zephyr/scripts/sanitycheck

1546 lines
60 KiB
Python
Executable File

#!/usr/bin/env python
"""Zephyr Sanity Tests
This script scans for the set of unit test applications in the git
repository and attempts to execute them. By default, it tries to
build each test case on one platform per architecture, using a precedence
list defined in an archtecture configuration file, and if possible
run the tests in the QEMU emulator.
Test cases are detected by the presence of a 'testcase.ini' file in
the application's project directory. This file may contain one or
more blocks, each identifying a test scenario. The title of the block
is a name for the test case, which only needs to be unique for the
test cases specified in that testcase.ini file. The full canonical
name for each test case is <path to test case under samples/>/<block>.
Each testcase.ini block can define the following key/value pairs:
tags = <list of tags> (required)
A set of string tags for the testcase. Usually pertains to
functional domains but can be anything. Command line invocations
of this script can filter the set of tests to run based on tag.
extra_args = <list of extra arguments>
Extra arguments to pass to Make when building or running the
test case.
build_only = <True|False>
If true, don't try to run the test under QEMU even if the
selected platform supports it.
timeout = <number of seconds>
Length of time to run test in QEMU before automatically killing it.
Default to 60 seconds.
arch_whitelist = <list of arches, such as x86, arm, arc>
Set of architectures that this test case should only be run for.
platform_whitelist = <list of platforms>
Set of platforms that this test case should only be run for for.
config_whitelist = <list of config options>
Config options can either be config names like CONFIG_FOO which
match if the configuration is defined to any value, or key/value
pairs like CONFIG_FOO=bar which match if it is set to a specific
value. May prepend a '!' to invert the match.
Architectures and platforms are defined in an archtecture configuration
file which are stored by default in scripts/sanity_chk/arches/. These
each define an [arch] block with the following key/value pairs:
name = <arch name>
The name of the arch. Example: x86
platforms = <list of supported platforms in order of precedence>
List of supported platforms for this arch. The ordering here
is used to select a default platform to build for that arch.
For every platform defined, there must be a corresponding block for it
in the arch configuration file. This block can be empty if there are
no special definitions for that arch. Options are:
qemu_support = <True|False> (default False)
Indicates whether binaries for this platform can run under QEMU
microkernel_support = <True|False> (default True)
Indicates whether this platform supports microkernel or just nanokernel
The set of test cases that actually run depends on directives in the
testcase and archtecture .ini file and options passed in on the command
line. If there is every any confusion, running with -v or --discard-report
can help show why particular test cases were skipped.
Metrics (such as pass/fail state and binary size) for the last code
release are stored in scripts/sanity_chk/sanity_last_release.csv.
To update this, pass the --all --release options.
Most everyday users will run with no arguments.
"""
import argparse
import os
import sys
import ConfigParser
import re
import tempfile
import subprocess
import multiprocessing
import select
import shutil
import signal
import threading
import time
import csv
if "ZEPHYR_BASE" not in os.environ:
sys.stderr.write("$ZEPHYR_BASE environment variable undefined.\n")
exit(1)
ZEPHYR_BASE = os.environ["ZEPHYR_BASE"]
VERBOSE = 0
LAST_SANITY = os.path.join(ZEPHYR_BASE, "scripts", "sanity_chk",
"last_sanity.csv")
RELEASE_DATA = os.path.join(ZEPHYR_BASE, "scripts", "sanity_chk",
"sanity_last_release.csv")
PARALLEL = multiprocessing.cpu_count() * 2
if os.isatty(sys.stdout.fileno()):
TERMINAL = True
COLOR_NORMAL = '\033[0m'
COLOR_RED = '\033[91m'
COLOR_GREEN = '\033[92m'
COLOR_YELLOW = '\033[93m'
else:
TERMINAL = False
COLOR_NORMAL = ""
COLOR_RED = ""
COLOR_GREEN = ""
COLOR_YELLOW = ""
class SanityCheckException(Exception):
pass
class SanityRuntimeError(SanityCheckException):
pass
class ConfigurationError(SanityCheckException):
def __init__(self, cfile, message):
self.cfile = cfile
self.message = message
def __str__(self):
return repr(self.cfile + ": " + self.message)
class MakeError(SanityCheckException):
pass
class BuildError(MakeError):
pass
class ExecutionError(MakeError):
pass
# Debug Functions
def debug(what):
if VERBOSE >= 1:
print what
def error(what):
sys.stderr.write(COLOR_RED + what + COLOR_NORMAL + "\n")
def verbose(what):
if VERBOSE >= 2:
print what
def info(what):
sys.stdout.write(what + "\n")
# Utility functions
class QEMUHandler:
"""Spawns a thread to monitor QEMU output from pipes
We pass QEMU_PIPE to 'make qemu' and monitor the pipes for output.
We need to do this as once qemu starts, it runs forever until killed.
Test cases emit special messages to the console as they run, we check
for these to collect whether the test passed or failed.
"""
RUN_PASSED = "PROJECT EXECUTION SUCCESSFUL"
RUN_FAILED = "PROJECT EXECUTION FAILED"
@staticmethod
def _thread(handler, timeout, outdir, logfile, fifo_fn, pid_fn, results):
fifo_in = fifo_fn + ".in"
fifo_out = fifo_fn + ".out"
# These in/out nodes are named from QEMU's perspective, not ours
if os.path.exists(fifo_in):
os.unlink(fifo_in)
os.mkfifo(fifo_in)
if os.path.exists(fifo_out):
os.unlink(fifo_out)
os.mkfifo(fifo_out)
# We don't do anything with out_fp but we need to open it for
# writing so that QEMU doesn't block, due to the way pipes work
out_fp = open(fifo_in, "wb")
# Disable internal buffering, we don't
# want read() or poll() to ever block if there is data in there
in_fp = open(fifo_out, "rb", buffering=0)
log_out_fp = open(logfile, "w")
start_time = time.time()
timeout_time = start_time + timeout
p = select.poll()
p.register(in_fp, select.POLLIN)
metrics = {}
line = ""
while True:
this_timeout = int((timeout_time - time.time()) * 1000)
if this_timeout < 0 or not p.poll(this_timeout):
out_state = "timeout"
break
c = in_fp.read(1)
if c == "":
# EOF, this shouldn't happen unless QEMU crashes
out_state = "unexpected eof"
break
line = line + c
if c != "\n":
continue
# If we get here, line contains a full line of data output from QEMU
log_out_fp.write(line)
log_out_fp.flush()
line = line.strip()
verbose("QEMU: %s" % line)
if line == QEMUHandler.RUN_PASSED:
out_state = "passed"
break
if line == QEMUHandler.RUN_FAILED:
out_state = "failed"
break
# TODO: Add support for getting numerical performance data
# from test cases. Will involve extending test case reporting
# APIs. Add whatever gets reported to the metrics dictionary
line = ""
metrics["qemu_time"] = time.time() - start_time
verbose("QEMU complete (%s) after %f seconds" %
(out_state, metrics["qemu_time"]))
handler.set_state(out_state, metrics)
log_out_fp.close()
out_fp.close()
in_fp.close()
pid = int(open(pid_fn).read())
os.unlink(pid_fn)
os.kill(pid, signal.SIGTERM)
os.unlink(fifo_in)
os.unlink(fifo_out)
def __init__(self, name, outdir, log_fn, timeout):
"""Constructor
@param name Arbitrary name of the created thread
@param outdir Working directory, shoudl be where qemu.pid gets created
by kbuild
@param log_fn Absolute path to write out QEMU's log data
@param timeout Kill the QEMU process if it doesn't finish up within
the given number of seconds
"""
# Create pipe to get QEMU's serial output
self.results = {}
self.state = "waiting"
self.lock = threading.Lock()
# We pass this to QEMU which looks for fifos with .in and .out
# suffixes.
self.fifo_fn = os.path.join(outdir, "qemu-fifo")
self.pid_fn = os.path.join(outdir, "qemu.pid")
if os.path.exists(self.pid_fn):
os.unlink(self.pid_fn)
self.log_fn = log_fn
self.thread = threading.Thread(name=name, target=QEMUHandler._thread,
args=(self, timeout, outdir, self.log_fn,
self.fifo_fn, self.pid_fn,
self.results))
self.thread.daemon = True
verbose("Spawning QEMU process for %s" % name)
self.thread.start()
def set_state(self, state, metrics):
self.lock.acquire()
self.state = state
self.metrics = metrics
self.lock.release()
def get_state(self):
self.lock.acquire()
ret = (self.state, self.metrics)
self.lock.release()
return ret
def get_fifo(self):
return self.fifo_fn
class SizeCalculator:
def __init__(self, filename):
"""Constructor
@param filename Path to the output binary
The <filename> is parsed by objdump to determine section sizes
"""
# Make sure this is an ELF binary
with open(filename, "rb") as f:
magic = f.read(4)
if (magic != "\x7fELF"):
raise SanityRuntimeError("%s is not an ELF binary" % filename)
# Search for CONFIG_XIP in the ELF's list of symbols using NM and AWK.
# GREP can not be used as it returns an error if the symbol is not found.
is_xip_command = "nm " + filename + " | awk '/CONFIG_XIP/ { print $3 }'"
is_xip_output = subprocess.check_output(is_xip_command, shell=True)
self.is_xip = (len(is_xip_output) != 0)
self.filename = filename
self.sections = {}
self.xip_rom_size = 0
self.xip_ram_size = 0
self.ram_size = 0
self._calculate_sizes()
def get_ram_size(self):
"""Get the amount of RAM the application will use up on the device
@return amount of RAM, in bytes
"""
if self.is_xip:
return self.xip_ram_size
else:
return self.ram_size
def get_rom_size(self):
"""Get the size of the data that this application uses on device's flash
@return amount of ROM, in bytes
"""
return self.xip_rom_size
def unrecognized_sections(self):
"""Get a list of sections inside the binary that weren't recognized
@return list of unrecogized section names
"""
slist = []
for k, v in self.sections.iteritems():
if not v["recognized"]:
slist.append(k)
return slist
def _calculate_sizes(self):
""" Calculate RAM and ROM usage by section """
objdump_command = "objdump -h " + self.filename
objdump_output = subprocess.check_output(objdump_command,
shell=True).splitlines()
for line in objdump_output:
words = line.split()
if (len(words) == 0): # Skip lines that are too short
continue
index = words[0]
if (not index[0].isdigit()): # Skip lines that do not start
continue # with a digit
name = words[1] # Skip lines with section names
if (name[0] == '.'): # starting with '.'
continue
size = int(words[2], 16)
phys_addr = int(words[4], 16)
# Add section to memory use totals (for both non-XIP and XIP scenarios)
#
# In an XIP image, the following sections are placed into ROM:
# text, ctors, rodata and datas
# In an XIP image, the following sections are placed into RAM:
# datas, bss and noinit
# In a non-XIP image, the following sections are placed into RAM
# text, ctors, rodata, datas, bss and noinit
# Unrecognized section names are not included in the calculations.
self.ram_size += size
recognized = True
if ((name == "text") or (name == "ctors") or (name == "rodata")):
self.xip_rom_size += size
elif (name == "datas"):
self.xip_rom_size += size
self.xip_ram_size += size
elif ((name == "bss") or (name == "noinit")):
self.xip_ram_size += size
else:
recognized = False
self.ram_size -= size # Undo the calculation
self.sections[name] = {"phys_addr" : phys_addr, "size" : size,
"recognized" : recognized}
class MakeGoal:
"""Metadata class representing one of the sub-makes called by MakeGenerator
MakeGenerator returns a dictionary of these which can then be associdated
with TestInstances to get a complete picture of what happened during a test.
MakeGenerator is used for tasks outside of building tests (such as
defconfigs) which is why MakeGoal is a separate class from TestInstance.
"""
def __init__(self, name, text, qemu, make_log, build_log, run_log,
qemu_log):
self.name = name
self.text = text
self.qemu = qemu
self.make_log = make_log
self.build_log = build_log
self.run_log = run_log
self.qemu_log = qemu_log
self.make_state = "waiting"
self.failed = False
self.finished = False
self.reason = None
self.metrics = {}
def get_error_log(self):
if self.make_state == "waiting":
# Shouldn't ever see this; breakage in the main Makefile itself.
return self.make_log
elif self.make_state == "building":
# Failure when calling the sub-make to build the code
return self.build_log
elif self.make_state == "running":
# Failure in sub-make for "make qemu", qemu probably failed to start
return self.run_log
elif self.make_state == "finished":
# QEMU finished, but timed out or otherwise wasn't successful
return self.qemu_log
def fail(self, reason):
self.failed = True
self.finished = True
self.reason = reason
def success(self):
self.finished = True
def __str__(self):
if self.finished:
if self.failed:
return "[%s] failed (%s: see %s)" % (self.name, self.reason,
self.get_error_log())
else:
return "[%s] passed" % self.name
else:
return "[%s] in progress (%s)" % (self.name, self.make_state)
class MakeGenerator:
"""Generates a Makefile which just calls a bunch of sub-make sessions
In any given test suite we may need to build dozens if not hundreds of
test cases. The cleanest way to parallelize this is to just let Make
do the parallelization, sharing the jobserver among all the different
sub-make targets.
"""
GOAL_HEADER_TMPL = """.PHONY: {goal}
{goal}:
"""
MAKE_RULE_TMPL = """\t@echo sanity_test_{phase} {goal} >&2
\t$(MAKE) -C {directory} O={outdir} V={verb} EXTRA_CFLAGS=-Werror EXTRA_ASMFLAGS=-Wa,--fatal-warnings EXTRA_LFLAGS=--fatal-warnings {args} >{logfile} 2>&1
"""
GOAL_FOOTER_TMPL = "\t@echo sanity_test_finished {goal} >&2\n\n"
re_make = re.compile("sanity_test_([A-Za-z0-9]+) (.+)|$|make[:] \*\*\* [[](.+)[]] Error.+$")
def __init__(self, base_outdir):
"""MakeGenerator constructor
@param base_outdir Intended to be the base out directory. A make.log
file will be created here which contains the output of the
top-level Make session, as well as the dynamic control Makefile
@param verbose If true, pass V=1 to all the sub-makes which greatly
increases their verbosity
"""
self.goals = {}
if not os.path.exists(base_outdir):
os.makedirs(base_outdir)
self.logfile = os.path.join(base_outdir, "make.log")
self.makefile = os.path.join(base_outdir, "Makefile")
def _get_rule_header(self, name):
return MakeGenerator.GOAL_HEADER_TMPL.format(goal=name)
def _get_sub_make(self, name, phase, workdir, outdir, logfile, args):
verb = "1" if VERBOSE else "0"
args = " ".join(args)
return MakeGenerator.MAKE_RULE_TMPL.format(phase=phase, goal=name,
outdir=outdir,
directory=workdir, verb=verb,
args=args, logfile=logfile)
def _get_rule_footer(self, name):
return MakeGenerator.GOAL_FOOTER_TMPL.format(goal=name)
def _add_goal(self, outdir):
if not os.path.exists(outdir):
os.makedirs(outdir)
def add_build_goal(self, name, directory, outdir, args):
"""Add a goal to invoke a Kbuild session
@param name A unique string name for this build goal. The results
dictionary returned by execute() will be keyed by this name.
@param directory Absolute path to working directory, will be passed
to make -C
@param outdir Absolute path to output directory, will be passed to
Kbuild via -O=<path>
@param args Extra command line arguments to pass to 'make', typically
environment variables or specific Make goals
"""
self._add_goal(outdir)
build_logfile = os.path.join(outdir, "build.log")
text = (self._get_rule_header(name) +
self._get_sub_make(name, "building", directory,
outdir, build_logfile, args) +
self._get_rule_footer(name))
self.goals[name] = MakeGoal(name, text, None, self.logfile, build_logfile,
None, None)
def add_qemu_goal(self, name, directory, outdir, args, timeout=30):
"""Add a goal to build a Zephyr project and then run it under QEMU
The generated make goal invokes Make twice, the first time it will
build the default goal, and the second will invoke the 'qemu' goal.
The output of the QEMU session will be monitored, and terminated
either upon pass/fail result of the test program, or the timeout
is reached.
@param name A unique string name for this build goal. The results
dictionary returned by execute() will be keyed by this name.
@param directory Absolute path to working directory, will be passed
to make -C
@param outdir Absolute path to output directory, will be passed to
Kbuild via -O=<path>
@param args Extra command line arguments to pass to 'make', typically
environment variables. Do not pass specific Make goals here.
@param timeout Maximum length of time QEMU session should be allowed
to run before automatically killing it. Default is 30 seconds.
"""
self._add_goal(outdir)
build_logfile = os.path.join(outdir, "build.log")
run_logfile = os.path.join(outdir, "run.log")
qemu_logfile = os.path.join(outdir, "qemu.log")
q = QEMUHandler(name, outdir, qemu_logfile, timeout)
args.append("QEMU_PIPE=%s" % q.get_fifo())
text = (self._get_rule_header(name) +
self._get_sub_make(name, "building", directory,
outdir, build_logfile, args) +
self._get_sub_make(name, "running", directory,
outdir, run_logfile,
args + ["qemu"]) +
self._get_rule_footer(name))
self.goals[name] = MakeGoal(name, text, q, self.logfile, build_logfile,
run_logfile, qemu_logfile)
def add_test_instance(self, ti, build_only=False):
"""Add a goal to build/test a TestInstance object
@param ti TestInstance object to build. The status dictionary returned
by execute() will be keyed by its .name field.
"""
args = ti.test.extra_args[:]
args.extend(["ARCH=%s" % ti.platform.arch.name,
"PLATFORM_CONFIG=%s" % ti.platform.name])
if ti.platform.qemu_support and not ti.build_only and not build_only:
self.add_qemu_goal(ti.name, ti.test.code_location, ti.outdir,
args, ti.test.timeout)
else:
self.add_build_goal(ti.name, ti.test.code_location, ti.outdir, args)
def execute(self, callback_fn=None, context=None):
"""Execute all the registered build goals
@param callback_fn If not None, a callback function will be called
as individual goals transition between states. This function
should accept two parameters: a string state and an arbitrary
context object, supplied here
@param context Context object to pass to the callback function.
Type and semantics are specific to that callback function.
@return A dictionary mapping goal names to final status.
"""
with open(self.makefile, "w") as tf, \
open(os.devnull, "wb") as devnull, \
open(self.logfile, "w") as make_log:
# Create our dynamic Makefile and execute it.
# Watch stderr output which is where we will keep
# track of build state
for name, goal in self.goals.iteritems():
tf.write(goal.text)
tf.write("all: %s\n" % (" ".join(self.goals.keys())))
tf.flush()
# os.environ["CC"] = "ccache gcc" FIXME doesn't work
cmd = ["make", "-k", "-j", str(PARALLEL), "-f", tf.name, "all"]
p = subprocess.Popen(cmd, stderr=subprocess.PIPE,
stdout=devnull)
for line in iter(p.stderr.readline, b''):
make_log.write(line)
verbose("MAKE: " + repr(line.strip()))
m = MakeGenerator.re_make.match(line)
if not m:
continue
state, name, error = m.groups()
if error:
goal = self.goals[error]
else:
goal = self.goals[name]
goal.make_state = state
if error:
goal.fail("build_error")
else:
if state == "finished":
if goal.qemu:
thread_status, metrics = goal.qemu.get_state()
goal.metrics.update(metrics)
if thread_status == "passed":
goal.success()
else:
goal.fail(thread_status)
else:
goal.success()
if callback_fn:
callback_fn(context, self.goals, goal)
p.wait()
return self.goals
# "list" - List of strings
# "list:<type>" - List of <type>
# "set" - Set of unordered, unique strings
# "set:<type>" - Set of <type>
# "float" - Floating point
# "int" - Integer
# "bool" - Boolean
# "str" - String
# XXX Be sure to update __doc__ if you change any of this!!
arch_valid_keys = {"name" : {"type" : "str", "required" : True},
"platforms" : {"type" : "list", "required" : True}}
platform_valid_keys = {"qemu_support" : {"type" : "bool", "default" : False},
"microkernel_support" : {"type" : "bool",
"default" : True}}
testcase_valid_keys = {"tags" : {"type" : "set", "required" : True},
"extra_args" : {"type" : "list"},
"build_only" : {"type" : "bool", "default" : False},
"timeout" : {"type" : "int", "default" : 60},
"arch_whitelist" : {"type" : "set"},
"platform_whitelist" : {"type" : "set"},
"config_whitelist" : {"type" : "set"}}
class SanityConfigParser:
"""Class to read architecture and test case .ini files with semantic checking
"""
def __init__(self, filename):
"""Instantiate a new SanityConfigParser object
@param filename Source .ini file to read
"""
cp = ConfigParser.SafeConfigParser()
cp.readfp(open(filename))
self.filename = filename
self.cp = cp
def _cast_value(self, value, typestr):
v = value.strip()
if typestr == "str":
return v
elif typestr == "float":
return float(v)
elif typestr == "int":
return int(v)
elif typestr == "bool":
v = v.lower()
if v == "true" or v == "1":
return True
elif v == "" or v == "false" or v == "0":
return False
raise ConfigurationError(self.filename,
"bad value for boolean: '%s'" % value)
elif typestr.startswith("list"):
vs = v.split()
if len(typestr) > 4 and typestr[4] == ":":
return [self._cast_value(vsi, typestr[5:]) for vsi in vs]
else:
return vs
elif typestr.startswith("set"):
vs = v.split()
if len(typestr) > 3 and typestr[3] == ":":
return set([self._cast_value(vsi, typestr[4:]) for vsi in vs])
else:
return set(vs)
else:
raise ConfigurationError(self.filename, "unknown type '%s'" % value)
def sections(self):
"""Get the set of sections within the .ini file
@return a list of string section names"""
return self.cp.sections()
def get_section(self, section, valid_keys):
"""Get a dictionary representing the keys/values within a section
@param section The section in the .ini file to retrieve data from
@param valid_keys A dictionary representing the intended semantics
for this section. Each key in this dictionary is a key that could
be specified, if a key is given in the .ini file which isn't in
here, it will generate an error. Each value in this dictionary
is another dictionary containing metadata:
"default" - Default value if not given
"type" - Data type to convert the text value to. Simple types
supported are "str", "float", "int", "bool" which will get
converted to respective Python data types. "set" and "list"
may also be specified which will split the value by
whitespace (but keep the elements as strings). finally,
"list:<type>" and "set:<type>" may be given which will
perform a type conversion after splitting the value up.
"required" - If true, raise an error if not defined. If false
and "default" isn't specified, a type conversion will be
done on an empty string
@return A dictionary containing the section key-value pairs with
type conversion and default values filled in per valid_keys
"""
d = {}
cp = self.cp
if not cp.has_section(section):
raise ConfigurationError(self.filename, "Missing section '%s'" % section)
for k, v in cp.items(section):
if k not in valid_keys:
raise ConfigurationError(self.filename,
"Unknown config key '%s' in defintiion for '%s'"
% (k, section))
d[k] = v
for k, kinfo in valid_keys.iteritems():
if k not in d:
if "required" in kinfo:
required = kinfo["required"]
else:
required = False
if required:
raise ConfigurationError(self.filename,
"missing required value for '%s' in section '%s'"
% (k, section))
else:
if "default" in kinfo:
default = kinfo["default"]
else:
default = self._cast_value("", kinfo["type"])
d[k] = default
else:
try:
d[k] = self._cast_value(d[k], kinfo["type"])
except ValueError, ve:
raise ConfigurationError(self.filename,
"bad %s value '%s' for key '%s' in section '%s'"
% (kinfo["type"], d[k], k, section))
return d
class Platform:
"""Class representing metadata for a particular platform
Maps directly to PLATFORM_CONFIG when building"""
def __init__(self, arch, name, plat_dict):
"""Constructor.
@param arch Architecture object for this platform
@param name String name for this platform, same as PLATFORM_CONFIG
@param plat_dict SanityConfigParser output on the relevant section
in the architecture configuration file which has lots of metadata.
See the Architecture class.
"""
self.name = name
self.qemu_support = plat_dict["qemu_support"]
self.microkernel_support = plat_dict["microkernel_support"]
self.arch = arch
# Gets populated in a separate step
self.defconfig = {"micro" : None, "nano" : None}
pass
def set_defconfig(self, ktype, defconfig):
"""Set defconfig information for a particular kernel type.
We do this in another step because all the defconfigs are generated
at once from a sub-make, see TestSuite constructor
@param ktype Kernel type, either "micro" or "nano"
@param defconfig Dictionary containing defconfig information
"""
self.defconfig[ktype] = defconfig
def get_defconfig(self, ktype):
"""Return a dictionary representing the key/value pairs expressed
in the kernel defconfig used for this arch/platform. Used to identify
platform features.
@param ktype Kernel type, either "micro" or "nano"
@return dictionary corresponding to the defconfig contents. unset
values will not be defined
"""
if ktype == "micro" and not self.microkernel_support:
raise SanityRuntimeError("Invalid kernel type queried")
return self.defconfig[ktype]
def __repr__(self):
return "<%s on %s>" % (self.name, self.arch.name)
class Architecture:
"""Class representing metadata for a particular architecture
"""
def __init__(self, cfile):
"""Architecture constructor
@param cfile Path to Architecture configuration file, which gives
info about the arch and all the platforms for it
"""
cp = SanityConfigParser(cfile)
self.platforms = []
arch = cp.get_section("arch", arch_valid_keys)
self.name = arch["name"]
for plat_name in arch["platforms"]:
verbose("Platform: %s" % plat_name)
plat_dict = cp.get_section(plat_name, platform_valid_keys)
self.platforms.append(Platform(self, plat_name, plat_dict))
def __repr__(self):
return "<arch %s>" % self.name
class TestCase:
"""Class representing a test application
"""
makefile_re = re.compile("\s*KERNEL_TYPE\s*[?=]+\s*(micro|nano)\s*")
def __init__(self, testcase_root, workdir, name, tc_dict):
"""TestCase constructor.
This gets called by TestSuite as it finds and reads testcase.ini files.
Multiple TestCase instances may be generated from a single testcase.ini,
each one corresponds to a section within that file.
Reads the Makefile inside the testcase directory to figure out the
kernel type for purposes of configuration filtering
We need to have a unique name for every single test case. Since
a testcase.ini can define multiple tests, the canonical name for
the test case is <workdir>/<name>.
@param testcase_root Absolute path to the root directory where
all the test cases live
@param workdir Relative path to the project directory for this
test application from the test_case root.
@param name Name of this test case, corresponding to the section name
in the test case configuration file. For many test cases that just
define one test, can be anything and is usually "test". This is
really only used to distinguish between different cases when
the testcase.ini defines multiple tests
@param tc_dict Dictionary with section values for this test case
from the testcase.ini file
"""
self.code_location = os.path.join(testcase_root, workdir)
self.tags = tc_dict["tags"]
self.extra_args = tc_dict["extra_args"]
self.arch_whitelist = tc_dict["arch_whitelist"]
self.platform_whitelist = tc_dict["platform_whitelist"]
self.config_whitelist = tc_dict["config_whitelist"]
self.timeout = tc_dict["timeout"]
self.build_only = tc_dict["build_only"]
self.path = os.path.join(workdir, name)
self.name = self.path # for now
self.ktype = None
with open(os.path.join(testcase_root, workdir, "Makefile")) as makefile:
for line in makefile.readlines():
m = TestCase.makefile_re.match(line)
if m:
self.ktype = m.group(1)
break
if not self.ktype:
raise ConfigurationError(os.path.join(workdir, "Makefile"),
"KERNEL_TYPE not found")
def __repr__(self):
return self.name
class TestInstance:
"""Class representing the execution of a particular TestCase on a platform
@param test The TestCase object we want to build/execute
@param platform Platform object that we want to build and run against
@param base_outdir Base directory for all test results. The actual
out directory used is <outdir>/<platform>/<test case name>
"""
def __init__(self, test, platform, base_outdir, build_only=False):
self.test = test
self.platform = platform
self.name = os.path.join(platform.name, test.path)
self.outdir = os.path.join(base_outdir, platform.name, test.path)
self.build_only = build_only or test.build_only
def calculate_sizes(self):
"""Get the RAM/ROM sizes of a test case.
This can only be run after the instance has been executed by
MakeGenerator, otherwise there won't be any binaries to measure.
@return A SizeCalculator object
"""
if self.test.ktype == "micro":
fn = os.path.join(self.outdir, "microkernel.elf")
else:
fn = os.path.join(self.outdir, "nanokernel.elf")
return SizeCalculator(fn)
def __repr__(self):
return "<TestCase %s on %s>" % (self.test.name, self.platform.name)
class TestSuite:
config_re = re.compile('(CONFIG_[A-Z0-9_]+)[=](.+)$')
def __init__(self, arch_root, testcase_root, outdir):
# Keep track of which test cases we've filtered out and why
discards = {}
self.arches = {}
self.testcases = {}
self.platforms = []
self.outdir = outdir
self.instances = {}
self.goals = None
self.discards = None
arch_root = os.path.abspath(arch_root)
testcase_root = os.path.abspath(testcase_root)
outdir = os.path.abspath(outdir)
debug("Reading test case configuration files under %s..." % testcase_root)
for dirpath, dirnames, filenames in os.walk(testcase_root,
topdown=True):
if "testcase.ini" in filenames:
verbose("Found test case in " + dirpath)
dirnames[:] = []
cp = SanityConfigParser(os.path.join(dirpath, "testcase.ini"))
workdir = os.path.relpath(dirpath, testcase_root)
for section in cp.sections():
tc_dict = cp.get_section(section, testcase_valid_keys)
tc = TestCase(testcase_root, workdir, section, tc_dict)
self.testcases[tc.name] = tc
debug("Reading architecture configuration files under %s..." % arch_root)
for dirpath, dirnames, filenames in os.walk(arch_root):
for filename in filenames:
if filename.endswith(".ini"):
fn = os.path.join(dirpath, filename)
verbose("Found arch configuration " + fn)
arch = Architecture(fn)
self.arches[arch.name] = arch
self.platforms.extend(arch.platforms)
# Now that we know the full set of arches/platforms, get the defconfig
# information from them by calling Make
info("Building platform defconfigs...")
dlist = {}
config_outdir = os.path.join(outdir, "configs")
mg = MakeGenerator(config_outdir)
for plat in self.platforms:
ktypes = ["nano"]
if plat.microkernel_support:
ktypes.append("micro")
for ktype in ktypes:
stem = ktype + "_" + plat.name
in_defconfig = stem + "_defconfig"
out_config = os.path.join(config_outdir, stem + "_config")
dlist[plat, ktype] = out_config
args = ["ARCH=" + plat.arch.name,
"KBUILD_DEFCONFIG=" + in_defconfig,
"KCONFIG_CONFIG=" + out_config, "defconfig"]
# FIXME would be nice to use a common outdir for this so that
# conf, gen_idt, etc aren't rebuilt for every plat/ktype combo,
# need a way to avoid different Make processe from clobbering
# each other since they all try to build them simultaneously
mg.add_build_goal(stem, ZEPHYR_BASE, os.path.join(config_outdir,
plat.name,
ktype), args)
results = mg.execute(None)
for k, out_config in dlist.iteritems():
plat, ktype = k
defconfig = {}
with open(out_config, "r") as fp:
for line in fp.readlines():
m = TestSuite.config_re.match(line)
if not m:
continue
defconfig[m.group(1)] = m.group(2).strip()
plat.set_defconfig(ktype, defconfig)
self.instances = {}
def get_last_failed(self):
if not os.path.exists(LAST_SANITY):
return []
result = []
with open(LAST_SANITY, "r") as fp:
cr = csv.DictReader(fp)
for row in cr:
if row["passed"] == "True":
continue
test = row["test"]
platform = row["platform"]
result.append((test, platform))
return result
def apply_filters(self, platform_filter, arch_filter, tag_filter,
config_filter, testcase_filter, last_failed):
instances = []
discards = {}
verbose("platform filter: " + str(platform_filter))
verbose(" arch_filter: " + str(arch_filter))
verbose(" tag_filter: " + str(tag_filter))
verbose(" config_filter: " + str(config_filter))
if last_failed:
failed_tests = self.get_last_failed()
if not platform_filter or "default" in platform_filter:
info("Selecting default platforms per test case")
default_platforms = True
platform_filter = []
else:
default_platforms = False
if "all" in platform_filter:
info("Selecting all possible platforms per test case")
platform_filter = []
for tc_name, tc in self.testcases.iteritems():
for arch_name, arch in self.arches.iteritems():
instance_list = []
for plat in arch.platforms:
instance = TestInstance(tc, plat, self.outdir)
if tag_filter and not tc.tags.intersection(tag_filter):
discards[instance] = "Command line testcase tag filter"
continue
if testcase_filter and tc_name not in testcase_filter:
discards[instance] = "Testcase name filter"
continue
if last_failed and (tc.name, plat.name) not in failed_tests:
discards[instance] = "Passed or skipped during last run"
continue
if arch_filter and arch_name not in arch_filter:
discards[instance] = "Command line testcase arch filter"
continue
if tc.arch_whitelist and arch.name not in tc.arch_whitelist:
discards[instance] = "Not in test case arch whitelist"
continue
if platform_filter and plat.name not in platform_filter:
discards[instance] = "Command line platform filter"
continue
if tc.platform_whitelist and plat.name not in tc.platform_whitelist:
discards[instance] = "Not in testcase platform whitelist"
continue
if not plat.microkernel_support and tc.ktype == "micro":
discards[instance] = "No microkernel support for platform"
continue
defconfig = plat.get_defconfig(tc.ktype)
config_pass = True
# FIXME this is kind of gross clean it up
for cw in tc.config_whitelist:
invert = (cw[0] == "!")
if invert:
cw = cw[1:]
if "=" in cw:
k, v = cw.split("=")
testval = k not in defconfig or defconfig[k] != v
if invert:
testval = not testval
if testval:
discards[instance] = "%s%s in platform defconfig" % (
cw, " not" if not invert else "")
config_pass = False
break
else:
testval = cw not in defconfig
if invert:
testval = not testval
if testval:
discards[instance] = "%s%s set in platform defconfig" % (
cw, " not" if not invert else "")
config_pass = False
break
if not config_pass:
continue
instance_list.append(instance)
if not instance_list:
# Every platform in this arch was rejected already
continue
if default_platforms:
self.add_instance(instance_list[0])
for instance in instance_list[1:]:
discards[instance] = "Not in default set for arch"
else:
for instance in instance_list:
self.add_instance(instance)
self.discards = discards
return discards
def add_instance(self, ti):
self.instances[ti.name] = ti
def execute(self, cb, cb_context, build_only):
mg = MakeGenerator(self.outdir)
for i in self.instances.values():
mg.add_test_instance(i, build_only)
self.goals = mg.execute(cb, cb_context)
for name, goal in self.goals.iteritems():
i = self.instances[name]
if goal.failed:
continue
sc = i.calculate_sizes()
goal.metrics["ram_size"] = sc.get_ram_size()
goal.metrics["rom_size"] = sc.get_rom_size()
return self.goals
def discard_report(self, filename):
if self.discards == None:
raise SanityRuntimeException("apply_filters() hasn't been run!")
with open(filename, "wb") as csvfile:
fieldnames = ["test", "arch", "platform", "reason"]
cw = csv.DictWriter(csvfile, fieldnames, lineterminator=os.linesep)
cw.writeheader()
for instance, reason in self.discards.iteritems():
rowdict = {"test" : i.test.name,
"arch" : i.platform.arch.name,
"platform" : i.platform.name,
"reason" : reason}
cw.writerow(rowdict)
def compare_metrics(self, filename):
# name, datatype, lower results better
interesting_metrics = [("ram_size", int, True),
("rom_size", int, True)]
if self.goals == None:
raise SanityRuntimeException("execute() hasn't been run!")
if not os.path.exists(filename):
info("Cannot compare metrics, %s not found" % filename)
return []
results = []
saved_metrics = {}
with open(filename) as fp:
cr = csv.DictReader(fp)
for row in cr:
d = {}
for m, _, _ in interesting_metrics:
d[m] = row[m]
saved_metrics[(row["test"], row["platform"])] = d
for name, goal in self.goals.iteritems():
i = self.instances[name]
mkey = (i.test.name, i.platform.name)
if mkey not in saved_metrics:
continue
sm = saved_metrics[mkey]
for metric, mtype, lower_better in interesting_metrics:
if metric not in goal.metrics:
continue
if sm[metric] == "":
continue
delta = goal.metrics[metric] - mtype(sm[metric])
if delta == 0:
continue
results.append((i, metric, goal.metrics[metric], delta,
lower_better))
return results
def testcase_report(self, filename):
if self.goals == None:
raise SanityRuntimeException("execute() hasn't been run!")
with open(filename, "wb") as csvfile:
fieldnames = ["test", "arch", "platform", "passed", "status",
"extra_args", "qemu", "qemu_time", "ram_size",
"rom_size"]
cw = csv.DictWriter(csvfile, fieldnames, lineterminator=os.linesep)
cw.writeheader()
for name, goal in self.goals.iteritems():
i = self.instances[name]
rowdict = {"test" : i.test.name,
"arch" : i.platform.arch.name,
"platform" : i.platform.name,
"extra_args" : " ".join(i.test.extra_args),
"qemu" : i.platform.qemu_support}
if goal.failed:
rowdict["passed"] = False
rowdict["status"] = goal.reason
else:
rowdict["passed"] = True
if goal.qemu:
rowdict["qemu_time"] = goal.metrics["qemu_time"]
rowdict["ram_size"] = goal.metrics["ram_size"]
rowdict["rom_size"] = goal.metrics["rom_size"]
cw.writerow(rowdict)
def parse_arguments():
parser = argparse.ArgumentParser(description = __doc__,
formatter_class = argparse.RawDescriptionHelpFormatter)
parser.add_argument("-p", "--platform", action="append",
help="Platform filter for testing. If unspecified, default to the "
"set of default platforms in the arch configuration files for "
"the selected arches. May also specify 'all' to match all "
"platforms for the selected arches. Multiple invocations "
"are treated as a logical 'or' relationship")
parser.add_argument("-a", "--arch", action="append",
help="Arch filter for testing. Takes precedence over --platform. "
"If unspecified, test all arches. Multiple invocations "
"are treated as a logical 'or' relationship")
parser.add_argument("-t", "--tag", action="append",
help="Specify tags to restrict which tests to run by tag value. "
"Default is to not do any tag filtering. Multiple invocations "
"are treated as a logical 'or' relationship")
parser.add_argument("-f", "--only-failed", action="store_true",
help="Run only those tests that failed the previous sanity check "
"invocation.")
parser.add_argument("-c", "--config", action="append",
help="Specify platform configuration values filtering. This can be "
"specified two ways: <config>=<value> or just <config>. The "
"defconfig for all platforms, for all kernel types will be "
"checked. For the <config>=<value> case, only match defconfig "
"that have that value defined. For the <config> case, match "
"defconfig that have that value assigned to any value. "
"Prepend a '!' to invert the match.")
parser.add_argument("-s", "--test", action="append",
help="Run only the specified test cases. These are named by "
"<path to test project relative to "
"--testcase-root>/<testcase.ini section name>")
parser.add_argument("-l", "--all", action="store_true",
help="Same as --platform all")
parser.add_argument("-o", "--testcase-report",
help="Output a CSV spreadsheet containing results of the test run")
parser.add_argument("-d", "--discard-report",
help="Output a CSV spreadhseet showing tests that were skipped "
"and why")
parser.add_argument("-y", "--dry-run", action="store_true",
help="Create the filtered list of test cases, but don't actually "
"run them. Useful if you're just interested in "
"--discard-report")
parser.add_argument("-r", "--release", action="store_true",
help="Update the benchmark database with the results of this test "
"run. Intended to be run by CI when tagging an official "
"release. This database is used as a basis for comparison "
"when looking for deltas in metrics such as footprint")
parser.add_argument("-w", "--warnings-as-errors", action="store_true",
help="Treat warning conditions as errors")
parser.add_argument("-v", "--verbose", action="count", default=0,
help="Emit debugging information, call multiple times to increase "
"verbosity")
parser.add_argument("-i", "--inline-logs", action="store_true",
help="Upon test failure, print relevant log data to stdout "
"instead of just a path to it")
parser.add_argument("-m", "--last-metrics", action="store_true",
help="Instead of comparing metrics from the last --release, "
"compare with the results of the previous sanity check "
"invocation")
parser.add_argument("-u", "--no-update", action="store_true",
help="do not update the results of the last run of the sanity "
"checks")
parser.add_argument("-b", "--build-only", action="store_true",
help="Only build the code, do not execute any of it in QEMU")
parser.add_argument("-j", "--jobs", type=int,
help="Number of cores to use when building, defaults to "
"number of CPUs * 2")
parser.add_argument("-H", "--footprint-threshold", type=float, default=5,
help="When checking test case footprint sizes, warn the user if "
"the new app size is greater then the specified percentage "
"from the last release. Default is 5. 0 to warn on any "
"increase on app size")
parser.add_argument("-D", "--all-deltas", action="store_true",
help="Show all footprint deltas, positive or negative. Implies "
"--footprint-threshold=0")
parser.add_argument("-O", "--outdir",
default="%s/sanity-out" % ZEPHYR_BASE,
help="Output directory for logs and binaries.")
parser.add_argument("-n", "--no-clean", action="store_true",
help="Do not delete the outdir before building. Will result in "
"faster compilation since builds will be incremental")
parser.add_argument("-T", "--testcase-root",
default="%s/samples" % ZEPHYR_BASE,
help="Base directory to recursively search for test cases. All "
"testcase.ini files under here will be processed")
parser.add_argument("-A", "--arch-root",
default="%s/scripts/sanity_chk/arches" % ZEPHYR_BASE,
help="Directory to search for arch configuration files. All .ini "
"files in the directory will be processed.")
parser.add_argument("-z", "--size", action="append",
help="Don't run sanity checks. Instead, produce a report to "
"stdout detailing RAM/ROM sizes on the specified filenames. "
"All other command line arguments ignored.")
return parser.parse_args()
def log_info(filename):
filename = os.path.relpath(filename)
if INLINE_LOGS:
print "{:-^100}".format(filename)
with open(filename) as fp:
sys.stdout.write(fp.read())
print "{:-^100}".format(filename)
else:
print "\tsee: " + COLOR_YELLOW + filename + COLOR_NORMAL
def terse_test_cb(instances, goals, goal):
total_tests = len(goals)
total_done = 0
total_failed = 0
for k, g in goals.iteritems():
if g.finished:
total_done += 1
if g.failed:
total_failed += 1
if goal.failed:
i = instances[goal.name]
info("\n\n{:<25} {:<50} {}FAILED{}: {}".format(i.platform.name,
i.test.name, COLOR_RED, COLOR_NORMAL, goal.reason))
log_info(goal.get_error_log())
info("")
sys.stdout.write("\rtotal complete: %s%3d/%3d%s failed: %s%3d%s" % (
COLOR_GREEN, total_done, total_tests, COLOR_NORMAL,
COLOR_RED if total_failed > 0 else COLOR_NORMAL,
total_failed, COLOR_NORMAL))
sys.stdout.flush()
def chatty_test_cb(instances, goals, goal):
i = instances[goal.name]
if VERBOSE < 2 and not goal.finished:
return
if goal.failed:
status = COLOR_RED + "FAILED" + COLOR_NORMAL + ": " + goal.reason
elif goal.finished:
status = COLOR_GREEN + "PASSED" + COLOR_NORMAL
else:
status = goal.make_state
info("{:<25} {:<50} {}".format(i.platform.name, i.test.name, status))
if goal.failed:
log_info(goal.get_error_log())
def size_report(sc):
info(sc.filename)
info("SECTION NAME ADDRESS SIZE HEX")
for k, v in sc.sections.iteritems():
if not v["recognized"]:
k += "*"
info("%-17s 0x%08x %8d %5x" %
(k, v["phys_addr"], v["size"], v["size"]))
if sc.is_xip:
info("Total: %d bytes (ROM) + %d bytes (RAM)" %
(sc.xip_rom_size, sc.xip_ram_size))
else:
info("Total: %d bytes (RAM)" % sc.ram_size)
info("")
def main():
start_time = time.time()
global VERBOSE, INLINE_LOGS, PARALLEL
args = parse_arguments()
if args.size:
for fn in args.size:
size_report(SizeCalculator(fn))
sys.exit(0)
VERBOSE += args.verbose
INLINE_LOGS = args.inline_logs
if args.jobs:
PARALLEL = args.jobs
if args.all:
args.platform = ["all"]
if os.path.exists(args.outdir) and not args.no_clean:
info("Cleaning output directory " + args.outdir)
shutil.rmtree(args.outdir)
ts = TestSuite(args.arch_root, args.testcase_root, args.outdir)
discards = ts.apply_filters(args.platform, args.arch, args.tag, args.config,
args.test, args.only_failed)
if args.discard_report:
ts.discard_report(args.discard_report)
if VERBOSE:
for i, reason in discards.iteritems():
debug("{:<25} {:<50} {}SKIPPED{}: {}".format(i.platform.name,
i.test.name, COLOR_YELLOW, COLOR_NORMAL, reason))
info("%d tests selected, %d tests discarded due to filters" %
(len(ts.instances), len(discards)))
if args.dry_run:
return
if VERBOSE or not TERMINAL:
goals = ts.execute(chatty_test_cb, ts.instances, args.build_only)
else:
goals = ts.execute(terse_test_cb, ts.instances, args.build_only)
print
deltas = ts.compare_metrics(LAST_SANITY if args.last_metrics
else RELEASE_DATA)
warnings = 0
if deltas:
for i, metric, value, delta, lower_better in deltas:
if not args.all_deltas and ((delta < 0 and lower_better) or
(delta > 0 and not lower_better)):
continue
percentage = (float(delta) / float(value - delta))
if not args.all_deltas and (percentage <
(args.footprint_threshold / 100.0)):
continue
info("{:<25} {:<50} {}{}{}: {} is now {} {:+.2%}".format(
i.platform.name, i.test.name, COLOR_YELLOW,
"INFO" if args.all_deltas else "WARNING", COLOR_NORMAL,
metric, value, percentage))
warnings += 1
if warnings:
info("Deltas based on metrics from last %s" %
("release" if not args.last_metrics else "run"))
failed = 0
for name, goal in goals.iteritems():
if goal.failed:
failed += 1
info("%s%d of %d%s tests passed with %s%d%s warnings in %d seconds" %
(COLOR_RED if failed else COLOR_GREEN, len(goals) - failed,
len(goals), COLOR_NORMAL, COLOR_YELLOW if warnings else COLOR_NORMAL,
warnings, COLOR_NORMAL, time.time() - start_time))
if args.testcase_report:
ts.testcase_report(args.testcase_report)
if not args.no_update:
ts.testcase_report(LAST_SANITY)
if args.release:
ts.testcase_report(RELEASE_DATA)
if failed or (warnings and args.warnings_as_errors):
sys.exit(1)
if __name__ == "__main__":
main()