/usr/lib/python2.7/dist-packages/cherrypy/lib/cpstats.py is in python-cherrypy3 8.9.1-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 | """CPStats, a package for collecting and reporting on program statistics.
Overview
========
Statistics about program operation are an invaluable monitoring and debugging
tool. Unfortunately, the gathering and reporting of these critical values is
usually ad-hoc. This package aims to add a centralized place for gathering
statistical performance data, a structure for recording that data which
provides for extrapolation of that data into more useful information,
and a method of serving that data to both human investigators and
monitoring software. Let's examine each of those in more detail.
Data Gathering
--------------
Just as Python's `logging` module provides a common importable for gathering
and sending messages, performance statistics would benefit from a similar
common mechanism, and one that does *not* require each package which wishes
to collect stats to import a third-party module. Therefore, we choose to
re-use the `logging` module by adding a `statistics` object to it.
That `logging.statistics` object is a nested dict. It is not a custom class,
because that would:
1. require libraries and applications to import a third-party module in
order to participate
2. inhibit innovation in extrapolation approaches and in reporting tools, and
3. be slow.
There are, however, some specifications regarding the structure of the dict.::
{
+----"SQLAlchemy": {
| "Inserts": 4389745,
| "Inserts per Second":
| lambda s: s["Inserts"] / (time() - s["Start"]),
| C +---"Table Statistics": {
| o | "widgets": {-----------+
N | l | "Rows": 1.3M, | Record
a | l | "Inserts": 400, |
m | e | },---------------------+
e | c | "froobles": {
s | t | "Rows": 7845,
p | i | "Inserts": 0,
a | o | },
c | n +---},
e | "Slow Queries":
| [{"Query": "SELECT * FROM widgets;",
| "Processing Time": 47.840923343,
| },
| ],
+----},
}
The `logging.statistics` dict has four levels. The topmost level is nothing
more than a set of names to introduce modularity, usually along the lines of
package names. If the SQLAlchemy project wanted to participate, for example,
it might populate the item `logging.statistics['SQLAlchemy']`, whose value
would be a second-layer dict we call a "namespace". Namespaces help multiple
packages to avoid collisions over key names, and make reports easier to read,
to boot. The maintainers of SQLAlchemy should feel free to use more than one
namespace if needed (such as 'SQLAlchemy ORM'). Note that there are no case
or other syntax constraints on the namespace names; they should be chosen
to be maximally readable by humans (neither too short nor too long).
Each namespace, then, is a dict of named statistical values, such as
'Requests/sec' or 'Uptime'. You should choose names which will look
good on a report: spaces and capitalization are just fine.
In addition to scalars, values in a namespace MAY be a (third-layer)
dict, or a list, called a "collection". For example, the CherryPy
:class:`StatsTool` keeps track of what each request is doing (or has most
recently done) in a 'Requests' collection, where each key is a thread ID; each
value in the subdict MUST be a fourth dict (whew!) of statistical data about
each thread. We call each subdict in the collection a "record". Similarly,
the :class:`StatsTool` also keeps a list of slow queries, where each record
contains data about each slow query, in order.
Values in a namespace or record may also be functions, which brings us to:
Extrapolation
-------------
The collection of statistical data needs to be fast, as close to unnoticeable
as possible to the host program. That requires us to minimize I/O, for example,
but in Python it also means we need to minimize function calls. So when you
are designing your namespace and record values, try to insert the most basic
scalar values you already have on hand.
When it comes time to report on the gathered data, however, we usually have
much more freedom in what we can calculate. Therefore, whenever reporting
tools (like the provided :class:`StatsPage` CherryPy class) fetch the contents
of `logging.statistics` for reporting, they first call
`extrapolate_statistics` (passing the whole `statistics` dict as the only
argument). This makes a deep copy of the statistics dict so that the
reporting tool can both iterate over it and even change it without harming
the original. But it also expands any functions in the dict by calling them.
For example, you might have a 'Current Time' entry in the namespace with the
value "lambda scope: time.time()". The "scope" parameter is the current
namespace dict (or record, if we're currently expanding one of those
instead), allowing you access to existing static entries. If you're truly
evil, you can even modify more than one entry at a time.
However, don't try to calculate an entry and then use its value in further
extrapolations; the order in which the functions are called is not guaranteed.
This can lead to a certain amount of duplicated work (or a redesign of your
schema), but that's better than complicating the spec.
After the whole thing has been extrapolated, it's time for:
Reporting
---------
The :class:`StatsPage` class grabs the `logging.statistics` dict, extrapolates
it all, and then transforms it to HTML for easy viewing. Each namespace gets
its own header and attribute table, plus an extra table for each collection.
This is NOT part of the statistics specification; other tools can format how
they like.
You can control which columns are output and how they are formatted by updating
StatsPage.formatting, which is a dict that mirrors the keys and nesting of
`logging.statistics`. The difference is that, instead of data values, it has
formatting values. Use None for a given key to indicate to the StatsPage that a
given column should not be output. Use a string with formatting
(such as '%.3f') to interpolate the value(s), or use a callable (such as
lambda v: v.isoformat()) for more advanced formatting. Any entry which is not
mentioned in the formatting dict is output unchanged.
Monitoring
----------
Although the HTML output takes pains to assign unique id's to each <td> with
statistical data, you're probably better off fetching /cpstats/data, which
outputs the whole (extrapolated) `logging.statistics` dict in JSON format.
That is probably easier to parse, and doesn't have any formatting controls,
so you get the "original" data in a consistently-serialized format.
Note: there's no treatment yet for datetime objects. Try time.time() instead
for now if you can. Nagios will probably thank you.
Turning Collection Off
----------------------
It is recommended each namespace have an "Enabled" item which, if False,
stops collection (but not reporting) of statistical data. Applications
SHOULD provide controls to pause and resume collection by setting these
entries to False or True, if present.
Usage
=====
To collect statistics on CherryPy applications::
from cherrypy.lib import cpstats
appconfig['/']['tools.cpstats.on'] = True
To collect statistics on your own code::
import logging
# Initialize the repository
if not hasattr(logging, 'statistics'): logging.statistics = {}
# Initialize my namespace
mystats = logging.statistics.setdefault('My Stuff', {})
# Initialize my namespace's scalars and collections
mystats.update({
'Enabled': True,
'Start Time': time.time(),
'Important Events': 0,
'Events/Second': lambda s: (
(s['Important Events'] / (time.time() - s['Start Time']))),
})
...
for event in events:
...
# Collect stats
if mystats.get('Enabled', False):
mystats['Important Events'] += 1
To report statistics::
root.cpstats = cpstats.StatsPage()
To format statistics reports::
See 'Reporting', above.
"""
import logging
import os
import sys
import threading
import time
import cherrypy
from cherrypy._cpcompat import json
# ------------------------------- Statistics -------------------------------- #
if not hasattr(logging, 'statistics'):
logging.statistics = {}
def extrapolate_statistics(scope):
"""Return an extrapolated copy of the given scope."""
c = {}
for k, v in list(scope.items()):
if isinstance(v, dict):
v = extrapolate_statistics(v)
elif isinstance(v, (list, tuple)):
v = [extrapolate_statistics(record) for record in v]
elif hasattr(v, '__call__'):
v = v(scope)
c[k] = v
return c
# -------------------- CherryPy Applications Statistics --------------------- #
appstats = logging.statistics.setdefault('CherryPy Applications', {})
appstats.update({
'Enabled': True,
'Bytes Read/Request': lambda s: (
s['Total Requests'] and
(s['Total Bytes Read'] / float(s['Total Requests'])) or
0.0
),
'Bytes Read/Second': lambda s: s['Total Bytes Read'] / s['Uptime'](s),
'Bytes Written/Request': lambda s: (
s['Total Requests'] and
(s['Total Bytes Written'] / float(s['Total Requests'])) or
0.0
),
'Bytes Written/Second': lambda s: (
s['Total Bytes Written'] / s['Uptime'](s)
),
'Current Time': lambda s: time.time(),
'Current Requests': 0,
'Requests/Second': lambda s: float(s['Total Requests']) / s['Uptime'](s),
'Server Version': cherrypy.__version__,
'Start Time': time.time(),
'Total Bytes Read': 0,
'Total Bytes Written': 0,
'Total Requests': 0,
'Total Time': 0,
'Uptime': lambda s: time.time() - s['Start Time'],
'Requests': {},
})
proc_time = lambda s: time.time() - s['Start Time']
class ByteCountWrapper(object):
"""Wraps a file-like object, counting the number of bytes read."""
def __init__(self, rfile):
self.rfile = rfile
self.bytes_read = 0
def read(self, size=-1):
data = self.rfile.read(size)
self.bytes_read += len(data)
return data
def readline(self, size=-1):
data = self.rfile.readline(size)
self.bytes_read += len(data)
return data
def readlines(self, sizehint=0):
# Shamelessly stolen from StringIO
total = 0
lines = []
line = self.readline()
while line:
lines.append(line)
total += len(line)
if 0 < sizehint <= total:
break
line = self.readline()
return lines
def close(self):
self.rfile.close()
def __iter__(self):
return self
def next(self):
data = self.rfile.next()
self.bytes_read += len(data)
return data
average_uriset_time = lambda s: s['Count'] and (s['Sum'] / s['Count']) or 0
def _get_threading_ident():
if sys.version_info >= (3, 3):
return threading.get_ident()
return threading._get_ident()
class StatsTool(cherrypy.Tool):
"""Record various information about the current request."""
def __init__(self):
cherrypy.Tool.__init__(self, 'on_end_request', self.record_stop)
def _setup(self):
"""Hook this tool into cherrypy.request.
The standard CherryPy request object will automatically call this
method when the tool is "turned on" in config.
"""
if appstats.get('Enabled', False):
cherrypy.Tool._setup(self)
self.record_start()
def record_start(self):
"""Record the beginning of a request."""
request = cherrypy.serving.request
if not hasattr(request.rfile, 'bytes_read'):
request.rfile = ByteCountWrapper(request.rfile)
request.body.fp = request.rfile
r = request.remote
appstats['Current Requests'] += 1
appstats['Total Requests'] += 1
appstats['Requests'][_get_threading_ident()] = {
'Bytes Read': None,
'Bytes Written': None,
# Use a lambda so the ip gets updated by tools.proxy later
'Client': lambda s: '%s:%s' % (r.ip, r.port),
'End Time': None,
'Processing Time': proc_time,
'Request-Line': request.request_line,
'Response Status': None,
'Start Time': time.time(),
}
def record_stop(
self, uriset=None, slow_queries=1.0, slow_queries_count=100,
debug=False, **kwargs):
"""Record the end of a request."""
resp = cherrypy.serving.response
w = appstats['Requests'][_get_threading_ident()]
r = cherrypy.request.rfile.bytes_read
w['Bytes Read'] = r
appstats['Total Bytes Read'] += r
if resp.stream:
w['Bytes Written'] = 'chunked'
else:
cl = int(resp.headers.get('Content-Length', 0))
w['Bytes Written'] = cl
appstats['Total Bytes Written'] += cl
w['Response Status'] = getattr(
resp, 'output_status', None) or resp.status
w['End Time'] = time.time()
p = w['End Time'] - w['Start Time']
w['Processing Time'] = p
appstats['Total Time'] += p
appstats['Current Requests'] -= 1
if debug:
cherrypy.log('Stats recorded: %s' % repr(w), 'TOOLS.CPSTATS')
if uriset:
rs = appstats.setdefault('URI Set Tracking', {})
r = rs.setdefault(uriset, {
'Min': None, 'Max': None, 'Count': 0, 'Sum': 0,
'Avg': average_uriset_time})
if r['Min'] is None or p < r['Min']:
r['Min'] = p
if r['Max'] is None or p > r['Max']:
r['Max'] = p
r['Count'] += 1
r['Sum'] += p
if slow_queries and p > slow_queries:
sq = appstats.setdefault('Slow Queries', [])
sq.append(w.copy())
if len(sq) > slow_queries_count:
sq.pop(0)
cherrypy.tools.cpstats = StatsTool()
# ---------------------- CherryPy Statistics Reporting ---------------------- #
thisdir = os.path.abspath(os.path.dirname(__file__))
missing = object()
locale_date = lambda v: time.strftime('%c', time.gmtime(v))
iso_format = lambda v: time.strftime('%Y-%m-%d %H:%M:%S', time.gmtime(v))
def pause_resume(ns):
def _pause_resume(enabled):
pause_disabled = ''
resume_disabled = ''
if enabled:
resume_disabled = 'disabled="disabled" '
else:
pause_disabled = 'disabled="disabled" '
return """
<form action="pause" method="POST" style="display:inline">
<input type="hidden" name="namespace" value="%s" />
<input type="submit" value="Pause" %s/>
</form>
<form action="resume" method="POST" style="display:inline">
<input type="hidden" name="namespace" value="%s" />
<input type="submit" value="Resume" %s/>
</form>
""" % (ns, pause_disabled, ns, resume_disabled)
return _pause_resume
class StatsPage(object):
formatting = {
'CherryPy Applications': {
'Enabled': pause_resume('CherryPy Applications'),
'Bytes Read/Request': '%.3f',
'Bytes Read/Second': '%.3f',
'Bytes Written/Request': '%.3f',
'Bytes Written/Second': '%.3f',
'Current Time': iso_format,
'Requests/Second': '%.3f',
'Start Time': iso_format,
'Total Time': '%.3f',
'Uptime': '%.3f',
'Slow Queries': {
'End Time': None,
'Processing Time': '%.3f',
'Start Time': iso_format,
},
'URI Set Tracking': {
'Avg': '%.3f',
'Max': '%.3f',
'Min': '%.3f',
'Sum': '%.3f',
},
'Requests': {
'Bytes Read': '%s',
'Bytes Written': '%s',
'End Time': None,
'Processing Time': '%.3f',
'Start Time': None,
},
},
'CherryPy WSGIServer': {
'Enabled': pause_resume('CherryPy WSGIServer'),
'Connections/second': '%.3f',
'Start time': iso_format,
},
}
@cherrypy.expose
def index(self):
# Transform the raw data into pretty output for HTML
yield """
<html>
<head>
<title>Statistics</title>
<style>
th, td {
padding: 0.25em 0.5em;
border: 1px solid #666699;
}
table {
border-collapse: collapse;
}
table.stats1 {
width: 100%;
}
table.stats1 th {
font-weight: bold;
text-align: right;
background-color: #CCD5DD;
}
table.stats2, h2 {
margin-left: 50px;
}
table.stats2 th {
font-weight: bold;
text-align: center;
background-color: #CCD5DD;
}
</style>
</head>
<body>
"""
for title, scalars, collections in self.get_namespaces():
yield """
<h1>%s</h1>
<table class='stats1'>
<tbody>
""" % title
for i, (key, value) in enumerate(scalars):
colnum = i % 3
if colnum == 0:
yield """
<tr>"""
yield (
"""
<th>%(key)s</th><td id='%(title)s-%(key)s'>%(value)s</td>""" %
vars()
)
if colnum == 2:
yield """
</tr>"""
if colnum == 0:
yield """
<th></th><td></td>
<th></th><td></td>
</tr>"""
elif colnum == 1:
yield """
<th></th><td></td>
</tr>"""
yield """
</tbody>
</table>"""
for subtitle, headers, subrows in collections:
yield """
<h2>%s</h2>
<table class='stats2'>
<thead>
<tr>""" % subtitle
for key in headers:
yield """
<th>%s</th>""" % key
yield """
</tr>
</thead>
<tbody>"""
for subrow in subrows:
yield """
<tr>"""
for value in subrow:
yield """
<td>%s</td>""" % value
yield """
</tr>"""
yield """
</tbody>
</table>"""
yield """
</body>
</html>
"""
def get_namespaces(self):
"""Yield (title, scalars, collections) for each namespace."""
s = extrapolate_statistics(logging.statistics)
for title, ns in sorted(s.items()):
scalars = []
collections = []
ns_fmt = self.formatting.get(title, {})
for k, v in sorted(ns.items()):
fmt = ns_fmt.get(k, {})
if isinstance(v, dict):
headers, subrows = self.get_dict_collection(v, fmt)
collections.append((k, ['ID'] + headers, subrows))
elif isinstance(v, (list, tuple)):
headers, subrows = self.get_list_collection(v, fmt)
collections.append((k, headers, subrows))
else:
format = ns_fmt.get(k, missing)
if format is None:
# Don't output this column.
continue
if hasattr(format, '__call__'):
v = format(v)
elif format is not missing:
v = format % v
scalars.append((k, v))
yield title, scalars, collections
def get_dict_collection(self, v, formatting):
"""Return ([headers], [rows]) for the given collection."""
# E.g., the 'Requests' dict.
headers = []
try:
# python2
vals = v.itervalues()
except AttributeError:
# python3
vals = v.values()
for record in vals:
for k3 in record:
format = formatting.get(k3, missing)
if format is None:
# Don't output this column.
continue
if k3 not in headers:
headers.append(k3)
headers.sort()
subrows = []
for k2, record in sorted(v.items()):
subrow = [k2]
for k3 in headers:
v3 = record.get(k3, '')
format = formatting.get(k3, missing)
if format is None:
# Don't output this column.
continue
if hasattr(format, '__call__'):
v3 = format(v3)
elif format is not missing:
v3 = format % v3
subrow.append(v3)
subrows.append(subrow)
return headers, subrows
def get_list_collection(self, v, formatting):
"""Return ([headers], [subrows]) for the given collection."""
# E.g., the 'Slow Queries' list.
headers = []
for record in v:
for k3 in record:
format = formatting.get(k3, missing)
if format is None:
# Don't output this column.
continue
if k3 not in headers:
headers.append(k3)
headers.sort()
subrows = []
for record in v:
subrow = []
for k3 in headers:
v3 = record.get(k3, '')
format = formatting.get(k3, missing)
if format is None:
# Don't output this column.
continue
if hasattr(format, '__call__'):
v3 = format(v3)
elif format is not missing:
v3 = format % v3
subrow.append(v3)
subrows.append(subrow)
return headers, subrows
if json is not None:
@cherrypy.expose
def data(self):
s = extrapolate_statistics(logging.statistics)
cherrypy.response.headers['Content-Type'] = 'application/json'
return json.dumps(s, sort_keys=True, indent=4)
@cherrypy.expose
def pause(self, namespace):
logging.statistics.get(namespace, {})['Enabled'] = False
raise cherrypy.HTTPRedirect('./')
pause.cp_config = {'tools.allow.on': True,
'tools.allow.methods': ['POST']}
@cherrypy.expose
def resume(self, namespace):
logging.statistics.get(namespace, {})['Enabled'] = True
raise cherrypy.HTTPRedirect('./')
resume.cp_config = {'tools.allow.on': True,
'tools.allow.methods': ['POST']}
|