Message-ID: <f4c9445f-d992-60d8-fab7-67e0eea4416c@intel.com>
Date:   Fri, 8 Mar 2019 11:47:55 +0200
From:   Adrian Hunter <adrian.hunter@...el.com>
To:     Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>,
        Tony Jones <tonyj@...e.de>
Cc:     linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
        Seeteena Thoufeek <s1seetee@...ux.vnet.ibm.com>
Subject: Re: [PATCH v2 6/7] perf script python: add Python3 support to sql
 scripts

On 7/03/19 8:51 PM, Arnaldo Carvalho de Melo wrote:
> Em Wed, Mar 06, 2019 at 08:32:42AM -0800, Tony Jones escreveu:
>> On 3/6/19 1:26 AM, Adrian Hunter wrote:
>>> On 2/03/19 3:19 AM, Tony Jones wrote:
>>>> Support both Python2 and Python3 in the exported-sql-viewer.py,
>>>> export-to-postgresql.py and export-to-sqlite.py scripts
>>>>
>>>> There may be differences in the ordering of output lines due to
>>>> differences in dictionary ordering etc.  However the format within lines
>>>> should be unchanged.
>>>>
>>>> The use of 'from __future__' implies the minimum supported Python2 version
>>>> is now v2.6
>>>>
>>>> Signed-off-by: Tony Jones <tonyj@...e.de>
>>>> Signed-off-by: Seeteena Thoufeek <s1seetee@...ux.vnet.ibm.com>
>>>> Cc: Adrian Hunter <adrian.hunter@...el.com>
>>>
>>> Apart from one issue (see below), it looks good, thank you!
>>>
>>>> ---
>>>>  tools/perf/scripts/python/export-to-postgresql.py | 65 +++++++++++++++--------
>>>>  tools/perf/scripts/python/export-to-sqlite.py     | 23 ++++----
>>>>  tools/perf/scripts/python/exported-sql-viewer.py  | 42 ++++++++++-----
>>>>  3 files changed, 84 insertions(+), 46 deletions(-)
>>>>
>>>> diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
>>>> index 390a351d15ea..439bbbf1e036 100644
>>>> --- a/tools/perf/scripts/python/export-to-postgresql.py
>>>> +++ b/tools/perf/scripts/python/export-to-postgresql.py
>>>> @@ -10,6 +10,8 @@
>>>>  # 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
>>>> @@ -199,6 +201,16 @@ import datetime
>>>>  
>>>>  from PySide.QtSql import *
>>>>  
>>>> +if sys.version_info < (3, 0):
>>>> +	def tobytes(str):
>>>> +		return str
>>>> +else:
>>>> +	def tobytes(str):
>>>> +		# Use latin-1 (ISO-8859-1) so all code-points 0-255 will result
>>>> +		# in one byte (note utf-8 is 2 bytes for values > 128 and
>>>> +		# ascii is limited to values <= 128)
>>>> +		return bytes(str, "ISO-8859-1")
>>>
>>> Probably this should be the server_encoding, but python2 allowed UTF-8
>>> so let's just use UTF-8 for now.  That will also mean doing the conversion
>>> before getting the len(), otherwise len() can be wrong.
>>
>> I'm not totally understanding what you're saying here.  The rationale for 
>> using latin-1 and not UTF-8 was clearly expressed in the comment.  Else you 
>> do indeed run into length issues.
>>
>> Would it be easier, since you have a) more familiarity with the code b) some
>> specific issues I'm not fully understanding if you just took this patch and
>> made the changes you want yourself.  I doubt I'll ever use these scripta, my
>> interest is purely in eliminating Python2 as a fixed requirement.
> 
> Adrian, can you please reply here? I'm not familiar with this tobytes()
> python2/python3 difference, what do you mean about using
> 'server_encoding'? Where is that defined?

Under python 2 the character set was not changed, so UTF-8, for example,
would pass through unmodified.

Under python 3, the perf strings are converted to unicode because that
is what python 3 uses for strings.

So under python 3, the correct character set must be used when converting
back to a character encoding that postgrsql expects.

client_encoding is a postgresql connection parameter.

server_encoding is a postgresql database parameter.

To keep things simple for now, I would prefer to hard code UTF-8 rather
than ISO-8859-1 because I think it is more future-proof.  UTF-8 is a
superset of ISO-8859-1 but can have multi-byte characters, so the
conversion must be performed before calculating the output string length.

Ideally, the script would ask/tell the client or server what character
encoding to use, but hard coding will do for now.


This is what I would like:


diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 390a351d15ea..00ab972a2eba 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -10,6 +10,8 @@
 # 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
@@ -199,6 +201,18 @@ import datetime
 
 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")
@@ -234,12 +248,14 @@ 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 usage():
-	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]"
-	print >> sys.stderr, "where:	columns		'all' or 'branches'"
-	print >> sys.stderr, "		calls		'calls' => create calls and call_paths table"
-	print >> sys.stderr, "		callchains	'callchains' => create call_paths table"
+	printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]")
+	printerr("where:	columns		'all' or 'branches'")
+	printerr("		calls		'calls' => create calls and call_paths table")
+	printerr("		callchains	'callchains' => create call_paths table")
 	raise Exception("Too few arguments")
 
 if (len(sys.argv) < 2):
@@ -273,7 +289,7 @@ def do_query(q, s):
 		return
 	raise Exception("Query failed: " + q.lastError().text())
 
-print datetime.datetime.today(), "Creating database..."
+print(datetime.datetime.today(), "Creating database...")
 
 db = QSqlDatabase.addDatabase('QPSQL')
 query = QSqlQuery(db)
@@ -506,12 +522,12 @@ do_query(query, 'CREATE VIEW samples_view AS '
 	' FROM samples')
 
 
-file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0)
-file_trailer = "\377\377"
+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, "w+")
+	file = open(path_name, "wb+")
 	file.write(file_header)
 	return file
 
@@ -526,13 +542,13 @@ def copy_output_file_direct(file, table_name):
 
 # Use COPY FROM STDIN because security may prevent postgres from accessing the files directly
 def copy_output_file(file, table_name):
-	conn = PQconnectdb("dbname = " + dbname)
+	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, sql)
+	res = PQexec(conn, toclientstr(sql))
 	if (PQresultStatus(res) != 4):
 		raise Exception("COPY FROM STDIN PQexec failed")
 	data = file.read(65536)
@@ -566,7 +582,7 @@ if perf_db_export_calls:
 	call_file		= open_output_file("call_table.bin")
 
 def trace_begin():
-	print datetime.datetime.today(), "Writing to intermediate files..."
+	print(datetime.datetime.today(), "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")
@@ -582,7 +598,7 @@ def trace_begin():
 unhandled_count = 0
 
 def trace_end():
-	print datetime.datetime.today(), "Copying to database..."
+	print(datetime.datetime.today(), "Copying to database...")
 	copy_output_file(evsel_file,		"selected_events")
 	copy_output_file(machine_file,		"machines")
 	copy_output_file(thread_file,		"threads")
@@ -597,7 +613,7 @@ def trace_end():
 	if perf_db_export_calls:
 		copy_output_file(call_file,		"calls")
 
-	print datetime.datetime.today(), "Removing intermediate files..."
+	print(datetime.datetime.today(), "Removing intermediate files...")
 	remove_output_file(evsel_file)
 	remove_output_file(machine_file)
 	remove_output_file(thread_file)
@@ -612,7 +628,7 @@ def trace_end():
 	if perf_db_export_calls:
 		remove_output_file(call_file)
 	os.rmdir(output_dir_name)
-	print datetime.datetime.today(), "Adding primary keys"
+	print(datetime.datetime.today(), "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)')
@@ -627,7 +643,7 @@ def trace_end():
 	if perf_db_export_calls:
 		do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
 
-	print datetime.datetime.today(), "Adding foreign keys"
+	print(datetime.datetime.today(), "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)')
@@ -663,8 +679,8 @@ def trace_end():
 		do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
 
 	if (unhandled_count):
-		print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
-	print datetime.datetime.today(), "Done"
+		print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events")
+	print(datetime.datetime.today(), "Done")
 
 def trace_unhandled(event_name, context, event_fields_dict):
 	global unhandled_count
@@ -674,12 +690,14 @@ 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)
@@ -690,6 +708,7 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
 	thread_file.write(value)
 
 def comm_table(comm_id, comm_str, *x):
+	comm_str = toserverstr(comm_str)
 	n = len(comm_str)
 	fmt = "!hiqi" + str(n) + "s"
 	value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
@@ -701,6 +720,9 @@ def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
 	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)
@@ -709,12 +731,14 @@ def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
 	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)

Powered by blists - more mailing lists