SlideShare une entreprise Scribd logo
1  sur  21
High Performance Computing
          Cloud point of view


                     Alexey Ragozin
         alexey.ragozin@gmail.com
                          Sep 2012
Massive parallel computing

 I/O bound workload
  • Data mining / machine learning / indexing
  • Focus: Do not move data, process in place
 CPU bound
  • complex simulations / complex math models
  • Focus: Keep all cores busy
 Latency bound
  • Physical process simulations
    (e.g. weather forecast)

  • Focus: Minimize communication latencies
CPU bound task

 Stream of independent tasks
  • Independent tasks
  • Random continuous stream of tasks
  • E.g. video conversion, crawling
 Structured batch jobs
  •   Single batch is split into subtasks for parallel execution
  •   Task may have data dependency on each other
  •   Task may be generated during batch execution
  •   E.g. portfolio risk calculation
Handling task stream in Cloud

               Worker pool
                                                                       incoming
                                     in   g    Task queue
                             p   oll                                   tasks
                                                 queue metrics


                                                    Controler

                                                 adjusts pool size
                                              based on queue metrics




  Simple pattern. Exploiting “elasticy” of cloud. Cost effective.
Structured batch jobs in cloud

Batches are usually more sporadic
 e.g. end of day risk calculations
Task may have cross dependencies
 scheduler should be “cloud-aware”
Supplying tasks with data
 data delivery delay is critical
 worker pool is generally very large
 data sets also could be very large
Data delivery strategy
Push approach
 scheduler controls data delivery
 worker expects data to be available locally
 more opportunities for optimization
 complex
Pull approach
 worker pulls required data from central service
 scheduler is unaware about data sets
 requires scalable data service
 much simpler
What kind of data do we have?

 Working set
 • working set is divided between jobs
 • each portion of working set processed by single job
 • often jobs are producing working set for next
   computation stage
 Reference data
 • exactly same data shared by multiple/all jobs
 • usually static data set
Data distribution problem

Working set
• Spiky work load – especially at the start
• Hard to predict there piece of data will be required
• Caching is ineffective
Reference data set
• Naïve approach will produce huge volume of
  redundant transfers – smart caching required
• Spiky work load
Private grid practice

     HPC Grid
                                    RDBMS
                                      or
                                Data Warehouse




                    Data grid
Data grid, what is it?

• Key/Value storage
• Data distributed across cluster of servers
• RAM is usually used as storage
• Redundant copies provide level of fault tolerant /
  durability
• No single point of failure
• Automatic rebalancing of data when servers
  added/removed from grid
• Capacity and throughput are scaling linearly
Data service for cloud HPC

• Block storage service
  Azure drive / Amazon EBS
  – Lack of shared access to data
• Key / Value storage
  Azure Tables / Amazon Simple DB
  – Pricing: volume + usage
• Blob store
  Azure Tables (blobs) / Amazon S3
  – Pricing: volume + transactions
  – Good read scalability
Use case for caching

 Avoid storage of data in cloud
  • Upload data once per batch and cache in cloud
 Reduce storage cost by reducing number of
  operations
 Save IO bandwidth for shared data
  • Edge caching
  • Routing overlays
Distribution tree /
  Routing overlays




                                Storage
                                Proxy
                                Clients
Switch     Switch      Switch
Task stealing

Task steeling – alternative scheduling approach
Task steeling in widely used for in-process multi-core concurrency

Why use it for cluster task scheduling?
• Stochastic and adaptive
• Can use cost models accounting internal cloud
  topology
• Decently solves problem of data delivery,
  without additional caching
• Unproven for cluster computation, so far
Task stealing

       Worker 1

                     Work backlog is organized in a
                      form of stack
                     Tasks are generated recursively
                     Top of stack – fine grained tasks
fork                 Bottom of stack – coarse
                      grained tasks
fork                 Execution from top of stack
fork
                     Stealing – bottom of stack
       processing
Task stealing

       Worker 1             Worker 2

                    steal



                    fork

                    fork
                            processing
fork




fork
       processing
fork
         done
IO bound workload in cloud

Dawn of Map/Reduce
- high bandwidth interconnects are expensive
- network storage is expensive (due to network cost)
- cheap serves and local processing for keeping costs low
- price – very complex computation model
“Cloud” reality
- network bandwidth is cheap
- disks are already “networked”
- RAM is abundant
Hadoop is cloud unfriendly

Assume I have 50 nodes Hadoop cluster in cloud
What will I gain by adding another 50 nodes?
- Not much, until they are populated with data.
What if I will shut these 50 afterward?
- Effort to populate them with data will be wasted.

Hadoop is coupling execution and storage services
together – you have pay for both even if you use one.
How cloud M/R should look?

• Use cloud storage service and persistent storage
• Streaming M/R processing
• Aggressive use of memory for intermediate data

Peregrine – storeless M/R framework
  http://peregrine_mapreduce.bitbucket.org/
Spark – in-memory M/R framework
  http://www.spark-project.org/
Looking into future

Highly anticipated features
 Scheduler as a Service
  Azure HPC / Amazon SWF
 Simple middleware for organizing caches and
  routing overlays
  Existing solutions are far from simple
 Cloud friendly map/reduce frameworks
  Could provider work hard to offer effective Hadoop
Thank you
http://blog.ragozin.info
- my articles


                                 Alexey Ragozin
                     alexey.ragozin@gmail.com

Contenu connexe

Tendances

load balancing in public cloud ppt
load balancing in public cloud pptload balancing in public cloud ppt
load balancing in public cloud pptKrishna Kumar
 
Tackling Scaling Challenges of Apache Spark at LinkedIn
Tackling Scaling Challenges of Apache Spark at LinkedInTackling Scaling Challenges of Apache Spark at LinkedIn
Tackling Scaling Challenges of Apache Spark at LinkedInDatabricks
 
Simulating Heterogeneous Resources in CloudLightning
Simulating Heterogeneous Resources in CloudLightningSimulating Heterogeneous Resources in CloudLightning
Simulating Heterogeneous Resources in CloudLightningCloudLightning
 
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...DataStax Academy
 
Pig on Tez: Low Latency Data Processing with Big Data
Pig on Tez: Low Latency Data Processing with Big DataPig on Tez: Low Latency Data Processing with Big Data
Pig on Tez: Low Latency Data Processing with Big DataDataWorks Summit
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and FutureDataWorks Summit
 
Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...WMLab,NCU
 
LOAD BALANCING ALGORITHMS
LOAD BALANCING ALGORITHMSLOAD BALANCING ALGORITHMS
LOAD BALANCING ALGORITHMStanmayshah95
 
Hadoop Map Reduce OS
Hadoop Map Reduce OSHadoop Map Reduce OS
Hadoop Map Reduce OSVedant Mane
 
Scalable analytics for iaas cloud availability
Scalable analytics for iaas cloud availabilityScalable analytics for iaas cloud availability
Scalable analytics for iaas cloud availabilityPapitha Velumani
 
Efficient node bootstrapping for decentralised shared-nothing Key-Value Stores
Efficient node bootstrapping for decentralised shared-nothing Key-Value StoresEfficient node bootstrapping for decentralised shared-nothing Key-Value Stores
Efficient node bootstrapping for decentralised shared-nothing Key-Value StoresHan Li
 
High Performance Computing (HPC) in cloud
High Performance Computing (HPC) in cloudHigh Performance Computing (HPC) in cloud
High Performance Computing (HPC) in cloudAccubits Technologies
 
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTING
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTINGLOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTING
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTINGijccsa
 
Tez big datacamp-la-bikas_saha
Tez big datacamp-la-bikas_sahaTez big datacamp-la-bikas_saha
Tez big datacamp-la-bikas_sahaData Con LA
 
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16MLconf
 
Transform your DBMS to drive engagement innovation with Big Data
Transform your DBMS to drive engagement innovation with Big DataTransform your DBMS to drive engagement innovation with Big Data
Transform your DBMS to drive engagement innovation with Big DataAshnikbiz
 
2016 may-countdown-to-postgres-v96-parallel-query
2016 may-countdown-to-postgres-v96-parallel-query2016 may-countdown-to-postgres-v96-parallel-query
2016 may-countdown-to-postgres-v96-parallel-queryAshnikbiz
 
Hadoop Network Performance profile
Hadoop Network Performance profileHadoop Network Performance profile
Hadoop Network Performance profilepramodbiligiri
 
Tune up Yarn and Hive
Tune up Yarn and HiveTune up Yarn and Hive
Tune up Yarn and Hiverxu
 

Tendances (20)

load balancing in public cloud ppt
load balancing in public cloud pptload balancing in public cloud ppt
load balancing in public cloud ppt
 
Tackling Scaling Challenges of Apache Spark at LinkedIn
Tackling Scaling Challenges of Apache Spark at LinkedInTackling Scaling Challenges of Apache Spark at LinkedIn
Tackling Scaling Challenges of Apache Spark at LinkedIn
 
Simulating Heterogeneous Resources in CloudLightning
Simulating Heterogeneous Resources in CloudLightningSimulating Heterogeneous Resources in CloudLightning
Simulating Heterogeneous Resources in CloudLightning
 
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...
Cassandra Summit 2014: Cassandra Compute Cloud: An elastic Cassandra Infrastr...
 
Pig on Tez: Low Latency Data Processing with Big Data
Pig on Tez: Low Latency Data Processing with Big DataPig on Tez: Low Latency Data Processing with Big Data
Pig on Tez: Low Latency Data Processing with Big Data
 
Apache Tez – Present and Future
Apache Tez – Present and FutureApache Tez – Present and Future
Apache Tez – Present and Future
 
Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...Probabilistic consolidation of virtual machines in self organizing cloud data...
Probabilistic consolidation of virtual machines in self organizing cloud data...
 
LOAD BALANCING ALGORITHMS
LOAD BALANCING ALGORITHMSLOAD BALANCING ALGORITHMS
LOAD BALANCING ALGORITHMS
 
Hadoop Map Reduce OS
Hadoop Map Reduce OSHadoop Map Reduce OS
Hadoop Map Reduce OS
 
Scalable analytics for iaas cloud availability
Scalable analytics for iaas cloud availabilityScalable analytics for iaas cloud availability
Scalable analytics for iaas cloud availability
 
Load balancing
Load balancingLoad balancing
Load balancing
 
Efficient node bootstrapping for decentralised shared-nothing Key-Value Stores
Efficient node bootstrapping for decentralised shared-nothing Key-Value StoresEfficient node bootstrapping for decentralised shared-nothing Key-Value Stores
Efficient node bootstrapping for decentralised shared-nothing Key-Value Stores
 
High Performance Computing (HPC) in cloud
High Performance Computing (HPC) in cloudHigh Performance Computing (HPC) in cloud
High Performance Computing (HPC) in cloud
 
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTING
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTINGLOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTING
LOAD BALANCING ALGORITHM TO IMPROVE RESPONSE TIME ON CLOUD COMPUTING
 
Tez big datacamp-la-bikas_saha
Tez big datacamp-la-bikas_sahaTez big datacamp-la-bikas_saha
Tez big datacamp-la-bikas_saha
 
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16
Dr. Ike Nassi, Founder, TidalScale at MLconf NYC - 4/15/16
 
Transform your DBMS to drive engagement innovation with Big Data
Transform your DBMS to drive engagement innovation with Big DataTransform your DBMS to drive engagement innovation with Big Data
Transform your DBMS to drive engagement innovation with Big Data
 
2016 may-countdown-to-postgres-v96-parallel-query
2016 may-countdown-to-postgres-v96-parallel-query2016 may-countdown-to-postgres-v96-parallel-query
2016 may-countdown-to-postgres-v96-parallel-query
 
Hadoop Network Performance profile
Hadoop Network Performance profileHadoop Network Performance profile
Hadoop Network Performance profile
 
Tune up Yarn and Hive
Tune up Yarn and HiveTune up Yarn and Hive
Tune up Yarn and Hive
 

Similaire à Взгляд на облака с точки зрения HPC

High Performance Computing - Cloud Point of View
High Performance Computing - Cloud Point of ViewHigh Performance Computing - Cloud Point of View
High Performance Computing - Cloud Point of Viewaragozin
 
Apache Tez : Accelerating Hadoop Query Processing
Apache Tez : Accelerating Hadoop Query ProcessingApache Tez : Accelerating Hadoop Query Processing
Apache Tez : Accelerating Hadoop Query ProcessingBikas Saha
 
Understanding and building big data Architectures - NoSQL
Understanding and building big data Architectures - NoSQLUnderstanding and building big data Architectures - NoSQL
Understanding and building big data Architectures - NoSQLHyderabad Scalability Meetup
 
Cloud infrastructure. Google File System and MapReduce - Andrii Vozniuk
Cloud infrastructure. Google File System and MapReduce - Andrii VozniukCloud infrastructure. Google File System and MapReduce - Andrii Vozniuk
Cloud infrastructure. Google File System and MapReduce - Andrii VozniukAndrii Vozniuk
 
Cloud Computing - Geektalk
Cloud Computing - GeektalkCloud Computing - Geektalk
Cloud Computing - GeektalkMalisa Ncube
 
Distributed Data processing in a Cloud
Distributed Data processing in a CloudDistributed Data processing in a Cloud
Distributed Data processing in a Cloudelliando dias
 
MEW22 22nd Machine Evaluation Workshop Microsoft
MEW22 22nd Machine Evaluation Workshop MicrosoftMEW22 22nd Machine Evaluation Workshop Microsoft
MEW22 22nd Machine Evaluation Workshop MicrosoftLee Stott
 
Architecture Best Practices on Windows Azure
Architecture Best Practices on Windows AzureArchitecture Best Practices on Windows Azure
Architecture Best Practices on Windows AzureNuno Godinho
 
Applications in the Cloud
Applications in the CloudApplications in the Cloud
Applications in the CloudEberhard Wolff
 
Apache Tez: Accelerating Hadoop Query Processing
Apache Tez: Accelerating Hadoop Query ProcessingApache Tez: Accelerating Hadoop Query Processing
Apache Tez: Accelerating Hadoop Query ProcessingHortonworks
 
Apache Tez - Accelerating Hadoop Data Processing
Apache Tez - Accelerating Hadoop Data ProcessingApache Tez - Accelerating Hadoop Data Processing
Apache Tez - Accelerating Hadoop Data Processinghitesh1892
 
Apache Tez - A New Chapter in Hadoop Data Processing
Apache Tez - A New Chapter in Hadoop Data ProcessingApache Tez - A New Chapter in Hadoop Data Processing
Apache Tez - A New Chapter in Hadoop Data ProcessingDataWorks Summit
 
Secure Networking in Big Data Environments
Secure Networking in Big Data EnvironmentsSecure Networking in Big Data Environments
Secure Networking in Big Data EnvironmentsNapier University
 
Workflowsim escience12
Workflowsim escience12Workflowsim escience12
Workflowsim escience12Weiwei Chen
 
Introduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesIntroduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesJason TC HOU (侯宗成)
 
Apache Tez -- A modern processing engine
Apache Tez -- A modern processing engineApache Tez -- A modern processing engine
Apache Tez -- A modern processing enginebigdatagurus_meetup
 
Apache Hadoop YARN - The Future of Data Processing with Hadoop
Apache Hadoop YARN - The Future of Data Processing with HadoopApache Hadoop YARN - The Future of Data Processing with Hadoop
Apache Hadoop YARN - The Future of Data Processing with HadoopHortonworks
 

Similaire à Взгляд на облака с точки зрения HPC (20)

High Performance Computing - Cloud Point of View
High Performance Computing - Cloud Point of ViewHigh Performance Computing - Cloud Point of View
High Performance Computing - Cloud Point of View
 
Apache Tez : Accelerating Hadoop Query Processing
Apache Tez : Accelerating Hadoop Query ProcessingApache Tez : Accelerating Hadoop Query Processing
Apache Tez : Accelerating Hadoop Query Processing
 
Understanding and building big data Architectures - NoSQL
Understanding and building big data Architectures - NoSQLUnderstanding and building big data Architectures - NoSQL
Understanding and building big data Architectures - NoSQL
 
Cloud infrastructure. Google File System and MapReduce - Andrii Vozniuk
Cloud infrastructure. Google File System and MapReduce - Andrii VozniukCloud infrastructure. Google File System and MapReduce - Andrii Vozniuk
Cloud infrastructure. Google File System and MapReduce - Andrii Vozniuk
 
Cloud computing
Cloud computingCloud computing
Cloud computing
 
Cloud Computing - Geektalk
Cloud Computing - GeektalkCloud Computing - Geektalk
Cloud Computing - Geektalk
 
Distributed Data processing in a Cloud
Distributed Data processing in a CloudDistributed Data processing in a Cloud
Distributed Data processing in a Cloud
 
MEW22 22nd Machine Evaluation Workshop Microsoft
MEW22 22nd Machine Evaluation Workshop MicrosoftMEW22 22nd Machine Evaluation Workshop Microsoft
MEW22 22nd Machine Evaluation Workshop Microsoft
 
Architecture Best Practices on Windows Azure
Architecture Best Practices on Windows AzureArchitecture Best Practices on Windows Azure
Architecture Best Practices on Windows Azure
 
Applications in the Cloud
Applications in the CloudApplications in the Cloud
Applications in the Cloud
 
Apache Tez: Accelerating Hadoop Query Processing
Apache Tez: Accelerating Hadoop Query ProcessingApache Tez: Accelerating Hadoop Query Processing
Apache Tez: Accelerating Hadoop Query Processing
 
Apache Tez - Accelerating Hadoop Data Processing
Apache Tez - Accelerating Hadoop Data ProcessingApache Tez - Accelerating Hadoop Data Processing
Apache Tez - Accelerating Hadoop Data Processing
 
Apache Tez - A New Chapter in Hadoop Data Processing
Apache Tez - A New Chapter in Hadoop Data ProcessingApache Tez - A New Chapter in Hadoop Data Processing
Apache Tez - A New Chapter in Hadoop Data Processing
 
Secure Networking in Big Data Environments
Secure Networking in Big Data EnvironmentsSecure Networking in Big Data Environments
Secure Networking in Big Data Environments
 
Workflowsim escience12
Workflowsim escience12Workflowsim escience12
Workflowsim escience12
 
Introduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network IssuesIntroduction to Cloud Data Center and Network Issues
Introduction to Cloud Data Center and Network Issues
 
Apache Tez -- A modern processing engine
Apache Tez -- A modern processing engineApache Tez -- A modern processing engine
Apache Tez -- A modern processing engine
 
Apache Hadoop YARN - The Future of Data Processing with Hadoop
Apache Hadoop YARN - The Future of Data Processing with HadoopApache Hadoop YARN - The Future of Data Processing with Hadoop
Apache Hadoop YARN - The Future of Data Processing with Hadoop
 
Hadoop
HadoopHadoop
Hadoop
 
try
trytry
try
 

Plus de Olga Lavrentieva

15 10-22 altoros-fact_sheet_st_v4
15 10-22 altoros-fact_sheet_st_v415 10-22 altoros-fact_sheet_st_v4
15 10-22 altoros-fact_sheet_st_v4Olga Lavrentieva
 
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive Performance
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive PerformanceСергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive Performance
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive PerformanceOlga Lavrentieva
 
Андрей Козлов (Altoros): Оптимизация производительности Cassandra
Андрей Козлов (Altoros): Оптимизация производительности CassandraАндрей Козлов (Altoros): Оптимизация производительности Cassandra
Андрей Козлов (Altoros): Оптимизация производительности CassandraOlga Lavrentieva
 
Владимир Иванов (Oracle): Java: прошлое и будущее
Владимир Иванов (Oracle): Java: прошлое и будущееВладимир Иванов (Oracle): Java: прошлое и будущее
Владимир Иванов (Oracle): Java: прошлое и будущееOlga Lavrentieva
 
Brug - Web push notification
Brug  - Web push notificationBrug  - Web push notification
Brug - Web push notificationOlga Lavrentieva
 
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"Olga Lavrentieva
 
Максим Жилинский: "Контейнеры: под капотом"
Максим Жилинский: "Контейнеры: под капотом"Максим Жилинский: "Контейнеры: под капотом"
Максим Жилинский: "Контейнеры: под капотом"Olga Lavrentieva
 
Александр Протасеня: "PayPal. Различные способы интеграции"
Александр Протасеня: "PayPal. Различные способы интеграции"Александр Протасеня: "PayPal. Различные способы интеграции"
Александр Протасеня: "PayPal. Различные способы интеграции"Olga Lavrentieva
 
Сергей Черничков: "Интеграция платежных систем в .Net приложения"
Сергей Черничков: "Интеграция платежных систем в .Net приложения"Сергей Черничков: "Интеграция платежных систем в .Net приложения"
Сергей Черничков: "Интеграция платежных систем в .Net приложения"Olga Lavrentieva
 
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...Антон Шемерей «Single responsibility principle в руби или почему instanceclas...
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...Olga Lavrentieva
 
Егор Воробьёв: «Ruby internals»
Егор Воробьёв: «Ruby internals»Егор Воробьёв: «Ruby internals»
Егор Воробьёв: «Ruby internals»Olga Lavrentieva
 
Андрей Колешко «Что не так с Rails»
Андрей Колешко «Что не так с Rails»Андрей Колешко «Что не так с Rails»
Андрей Колешко «Что не так с Rails»Olga Lavrentieva
 
Дмитрий Савицкий «Ruby Anti Magic Shield»
Дмитрий Савицкий «Ruby Anti Magic Shield»Дмитрий Савицкий «Ruby Anti Magic Shield»
Дмитрий Савицкий «Ruby Anti Magic Shield»Olga Lavrentieva
 
Сергей Алексеев «Парное программирование. Удаленно»
Сергей Алексеев «Парное программирование. Удаленно»Сергей Алексеев «Парное программирование. Удаленно»
Сергей Алексеев «Парное программирование. Удаленно»Olga Lavrentieva
 
«Почему Spark отнюдь не так хорош»
«Почему Spark отнюдь не так хорош»«Почему Spark отнюдь не так хорош»
«Почему Spark отнюдь не так хорош»Olga Lavrentieva
 
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»Olga Lavrentieva
 
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»«Практика построения высокодоступного решения на базе Cloud Foundry Paas»
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»Olga Lavrentieva
 
«Дизайн продвинутых нереляционных схем для Big Data»
«Дизайн продвинутых нереляционных схем для Big Data»«Дизайн продвинутых нереляционных схем для Big Data»
«Дизайн продвинутых нереляционных схем для Big Data»Olga Lavrentieva
 
«Обзор возможностей Open cv»
«Обзор возможностей Open cv»«Обзор возможностей Open cv»
«Обзор возможностей Open cv»Olga Lavrentieva
 
«Нужно больше шин! Eventbus based framework vertx.io»
«Нужно больше шин! Eventbus based framework vertx.io»«Нужно больше шин! Eventbus based framework vertx.io»
«Нужно больше шин! Eventbus based framework vertx.io»Olga Lavrentieva
 

Plus de Olga Lavrentieva (20)

15 10-22 altoros-fact_sheet_st_v4
15 10-22 altoros-fact_sheet_st_v415 10-22 altoros-fact_sheet_st_v4
15 10-22 altoros-fact_sheet_st_v4
 
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive Performance
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive PerformanceСергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive Performance
Сергей Ковалёв (Altoros): Practical Steps to Improve Apache Hive Performance
 
Андрей Козлов (Altoros): Оптимизация производительности Cassandra
Андрей Козлов (Altoros): Оптимизация производительности CassandraАндрей Козлов (Altoros): Оптимизация производительности Cassandra
Андрей Козлов (Altoros): Оптимизация производительности Cassandra
 
Владимир Иванов (Oracle): Java: прошлое и будущее
Владимир Иванов (Oracle): Java: прошлое и будущееВладимир Иванов (Oracle): Java: прошлое и будущее
Владимир Иванов (Oracle): Java: прошлое и будущее
 
Brug - Web push notification
Brug  - Web push notificationBrug  - Web push notification
Brug - Web push notification
 
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"
Александр Ломов: "Reactjs + Haskell + Cloud Foundry = Love"
 
Максим Жилинский: "Контейнеры: под капотом"
Максим Жилинский: "Контейнеры: под капотом"Максим Жилинский: "Контейнеры: под капотом"
Максим Жилинский: "Контейнеры: под капотом"
 
Александр Протасеня: "PayPal. Различные способы интеграции"
Александр Протасеня: "PayPal. Различные способы интеграции"Александр Протасеня: "PayPal. Различные способы интеграции"
Александр Протасеня: "PayPal. Различные способы интеграции"
 
Сергей Черничков: "Интеграция платежных систем в .Net приложения"
Сергей Черничков: "Интеграция платежных систем в .Net приложения"Сергей Черничков: "Интеграция платежных систем в .Net приложения"
Сергей Черничков: "Интеграция платежных систем в .Net приложения"
 
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...Антон Шемерей «Single responsibility principle в руби или почему instanceclas...
Антон Шемерей «Single responsibility principle в руби или почему instanceclas...
 
Егор Воробьёв: «Ruby internals»
Егор Воробьёв: «Ruby internals»Егор Воробьёв: «Ruby internals»
Егор Воробьёв: «Ruby internals»
 
Андрей Колешко «Что не так с Rails»
Андрей Колешко «Что не так с Rails»Андрей Колешко «Что не так с Rails»
Андрей Колешко «Что не так с Rails»
 
Дмитрий Савицкий «Ruby Anti Magic Shield»
Дмитрий Савицкий «Ruby Anti Magic Shield»Дмитрий Савицкий «Ruby Anti Magic Shield»
Дмитрий Савицкий «Ruby Anti Magic Shield»
 
Сергей Алексеев «Парное программирование. Удаленно»
Сергей Алексеев «Парное программирование. Удаленно»Сергей Алексеев «Парное программирование. Удаленно»
Сергей Алексеев «Парное программирование. Удаленно»
 
«Почему Spark отнюдь не так хорош»
«Почему Spark отнюдь не так хорош»«Почему Spark отнюдь не так хорош»
«Почему Spark отнюдь не так хорош»
 
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»
«Cassandra data modeling – моделирование данных для NoSQL СУБД Cassandra»
 
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»«Практика построения высокодоступного решения на базе Cloud Foundry Paas»
«Практика построения высокодоступного решения на базе Cloud Foundry Paas»
 
«Дизайн продвинутых нереляционных схем для Big Data»
«Дизайн продвинутых нереляционных схем для Big Data»«Дизайн продвинутых нереляционных схем для Big Data»
«Дизайн продвинутых нереляционных схем для Big Data»
 
«Обзор возможностей Open cv»
«Обзор возможностей Open cv»«Обзор возможностей Open cv»
«Обзор возможностей Open cv»
 
«Нужно больше шин! Eventbus based framework vertx.io»
«Нужно больше шин! Eventbus based framework vertx.io»«Нужно больше шин! Eventbus based framework vertx.io»
«Нужно больше шин! Eventbus based framework vertx.io»
 

Dernier

DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenHervé Boutemy
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .Alan Dix
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersNicole Novielli
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionDilum Bandara
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 

Dernier (20)

DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache MavenDevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .From Family Reminiscence to Scholarly Archive .
From Family Reminiscence to Scholarly Archive .
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
A Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software DevelopersA Journey Into the Emotions of Software Developers
A Journey Into the Emotions of Software Developers
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
Advanced Computer Architecture – An Introduction
Advanced Computer Architecture – An IntroductionAdvanced Computer Architecture – An Introduction
Advanced Computer Architecture – An Introduction
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 

Взгляд на облака с точки зрения HPC

  • 1. High Performance Computing Cloud point of view Alexey Ragozin alexey.ragozin@gmail.com Sep 2012
  • 2. Massive parallel computing  I/O bound workload • Data mining / machine learning / indexing • Focus: Do not move data, process in place  CPU bound • complex simulations / complex math models • Focus: Keep all cores busy  Latency bound • Physical process simulations (e.g. weather forecast) • Focus: Minimize communication latencies
  • 3. CPU bound task  Stream of independent tasks • Independent tasks • Random continuous stream of tasks • E.g. video conversion, crawling  Structured batch jobs • Single batch is split into subtasks for parallel execution • Task may have data dependency on each other • Task may be generated during batch execution • E.g. portfolio risk calculation
  • 4. Handling task stream in Cloud Worker pool incoming in g Task queue p oll tasks queue metrics Controler adjusts pool size based on queue metrics Simple pattern. Exploiting “elasticy” of cloud. Cost effective.
  • 5. Structured batch jobs in cloud Batches are usually more sporadic  e.g. end of day risk calculations Task may have cross dependencies  scheduler should be “cloud-aware” Supplying tasks with data  data delivery delay is critical  worker pool is generally very large  data sets also could be very large
  • 6. Data delivery strategy Push approach  scheduler controls data delivery  worker expects data to be available locally  more opportunities for optimization  complex Pull approach  worker pulls required data from central service  scheduler is unaware about data sets  requires scalable data service  much simpler
  • 7. What kind of data do we have? Working set • working set is divided between jobs • each portion of working set processed by single job • often jobs are producing working set for next computation stage Reference data • exactly same data shared by multiple/all jobs • usually static data set
  • 8. Data distribution problem Working set • Spiky work load – especially at the start • Hard to predict there piece of data will be required • Caching is ineffective Reference data set • Naïve approach will produce huge volume of redundant transfers – smart caching required • Spiky work load
  • 9. Private grid practice HPC Grid RDBMS or Data Warehouse Data grid
  • 10. Data grid, what is it? • Key/Value storage • Data distributed across cluster of servers • RAM is usually used as storage • Redundant copies provide level of fault tolerant / durability • No single point of failure • Automatic rebalancing of data when servers added/removed from grid • Capacity and throughput are scaling linearly
  • 11. Data service for cloud HPC • Block storage service Azure drive / Amazon EBS – Lack of shared access to data • Key / Value storage Azure Tables / Amazon Simple DB – Pricing: volume + usage • Blob store Azure Tables (blobs) / Amazon S3 – Pricing: volume + transactions – Good read scalability
  • 12. Use case for caching  Avoid storage of data in cloud • Upload data once per batch and cache in cloud  Reduce storage cost by reducing number of operations  Save IO bandwidth for shared data • Edge caching • Routing overlays
  • 13. Distribution tree / Routing overlays Storage Proxy Clients Switch Switch Switch
  • 14. Task stealing Task steeling – alternative scheduling approach Task steeling in widely used for in-process multi-core concurrency Why use it for cluster task scheduling? • Stochastic and adaptive • Can use cost models accounting internal cloud topology • Decently solves problem of data delivery, without additional caching • Unproven for cluster computation, so far
  • 15. Task stealing Worker 1  Work backlog is organized in a form of stack  Tasks are generated recursively  Top of stack – fine grained tasks fork  Bottom of stack – coarse grained tasks fork  Execution from top of stack fork  Stealing – bottom of stack processing
  • 16. Task stealing Worker 1 Worker 2 steal fork fork processing fork fork processing fork done
  • 17. IO bound workload in cloud Dawn of Map/Reduce - high bandwidth interconnects are expensive - network storage is expensive (due to network cost) - cheap serves and local processing for keeping costs low - price – very complex computation model “Cloud” reality - network bandwidth is cheap - disks are already “networked” - RAM is abundant
  • 18. Hadoop is cloud unfriendly Assume I have 50 nodes Hadoop cluster in cloud What will I gain by adding another 50 nodes? - Not much, until they are populated with data. What if I will shut these 50 afterward? - Effort to populate them with data will be wasted. Hadoop is coupling execution and storage services together – you have pay for both even if you use one.
  • 19. How cloud M/R should look? • Use cloud storage service and persistent storage • Streaming M/R processing • Aggressive use of memory for intermediate data Peregrine – storeless M/R framework http://peregrine_mapreduce.bitbucket.org/ Spark – in-memory M/R framework http://www.spark-project.org/
  • 20. Looking into future Highly anticipated features  Scheduler as a Service Azure HPC / Amazon SWF  Simple middleware for organizing caches and routing overlays Existing solutions are far from simple  Cloud friendly map/reduce frameworks Could provider work hard to offer effective Hadoop
  • 21. Thank you http://blog.ragozin.info - my articles Alexey Ragozin alexey.ragozin@gmail.com