1114 lines · 38.9 KB · Python
RawDownload
# 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 osimport sysimport structimport 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 = Trueif 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 strelse:	# 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 STDINfrom ctypes import *libpq = CDLL("libpq.so.5")PQconnectdb = libpq.PQconnectdbPQconnectdb.restype = c_void_pPQconnectdb.argtypes = [ c_char_p ]PQfinish = libpq.PQfinishPQfinish.argtypes = [ c_void_p ]PQstatus = libpq.PQstatusPQstatus.restype = c_intPQstatus.argtypes = [ c_void_p ]PQexec = libpq.PQexecPQexec.restype = c_void_pPQexec.argtypes = [ c_void_p, c_char_p ]PQresultStatus = libpq.PQresultStatusPQresultStatus.restype = c_intPQresultStatus.argtypes = [ c_void_p ]PQputCopyData = libpq.PQputCopyDataPQputCopyData.restype = c_intPQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]PQputCopyEnd = libpq.PQputCopyEndPQputCopyEnd.restype = c_intPQputCopyEnd.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 = Trueperf_db_export_calls = Falseperf_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)	raisequery.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,'

Lines 1–500 of 1114.