + return "Persistent Memory" + + #slow path, search all + f.seek(0, 0) + for j in f: + m = re.split('-|:',j,2) + if int(m[0], 16) <= phys_addr <= int(m[1], 16): + return m[2] + return "N/A" + +def process_event(param_dict): + name = param_dict["ev_name"] + sample = param_dict["sample"] + phys_addr = sample["phys_addr"] + + global event_name + if event_name == None: + event_name = name + load_mem_type_cnt[find_memory_type(phys_addr)] += 1 diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py new file mode 100755 index 000000000..101059971 --- /dev/null +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -0,0 +1,78 @@ +# Monitor the system for dropped packets and proudce a report of drop locations and counts +# SPDX-License-Identifier: GPL-2.0 + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +drop_log = {} +kallsyms = [] + +def get_kallsyms_table(): + global kallsyms + + try: + f = open("/proc/kallsyms", "r") + except: + return + + for line in f: + loc = int(line.split()[0], 16) + name = line.split()[2] + kallsyms.append((loc, name)) + kallsyms.sort() + +def get_sym(sloc): + loc = int(sloc) + + # Invariant: kallsyms[i][0] <= loc for all 0 <= i <= start + # kallsyms[i][0] > loc for all end <= i < len(kallsyms) + start, end = -1, len(kallsyms) + while end != start + 1: + pivot = (start + end) // 2 + if loc < kallsyms[pivot][0]: + end = pivot + else: + start = pivot + + # Now (start == -1 or kallsyms[start][0] <= loc) + # and (start == len(kallsyms) - 1 or loc < kallsyms[start + 1][0]) + if start >= 0: + symloc, name = kallsyms[start] + return (name, loc - symloc) + else: + return (None, 0) + +def print_drop_table(): + print("%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT")) + for i in drop_log.keys(): + (sym, off) = get_sym(i) + if sym == None: + sym = i + print("%25s %25s %25s" % (sym, off, drop_log[i])) + + +def trace_begin(): + print("Starting trace (Ctrl-C to dump results)") + +def trace_end(): + print("Gathering kallsyms data") + get_kallsyms_table() + print_drop_table() + +# called from perf, when it finds a correspoinding event +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, + skbaddr, location, protocol): + slocation = str(location) + try: + drop_log[slocation] = drop_log[slocation] + 1 + except: + drop_log[slocation] = 1 diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py new file mode 100644 index 000000000..a0cfc7fe5 --- /dev/null +++ b/tools/perf/scripts/python/netdev-times.py @@ -0,0 +1,472 @@ +# Display a process of packets and processed time. +# SPDX-License-Identifier: GPL-2.0 +# It helps us to investigate networking or network device. +# +# options +# tx: show only tx chart +# rx: show only rx chart +# dev=: show only thing related to specified device +# debug: work with debug mode. It shows buffer status. + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * +from functools import cmp_to_key + +all_event_list = []; # insert all tracepoint event related with this script +irq_dic = {}; # key is cpu and value is a list which stacks irqs + # which raise NET_RX softirq +net_rx_dic = {}; # key is cpu and value include time of NET_RX softirq-entry + # and a list which stacks receive +receive_hunk_list = []; # a list which include a sequence of receive events +rx_skb_list = []; # received packet list for matching + # skb_copy_datagram_iovec + +buffer_budget = 65536; # the budget of rx_skb_list, tx_queue_list and + # tx_xmit_list +of_count_rx_skb_list = 0; # overflow count + +tx_queue_list = []; # list of packets which pass through dev_queue_xmit +of_count_tx_queue_list = 0; # overflow count + +tx_xmit_list = []; # list of packets which pass through dev_hard_start_xmit +of_count_tx_xmit_list = 0; # overflow count + +tx_free_list = []; # list of packets which is freed + +# options +show_tx = 0; +show_rx = 0; +dev = 0; # store a name of device specified by option "dev=" +debug = 0; + +# indices of event_info tuple +EINFO_IDX_NAME= 0 +EINFO_IDX_CONTEXT=1 +EINFO_IDX_CPU= 2 +EINFO_IDX_TIME= 3 +EINFO_IDX_PID= 4 +EINFO_IDX_COMM= 5 + +# Calculate a time interval(msec) from src(nsec) to dst(nsec) +def diff_msec(src, dst): + return (dst - src) / 1000000.0 + +# Display a process of transmitting a packet +def print_transmit(hunk): + if dev != 0 and hunk['dev'].find(dev) < 0: + return + print("%7s %5d %6d.%06dsec %12.3fmsec %12.3fmsec" % + (hunk['dev'], hunk['len'], + nsecs_secs(hunk['queue_t']), + nsecs_nsecs(hunk['queue_t'])/1000, + diff_msec(hunk['queue_t'], hunk['xmit_t']), + diff_msec(hunk['xmit_t'], hunk['free_t']))) + +# Format for displaying rx packet processing +PF_IRQ_ENTRY= " irq_entry(+%.3fmsec irq=%d:%s)" +PF_SOFT_ENTRY=" softirq_entry(+%.3fmsec)" +PF_NAPI_POLL= " napi_poll_exit(+%.3fmsec %s)" +PF_JOINT= " |" +PF_WJOINT= " | |" +PF_NET_RECV= " |---netif_receive_skb(+%.3fmsec skb=%x len=%d)" +PF_NET_RX= " |---netif_rx(+%.3fmsec skb=%x)" +PF_CPY_DGRAM= " | skb_copy_datagram_iovec(+%.3fmsec %d:%s)" +PF_KFREE_SKB= " | kfree_skb(+%.3fmsec location=%x)" +PF_CONS_SKB= " | consume_skb(+%.3fmsec)" + +# Display a process of received packets and interrputs associated with +# a NET_RX softirq +def print_receive(hunk): + show_hunk = 0 + irq_list = hunk['irq_list'] + cpu = irq_list[0]['cpu'] + base_t = irq_list[0]['irq_ent_t'] + # check if this hunk should be showed + if dev != 0: + for i in range(len(irq_list)): + if irq_list[i]['name'].find(dev) >= 0: + show_hunk = 1 + break + else: + show_hunk = 1 + if show_hunk == 0: + return + + print("%d.%06dsec cpu=%d" % + (nsecs_secs(base_t), nsecs_nsecs(base_t)/1000, cpu)) + for i in range(len(irq_list)): + print(PF_IRQ_ENTRY % + (diff_msec(base_t, irq_list[i]['irq_ent_t']), + irq_list[i]['irq'], irq_list[i]['name'])) + print(PF_JOINT) + irq_event_list = irq_list[i]['event_list'] + for j in range(len(irq_event_list)): + irq_event = irq_event_list[j] + if irq_event['event'] == 'netif_rx': + print(PF_NET_RX % + (diff_msec(base_t, irq_event['time']), + irq_event['skbaddr'])) + print(PF_JOINT) + print(PF_SOFT_ENTRY % + diff_msec(base_t, hunk['sirq_ent_t'])) + print(PF_JOINT) + event_list = hunk['event_list'] + for i in range(len(event_list)): + event = event_list[i] + if event['event_name'] == 'napi_poll': + print(PF_NAPI_POLL % + (diff_msec(base_t, event['event_t']), + event['dev'])) + if i == len(event_list) - 1: + print("") + else: + print(PF_JOINT) + else: + print(PF_NET_RECV % + (diff_msec(base_t, event['event_t']), + event['skbaddr'], + event['len'])) + if 'comm' in event.keys(): + print(PF_WJOINT) + print(PF_CPY_DGRAM % + (diff_msec(base_t, event['comm_t']), + event['pid'], event['comm'])) + elif 'handle' in event.keys(): + print(PF_WJOINT) + if event['handle'] == "kfree_skb": + print(PF_KFREE_SKB % + (diff_msec(base_t, + event['comm_t']), + event['location'])) + elif event['handle'] == "consume_skb": + print(PF_CONS_SKB % + diff_msec(base_t, + event['comm_t'])) + print(PF_JOINT) + +def trace_begin(): + global show_tx + global show_rx + global dev + global debug + + for i in range(len(sys.argv)): + if i == 0: + continue + arg = sys.argv[i] + if arg == 'tx': + show_tx = 1 + elif arg =='rx': + show_rx = 1 + elif arg.find('dev=',0, 4) >= 0: + dev = arg[4:] + elif arg == 'debug': + debug = 1 + if show_tx == 0 and show_rx == 0: + show_tx = 1 + show_rx = 1 + +def trace_end(): + # order all events in time + all_event_list.sort(key=cmp_to_key(lambda a,b :a[EINFO_IDX_TIME] < b[EINFO_IDX_TIME])) + # process all events + for i in range(len(all_event_list)): + event_info = all_event_list[i] + name = event_info[EINFO_IDX_NAME] + if name == 'irq__softirq_exit': + handle_irq_softirq_exit(event_info) + elif name == 'irq__softirq_entry': + handle_irq_softirq_entry(event_info) + elif name == 'irq__softirq_raise': + handle_irq_softirq_raise(event_info) + elif name == 'irq__irq_handler_entry': + handle_irq_handler_entry(event_info) + elif name == 'irq__irq_handler_exit': + handle_irq_handler_exit(event_info) + elif name == 'napi__napi_poll': + handle_napi_poll(event_info) + elif name == 'net__netif_receive_skb': + handle_netif_receive_skb(event_info) + elif name == 'net__netif_rx': + handle_netif_rx(event_info) + elif name == 'skb__skb_copy_datagram_iovec': + handle_skb_copy_datagram_iovec(event_info) + elif name == 'net__net_dev_queue': + handle_net_dev_queue(event_info) + elif name == 'net__net_dev_xmit': + handle_net_dev_xmit(event_info) + elif name == 'skb__kfree_skb': + handle_kfree_skb(event_info) + elif name == 'skb__consume_skb': + handle_consume_skb(event_info) + # display receive hunks + if show_rx: + for i in range(len(receive_hunk_list)): + print_receive(receive_hunk_list[i]) + # display transmit hunks + if show_tx: + print(" dev len Qdisc " + " netdevice free") + for i in range(len(tx_free_list)): + print_transmit(tx_free_list[i]) + if debug: + print("debug buffer status") + print("----------------------------") + print("xmit Qdisc:remain:%d overflow:%d" % + (len(tx_queue_list), of_count_tx_queue_list)) + print("xmit netdevice:remain:%d overflow:%d" % + (len(tx_xmit_list), of_count_tx_xmit_list)) + print("receive:remain:%d overflow:%d" % + (len(rx_skb_list), of_count_rx_skb_list)) + +# called from perf, when it finds a correspoinding event +def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec): + if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": + return + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) + all_event_list.append(event_info) + +def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec): + if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": + return + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) + all_event_list.append(event_info) + +def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec): + if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": + return + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) + all_event_list.append(event_info) + +def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm, + callchain, irq, irq_name): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + irq, irq_name) + all_event_list.append(event_info) + +def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret) + all_event_list.append(event_info) + +def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, + dev_name, work=None, budget=None): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + napi, dev_name, work, budget) + all_event_list.append(event_info) + +def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, + skblen, dev_name): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, skblen, dev_name) + all_event_list.append(event_info) + +def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, + skblen, dev_name): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, skblen, dev_name) + all_event_list.append(event_info) + +def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain, + skbaddr, skblen, dev_name): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, skblen, dev_name) + all_event_list.append(event_info) + +def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain, + skbaddr, skblen, rc, dev_name): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, skblen, rc ,dev_name) + all_event_list.append(event_info) + +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, + skbaddr, protocol, location): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, protocol, location) + all_event_list.append(event_info) + +def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr) + all_event_list.append(event_info) + +def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain, + skbaddr, skblen): + event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, + skbaddr, skblen) + all_event_list.append(event_info) + +def handle_irq_handler_entry(event_info): + (name, context, cpu, time, pid, comm, irq, irq_name) = event_info + if cpu not in irq_dic.keys(): + irq_dic[cpu] = [] + irq_record = {'irq':irq, 'name':irq_name, 'cpu':cpu, 'irq_ent_t':time} + irq_dic[cpu].append(irq_record) + +def handle_irq_handler_exit(event_info): + (name, context, cpu, time, pid, comm, irq, ret) = event_info + if cpu not in irq_dic.keys(): + return + irq_record = irq_dic[cpu].pop() + if irq != irq_record['irq']: + return + irq_record.update({'irq_ext_t':time}) + # if an irq doesn't include NET_RX softirq, drop. + if 'event_list' in irq_record.keys(): + irq_dic[cpu].append(irq_record) + +def handle_irq_softirq_raise(event_info): + (name, context, cpu, time, pid, comm, vec) = event_info + if cpu not in irq_dic.keys() \ + or len(irq_dic[cpu]) == 0: + return + irq_record = irq_dic[cpu].pop() + if 'event_list' in irq_record.keys(): + irq_event_list = irq_record['event_list'] + else: + irq_event_list = [] + irq_event_list.append({'time':time, 'event':'sirq_raise'}) + irq_record.update({'event_list':irq_event_list}) + irq_dic[cpu].append(irq_record) + +def handle_irq_softirq_entry(event_info): + (name, context, cpu, time, pid, comm, vec) = event_info + net_rx_dic[cpu] = {'sirq_ent_t':time, 'event_list':[]} + +def handle_irq_softirq_exit(event_info): + (name, context, cpu, time, pid, comm, vec) = event_info + irq_list = [] + event_list = 0 + if cpu in irq_dic.keys(): + irq_list = irq_dic[cpu] + del irq_dic[cpu] + if cpu in net_rx_dic.keys(): + sirq_ent_t = net_rx_dic[cpu]['sirq_ent_t'] + event_list = net_rx_dic[cpu]['event_list'] + del net_rx_dic[cpu] + if irq_list == [] or event_list == 0: + return + rec_data = {'sirq_ent_t':sirq_ent_t, 'sirq_ext_t':time, + 'irq_list':irq_list, 'event_list':event_list} + # merge information related to a NET_RX softirq + receive_hunk_list.append(rec_data) + +def handle_napi_poll(event_info): + (name, context, cpu, time, pid, comm, napi, dev_name, + work, budget) = event_info + if cpu in net_rx_dic.keys(): + event_list = net_rx_dic[cpu]['event_list'] + rec_data = {'event_name':'napi_poll', + 'dev':dev_name, 'event_t':time, + 'work':work, 'budget':budget} + event_list.append(rec_data) + +def handle_netif_rx(event_info): + (name, context, cpu, time, pid, comm, + skbaddr, skblen, dev_name) = event_info + if cpu not in irq_dic.keys() \ + or len(irq_dic[cpu]) == 0: + return + irq_record = irq_dic[cpu].pop() + if 'event_list' in irq_record.keys(): + irq_event_list = irq_record['event_list'] + else: + irq_event_list = [] + irq_event_list.append({'time':time, 'event':'netif_rx', + 'skbaddr':skbaddr, 'skblen':skblen, 'dev_name':dev_name}) + irq_record.update({'event_list':irq_event_list}) + irq_dic[cpu].append(irq_record) + +def handle_netif_receive_skb(event_info): + global of_count_rx_skb_list + + (name, context, cpu, time, pid, comm, + skbaddr, skblen, dev_name) = event_info + if cpu in net_rx_dic.keys(): + rec_data = {'event_name':'netif_receive_skb', + 'event_t':time, 'skbaddr':skbaddr, 'len':skblen} + event_list = net_rx_dic[cpu]['event_list'] + event_list.append(rec_data) + rx_skb_list.insert(0, rec_data) + if len(rx_skb_list) > buffer_budget: + rx_skb_list.pop() + of_count_rx_skb_list += 1 + +def handle_net_dev_queue(event_info): + global of_count_tx_queue_list + + (name, context, cpu, time, pid, comm, + skbaddr, skblen, dev_name) = event_info + skb = {'dev':dev_name, 'skbaddr':skbaddr, 'len':skblen, 'queue_t':time} + tx_queue_list.insert(0, skb) + if len(tx_queue_list) > buffer_budget: + tx_queue_list.pop() + of_count_tx_queue_list += 1 + +def handle_net_dev_xmit(event_info): + global of_count_tx_xmit_list + + (name, context, cpu, time, pid, comm, + skbaddr, skblen, rc, dev_name) = event_info + if rc == 0: # NETDEV_TX_OK + for i in range(len(tx_queue_list)): + skb = tx_queue_list[i] + if skb['skbaddr'] == skbaddr: + skb['xmit_t'] = time + tx_xmit_list.insert(0, skb) + del tx_queue_list[i] + if len(tx_xmit_list) > buffer_budget: + tx_xmit_list.pop() + of_count_tx_xmit_list += 1 + return + +def handle_kfree_skb(event_info): + (name, context, cpu, time, pid, comm, + skbaddr, protocol, location) = event_info + for i in range(len(tx_queue_list)): + skb = tx_queue_list[i] + if skb['skbaddr'] == skbaddr: + del tx_queue_list[i] + return + for i in range(len(tx_xmit_list)): + skb = tx_xmit_list[i] + if skb['skbaddr'] == skbaddr: + skb['free_t'] = time + tx_free_list.append(skb) + del tx_xmit_list[i] + return + for i in range(len(rx_skb_list)): + rec_data = rx_skb_list[i] + if rec_data['skbaddr'] == skbaddr: + rec_data.update({'handle':"kfree_skb", + 'comm':comm, 'pid':pid, 'comm_t':time}) + del rx_skb_list[i] + return + +def handle_consume_skb(event_info): + (name, context, cpu, time, pid, comm, skbaddr) = event_info + for i in range(len(tx_xmit_list)): + skb = tx_xmit_list[i] + if skb['skbaddr'] == skbaddr: + skb['free_t'] = time + tx_free_list.append(skb) + del tx_xmit_list[i] + return + +def handle_skb_copy_datagram_iovec(event_info): + (name, context, cpu, time, pid, comm, skbaddr, skblen) = event_info + for i in range(len(rx_skb_list)): + rec_data = rx_skb_list[i] + if skbaddr == rec_data['skbaddr']: + rec_data.update({'handle':"skb_copy_datagram_iovec", + 'comm':comm, 'pid':pid, 'comm_t':time}) + del rx_skb_list[i] + return diff --git a/tools/perf/scripts/python/powerpc-hcalls.py b/tools/perf/scripts/python/powerpc-hcalls.py new file mode 100644 index 000000000..8b78dc790 --- /dev/null +++ b/tools/perf/scripts/python/powerpc-hcalls.py @@ -0,0 +1,202 @@ +# SPDX-License-Identifier: GPL-2.0+ +# +# Copyright (C) 2018 Ravi Bangoria, IBM Corporation +# +# Hypervisor call statisics + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +# output: { +# opcode: { +# 'min': minimum time nsec +# 'max': maximum time nsec +# 'time': average time nsec +# 'cnt': counter +# } ... +# } +output = {} + +# d_enter: { +# cpu: { +# opcode: nsec +# } ... +# } +d_enter = {} + +hcall_table = { + 4: 'H_REMOVE', + 8: 'H_ENTER', + 12: 'H_READ', + 16: 'H_CLEAR_MOD', + 20: 'H_CLEAR_REF', + 24: 'H_PROTECT', + 28: 'H_GET_TCE', + 32: 'H_PUT_TCE', + 36: 'H_SET_SPRG0', + 40: 'H_SET_DABR', + 44: 'H_PAGE_INIT', + 48: 'H_SET_ASR', + 52: 'H_ASR_ON', + 56: 'H_ASR_OFF', + 60: 'H_LOGICAL_CI_LOAD', + 64: 'H_LOGICAL_CI_STORE', + 68: 'H_LOGICAL_CACHE_LOAD', + 72: 'H_LOGICAL_CACHE_STORE', + 76: 'H_LOGICAL_ICBI', + 80: 'H_LOGICAL_DCBF', + 84: 'H_GET_TERM_CHAR', + 88: 'H_PUT_TERM_CHAR', + 92: 'H_REAL_TO_LOGICAL', + 96: 'H_HYPERVISOR_DATA', + 100: 'H_EOI', + 104: 'H_CPPR', + 108: 'H_IPI', + 112: 'H_IPOLL', + 116: 'H_XIRR', + 120: 'H_MIGRATE_DMA', + 124: 'H_PERFMON', + 220: 'H_REGISTER_VPA', + 224: 'H_CEDE', + 228: 'H_CONFER', + 232: 'H_PROD', + 236: 'H_GET_PPP', + 240: 'H_SET_PPP', + 244: 'H_PURR', + 248: 'H_PIC', + 252: 'H_REG_CRQ', + 256: 'H_FREE_CRQ', + 260: 'H_VIO_SIGNAL', + 264: 'H_SEND_CRQ', + 272: 'H_COPY_RDMA', + 276: 'H_REGISTER_LOGICAL_LAN', + 280: 'H_FREE_LOGICAL_LAN', + 284: 'H_ADD_LOGICAL_LAN_BUFFER', + 288: 'H_SEND_LOGICAL_LAN', + 292: 'H_BULK_REMOVE', + 304: 'H_MULTICAST_CTRL', + 308: 'H_SET_XDABR', + 312: 'H_STUFF_TCE', + 316: 'H_PUT_TCE_INDIRECT', + 332: 'H_CHANGE_LOGICAL_LAN_MAC', + 336: 'H_VTERM_PARTNER_INFO', + 340: 'H_REGISTER_VTERM', + 344: 'H_FREE_VTERM', + 348: 'H_RESET_EVENTS', + 352: 'H_ALLOC_RESOURCE', + 356: 'H_FREE_RESOURCE', + 360: 'H_MODIFY_QP', + 364: 'H_QUERY_QP', + 368: 'H_REREGISTER_PMR', + 372: 'H_REGISTER_SMR', + 376: 'H_QUERY_MR', + 380: 'H_QUERY_MW', + 384: 'H_QUERY_HCA', + 388: 'H_QUERY_PORT', + 392: 'H_MODIFY_PORT', + 396: 'H_DEFINE_AQP1', + 400: 'H_GET_TRACE_BUFFER', + 404: 'H_DEFINE_AQP0', + 408: 'H_RESIZE_MR', + 412: 'H_ATTACH_MCQP', + 416: 'H_DETACH_MCQP', + 420: 'H_CREATE_RPT', + 424: 'H_REMOVE_RPT', + 428: 'H_REGISTER_RPAGES', + 432: 'H_DISABLE_AND_GETC', + 436: 'H_ERROR_DATA', + 440: 'H_GET_HCA_INFO', + 444: 'H_GET_PERF_COUNT', + 448: 'H_MANAGE_TRACE', + 468: 'H_FREE_LOGICAL_LAN_BUFFER', + 472: 'H_POLL_PENDING', + 484: 'H_QUERY_INT_STATE', + 580: 'H_ILLAN_ATTRIBUTES', + 592: 'H_MODIFY_HEA_QP', + 596: 'H_QUERY_HEA_QP', + 600: 'H_QUERY_HEA', + 604: 'H_QUERY_HEA_PORT', + 608: 'H_MODIFY_HEA_PORT', + 612: 'H_REG_BCMC', + 616: 'H_DEREG_BCMC', + 620: 'H_REGISTER_HEA_RPAGES', + 624: 'H_DISABLE_AND_GET_HEA', + 628: 'H_GET_HEA_INFO', + 632: 'H_ALLOC_HEA_RESOURCE', + 644: 'H_ADD_CONN', + 648: 'H_DEL_CONN', + 664: 'H_JOIN', + 676: 'H_VASI_STATE', + 688: 'H_ENABLE_CRQ', + 696: 'H_GET_EM_PARMS', + 720: 'H_SET_MPP', + 724: 'H_GET_MPP', + 748: 'H_HOME_NODE_ASSOCIATIVITY', + 756: 'H_BEST_ENERGY', + 764: 'H_XIRR_X', + 768: 'H_RANDOM', + 772: 'H_COP', + 788: 'H_GET_MPP_X', + 796: 'H_SET_MODE', + 61440: 'H_RTAS', +} + +def hcall_table_lookup(opcode): + if (opcode in hcall_table): + return hcall_table[opcode] + else: + return opcode + +print_ptrn = '%-28s%10s%10s%10s%10s' + +def trace_end(): + print(print_ptrn % ('hcall', 'count', 'min(ns)', 'max(ns)', 'avg(ns)')) + print('-' * 68) + for opcode in output: + h_name = hcall_table_lookup(opcode) + time = output[opcode]['time'] + cnt = output[opcode]['cnt'] + min_t = output[opcode]['min'] + max_t = output[opcode]['max'] + + print(print_ptrn % (h_name, cnt, min_t, max_t, time//cnt)) + +def powerpc__hcall_exit(name, context, cpu, sec, nsec, pid, comm, callchain, + opcode, retval): + if (cpu in d_enter and opcode in d_enter[cpu]): + diff = nsecs(sec, nsec) - d_enter[cpu][opcode] + + if (opcode in output): + output[opcode]['time'] += diff + output[opcode]['cnt'] += 1 + if (output[opcode]['min'] > diff): + output[opcode]['min'] = diff + if (output[opcode]['max'] < diff): + output[opcode]['max'] = diff + else: + output[opcode] = { + 'time': diff, + 'cnt': 1, + 'min': diff, + 'max': diff, + } + + del d_enter[cpu][opcode] +# else: +# print("Can't find matching hcall_enter event. Ignoring sample") + +def powerpc__hcall_entry(event_name, context, cpu, sec, nsec, pid, comm, + callchain, opcode): + if (cpu in d_enter): + d_enter[cpu][opcode] = nsecs(sec, nsec) + else: + d_enter[cpu] = {opcode: nsecs(sec, nsec)} diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py new file mode 100644 index 000000000..8196e3087 --- /dev/null +++ b/tools/perf/scripts/python/sched-migration.py @@ -0,0 +1,462 @@ +# Cpu task migration overview toy +# +# Copyright (C) 2010 Frederic Weisbecker <fweisbec@gmail.com> +# +# perf script event handlers have been generated by perf script -g python +# +# This software is distributed under the terms of the GNU General +# Public License ("GPL") version 2 as published by the Free Software +# Foundation. +from __future__ import print_function + +import os +import sys + +from collections import defaultdict +try: + from UserList import UserList +except ImportError: + # Python 3: UserList moved to the collections package + from collections import UserList + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') +sys.path.append('scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from SchedGui import * + + +threads = { 0 : "idle"} + +def thread_name(pid): + return "%s:%d" % (threads[pid], pid) + +class RunqueueEventUnknown: + @staticmethod + def color(): + return None + + def __repr__(self): + return "unknown" + +class RunqueueEventSleep: + @staticmethod + def color(): + return (0, 0, 0xff) + + def __init__(self, sleeper): + self.sleeper = sleeper + + def __repr__(self): + return "%s gone to sleep" % thread_name(self.sleeper) + +class RunqueueEventWakeup: + @staticmethod + def color(): + return (0xff, 0xff, 0) + + def __init__(self, wakee): + self.wakee = wakee + + def __repr__(self): + return "%s woke up" % thread_name(self.wakee) + +class RunqueueEventFork: + @staticmethod + def color(): + return (0, 0xff, 0) + + def __init__(self, child): + self.child = child + + def __repr__(self): + return "new forked task %s" % thread_name(self.child) + +class RunqueueMigrateIn: + @staticmethod + def color(): + return (0, 0xf0, 0xff) + + def __init__(self, new): + self.new = new + + def __repr__(self): + return "task migrated in %s" % thread_name(self.new) + +class RunqueueMigrateOut: + @staticmethod + def color(): + return (0xff, 0, 0xff) + + def __init__(self, old): + self.old = old + + def __repr__(self): + return "task migrated out %s" % thread_name(self.old) + +class RunqueueSnapshot: + def __init__(self, tasks = [0], event = RunqueueEventUnknown()): + self.tasks = tuple(tasks) + self.event = event + + def sched_switch(self, prev, prev_state, next): + event = RunqueueEventUnknown() + + if taskState(prev_state) == "R" and next in self.tasks \ + and prev in self.tasks: + return self + + if taskState(prev_state) != "R": + event = RunqueueEventSleep(prev) + + next_tasks = list(self.tasks[:]) + if prev in self.tasks: + if taskState(prev_state) != "R": + next_tasks.remove(prev) + elif taskState(prev_state) == "R": + next_tasks.append(prev) + + if next not in next_tasks: + next_tasks.append(next) + + return RunqueueSnapshot(next_tasks, event) + + def migrate_out(self, old): + if old not in self.tasks: + return self + next_tasks = [task for task in self.tasks if task != old] + + return RunqueueSnapshot(next_tasks, RunqueueMigrateOut(old)) + + def __migrate_in(self, new, event): + if new in self.tasks: + self.event = event + return self + next_tasks = self.tasks[:] + tuple([new]) + + return RunqueueSnapshot(next_tasks, event) + + def migrate_in(self, new): + return self.__migrate_in(new, RunqueueMigrateIn(new)) + + def wake_up(self, new): + return self.__migrate_in(new, RunqueueEventWakeup(new)) + + def wake_up_new(self, new): + return self.__migrate_in(new, RunqueueEventFork(new)) + + def load(self): + """ Provide the number of tasks on the runqueue. + Don't count idle""" + return len(self.tasks) - 1 + + def __repr__(self): + ret = self.tasks.__repr__() + ret += self.origin_tostring() + + return ret + +class TimeSlice: + def __init__(self, start, prev): + self.start = start + self.prev = prev + self.end = start + # cpus that triggered the event + self.event_cpus = [] + if prev is not None: + self.total_load = prev.total_load + self.rqs = prev.rqs.copy() + else: + self.rqs = defaultdict(RunqueueSnapshot) + self.total_load = 0 + + def __update_total_load(self, old_rq, new_rq): + diff = new_rq.load() - old_rq.load() + self.total_load += diff + + def sched_switch(self, ts_list, prev, prev_state, next, cpu): + old_rq = self.prev.rqs[cpu] + new_rq = old_rq.sched_switch(prev, prev_state, next) + + if old_rq is new_rq: + return + + self.rqs[cpu] = new_rq + self.__update_total_load(old_rq, new_rq) + ts_list.append(self) + self.event_cpus = [cpu] + + def migrate(self, ts_list, new, old_cpu, new_cpu): + if old_cpu == new_cpu: + return + old_rq = self.prev.rqs[old_cpu] + out_rq = old_rq.migrate_out(new) + self.rqs[old_cpu] = out_rq + self.__update_total_load(old_rq, out_rq) + + new_rq = self.prev.rqs[new_cpu] + in_rq = new_rq.migrate_in(new) + self.rqs[new_cpu] = in_rq + self.__update_total_load(new_rq, in_rq) + + ts_list.append(self) + + if old_rq is not out_rq: + self.event_cpus.append(old_cpu) + self.event_cpus.append(new_cpu) + + def wake_up(self, ts_list, pid, cpu, fork): + old_rq = self.prev.rqs[cpu] + if fork: + new_rq = old_rq.wake_up_new(pid) + else: + new_rq = old_rq.wake_up(pid) + + if new_rq is old_rq: + return + self.rqs[cpu] = new_rq + self.__update_total_load(old_rq, new_rq) + ts_list.append(self) + self.event_cpus = [cpu] + + def next(self, t): + self.end = t + return TimeSlice(t, self) + +class TimeSliceList(UserList): + def __init__(self, arg = []): + self.data = arg + + def get_time_slice(self, ts): + if len(self.data) == 0: + slice = TimeSlice(ts, TimeSlice(-1, None)) + else: + slice = self.data[-1].next(ts) + return slice + + def find_time_slice(self, ts): + start = 0 + end = len(self.data) + found = -1 + searching = True + while searching: + if start == end or start == end - 1: + searching = False + + i = (end + start) / 2 + if self.data[i].start <= ts and self.data[i].end >= ts: + found = i + end = i + continue + + if self.data[i].end < ts: + start = i + + elif self.data[i].start > ts: + end = i + + return found + + def set_root_win(self, win): + self.root_win = win + + def mouse_down(self, cpu, t): + idx = self.find_time_slice(t) + if idx == -1: + return + + ts = self[idx] + rq = ts.rqs[cpu] + raw = "CPU: %d\n" % cpu + raw += "Last event : %s\n" % rq.event.__repr__() + raw += "Timestamp : %d.%06d\n" % (ts.start / (10 ** 9), (ts.start % (10 ** 9)) / 1000) + raw += "Duration : %6d us\n" % ((ts.end - ts.start) / (10 ** 6)) + raw += "Load = %d\n" % rq.load() + for t in rq.tasks: + raw += "%s \n" % thread_name(t) + + self.root_win.update_summary(raw) + + def update_rectangle_cpu(self, slice, cpu): + rq = slice.rqs[cpu] + + if slice.total_load != 0: + load_rate = rq.load() / float(slice.total_load) + else: + load_rate = 0 + + red_power = int(0xff - (0xff * load_rate)) + color = (0xff, red_power, red_power) + + top_color = None + + if cpu in slice.event_cpus: + top_color = rq.event.color() + + self.root_win.paint_rectangle_zone(cpu, color, top_color, slice.start, slice.end) + + def fill_zone(self, start, end): + i = self.find_time_slice(start) + if i == -1: + return + + for i in range(i, len(self.data)): + timeslice = self.data[i] + if timeslice.start > end: + return + + for cpu in timeslice.rqs: + self.update_rectangle_cpu(timeslice, cpu) + + def interval(self): + if len(self.data) == 0: + return (0, 0) + + return (self.data[0].start, self.data[-1].end) + + def nr_rectangles(self): + last_ts = self.data[-1] + max_cpu = 0 + for cpu in last_ts.rqs: + if cpu > max_cpu: + max_cpu = cpu + return max_cpu + + +class SchedEventProxy: + def __init__(self): + self.current_tsk = defaultdict(lambda : -1) + self.timeslices = TimeSliceList() + + def sched_switch(self, headers, prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio): + """ Ensure the task we sched out this cpu is really the one + we logged. Otherwise we may have missed traces """ + + on_cpu_task = self.current_tsk[headers.cpu] + + if on_cpu_task != -1 and on_cpu_task != prev_pid: + print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \ + headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid) + + threads[prev_pid] = prev_comm + threads[next_pid] = next_comm + self.current_tsk[headers.cpu] = next_pid + + ts = self.timeslices.get_time_slice(headers.ts()) + ts.sched_switch(self.timeslices, prev_pid, prev_state, next_pid, headers.cpu) + + def migrate(self, headers, pid, prio, orig_cpu, dest_cpu): + ts = self.timeslices.get_time_slice(headers.ts()) + ts.migrate(self.timeslices, pid, orig_cpu, dest_cpu) + + def wake_up(self, headers, comm, pid, success, target_cpu, fork): + if success == 0: + return + ts = self.timeslices.get_time_slice(headers.ts()) + ts.wake_up(self.timeslices, pid, target_cpu, fork) + + +def trace_begin(): + global parser + parser = SchedEventProxy() + +def trace_end(): + app = wx.App(False) + timeslices = parser.timeslices + frame = RootFrame(timeslices, "Migration") + app.MainLoop() + +def sched__sched_stat_runtime(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, runtime, vruntime): + pass + +def sched__sched_stat_iowait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, delay): + pass + +def sched__sched_stat_sleep(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, delay): + pass + +def sched__sched_stat_wait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, delay): + pass + +def sched__sched_process_fork(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, parent_comm, parent_pid, child_comm, child_pid): + pass + +def sched__sched_process_wait(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio): + pass + +def sched__sched_process_exit(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio): + pass + +def sched__sched_process_free(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio): + pass + +def sched__sched_migrate_task(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio, orig_cpu, + dest_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm, common_callchain) + parser.migrate(headers, pid, prio, orig_cpu, dest_cpu) + +def sched__sched_switch(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, common_callchain, + prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio): + + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm, common_callchain) + parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state, + next_comm, next_pid, next_prio) + +def sched__sched_wakeup_new(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio, success, + target_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm, common_callchain) + parser.wake_up(headers, comm, pid, success, target_cpu, 1) + +def sched__sched_wakeup(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio, success, + target_cpu): + headers = EventHeaders(common_cpu, common_secs, common_nsecs, + common_pid, common_comm, common_callchain) + parser.wake_up(headers, comm, pid, success, target_cpu, 0) + +def sched__sched_wait_task(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid, prio): + pass + +def sched__sched_kthread_stop_ret(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, ret): + pass + +def sched__sched_kthread_stop(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, comm, pid): + pass + +def trace_unhandled(event_name, context, event_fields_dict): + pass diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py new file mode 100644 index 000000000..6e0278dcb --- /dev/null +++ b/tools/perf/scripts/python/sctop.py @@ -0,0 +1,89 @@ +# system call top +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Periodically displays system-wide system call totals, broken down by +# syscall. If a [comm] arg is specified, only syscalls called by +# [comm] are displayed. If an [interval] arg is specified, the display +# will be refreshed every [interval] seconds. The default interval is +# 3 seconds. + +from __future__ import print_function + +import os, sys, time + +try: + import thread +except ImportError: + import _thread as thread + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +usage = "perf script -s sctop.py [comm] [interval]\n"; + +for_comm = None +default_interval = 3 +interval = default_interval + +if len(sys.argv) > 3: + sys.exit(usage) + +if len(sys.argv) > 2: + for_comm = sys.argv[1] + interval = int(sys.argv[2]) +elif len(sys.argv) > 1: + try: + interval = int(sys.argv[1]) + except ValueError: + for_comm = sys.argv[1] + interval = default_interval + +syscalls = autodict() + +def trace_begin(): + thread.start_new_thread(print_syscall_totals, (interval,)) + pass + +def raw_syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, id, args): + if for_comm is not None: + if common_comm != for_comm: + return + try: + syscalls[id] += 1 + except TypeError: + syscalls[id] = 1 + +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + +def print_syscall_totals(interval): + while 1: + clear_term() + if for_comm is not None: + print("\nsyscall events for %s:\n" % (for_comm)) + else: + print("\nsyscall events:\n") + + print("%-40s %10s" % ("event", "count")) + print("%-40s %10s" % + ("----------------------------------------", + "----------")) + + for id, val in sorted(syscalls.items(), + key = lambda kv: (kv[1], kv[0]), + reverse = True): + try: + print("%-40s %10d" % (syscall_name(id), val)) + except TypeError: + pass + syscalls.clear() + time.sleep(interval) diff --git a/tools/perf/scripts/python/stackcollapse.py b/tools/perf/scripts/python/stackcollapse.py new file mode 100755 index 000000000..b1c4def14 --- /dev/null +++ b/tools/perf/scripts/python/stackcollapse.py @@ -0,0 +1,127 @@ +# stackcollapse.py - format perf samples with one line per distinct call stack +# SPDX-License-Identifier: GPL-2.0 +# +# This script's output has two space-separated fields. The first is a semicolon +# separated stack including the program name (from the "comm" field) and the +# function names from the call stack. The second is a count: +# +# swapper;start_kernel;rest_init;cpu_idle;default_idle;native_safe_halt 2 +# +# The file is sorted according to the first field. +# +# Input may be created and processed using: +# +# perf record -a -g -F 99 sleep 60 +# perf script report stackcollapse > out.stacks-folded +# +# (perf script record stackcollapse works too). +# +# Written by Paolo Bonzini <pbonzini@redhat.com> +# Based on Brendan Gregg's stackcollapse-perf.pl script. + +from __future__ import print_function + +import os +import sys +from collections import defaultdict +from optparse import OptionParser, make_option + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from EventClass import * + +# command line parsing + +option_list = [ + # formatting options for the bottom entry of the stack + make_option("--include-tid", dest="include_tid", + action="store_true", default=False, + help="include thread id in stack"), + make_option("--include-pid", dest="include_pid", + action="store_true", default=False, + help="include process id in stack"), + make_option("--no-comm", dest="include_comm", + action="store_false", default=True, + help="do not separate stacks according to comm"), + make_option("--tidy-java", dest="tidy_java", + action="store_true", default=False, + help="beautify Java signatures"), + make_option("--kernel", dest="annotate_kernel", + action="store_true", default=False, + help="annotate kernel functions with _[k]") +] + +parser = OptionParser(option_list=option_list) +(opts, args) = parser.parse_args() + +if len(args) != 0: + parser.error("unexpected command line argument") +if opts.include_tid and not opts.include_comm: + parser.error("requesting tid but not comm is invalid") +if opts.include_pid and not opts.include_comm: + parser.error("requesting pid but not comm is invalid") + +# event handlers + +lines = defaultdict(lambda: 0) + +def process_event(param_dict): + def tidy_function_name(sym, dso): + if sym is None: + sym = '[unknown]' + + sym = sym.replace(';', ':') + if opts.tidy_java: + # the original stackcollapse-perf.pl script gives the + # example of converting this: + # Lorg/mozilla/javascript/MemberBox;.<init>(Ljava/lang/reflect/Method;)V + # to this: + # org/mozilla/javascript/MemberBox:.init + sym = sym.replace('<', '') + sym = sym.replace('>', '') + if sym[0] == 'L' and sym.find('/'): + sym = sym[1:] + try: + sym = sym[:sym.index('(')] + except ValueError: + pass + + if opts.annotate_kernel and dso == '[kernel.kallsyms]': + return sym + '_[k]' + else: + return sym + + stack = list() + if 'callchain' in param_dict: + for entry in param_dict['callchain']: + entry.setdefault('sym', dict()) + entry['sym'].setdefault('name', None) + entry.setdefault('dso', None) + stack.append(tidy_function_name(entry['sym']['name'], + entry['dso'])) + else: + param_dict.setdefault('symbol', None) + param_dict.setdefault('dso', None) + stack.append(tidy_function_name(param_dict['symbol'], + param_dict['dso'])) + + if opts.include_comm: + comm = param_dict["comm"].replace(' ', '_') + sep = "-" + if opts.include_pid: + comm = comm + sep + str(param_dict['sample']['pid']) + sep = "/" + if opts.include_tid: + comm = comm + sep + str(param_dict['sample']['tid']) + stack.append(comm) + + stack_string = ';'.join(reversed(stack)) + lines[stack_string] = lines[stack_string] + 1 + +def trace_end(): + list = sorted(lines) + for stack in list: + print("%s %d" % (stack, lines[stack])) diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py new file mode 100644 index 000000000..01fa933ff --- /dev/null +++ b/tools/perf/scripts/python/stat-cpi.py @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: GPL-2.0 + +from __future__ import print_function + +data = {} +times = [] +threads = [] +cpus = [] + +def get_key(time, event, cpu, thread): + return "%d-%s-%d-%d" % (time, event, cpu, thread) + +def store_key(time, cpu, thread): + if (time not in times): + times.append(time) + + if (cpu not in cpus): + cpus.append(cpu) + + if (thread not in threads): + threads.append(thread) + +def store(time, event, cpu, thread, val, ena, run): + #print("event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % + # (event, cpu, thread, time, val, ena, run)) + + store_key(time, cpu, thread) + key = get_key(time, event, cpu, thread) + data[key] = [ val, ena, run] + +def get(time, event, cpu, thread): + key = get_key(time, event, cpu, thread) + return data[key][0] + +def stat__cycles_k(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_k(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles_u(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_u(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__interval(time): + for cpu in cpus: + for thread in threads: + cyc = get(time, "cycles", cpu, thread) + ins = get(time, "instructions", cpu, thread) + cpi = 0 + + if ins != 0: + cpi = cyc/float(ins) + + print("%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins)) + +def trace_end(): + pass +# XXX trace_end callback could be used as an alternative place +# to compute same values as in the script above: +# +# for time in times: +# for cpu in cpus: +# for thread in threads: +# cyc = get(time, "cycles", cpu, thread) +# ins = get(time, "instructions", cpu, thread) +# +# if ins != 0: +# cpi = cyc/float(ins) +# +# print("time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi)) diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py new file mode 100644 index 000000000..f254e40c6 --- /dev/null +++ b/tools/perf/scripts/python/syscall-counts-by-pid.py @@ -0,0 +1,75 @@ +# system call counts, by pid +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Displays system-wide system call totals, broken down by syscall. +# If a [comm] arg is specified, only syscalls called by [comm] are displayed. + +from __future__ import print_function + +import os, sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import syscall_name + +usage = "perf script -s syscall-counts-by-pid.py [comm]\n"; + +for_comm = None +for_pid = None + +if len(sys.argv) > 2: + sys.exit(usage) + +if len(sys.argv) > 1: + try: + for_pid = int(sys.argv[1]) + except: + for_comm = sys.argv[1] + +syscalls = autodict() + +def trace_begin(): + print("Press control+C to stop and show the summary") + +def trace_end(): + print_syscall_totals() + +def raw_syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, id, args): + if (for_comm and common_comm != for_comm) or \ + (for_pid and common_pid != for_pid ): + return + try: + syscalls[common_comm][common_pid][id] += 1 + except TypeError: + syscalls[common_comm][common_pid][id] = 1 + +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + id, args): + raw_syscalls__sys_enter(**locals()) + +def print_syscall_totals(): + if for_comm is not None: + print("\nsyscall events for %s:\n" % (for_comm)) + else: + print("\nsyscall events by comm/pid:\n") + + print("%-40s %10s" % ("comm [pid]/syscalls", "count")) + print("%-40s %10s" % ("----------------------------------------", + "----------")) + + comm_keys = syscalls.keys() + for comm in comm_keys: + pid_keys = syscalls[comm].keys() + for pid in pid_keys: + print("\n%s [%d]" % (comm, pid)) + id_keys = syscalls[comm][pid].keys() + for id, val in sorted(syscalls[comm][pid].items(), + key = lambda kv: (kv[1], kv[0]), reverse = True): + print(" %-38s %10d" % (syscall_name(id), val)) diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py new file mode 100644 index 000000000..8adb95ff1 --- /dev/null +++ b/tools/perf/scripts/python/syscall-counts.py @@ -0,0 +1,65 @@ +# system call counts +# (c) 2010, Tom Zanussi <tzanussi@gmail.com> +# Licensed under the terms of the GNU GPL License version 2 +# +# Displays system-wide system call totals, broken down by syscall. +# If a [comm] arg is specified, only syscalls called by [comm] are displayed. + +from __future__ import print_function + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import syscall_name + +usage = "perf script -s syscall-counts.py [comm]\n"; + +for_comm = None + +if len(sys.argv) > 2: + sys.exit(usage) + +if len(sys.argv) > 1: + for_comm = sys.argv[1] + +syscalls = autodict() + +def trace_begin(): + print("Press control+C to stop and show the summary") + +def trace_end(): + print_syscall_totals() + +def raw_syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, + common_callchain, id, args): + if for_comm is not None: + if common_comm != for_comm: + return + try: + syscalls[id] += 1 + except TypeError: + syscalls[id] = 1 + +def syscalls__sys_enter(event_name, context, common_cpu, + common_secs, common_nsecs, common_pid, common_comm, id, args): + raw_syscalls__sys_enter(**locals()) + +def print_syscall_totals(): + if for_comm is not None: + print("\nsyscall events for %s:\n" % (for_comm)) + else: + print("\nsyscall events:\n") + + print("%-40s %10s" % ("event", "count")) + print("%-40s %10s" % ("----------------------------------------", + "-----------")) + + for id, val in sorted(syscalls.items(), + key = lambda kv: (kv[1], kv[0]), reverse = True): + print("%-40s %10d" % (syscall_name(id), val)) |