Microservices on the Edge: The Infrastructure Impact Ram (Ramki) Krishnan: Industry Consultant, SupportVectors Chris Wright: Vice President and Chief Technologist, Office of Technology at Red Hat
Presentation Outline • Enterpr terprise ise Mi Microser oservices vices Ba Backg kgrounder ounder • Enter erprise prise Infrast rastru ructu cture e Architec itectu ture e Impact act • Mi Microser oservice vices s on th the Edge ge • Edge ge Infras rastru tructur cture Archit hitectur ecture Impact ct • Microser services vices for Virtua ual Network work Function ctions s – New Poten tentia tial l Models dels • Comm mmon on Infrastructur astructure e Archi chitect tectur ure e for Mi Microser oservice vices • Conta ntainer iners, Reso source ce Model delling ling, , SLA Monitorin itoring g and d Poli licy cy Abst stract ractions ions • Open Source/St ce/Standar ndards ds Effor forts ts Next Steps ps
Enterp erpris rise e Micr crose servic vices es - Back ckgr ground nder er Key Microservice Architecture Tenants - Service split based on business need Classic Application Architecture - Decentralized governance – different processes and data stores Any organization will produce a design whose - Module reuse - share common modules such as logging, monitoring structure is a copy of the organization's - Loosely coupled - scale independently, new service flexibility communication structure -- Melvyn Conway, 1967 - Standardize the APIs across microservices Adapted from: https://martinfowler.com/articles/microservices.html
Enterp erpris rise e Micr crose servic vices: es: Re Real-time ime Transa sact ction ion Travel-boo bookin king g Examp mple le Individual services: Seven tiles in the figure. Interaction: Arranged to show which microservices can interact with other microservices. bookFlights service – receives external customer request. Independent scale : The services' different vertical heights represent how they are used in different quantities in relation to one another. Loosely coupled – flexible to add new service: Example -- add discount coupon service Adapted from: https://www.ibm.com/developerworks/cloud/library/cl-bluemix-microservices-in-action-part-1-trs/
Infr frast astruc ructur ure e Arch chitec itectur ure e Imp mpact ct – An Exem empl plary y Depl ploy oyme ment nt Mode del Network Fabric E.g. Leaf/Spine E.g. 3 Stage switches with leaf-spine Clos small buffers Storage Intensive Nodes Memory Intensive Nodes e.g. Red Hat Ceph, Microsoft e.g. SAP Hana, Microsoft SQL Azure storage General Purpose Nodes server, Big Data Apache Spark Compute Intensive Nodes e.g. Web/Middle Tier e.g. Machine Learning, 3D HW Acceleration e.g.: applications HW Acceleration e.g.: Compute application streaming Compute/Network – RDMA /Network – RDMA (RoCE, (RoCE, InfiniBand etc.), InfiniBand etc.), Network crypto HW Acceleration e.g.: HW Acceleration e.g.: GPU, Network/Storage – x86 AES-NI, – x86 AES-NI, Cavium Network crypto – x86 AES- customizable FPGA (Parallel Intel Quick Assist, Cavium (ARM) ThunderX2, Customizable FPGA NI, Cavium ThunderX2 (TLS floating point etc.), RDMA ThunderX2, Customizable FPGA etc. (TLS etc.) etc.) (RoCE, InfiniBand etc.), etc. (TLS, Secure storage etc.) Takeaways - Towards a Converged infrastructure -> Flexible node personality is important - HW acceleration key for deterministic performance, especially for latency sensitive workloads -> Reconfigurable components are highly desirable
Infr frast astruc ructur ure e Arch chitect itectur ure e Imp mpact ct: Re Real-time ime Transa sact ction ion Travel-bo booki king ng Examp mple le General Purpose Nodes Storage Intensive Nodes Memory Intensive Nodes General Purpose Nodes HW Acceleration e.g.: Network HW Acceleration e.g.: Compute HW Acceleration e.g.: Compute crypto – x86 AES-NI, Cavium /Network – RDMA (RoCE, InfiniBand /Network – RDMA (RoCE, InfiniBand ThunderX2 , Customizable FPGA etc. etc.), Network /Storage crypto – x86 etc.), Network crypto – x86 AES-NI, (TLS, IPSEC etc.) AES-NI, Intel Quick Assist, Cavium App Tier – Book Flight Cavium ThunderX2, Customizable ThunderX2, Customizable FPGA etc. FPGA etc. (TLS etc.) Microservice Aggregator (TLS, Secure storage etc.) App Tier – Create Web Front End – Book App Tier – Create Database Tier – Create Storage Tier – Create Customer Microservice Flight Customer Input Customer Microservice Customer Trigger Customer Trigger Network Fabric App Tier – Adjust Database Tier – Adjust Storage Tier – Adjust App Tier – Create Inventory Microservice Inventory Trigger Inventory Trigger Customer Microservice Takeaways - No. of hops proportional to number of microservices, bursty nature of data (Storage I/O block operations, HW Protocol (TCP etc.) offload batching, CPU batch processing etc.) -> service assurance challenge for latency sensitive applications - HW acceleration is key for deterministic performance -> challenge managing heterogeneity - Dynamic service creation -> challenge managing dynamic scaling in a shared heterogenous infrastructure - Database decoupling/scale/PACLEC requirements -> challenge in choosing the right database
Up Next • Enterpr terprise ise Mi Microser oservices vices Ba Backg kgrounder ounder • Enter erprise prise Infrast rastru ructu cture e Architec itectu ture e Impact act • Mi Microser oservice vices s on th the Edge ge • Edge Infrastructure Architecture Impact …
Edg dge Comp mputing ing – Use se Case se Summ mmary Use cases from MEC -- http://www.etsi.org/technologies-clusters/technologies/multi-access-edge-computing Video analytics • Location services • Internet-of-Things (IoT) • Examine in detail a low-latency service such as air quality measurement • Augmented reality • Optimized local content distribution • Data caching •
Edg dge Compu puting ting Io IoT Mi T Micr croser oservices ices: Re Real-time ime Analytic ytics s Air Quality ity Measurement ement Example mple Alerting Microservice: Trigger air quality alerts - leverage statistics and machine learning jobs. Weekly reporting Microservice: Weekly air quality reports – leverage statistics job. Event reporting Microservice: Process dynamic events from Mobile and Web applications. Data Reception, Storage & Transformation Job: Receive raw sensor data from IoT device - store in file system. Perform data validation and transform data into (JSON) format. Takeaways Contextual Enrichment Job: Add device specific - Microservices architecture key to distributed data to transformed JSON format. computing across smart sensors, IoT Statistics Job: Compute moving average/long-term gateways, Edge DC, Cloud DC statistics. - HW acceleration key to deterministic Machine Learning Job : Dynamic performance and reducing edge node footprint learning/refinement of air quality alter threshold. Adapted from: http://airboxlab.github.io/streaming/microservices/iot/spark/real-time/2016/08/29/streaming-microservices.html
Infr frast astruc ructur ure e Arch chitec itectur ure e Imp mpact ct: Re Real-time ime Analyt lytics ics IoT Air Qualit lity y Measu surement ement Examp mple le General Purpose Nodes Storage Intensive Nodes Memory Intensive Nodes Compute Intensive Nodes HW Acceleration e.g.: Network (HDFS etc.) (SQL/NoSQL DB, Spark (Spark ML etc.) crypto – x86 AES-NI, Cavium etc.) HW Acceleration e.g.: Storage crypto ThunderX2, Customizable FPGA etc. – x86 AES-NI, Intel Quick Assist, (TLS, IPSEC etc.) HW Accln.: x86 AVX, ARM Cortex Cavium ThunderX2, Customizable M4 FPGA etc. (TLS, Secure storage etc.) AI Tier - Machine Learning Job Data Reception and Storage Tier – Statistics Analytics Tier – Statistics HW Accln.: x86 AVX, ARM Storage Microservice Streaming Job Cortex M4 Streaming Job HW Accln.: MQTT (TLS etc.) HW Accln.: Secure storage, decryption Storage integrity check Network Fabric Analytics Tier – Alerting Storage Tier – Machine Alerting Microservice Streaming Job Learning Job HW Accln.: Machine Learning HW Accln.: Secure storage, model evaluation Storage integrity check Takeaways (similar to enterprise travel booking example) - No. of hops proportional to number of microservices, bursty nature of data (Storage I/O block operations, CPU batch processing etc.) -> service assurance challenge for latency sensitive applications such as real-time alerting
Up Next • Enterpri terprise se Mi Microser oservices vices Ba Backgr kgroun ounder der • Enterprise erprise Infras rastructu tructure e Architectu itecture e Impact ct • Mi Microser oservice vices s on th the Edge ge • Edge ge Infrast rastructur ructure Archit hitec ectur ture Impact act • Microser services vices for Virtua ual Network work Function ctions s – New Potential Models …
Recommend
More recommend
