Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Â
A Short History of Performance Engineering
1. Velocity NY
A Short History of
Performance Engineering
Alexander Podelko
alex.podelko@oracle.com
alexanderpodelko.com/blog
@apodelko
October 14, 2013
1
2. About Me
ïŹ
I have specialized in performance for the last
16 years
ïŹ
Currently performance testing and
optimization of Hyperion products at Oracle
ïŹ
Board director at CMG http://cmg.org, organization
of performance and capacity professionals
â Conference November 4-8, 2013 in La Jolla, CA
Disclaimer: The views expressed here are my personal views only and do not necessarily represent those of my
current or previous employers. All brands and trademarks mentioned are the property of their owners.
2
3. There Was [Performance]
Life Even Before Web
ïŹ
Some statements referring to history look
incorrect
ïŹ
Performance engineering history is not well
known
â Not much information readily available
ïŹ
So I decided to share a few bits of
information I know / found
3
4. The Approach
ïŹ
First mature appearances of still relevant
performance notions
â From what I found
â No discussion about further rich history of each
notion
ïŹ
My subjective choices based on very limited
information
4
5. Computing Paradigms
ïŹ
Looks like a new wave of performance
engineering starts 10+ years after new
computing paradigm
ïŹ
Mainframes
â Late 50s
ïŹ
Distributed Systems
â Late 70s
ïŹ
Web
â Mid 90s
ïŹ
? â Mobile, Cloud
5
6. 1966: Instrumentation
ïŹ
1966 â SMF (System Management
Facilities) released as part of OS/360
â Still in use
ïŹBig
Data ?
ïŹDeep
Diagnostics ?
ïŹIT
Operations
Analytics ?
6
7. 1968: Response Times
ïŹ
1968 - Robert Miller (IBM) in his "Response
Time in Man-Computer Conversational
Transactions" paper described several
threshold levels of human attention
â Widely cited by many later researchers
7
8. 1974: Monitoring
ïŹ
1974 â RMF (Resource Measurement
Facility) released as part of MVS
â Still in use
ïŹ
1975 â OMEGAMON for MVS by Candle
â Claimed to be the first real-time monitor
â Acquired by IBM in 2004
8
9. 1975: Community
ïŹ
1975 â The Computer Measurement Group
(CMG) was created, holding annual
conferences since
â Coming Performance and Capacity 2013 by CMG
November 4-8 in La Jolla, CA
http://cmg.org/conference/cmg2013/
â Proceedings available to public (1976-2010)
http://cmg.org/proceedings/
9
10. 1977: Performance Analysis
Tool
ïŹ
1977 â BEST/1 was released by BGS Systems,
capacity and performance management tool
â the first commercial package for computer
performance analysis to be based on analytic
models.
ï§BGS
Systems
was acquired by
BMC Software in
1998
10
11. Late 70s - Distributed
Systems
ïŹ
Distributed Systems
â Client/Server, Three-Tier, N-Tier,
etc.
ïŹ
Less control, less
instrumentation
ïŹ
More need for performance
design and testing
11
12. 1990: Software Performance
Engineering
ïŹ
1990 â Dr. Connie Smith's book
Performance Engineering of Software
Systems was published
â 15 pages of bibliography
"Fix-it-later was once a
viable approach, but it is
now inappropriate and
dangerous"
12
13. Does It Remind You
Anything?
ïŹ
Fix-it-later was a viable approach in the
1970s, but today the original promises no
longer hold, and fix-it-later is archaic and
dangerous. The original premises were:
â Performance problems are rare.
â Hardware is fast and inexpensive.
â It's too expensive to build responsive software.
â You can tune software later, if necessary.
Performance Engineering of Software Systems, 1990.
13
14. 1991: Load Testing Tools
ïŹ
1991 â LoadRunner was released by
Mercury Interactive
â Acquired by HP in 2006 for $4.5B
ïŹ
Performance expertise moves to
performance testing teams
14
15. 1998 ? â End-User Monitoring
ïŹ
1998 â ETEWatch released by Candle
â Application response time monitor
â End-to-End Watch
â Candle acquired by IBM in 2004, then a part of
Tivioli
ïŹ
Anybody know other EUM/RUM roots?
15
16. Mid 90s - Web
Most of existing expertise from mainframe
and distributed eras still applicable to back
end
ïŹ Books by D. Menasce and V. Almeida (1998,
2000, and 2001)
ïŹ
â Applying existing expertise to Web
16
17. 2007: Web Performance
Optimization
ïŹ
2007 â Steve Souders' book High
Performance Web Sites: Essential
Knowledge for Front-End Engineers was
published
ïŹ
New Web-specific expertise
17
19. Takeaways
ïŹ
Check your facts when you refer to history
ïŹ
A lot was done in the past â not always
necessary to re-invent the wheel
ïŹ
The feeling that we are close to solving
performance problems exists last 40+ years
â Probably will stay with us for a while
19