Date: Thu, 28 Mar 2024 19:30:30 -0400 (EDT)
Message-ID: <2045821916.29194.1711668630406@lyrasis1-roc-mp1>
Subject: Exported From Confluence
MIME-Version: 1.0
Content-Type: multipart/related;
boundary="----=_Part_29193_125872329.1711668630405"
------=_Part_29193_125872329.1711668630405
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Content-Location: file:///C:/exported.html
2016-09-26 Performance - Scale meeting
2016-09-26 Performance - Scale meeting
- Time: 11:00AM Eastern Time US (UTC-5)
- Dial-in Number: (712) 775-7035=20
- Status of Current testing=20
- Nick will update tests results. 2 month test appears=
to have failed. Will run tests again on new equipment.
- He will run RDF serialization improvements from Aaron Cobu=
rn on his new hardware.
- Yinlin - 100K Items - 230MB files - 20 Mbs per clie=
nt. Takes about 1 week.
- General agreement on the value of aggregating and su=
mmarizing the results of the tests that we have run so far.
- There is general agreement that it would be good to summar=
ize relative improvements between runs of a given test (graphs in addition =
to any other details/observations)=20
- Factors would be good to include in the summary: =20
- Hardware specifics
- Total execution time
- Average response time over the course of the execution
- Fedora version
- Database type/specs
- Client count
- Colin suggested it might be helpful to have a basic test t=
o establish baseline conditions in the environment to account for variation=
s in network performance characteristics, disk performance, etc. &nbs=
p;=20
- The team sees promise in expending effort to develop=
an automated system for performance tests that would=20
- enable us to perform tests against on a consistent set of =
hardware hardware and network resources
- automatically run the test suite against new tags / =
branches / forked repos?
- focus on time-limited tests with known inputs and expected=
execution time framef.
- Aaron Coburn would like a test for understanding how memor=
y is affected by specific kinds of serializations (Turtle and N-Triples) of=
RDF Sources and differing degrees of concurrency.
Actions<=
/h1>
- Colin will look into putting together a scrip=
t for baselining hardware and network characteristics to be factored into e=
ach test run.
- Nick: Add the log fil=
es to be added to the performance test results on the Test Plan page ( =
;https://wiki.durasp=
ace.org/display/FF/Performance+and+Scalability+Test+Plans ) <=
/li>
- Aaron will create a summary of what he would =
like to see out of a test.
- Danny: Summarize the existing test data.
------=_Part_29193_125872329.1711668630405--