ithome cloud summit: the next generation of data center: machine intelligent cluster
TRANSCRIPT
![Page 1: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/1.jpg)
MachineIntelligentCluster:Thenextgenerationofdatacenter
EvanLin@LinkerNetworks
![Page 2: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/2.jpg)
About meCloud Architect @ Linker Networks
Golang User Group - Co-Organizer
Top 5 Taiwan Golang open source contributor (githubaward)
Developer, Curator, Blogger
![Page 3: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/3.jpg)
Recap Cloud Summit 2016
![Page 4: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/4.jpg)
Agenda• Problems on data center• How machine learning helps• Machine Intelligent Cluster• Applications• Q&A
![Page 5: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/5.jpg)
Data center
![Page 6: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/6.jpg)
• Power consumption• Low usage• Unpredictable peak• Noisy neighbors
Efficiency
• Physical damage• Networking problem• Anomaly• Attack
Risk
Real data center
![Page 7: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/7.jpg)
Power consumption
![Page 8: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/8.jpg)
Low usage and Unpredictable peak
![Page 9: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/9.jpg)
Noisy neighbor
![Page 10: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/10.jpg)
Use machine learning improve DC power consumption
![Page 11: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/11.jpg)
None of your business?
![Page 12: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/12.jpg)
Modern Data center: Machine Cluster
![Page 13: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/13.jpg)
Before machine clusterDB Master:IP: 192.168.1.222
DB Slave:IP: 192.168.1.223
Web Server 1:IP: 192.168.1.101
Web Server 2:IP: 192.168.1.102
Web Server 3:IP: 192.168.1.103
Load Balancer:IP: 1.2.3.4
![Page 14: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/14.jpg)
Container orchestration
Resource arrangement
Scalability
Portability
Automation migration
![Page 15: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/15.jpg)
Resource management
3 Web App Servers2 DB Servers
1 Load Balancer
![Page 16: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/16.jpg)
Scalability
![Page 17: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/17.jpg)
Automation migration
![Page 18: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/18.jpg)
Automation migration
![Page 19: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/19.jpg)
Automation migration
![Page 20: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/20.jpg)
Automation migration
![Page 21: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/21.jpg)
But .. we need better ..
![Page 22: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/22.jpg)
No prediction
![Page 23: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/23.jpg)
How to define scale out threshold?
50 %?
75 %?
25 %?
![Page 24: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/24.jpg)
MachineIntelligentCluster
![Page 25: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/25.jpg)
Efficiency
Maximize Utilization
Operation Optimization
Accident
RiskMitigation
ServiceabilityManagement
Machine Intelligence
Cluster
How MIC helps
![Page 26: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/26.jpg)
Operation Optimization1. Reinforcement learning 2. Adjust thermostat3. Check the reward (CPU performance).
[1]: Refer from https://goo.gl/ly3zyX
![Page 27: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/27.jpg)
Maximize UtilizationAnalyze utilization and reduce working machines to save our customer budget
- Predict utilization trend- Provide auto-scaling threshold
adjustment
![Page 28: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/28.jpg)
Prediction and dynamic threshold
![Page 29: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/29.jpg)
OptimizedScheduler
Node 1 Node 2Node 3
Node 1 Node 2 Node 3
Nginx(CPU 30%)
DB- MySQL(IO 25%)
DB- Mongo(IO 30%)
Apache(CPU 30%)
Backend Process(CPU 35%)
DB- Oracle(IO 35%)
NodeJS(CPU 7%)
Go backend(CPU 8%) Nginx
(CPU 30%)
DB- MySQL(IO 25%)
NodeJS(CPU 7%)
Go backend(CPU 8%)
Apache(CPU 30%)
Backend Process(CPU 35%)
DB- Mongo(IO 30%)
DB- Oracle(IO 35%)
Maximize Utilization
P.S. Not rearrange processes, we change the scheduler to avoid it happen..
![Page 30: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/30.jpg)
Model 1
Serial Number Prediction
S.M.A.R.T. RNN Prediction
Serviceability Management (cont.)
Model 2
![Page 31: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/31.jpg)
Dummy VM Detection Outlier Attack Detection
Mitigate risk
![Page 32: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/32.jpg)
Storage SDN
Zombie Tagging system
![Page 33: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/33.jpg)
Architecture
![Page 34: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/34.jpg)
Cloud Native Architecture
![Page 35: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/35.jpg)
HPC (with GPU) Server
Storage SDN
Storage SDN
Data Collect Probe & Sensor & Smart GW
Visualization
Data Process
Data Analysis &Machine Learning
DCOS/ Kubernetes Spark ML Tensorflow
DCOS / Kubernetes
Cassandra (Storage)
Kafka (Queueing)
Go/Akka (Connector)
Spark (ETL/Streaming)
D3.js
Scikit Learn R
Interactive Dashboard
Jupyter Notebook
Zeppelin
ML Job Scheduler Chronos
MIC System Architecture
![Page 36: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/36.jpg)
Data Agent KafkaSpark
Streaming
Cassandra
Spark ML(Classification,
Clustering)
TensorFlow(Deep
Learning)
Backend ServerAPI
Portal
TensorFlow Predict
SparkML Predict
MIC Data Flow
![Page 37: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/37.jpg)
Applications on MIC
Machine Intelligent Cluster
IOT Gaming 5G NFV E-Commerce
![Page 38: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/38.jpg)
Machine Intelligent Cluster Summary
• Machine cluster with Intelligent• Features• Self-Optimization• Self-Learning• Self-Recovery• Green, Secure and Predictive machine cluster
![Page 39: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/39.jpg)
歡迎訂閱碼天狗
http://weekly.codetengu.com/
![Page 40: iThome Cloud Summit: The next generation of data center: Machine Intelligent Cluster](https://reader034.vdocument.in/reader034/viewer/2022050613/5a6597cb7f8b9ac2368b46af/html5/thumbnails/40.jpg)
ThankYou