mirror of
git://git.psyc.eu/libpsyc
synced 2024-08-15 03:19:02 +00:00
bench: converted to org, added packet extraction script, added first results
This commit is contained in:
tg(x)
parent
1aa7d2b718
commit
15bca0ea2a
3 changed files with 353 additions and 0 deletions
28
bench/Makefile
Normal file
28
bench/Makefile
Normal file
|
|
@ -0,0 +1,28 @@
|
||||||
|
ORG_PATH = /usr/share/emacs/site-lisp/org-mode
|
||||||
|
INIT = (setq load-path (cons \"/usr/share/emacs/site-lisp/org-mode\" load-path)) (require 'org-install)
|
||||||
|
|
||||||
|
wiki2org:
|
||||||
|
perl -pe '\
|
||||||
|
s/^= (.*) =\s*$$/#+TITLE: $$1\n/; \
|
||||||
|
s/^== (.*) ==\s*$$/* $$1/; \
|
||||||
|
s/^=== (.*) ===\s*$$/** $$1/; \
|
||||||
|
s/^{{{/#+BEGIN_SRC/; \
|
||||||
|
s/^}}}/#+END_SRC/ \
|
||||||
|
' benchmark.wiki >benchmark.org
|
||||||
|
|
||||||
|
tangle:
|
||||||
|
emacs -Q --batch --eval \
|
||||||
|
"(progn ${INIT} (find-file \"benchmark.org\") \
|
||||||
|
(setq org-babel-tangle-pad-newline nil org-src-preserve-indentation t) \
|
||||||
|
(org-babel-tangle) (kill-buffer))"
|
||||||
|
perl -pi -e 'print "\n" unless $$p; $$p=1' packets/user_profile.psyc
|
||||||
|
|
||||||
|
html:
|
||||||
|
emacs -Q --batch --eval \
|
||||||
|
"(progn ${INIT} (find-file \"benchmark.org\") \
|
||||||
|
(org-export-as-html-batch) (kill-buffer))"
|
||||||
|
|
||||||
|
pdf:
|
||||||
|
emacs -Q --batch --eval \
|
||||||
|
"(progn ${INIT} (find-file \"benchmark.org\") \
|
||||||
|
(org-export-as-pdf org-export-headline-levels) (kill-buffer))"
|
||||||
270
bench/benchmark.org
Normal file
270
bench/benchmark.org
Normal file
|
|
@ -0,0 +1,270 @@
|
||||||
|
#+TITLE: libpsyc Performance Benchmarks
|
||||||
|
|
||||||
|
In this document we present the results of performance benchmarks
|
||||||
|
of libpsyc compared with libjson-glib and libxml2.
|
||||||
|
|
||||||
|
* Procedure
|
||||||
|
We'll use typical messages from the XMPP ("stanzas" in Jabber
|
||||||
|
lingo) and compare them with equivalent JSON encodings,
|
||||||
|
verbose and compact PSYC formats.
|
||||||
|
|
||||||
|
In some cases we will additionally compare PSYC packets to
|
||||||
|
a more efficient XML encoding based on PSYC methods, to have
|
||||||
|
a more accurate comparison of the actual PSYC and XML
|
||||||
|
syntaxes, rather than the protocol structures of PSYC and XMPP.
|
||||||
|
|
||||||
|
* The Benchmarks
|
||||||
|
** A presence packet
|
||||||
|
Since presence packets are by far the dominant messaging content
|
||||||
|
in the XMPP network, we'll start with one of them.
|
||||||
|
Here's an example from paragraph 4.4.2 of RFC 6121.
|
||||||
|
|
||||||
|
#+BEGIN_SRC xml :tangle packets/presence.xml
|
||||||
|
<presence from='juliet@example.com/balcony'
|
||||||
|
to='benvolio@example.net'>
|
||||||
|
<show>away</show>
|
||||||
|
</presence>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
And here's the same information in a JSON rendition:
|
||||||
|
|
||||||
|
#+BEGIN_SRC js :tangle packets/presence.json
|
||||||
|
["presence",{"from":"juliet@example.com/balcony","to":"benvolio@example.net"},{"show":"away"}]
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
Here's the equivalent PSYC packet in verbose form
|
||||||
|
(since it is a multicast, the single recipients do not
|
||||||
|
need to be mentioned):
|
||||||
|
|
||||||
|
#+BEGIN_SRC psyc :tangle packets/presence.psyc
|
||||||
|
:_context psyc://example.com/~juliet
|
||||||
|
|
||||||
|
=_degree_availability 4
|
||||||
|
_notice_presence
|
||||||
|
|
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
And the same in compact form:
|
||||||
|
|
||||||
|
#+BEGIN_SRC psyc
|
||||||
|
:c psyc://example.com/~juliet
|
||||||
|
|
||||||
|
=da 4
|
||||||
|
np
|
||||||
|
|
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** An average chat message
|
||||||
|
|
||||||
|
XML:
|
||||||
|
|
||||||
|
#+BEGIN_SRC xml :tangle packets/chat_msg.xml
|
||||||
|
<message
|
||||||
|
from='juliet@example.com/balcony'
|
||||||
|
id='ktx72v49'
|
||||||
|
to='romeo@example.net'
|
||||||
|
type='chat'
|
||||||
|
xml:lang='en'>
|
||||||
|
<body>Art thou not Romeo, and a Montague?</body>
|
||||||
|
</message>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
PSYC:
|
||||||
|
|
||||||
|
#+BEGIN_SRC psyc :tangle packets/chat_msg.psyc
|
||||||
|
:_source psyc://example.com/~juliet
|
||||||
|
:_target psyc://example.net/~romeo
|
||||||
|
|
||||||
|
_message_private
|
||||||
|
Art thou not Romeo, and a Montague?
|
||||||
|
|
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** A new status updated activity
|
||||||
|
Example taken from http://onesocialweb.org/spec/1.0/osw-activities.html
|
||||||
|
You could call this XML namespace hell:
|
||||||
|
|
||||||
|
#+BEGIN_SRC xml :tangle packets/activity.xml
|
||||||
|
<iq type='set'
|
||||||
|
from='hamlet@denmark.lit/snsclient'
|
||||||
|
to='hamlet@denmark.lit'
|
||||||
|
id='osw1'>
|
||||||
|
<pubsub xmlns='http://jabber.org/protocol/pubsub'>
|
||||||
|
<publish node='urn:xmpp:microblog:0'>
|
||||||
|
<item>
|
||||||
|
<entry xmlns="http://www.w3.org/2005/Atom"
|
||||||
|
xmlns:activity="http://activitystrea.ms/spec/1.0/"
|
||||||
|
xmlns:osw="http://onesocialweb.org/spec/1.0/">
|
||||||
|
<title>to be or not to be ?</title>
|
||||||
|
<activity:verb>http://activitystrea.ms/schema/1.0/post</activity:verb>
|
||||||
|
<activity:object>
|
||||||
|
<activity:object-type>http://onesocialweb.org/spec/1.0/object/status</activity:object-type>
|
||||||
|
<content type="text/plain">to be or not to be ?</content>
|
||||||
|
</activity:object>
|
||||||
|
<osw:acl-rule>
|
||||||
|
<osw:acl-action permission="http://onesocialweb.org/spec/1.0/acl/permission/grant">
|
||||||
|
http://onesocialweb.org/spec/1.0/acl/action/view
|
||||||
|
</osw:acl-action>
|
||||||
|
<osw:acl-subject type="http://onesocialweb.org/spec/1.0/acl/subject/everyone"/>
|
||||||
|
</osw:acl-rule>
|
||||||
|
</entry>
|
||||||
|
</item>
|
||||||
|
</publish>
|
||||||
|
</pubsub>
|
||||||
|
</iq>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
http://activitystrea.ms/head/json-activity.html proposes a JSON encoding
|
||||||
|
of this. We'll have to add a routing header to it.
|
||||||
|
|
||||||
|
#+BEGIN_SRC js :tangle packets/activity.json
|
||||||
|
["activity",{"from":"hamlet@denmark.lit/snsclient"},{"verb":"post",
|
||||||
|
"title":"to be or not to be ?","object":{"type":"status",
|
||||||
|
"content":"to be or not to be ?","contentType":"text/plain"}}]
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
http://about.psyc.eu/Activity suggests a PSYC mapping for activity
|
||||||
|
streams. Should a "status post" be considered equivalent to a presence
|
||||||
|
description announcement or just a message in the "microblogging" channel?
|
||||||
|
We'll use the latter here:
|
||||||
|
|
||||||
|
#+BEGIN_SRC psyc :tangle packets/activity.psyc
|
||||||
|
:_context psyc://denmark.lit/~hamlet#_follow
|
||||||
|
|
||||||
|
:_subject to be or not to be ?
|
||||||
|
:_type_content text/plain
|
||||||
|
_message
|
||||||
|
to be or not to be ?
|
||||||
|
|
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** A message with JSON-unfriendly characters
|
||||||
|
#+BEGIN_SRC xml :tangle packets/json-unfriendly.xml
|
||||||
|
<message
|
||||||
|
from='romeo@example.net/orchard'
|
||||||
|
id='sl3nx51f'
|
||||||
|
to='juliet@example.com/balcony'
|
||||||
|
type='chat'
|
||||||
|
xml:lang='en'>
|
||||||
|
<body>"Neither, fair saint, if either thee dislike.", he said.
|
||||||
|
And
|
||||||
|
the
|
||||||
|
rest
|
||||||
|
is
|
||||||
|
history.</body>
|
||||||
|
</message>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** A message with XML-unfriendly characters
|
||||||
|
#+BEGIN_SRC xml :tangle packets/xml-unfriendly.xml
|
||||||
|
<message
|
||||||
|
from='juliet@example.com/balcony'
|
||||||
|
id='z94nb37h'
|
||||||
|
to='romeo@example.net'
|
||||||
|
type='chat'
|
||||||
|
xml:lang='en'>
|
||||||
|
<body>Wherefore art thou, Romeo?</body>
|
||||||
|
<body xml:lang='cs'>
|
||||||
|
PročeŽ jsi ty, Romeo?
|
||||||
|
</body>
|
||||||
|
</message>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** A message with PSYC-unfriendly strings
|
||||||
|
#+BEGIN_SRC xml :tangle packets/psyc-unfriendly.xml
|
||||||
|
<message
|
||||||
|
from='juliet@example.com/balcony'
|
||||||
|
id='c8xg3nf8'
|
||||||
|
to='romeo@example.net'
|
||||||
|
type='chat'
|
||||||
|
xml:lang='en'>
|
||||||
|
<subject>I implore you with a pointless
|
||||||
|
newline in a header variable</subject>
|
||||||
|
<body>Wherefore art thou, Romeo?
|
||||||
|
|
|
||||||
|
And for practicing purposes we added a PSYC packet delimiter.</body>
|
||||||
|
</message>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
** A packet containing a JPEG photograph
|
||||||
|
... TBD ...
|
||||||
|
|
||||||
|
** A random data structure
|
||||||
|
In this test we'll not consider XMPP at all and simply compare the
|
||||||
|
efficiency of the three syntaxes at serializing a typical user data base
|
||||||
|
storage information. We'll again start with XML:
|
||||||
|
|
||||||
|
#+BEGIN_SRC xml :tangle packets/user_profile.xml
|
||||||
|
<UserProfile>
|
||||||
|
<Name>Silvio Berlusconi</Name>
|
||||||
|
<JobTitle>Premier</JobTitle>
|
||||||
|
<Country>I</Country>
|
||||||
|
<Address>
|
||||||
|
<Street>Via del Colosseo, 1</Street>
|
||||||
|
<PostalCode>00100</PostalCode>
|
||||||
|
<City>Roma</City>
|
||||||
|
</Address>
|
||||||
|
<Page>http://example.org</Page>
|
||||||
|
</UserProfile>
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
In JSON this would look like this:
|
||||||
|
|
||||||
|
#+BEGIN_SRC js :tangle packets/user_profile.json
|
||||||
|
["UserProfile",{"Name":"Silvio Berlusconi","JobTitle":"Premier","Country":"I","Address":
|
||||||
|
{"Street":"Via del Colosseo, 1","PostalCode":"00100","City":"Roma"},"Page":"http://example.org"}]
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
Here's a way to model this in PSYC:
|
||||||
|
|
||||||
|
#+BEGIN_SRC psyc :tangle packets/user_profile.psyc
|
||||||
|
|
||||||
|
:_name Silvio Berlusconi
|
||||||
|
:_title_job Premier
|
||||||
|
:_country I
|
||||||
|
:_address_street Via del Colosseo, 1
|
||||||
|
:_address_code_postal 00100
|
||||||
|
:_address_city Roma
|
||||||
|
:_page http://example.org
|
||||||
|
_profile_user
|
||||||
|
|
|
||||||
|
#+END_SRC
|
||||||
|
|
||||||
|
* Conclusions
|
||||||
|
... TBD ...
|
||||||
|
|
||||||
|
* Criticism
|
||||||
|
Are we comparing apples and oranges? Yes and no, depends on what you
|
||||||
|
need. XML is a syntax best suited for complex structured data in
|
||||||
|
well-defined formats - especially good for text mark-up. JSON is a syntax
|
||||||
|
intended to hold arbitrarily structured data suitable for immediate
|
||||||
|
inclusion in javascript source codes. The PSYC syntax is an evolved
|
||||||
|
derivate of RFC 822, the syntax used by HTTP and E-Mail, and is therefore
|
||||||
|
limited in the kind and depth of data structures that can be represented
|
||||||
|
with it, but in exchange it is highly performant at doing just that.
|
||||||
|
|
||||||
|
So it is up to you to find out which of the three formats fulfils your
|
||||||
|
requirements the best. We use PSYC for the majority of messaging where
|
||||||
|
JSON and XMPP aren't efficient and opaque enough, but we employ XML and
|
||||||
|
JSON as payloads within PSYC for data that doesn't fit the PSYC model.
|
||||||
|
For some reason all three formats are being used for messaging, although
|
||||||
|
only PSYC was actually designed for that purpose.
|
||||||
|
|
||||||
|
* Caveats
|
||||||
|
In every case we'll compare performance of parsing and re-rendering
|
||||||
|
these messages, but consider also that the applicative processing
|
||||||
|
of an XML DOM tree is more complicated than just accessing
|
||||||
|
certain elements in a JSON data structure or PSYC variable
|
||||||
|
mapping.
|
||||||
|
|
||||||
|
For a speed check in real world conditions which also consider the
|
||||||
|
complexity of processing incoming messages we should compare
|
||||||
|
the performance of a chat client using the two protocols,
|
||||||
|
for instance by using libpurple with XMPP and PSYC accounts.
|
||||||
|
To this purpose we first need to integrate libpsyc into libpurple.
|
||||||
|
|
||||||
|
* Futures
|
||||||
|
After a month of development libpsyc is already performing pretty
|
||||||
|
well, but we presume various optimizations, like rewriting parts
|
||||||
|
in assembler, are possible.
|
||||||
|
|
||||||
55
bench/results.org
Normal file
55
bench/results.org
Normal file
|
|
@ -0,0 +1,55 @@
|
||||||
|
#+TITLE: Benchmark results
|
||||||
|
#+OPTIONS: ^:{}
|
||||||
|
|
||||||
|
* libpsyc
|
||||||
|
|
||||||
|
: ./testPsyc -snqc 1000000 -f $file
|
||||||
|
|
||||||
|
- presence: 597 ms
|
||||||
|
- chat_msg: 714 ms
|
||||||
|
- user_profile: 1806 ms
|
||||||
|
- activity: 903 ms
|
||||||
|
|
||||||
|
* libjson
|
||||||
|
|
||||||
|
: ./testJson -snqc 1000000 -f $file
|
||||||
|
|
||||||
|
- presence: 3247 ms
|
||||||
|
- user_profile: 5847 ms
|
||||||
|
- activity: 5768 ms
|
||||||
|
|
||||||
|
* rapidxml
|
||||||
|
|
||||||
|
: ./rapidxml 1000000 $file
|
||||||
|
|
||||||
|
- presence: 1719 ms
|
||||||
|
- chat_msg: 1893 ms
|
||||||
|
- user_profile: 2477 ms
|
||||||
|
- activity: 4419 ms
|
||||||
|
|
||||||
|
* rapidxml fast mode
|
||||||
|
|
||||||
|
: fast_mode=1 ./rapidxml 1000000 $file
|
||||||
|
|
||||||
|
- presence: 1643 ms
|
||||||
|
- chat_msg: 1799 ms
|
||||||
|
- user_profile: 2218 ms
|
||||||
|
- activity: 4001 ms
|
||||||
|
|
||||||
|
* libxml
|
||||||
|
|
||||||
|
: ./libxml 1000000 $file
|
||||||
|
|
||||||
|
- presence: 7557 ms
|
||||||
|
- chat_msg: 9777 ms
|
||||||
|
- user_profile: 12377 ms
|
||||||
|
- activity: 28858 ms
|
||||||
|
|
||||||
|
* libxml sax
|
||||||
|
|
||||||
|
: ./libxml-sax 1000000 $file
|
||||||
|
|
||||||
|
- presence: 4997 ms
|
||||||
|
- chat_msg: 5997 ms
|
||||||
|
- user_profile: 7350 ms
|
||||||
|
- activity: 13357 ms
|
||||||
Loading…
Reference in a new issue