Performance test on Jetty/HSQLDB with a single wiki between 8.4.4 and 9.2

Last modified by Thomas Mortagne on 2017/04/05 10:05

Environment

  • Ubuntu 16.10 64b
  • Quad core i7-6700HQ
  • Oracle JDK 1.8.0_121 64b
  • Dumbbench 0.10
  • standard jetty+hsqldb
  • permdir in a SSD
  • only main wiki
  • configuration
    • Admin user:
      • hidden documents enabled
  • import perf.xar

Most of response time statistics are made with Dumbbench, you can install it using cpan.
For example on Debian/Ubuntu:

$ sudo apt-get install cpanminus
$ sudo cpanm Dumbbench

Unless specifically indicated otherwise all the tests are executed with a fully initialized instance (core extensions don't run anymore, SOLR index is fully up to date, etc.) and logged in with Admin user. Basically except for a few special tests we are using an instance that already been started and run until the proc is flat for some time.

Login with Admin user:

wget --save-cookies cookies.txt --post-data 'j_username=Admin&j_password=admin&j_rememberme=true' -O /dev/null -o /dev/null "http://127.0.0.1:8080/xwiki/bin/loginsubmit/XWiki/XWikiLogin?j_username=Admin&j_password=admin&j_rememberme=true"

Tests

Summary

There hasn't been much work on performance in 9.x so it's very similar to 8.4.4. Solr has been upgraded (from 6.2.1 to 6.4.2) and looks like it affected the speed of the job responsible for finding out what need to be indexed/removed but it does not seems to have any impact on actual indexing or standard document search. 

"similar": difference is lower than 10%
"slightly": difference is lower than 20%

Note that most of the speed related values are an average of very moving results, a lot of things is happening during a HTTP request and it's far from stable duration (that's why 10% may sounds a lot for something called "similar" but the variable can go up and down around 5% sometimes so 10% average is really not that much of a clear win). Dumbbench based tests are executed several times and the lowest result is selected. 

Speed

ActionsDifference
Jetty startupsimilar
First accessnot existing page without UIsimilar
not existing page with UI 
Reloadnot existing page without UIsimilar
not existing page with UIsimilar
empty page without UIsimilar
empty page with UIsimilar
Main.WebHome without UIsimilar
Main.WebHome with UIsimilar
SOLRFull SOLR reindexsimilar
SOLR sync when index is empty+70%
SOLR sync when there is nothing to do+70%
Result of search finding lots of resultssimilar
Result of search finding one resultsimilar
RenderingPage with 1000 macros without UIsimilar
Page with 1000 html macros without UIsimilar

Memory

ActionsDifference
Heap Memory after jetty startup-3MB
Heap Memory after full SOLR indexsimilar

Jetty startup

Unit: seconds

You get this from the log with the line looking like 2016-10-19 16:52:25.309:INFO:oejs.Server:main: Started @8434ms.

  • 8.4.4: 10
  • 9.2: 10

First access

First HTTP request after restarting Jetty.

First access to not existing page without UI

(/xwiki/bin/get/NoSpace/NoPage)

Unit: seconds

Firefox network statistics to load the root resource (image/js/css/etc. resources are not taken into account).

  • 8.4.4: 5.5
  • 9.2: 5.7

First access to not existing page with UI

(/xwiki/bin/view/NoSpace/NoPage)

Unit: seconds

Done by hand with a chronometer (image/js/css/etc. resources are not taken into account).

  • 8.4.4: 10
  • 9.2: 10

Reload

XWiki is doing nothing on background and everything is both in server and client cache already. Values are calculated using dumbbench (image/js/css/etc. resources are not taken into account).

Reload of not existing page without UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/get/NoSpace/NoPage"

Unit: milliseconds

  • 8.4.4: 6.6
  • 9.2: 6.4

Reload of not existing page with UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/view/NoSpace/NoPage"

Unit: milliseconds

  • 8.4.4: 85
  • 9.2: 85

Reload of empty page without UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/get/EmptySpace/EmptyPage"

Unit: milliseconds

  • 8.4.4: 6.8
  • 9.2: 6.5

Reload of empty page with UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/view/EmptySpace/EmptyPage"

Unit: milliseconds

  • 8.4.4: 82
  • 9.2: 80

Reload of Main.WebHome without UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/get/Main/WebHome"

Unit: milliseconds

  • 8.4.4: 8
  • 9.2: 8

Reload of Main.WebHome with UI

dumbbench -p 0.1 -i 1000 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/view/Main/WebHome"

Unit: milliseconds

  • 8.4.4: 85
  • 9.2: 86

SOLR

Full SOLR reindex

Unit: seconds

Delete the data/solr folder, restart, load home page and calculate the time of activity of the SOLR index thread using Yourkit (Yourkit is slowing down a bit all that but what is important is the difference anyway).

  • 8.4.4: 53
  • 9.2: 56

SOLR sync

Only the thread determining what need to be indexed and not the actual indexing.

when index is empty

Unit: milliseconds

  • 8.4.4: 906
  • 9.2: 1611

when there is nothing to do

Unit: milliseconds

  • 8.4.4: 406
  • 9.2: 694

Search

XWiki is doing nothing on background and everything is both in server and client cache already. Values are calculated using dumbbench (image/js/css/etc. resources are not taken into account).

Unit: milliseconds

Result of search finding lots of results

Login with Admin user and make sure hidden document display is enabled.

dumbbench -p 0.1 -i 100 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/view/Main/Search?sort=score&sortOrder=desc&r=1&f_type=DOCUMENT&text=*"
  • 8.4.4: 157
  • 9.2: 172

Result of search finding one result

dumbbench -p 0.1 -i 100 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/view/Main/Search?sort=score&sortOrder=desc&r=1&f_type=DOCUMENT&text=name%3A1000Macros"
  • 8.4.4: 116
  • 9.2: 118

Rendering

Page with 1000 macros without UI

dumbbench -p 0.1 -i 100 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/get/Test/1000Macros"

Unit: milliseconds

  • 8.4.4: 61
  • 9.2: 62

Page with 1000 html macros without UI

dumbbench -p 0.1 -i 100 -- wget -q -o /dev/null -O /dev/null --load-cookies cookies.txt "http://127.0.0.1:8080/xwiki/bin/get/Test/1000HTMLMacros"

Unit: milliseconds

  • 8.4.4: 718
  • 9.2: 683

Heap Memory

Attach Yourkit to get the information.

Unit: MB

Heap Memory after jetty startup

Start jetty and wait until java is not doing anything on both (wait for potential initialization of various stuff like core extension cache, etc). Force garbage collector before looking at "used".

  • 8.4.4: 62 used, 567 allocated
  • 9.2: 59 used, 500 allocated

Heap Memory after full SOLR index

Delete the data/solr folder, restart, load home page then wait until nothing is happening in background. Force garbage collector before looking at "used".

Unit: MB

  • 8.4.4: 162 used, 732 allocated
  • 9.2: 162 used, 785 allocated
Tags:
   

Get Connected