1
Scalability
Basics, application to systems, teams and processes
Hello!
I am Fran Ortiz
@fortiz2305
I am Edu Ferro
@eferro
https://www.eferro.net
3
What is scalability?
4
Scalability vs. Performance
5
Performance measures the speed/latency of a single request.
Scalability measures the ability of a system to handle a growing amount of work.
6
Linear Scalability
Ideal case
7
1
Linear Scalability
8
Linear Scalability: ideal case
9
Throughput increases linearly with load.
10
Amdahl’s Law
Contention factor
11
2
Contention factor
Contention factor measures the effect of waiting or queueing for shared resources.
12
Amdahl’s Law: contention factor
13
Contention factor: measures the effect of waiting or queueing for shared resources.
14
0% 1% 2% 5%
Contention factor: examples
Teams
Systems�
15
Nextail Optimization engine
16
Universal Scalability�Law (USL)
Coherence factor
17
3
Coherence factor
Coherence factor refers to the time spent restoring a common view of the world or getting an agreement across different processors.
18
The Universal Scalability Law
19
Coherence factor
Contention factor
😭
Why is coherency quadratic?
N workers = N(N-1) pairs of interactions.
20
USL: examples
Teams
Systems�
21
Nextail BI Subsystem
22
Nextail BI Subsystem
23
Queueing Theory
24
4
Queueing Theory
25
😭
😉
Source: Queueing Theory in Practice
Queues
26
27
28
High variability
Low variability
Queuing: examples
Teams
Systems�
29
Little’s Law
30
Little’s Law: examples
Teams/Processes
31
Conclusions
32
5
Mental models
33
Think about scalability
Nextail
34
35
36
References
37
Thanks!
Any questions ?
You can find us at
38
39