SlideShare a Scribd company logo
Speed Up Uber’s Presto
with Alluxio
Chen Liang: Senior Software Engineer@Uber Data Analytics
Beinan Wang: Software Engineer@Alluxio
Data informs every decision at Uber
Marketplace
Pricing
Community
Operations
Growth Marketing Data Science
Compliance
Eats
Presto @ Uber: Numbers
7K
Weekly Active Users
500K
Queries/day
2
Regions
5K
Nodes
15
Clusters
50PB
HDFS bytes read/day
Workloads
Interactive
Ad hoc queries
Batch
Scheduled
Presto Deployment
Alluxio Local Cache: Overview
Production Deployment
● Deployed to 3 clusters, with >200
nodes each
● Plugged in as a local library in
Presto worker
● Leverage Presto workers’ local
NVMe disks
● Selective caching based on cache
filter
https://prestodb.io/blog/2020/06/16/alluxio-datacaching
Challenges Alluxio@Uber
● Challenge #1: Realtime Partition Updates
● Challenge #2: Cluster Membership Change
● Challenge #3: Cache Size Restriction
Challenge #1: Realtime Partition Updates
● At Uber, a lot of tables/partitions are constantly changing
○ Upsert queries constantly into Hudi tables
● Partition id alone as caching key is not sufficient
○ Same partition may have changed in Hive, while Alluxio still caches the
outdated version
● Partitions in cache are outdated
Challenge #1: Realtime Partition Updates
● Solution: Add Hive latest modification time to caching key
○ Previous caching key: hdfs://<path>
○ New caching key: hdfs://<path><mod time>
■ Concatenate last modification time to the path
● New partition with latest modification gets cached
● Tradeoff: outdated partition still present in cache, wasting caching space until
evicted
○ Improving eviction strategy WIP
Challenge #2: Cluster Membership Change
● Cached bytes only present on certain nodes
○ SOFT_AFFINITY
● Presto worker nodes may go up/down due to operational activities
○ Node crash
○ Node taken down for maintenance
○ Ad-hoc Node restart
● When node changes, node selection may hit wrong nodes
Challenge #2: Cluster Membership Change
Presto Coordinator
Presto Worker#0 Presto Worker#1 Presto Worker#2
key=4
Currently, simple hash mod based node lookup : key 4 % 3 nodes = worker # 1
Challenge #2: Cluster Membership Change
Presto Coordinator
Presto Worker#0 Presto Worker#1 Presto Worker#2
key=4
Now node#3 goes down, new lookup: key 4 % 2 nodes = 0, but worker#0 does not have the bytes
Challenge #2: Cluster Membership Change
Solution: Node id based consistent
hashing
● All nodes are placed on a virtual
ring
● Relative ordering of nodes on
the ring doesn’t change
● Always look up the key on the
ring
○ Instead of using mode
based hash
● Use replication for better
robustness
Challenge #3: Cache Size Restriction
● At Uber, PBs accessed by Presto queries >> PBs Disks space available on
Worker nodes
○ 50PB of data accessed daily v.s 500GB local disk space
○ Heavy eviction can hurt overall cache performance
● Only a selected set of data can fit into cache:
○ certain tables
○ certain number of partitions
Challenge #3: Cache Size Restriction
● Solution: Cache Filter
○ A mechanism that decide whether to cache a table and how many
partitions
○ Based on a static json config that specifies:
■ which table are eligible for caching
■ how many partitions to cache for each table
● A sample configuration:
{
"databases": [{
"name": "database_foo",
"tables": [{
"name" : "table_bar",
"maxCachedPartitions": 100}]}]
}
Challenge #3: Cache Size Restriction
● Greatly increased cache hit rate
○ From ~65% to >90%
● Notes wrt Cache Filter
○ Manual, static configuration
○ Should be based on traffic pattern, e.g.:
■ Most frequently accessed tables
■ Most common # of partitions being accessed
■ Tables that do not change too frequently
■ Ideally, should be based on shadow caching numbers and table
level metrics
Monitoring/Dashboarding
● Integrated with Uber’s internal metrics platform
● Jmx metrics emitted to Grafana based dashboard
Current Status and Next Steps
● Deployed to production cluster
○ 3 clusters of 200+ nodes each, all nodes on NVMe disks, 500GB cache space per
node
○ Using cache filter to cache ~20 most frequently accessed tables
○ Initial measurement shows great improvement
■ ~1/3 of wall time for input scan (TableScanOperator and
ScanFilterProjectOperator) vs no cache
● Next Steps
○ Onboard more tables/Improve process of table onboarding
■ E.g. shadow cache
○ Better support for changing partitions/Hoodie tables
○ Other optimizations
■ E.g. load balancing between nodes
Table Level Metrics - Motivation
Table Level Metrics - Architecture
Table Level Metrics - Dashboard
Persistent File Level Metadata for Local Cache
● Prevent stale caching
○ The underlying data files might be changed by the 3rd
party frameworks. (This situation might be rare in hive
table, but very common in hudi tables)
● Metadata should be recoverable after server restart
● File or Partition Level Eviction
Future Work
● Performance Tuning
○ Improve cache efficiency
○ Optimized for SATA or mechanical hard drives
● Adopt Shadow Cache
○ Table-level working set estimation
○ Partition-level popularity estimation

More Related Content

What's hot

Building a SIMD Supported Vectorized Native Engine for Spark SQL
Building a SIMD Supported Vectorized Native Engine for Spark SQLBuilding a SIMD Supported Vectorized Native Engine for Spark SQL
Building a SIMD Supported Vectorized Native Engine for Spark SQL
Databricks
 
Hudi architecture, fundamentals and capabilities
Hudi architecture, fundamentals and capabilitiesHudi architecture, fundamentals and capabilities
Hudi architecture, fundamentals and capabilities
Nishith Agarwal
 
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
InfluxData
 
Substrait Overview.pdf
Substrait Overview.pdfSubstrait Overview.pdf
Substrait Overview.pdf
Rinat Abdullin
 
Apache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
Apache Spark Data Source V2 with Wenchen Fan and Gengliang WangApache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
Apache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
Databricks
 
Arbitrary Stateful Aggregations using Structured Streaming in Apache Spark
Arbitrary Stateful Aggregations using Structured Streaming in Apache SparkArbitrary Stateful Aggregations using Structured Streaming in Apache Spark
Arbitrary Stateful Aggregations using Structured Streaming in Apache Spark
Databricks
 
Optimizing Delta/Parquet Data Lakes for Apache Spark
Optimizing Delta/Parquet Data Lakes for Apache SparkOptimizing Delta/Parquet Data Lakes for Apache Spark
Optimizing Delta/Parquet Data Lakes for Apache Spark
Databricks
 
Write Faster SQL with Trino.pdf
Write Faster SQL with Trino.pdfWrite Faster SQL with Trino.pdf
Write Faster SQL with Trino.pdf
Eric Xiao
 
Autoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive ModeAutoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive Mode
Flink Forward
 
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
Altinity Ltd
 
Dynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisationDynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisation
Ori Reshef
 
Dynamic Partition Pruning in Apache Spark
Dynamic Partition Pruning in Apache SparkDynamic Partition Pruning in Apache Spark
Dynamic Partition Pruning in Apache Spark
Databricks
 
Aggregated queries with Druid on terrabytes and petabytes of data
Aggregated queries with Druid on terrabytes and petabytes of dataAggregated queries with Druid on terrabytes and petabytes of data
Aggregated queries with Druid on terrabytes and petabytes of data
Rostislav Pashuto
 
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander ZaitsevClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
Altinity Ltd
 
Fine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark JobsFine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark Jobs
Databricks
 
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
Altinity Ltd
 
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Databricks
 
Airflow introduction
Airflow introductionAirflow introduction
Airflow introduction
Chandler Huang
 
Monitor Apache Spark 3 on Kubernetes using Metrics and Plugins
Monitor Apache Spark 3 on Kubernetes using Metrics and PluginsMonitor Apache Spark 3 on Kubernetes using Metrics and Plugins
Monitor Apache Spark 3 on Kubernetes using Metrics and Plugins
Databricks
 
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEOClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
Altinity Ltd
 

What's hot (20)

Building a SIMD Supported Vectorized Native Engine for Spark SQL
Building a SIMD Supported Vectorized Native Engine for Spark SQLBuilding a SIMD Supported Vectorized Native Engine for Spark SQL
Building a SIMD Supported Vectorized Native Engine for Spark SQL
 
Hudi architecture, fundamentals and capabilities
Hudi architecture, fundamentals and capabilitiesHudi architecture, fundamentals and capabilities
Hudi architecture, fundamentals and capabilities
 
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
InfluxDB IOx Tech Talks: Query Engine Design and the Rust-Based DataFusion in...
 
Substrait Overview.pdf
Substrait Overview.pdfSubstrait Overview.pdf
Substrait Overview.pdf
 
Apache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
Apache Spark Data Source V2 with Wenchen Fan and Gengliang WangApache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
Apache Spark Data Source V2 with Wenchen Fan and Gengliang Wang
 
Arbitrary Stateful Aggregations using Structured Streaming in Apache Spark
Arbitrary Stateful Aggregations using Structured Streaming in Apache SparkArbitrary Stateful Aggregations using Structured Streaming in Apache Spark
Arbitrary Stateful Aggregations using Structured Streaming in Apache Spark
 
Optimizing Delta/Parquet Data Lakes for Apache Spark
Optimizing Delta/Parquet Data Lakes for Apache SparkOptimizing Delta/Parquet Data Lakes for Apache Spark
Optimizing Delta/Parquet Data Lakes for Apache Spark
 
Write Faster SQL with Trino.pdf
Write Faster SQL with Trino.pdfWrite Faster SQL with Trino.pdf
Write Faster SQL with Trino.pdf
 
Autoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive ModeAutoscaling Flink with Reactive Mode
Autoscaling Flink with Reactive Mode
 
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
ClickHouse Data Warehouse 101: The First Billion Rows, by Alexander Zaitsev a...
 
Dynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisationDynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisation
 
Dynamic Partition Pruning in Apache Spark
Dynamic Partition Pruning in Apache SparkDynamic Partition Pruning in Apache Spark
Dynamic Partition Pruning in Apache Spark
 
Aggregated queries with Druid on terrabytes and petabytes of data
Aggregated queries with Druid on terrabytes and petabytes of dataAggregated queries with Druid on terrabytes and petabytes of data
Aggregated queries with Druid on terrabytes and petabytes of data
 
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander ZaitsevClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
ClickHouse in Real Life. Case Studies and Best Practices, by Alexander Zaitsev
 
Fine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark JobsFine Tuning and Enhancing Performance of Apache Spark Jobs
Fine Tuning and Enhancing Performance of Apache Spark Jobs
 
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...HTTP Analytics for 6M requests per second using ClickHouse, by  Alexander Boc...
HTTP Analytics for 6M requests per second using ClickHouse, by Alexander Boc...
 
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
Deep Dive into Spark SQL with Advanced Performance Tuning with Xiao Li & Wenc...
 
Airflow introduction
Airflow introductionAirflow introduction
Airflow introduction
 
Monitor Apache Spark 3 on Kubernetes using Metrics and Plugins
Monitor Apache Spark 3 on Kubernetes using Metrics and PluginsMonitor Apache Spark 3 on Kubernetes using Metrics and Plugins
Monitor Apache Spark 3 on Kubernetes using Metrics and Plugins
 
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEOClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
ClickHouse Query Performance Tips and Tricks, by Robert Hodges, Altinity CEO
 

Similar to Speed Up Uber's Presto with Alluxio

Speed Up Presto at Uber with Alluxio Caching
Speed Up Presto at Uber with Alluxio CachingSpeed Up Presto at Uber with Alluxio Caching
Speed Up Presto at Uber with Alluxio Caching
Alluxio, Inc.
 
Enabling Presto Caching at Uber with Alluxio
Enabling Presto Caching at Uber with AlluxioEnabling Presto Caching at Uber with Alluxio
Enabling Presto Caching at Uber with Alluxio
Alluxio, Inc.
 
Logs @ OVHcloud
Logs @ OVHcloudLogs @ OVHcloud
Logs @ OVHcloud
OVHcloud
 
HBaseCon2017 Improving HBase availability in a multi tenant environment
HBaseCon2017 Improving HBase availability in a multi tenant environmentHBaseCon2017 Improving HBase availability in a multi tenant environment
HBaseCon2017 Improving HBase availability in a multi tenant environment
HBaseCon
 
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBasehbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
Michael Stack
 
How to Develop and Operate Cloud First Data Platforms
How to Develop and Operate Cloud First Data PlatformsHow to Develop and Operate Cloud First Data Platforms
How to Develop and Operate Cloud First Data Platforms
Alluxio, Inc.
 
OpenTSDB: HBaseCon2017
OpenTSDB: HBaseCon2017OpenTSDB: HBaseCon2017
OpenTSDB: HBaseCon2017
HBaseCon
 
The Dark Side Of Go -- Go runtime related problems in TiDB in production
The Dark Side Of Go -- Go runtime related problems in TiDB  in productionThe Dark Side Of Go -- Go runtime related problems in TiDB  in production
The Dark Side Of Go -- Go runtime related problems in TiDB in production
PingCAP
 
Big data should be simple
Big data should be simpleBig data should be simple
Big data should be simple
Dori Waldman
 
Let the Tiger Roar!
Let the Tiger Roar!Let the Tiger Roar!
Let the Tiger Roar!
MongoDB
 
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB AtlasMongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
MongoDB
 
The Google file system
The Google file systemThe Google file system
The Google file system
Sergio Shevchenko
 
Caching and tuning fun for high scalability
Caching and tuning fun for high scalabilityCaching and tuning fun for high scalability
Caching and tuning fun for high scalability
Wim Godden
 
Our Story With ClickHouse at seo.do
Our Story With ClickHouse at seo.doOur Story With ClickHouse at seo.do
Our Story With ClickHouse at seo.do
Metehan Çetinkaya
 
Loadays MySQL
Loadays MySQLLoadays MySQL
Loadays MySQL
lefredbe
 
Data Science in the Cloud @StitchFix
Data Science in the Cloud @StitchFixData Science in the Cloud @StitchFix
Data Science in the Cloud @StitchFix
C4Media
 
August 2013 HUG: Removing the NameNode's memory limitation
August 2013 HUG: Removing the NameNode's memory limitation August 2013 HUG: Removing the NameNode's memory limitation
August 2013 HUG: Removing the NameNode's memory limitation
Yahoo Developer Network
 
Enabling Presto to handle massive scale at lightning speed
Enabling Presto to handle massive scale at lightning speedEnabling Presto to handle massive scale at lightning speed
Enabling Presto to handle massive scale at lightning speed
Shubham Tagra
 
Let the Tiger Roar! - MongoDB 3.0 + WiredTiger
Let the Tiger Roar! - MongoDB 3.0 + WiredTigerLet the Tiger Roar! - MongoDB 3.0 + WiredTiger
Let the Tiger Roar! - MongoDB 3.0 + WiredTiger
Jon Rangel
 
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
MongoDB
 

Similar to Speed Up Uber's Presto with Alluxio (20)

Speed Up Presto at Uber with Alluxio Caching
Speed Up Presto at Uber with Alluxio CachingSpeed Up Presto at Uber with Alluxio Caching
Speed Up Presto at Uber with Alluxio Caching
 
Enabling Presto Caching at Uber with Alluxio
Enabling Presto Caching at Uber with AlluxioEnabling Presto Caching at Uber with Alluxio
Enabling Presto Caching at Uber with Alluxio
 
Logs @ OVHcloud
Logs @ OVHcloudLogs @ OVHcloud
Logs @ OVHcloud
 
HBaseCon2017 Improving HBase availability in a multi tenant environment
HBaseCon2017 Improving HBase availability in a multi tenant environmentHBaseCon2017 Improving HBase availability in a multi tenant environment
HBaseCon2017 Improving HBase availability in a multi tenant environment
 
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBasehbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
hbaseconasia2019 Test-suite for Automating Data-consistency checks on HBase
 
How to Develop and Operate Cloud First Data Platforms
How to Develop and Operate Cloud First Data PlatformsHow to Develop and Operate Cloud First Data Platforms
How to Develop and Operate Cloud First Data Platforms
 
OpenTSDB: HBaseCon2017
OpenTSDB: HBaseCon2017OpenTSDB: HBaseCon2017
OpenTSDB: HBaseCon2017
 
The Dark Side Of Go -- Go runtime related problems in TiDB in production
The Dark Side Of Go -- Go runtime related problems in TiDB  in productionThe Dark Side Of Go -- Go runtime related problems in TiDB  in production
The Dark Side Of Go -- Go runtime related problems in TiDB in production
 
Big data should be simple
Big data should be simpleBig data should be simple
Big data should be simple
 
Let the Tiger Roar!
Let the Tiger Roar!Let the Tiger Roar!
Let the Tiger Roar!
 
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB AtlasMongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
MongoDB World 2019: Packing Up Your Data and Moving to MongoDB Atlas
 
The Google file system
The Google file systemThe Google file system
The Google file system
 
Caching and tuning fun for high scalability
Caching and tuning fun for high scalabilityCaching and tuning fun for high scalability
Caching and tuning fun for high scalability
 
Our Story With ClickHouse at seo.do
Our Story With ClickHouse at seo.doOur Story With ClickHouse at seo.do
Our Story With ClickHouse at seo.do
 
Loadays MySQL
Loadays MySQLLoadays MySQL
Loadays MySQL
 
Data Science in the Cloud @StitchFix
Data Science in the Cloud @StitchFixData Science in the Cloud @StitchFix
Data Science in the Cloud @StitchFix
 
August 2013 HUG: Removing the NameNode's memory limitation
August 2013 HUG: Removing the NameNode's memory limitation August 2013 HUG: Removing the NameNode's memory limitation
August 2013 HUG: Removing the NameNode's memory limitation
 
Enabling Presto to handle massive scale at lightning speed
Enabling Presto to handle massive scale at lightning speedEnabling Presto to handle massive scale at lightning speed
Enabling Presto to handle massive scale at lightning speed
 
Let the Tiger Roar! - MongoDB 3.0 + WiredTiger
Let the Tiger Roar! - MongoDB 3.0 + WiredTigerLet the Tiger Roar! - MongoDB 3.0 + WiredTiger
Let the Tiger Roar! - MongoDB 3.0 + WiredTiger
 
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
MongoDB World 2019: Finding the Right MongoDB Atlas Cluster Size: Does This I...
 

More from Alluxio, Inc.

AI/ML Infra Meetup | ML explainability in Michelangelo
AI/ML Infra Meetup | ML explainability in MichelangeloAI/ML Infra Meetup | ML explainability in Michelangelo
AI/ML Infra Meetup | ML explainability in Michelangelo
Alluxio, Inc.
 
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAGAI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
Alluxio, Inc.
 
AI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning FrameworkAI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning Framework
Alluxio, Inc.
 
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
Alluxio, Inc.
 
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio, Inc.
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio, Inc.
 
Optimizing Data Access for Analytics And AI with Alluxio
Optimizing Data Access for Analytics And AI with AlluxioOptimizing Data Access for Analytics And AI with Alluxio
Optimizing Data Access for Analytics And AI with Alluxio
Alluxio, Inc.
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
Alluxio, Inc.
 
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/MLBig Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
Alluxio, Inc.
 
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
Alluxio, Inc.
 
Alluxio Monthly Webinar | Five Disruptive Trends that Every Data & AI Leader...
Alluxio Monthly Webinar | Five Disruptive Trends that Every  Data & AI Leader...Alluxio Monthly Webinar | Five Disruptive Trends that Every  Data & AI Leader...
Alluxio Monthly Webinar | Five Disruptive Trends that Every Data & AI Leader...
Alluxio, Inc.
 
Data Infra Meetup | FIFO Queues are All You Need for Cache Eviction
Data Infra Meetup | FIFO Queues are All You Need for Cache EvictionData Infra Meetup | FIFO Queues are All You Need for Cache Eviction
Data Infra Meetup | FIFO Queues are All You Need for Cache Eviction
Alluxio, Inc.
 
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio EdgeData Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
Alluxio, Inc.
 
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the CloudData Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
Alluxio, Inc.
 
Data Infra Meetup | ByteDance's Native Parquet Reader
Data Infra Meetup | ByteDance's Native Parquet ReaderData Infra Meetup | ByteDance's Native Parquet Reader
Data Infra Meetup | ByteDance's Native Parquet Reader
Alluxio, Inc.
 
Data Infra Meetup | Uber's Data Storage Evolution
Data Infra Meetup | Uber's Data Storage EvolutionData Infra Meetup | Uber's Data Storage Evolution
Data Infra Meetup | Uber's Data Storage Evolution
Alluxio, Inc.
 
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
Alluxio, Inc.
 
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
Alluxio, Inc.
 
AI Infra Day | The AI Infra in the Generative AI Era
AI Infra Day | The AI Infra in the Generative AI EraAI Infra Day | The AI Infra in the Generative AI Era
AI Infra Day | The AI Infra in the Generative AI Era
Alluxio, Inc.
 
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
Alluxio, Inc.
 

More from Alluxio, Inc. (20)

AI/ML Infra Meetup | ML explainability in Michelangelo
AI/ML Infra Meetup | ML explainability in MichelangeloAI/ML Infra Meetup | ML explainability in Michelangelo
AI/ML Infra Meetup | ML explainability in Michelangelo
 
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAGAI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
AI/ML Infra Meetup | Reducing Prefill for LLM Serving in RAG
 
AI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning FrameworkAI/ML Infra Meetup | Perspective on Deep Learning Framework
AI/ML Infra Meetup | Perspective on Deep Learning Framework
 
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
AI/ML Infra Meetup | Improve Speed and GPU Utilization for Model Training & S...
 
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
 
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed DataAlluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
Alluxio Monthly Webinar | Cloud-Native Model Training on Distributed Data
 
Optimizing Data Access for Analytics And AI with Alluxio
Optimizing Data Access for Analytics And AI with AlluxioOptimizing Data Access for Analytics And AI with Alluxio
Optimizing Data Access for Analytics And AI with Alluxio
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
 
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/MLBig Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
Big Data Bellevue Meetup | Enhancing Python Data Loading in the Cloud for AI/ML
 
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
Alluxio Monthly Webinar | Why a Multi-Cloud Strategy Matters for Your AI Plat...
 
Alluxio Monthly Webinar | Five Disruptive Trends that Every Data & AI Leader...
Alluxio Monthly Webinar | Five Disruptive Trends that Every  Data & AI Leader...Alluxio Monthly Webinar | Five Disruptive Trends that Every  Data & AI Leader...
Alluxio Monthly Webinar | Five Disruptive Trends that Every Data & AI Leader...
 
Data Infra Meetup | FIFO Queues are All You Need for Cache Eviction
Data Infra Meetup | FIFO Queues are All You Need for Cache EvictionData Infra Meetup | FIFO Queues are All You Need for Cache Eviction
Data Infra Meetup | FIFO Queues are All You Need for Cache Eviction
 
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio EdgeData Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
Data Infra Meetup | Accelerate Your Trino/Presto Queries - Gain the Alluxio Edge
 
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the CloudData Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
Data Infra Meetup | Accelerate Distributed PyTorch/Ray Workloads in the Cloud
 
Data Infra Meetup | ByteDance's Native Parquet Reader
Data Infra Meetup | ByteDance's Native Parquet ReaderData Infra Meetup | ByteDance's Native Parquet Reader
Data Infra Meetup | ByteDance's Native Parquet Reader
 
Data Infra Meetup | Uber's Data Storage Evolution
Data Infra Meetup | Uber's Data Storage EvolutionData Infra Meetup | Uber's Data Storage Evolution
Data Infra Meetup | Uber's Data Storage Evolution
 
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
Alluxio Monthly Webinar | Why NFS/NAS on Object Storage May Not Solve Your AI...
 
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
AI Infra Day | Accelerate Your Model Training and Serving with Distributed Ca...
 
AI Infra Day | The AI Infra in the Generative AI Era
AI Infra Day | The AI Infra in the Generative AI EraAI Infra Day | The AI Infra in the Generative AI Era
AI Infra Day | The AI Infra in the Generative AI Era
 
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
AI Infra Day | Hands-on Lab: CV Model Training with PyTorch & Alluxio on Kube...
 

Recently uploaded

Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
Matt Welsh
 
Strategies for Successful Data Migration Tools.pptx
Strategies for Successful Data Migration Tools.pptxStrategies for Successful Data Migration Tools.pptx
Strategies for Successful Data Migration Tools.pptx
varshanayak241
 
Providing Globus Services to Users of JASMIN for Environmental Data Analysis
Providing Globus Services to Users of JASMIN for Environmental Data AnalysisProviding Globus Services to Users of JASMIN for Environmental Data Analysis
Providing Globus Services to Users of JASMIN for Environmental Data Analysis
Globus
 
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.ILBeyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Natan Silnitsky
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
Georgi Kodinov
 
First Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User EndpointsFirst Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User Endpoints
Globus
 
Software Testing Exam imp Ques Notes.pdf
Software Testing Exam imp Ques Notes.pdfSoftware Testing Exam imp Ques Notes.pdf
Software Testing Exam imp Ques Notes.pdf
MayankTawar1
 
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoamOpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
takuyayamamoto1800
 
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Globus
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Globus
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
Globus
 
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
informapgpstrackings
 
Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024
Globus
 
Corporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMSCorporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMS
Tendenci - The Open Source AMS (Association Management Software)
 
GlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote sessionGlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote session
Globus
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
kalichargn70th171
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
Globus
 
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Anthony Dahanne
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus
 
Explore Modern SharePoint Templates for 2024
Explore Modern SharePoint Templates for 2024Explore Modern SharePoint Templates for 2024
Explore Modern SharePoint Templates for 2024
Sharepoint Designs
 

Recently uploaded (20)

Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
 
Strategies for Successful Data Migration Tools.pptx
Strategies for Successful Data Migration Tools.pptxStrategies for Successful Data Migration Tools.pptx
Strategies for Successful Data Migration Tools.pptx
 
Providing Globus Services to Users of JASMIN for Environmental Data Analysis
Providing Globus Services to Users of JASMIN for Environmental Data AnalysisProviding Globus Services to Users of JASMIN for Environmental Data Analysis
Providing Globus Services to Users of JASMIN for Environmental Data Analysis
 
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.ILBeyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
Beyond Event Sourcing - Embracing CRUD for Wix Platform - Java.IL
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
 
First Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User EndpointsFirst Steps with Globus Compute Multi-User Endpoints
First Steps with Globus Compute Multi-User Endpoints
 
Software Testing Exam imp Ques Notes.pdf
Software Testing Exam imp Ques Notes.pdfSoftware Testing Exam imp Ques Notes.pdf
Software Testing Exam imp Ques Notes.pdf
 
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoamOpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
OpenFOAM solver for Helmholtz equation, helmholtzFoam / helmholtzBubbleFoam
 
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
 
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
 
Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024Globus Compute Introduction - GlobusWorld 2024
Globus Compute Introduction - GlobusWorld 2024
 
Corporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMSCorporate Management | Session 3 of 3 | Tendenci AMS
Corporate Management | Session 3 of 3 | Tendenci AMS
 
GlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote sessionGlobusWorld 2024 Opening Keynote session
GlobusWorld 2024 Opening Keynote session
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
 
How to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good PracticesHow to Position Your Globus Data Portal for Success Ten Good Practices
How to Position Your Globus Data Portal for Success Ten Good Practices
 
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
 
Explore Modern SharePoint Templates for 2024
Explore Modern SharePoint Templates for 2024Explore Modern SharePoint Templates for 2024
Explore Modern SharePoint Templates for 2024
 

Speed Up Uber's Presto with Alluxio

  • 1. Speed Up Uber’s Presto with Alluxio Chen Liang: Senior Software Engineer@Uber Data Analytics Beinan Wang: Software Engineer@Alluxio
  • 2. Data informs every decision at Uber Marketplace Pricing Community Operations Growth Marketing Data Science Compliance Eats
  • 3. Presto @ Uber: Numbers 7K Weekly Active Users 500K Queries/day 2 Regions 5K Nodes 15 Clusters 50PB HDFS bytes read/day
  • 6. Alluxio Local Cache: Overview Production Deployment ● Deployed to 3 clusters, with >200 nodes each ● Plugged in as a local library in Presto worker ● Leverage Presto workers’ local NVMe disks ● Selective caching based on cache filter https://prestodb.io/blog/2020/06/16/alluxio-datacaching
  • 7. Challenges Alluxio@Uber ● Challenge #1: Realtime Partition Updates ● Challenge #2: Cluster Membership Change ● Challenge #3: Cache Size Restriction
  • 8. Challenge #1: Realtime Partition Updates ● At Uber, a lot of tables/partitions are constantly changing ○ Upsert queries constantly into Hudi tables ● Partition id alone as caching key is not sufficient ○ Same partition may have changed in Hive, while Alluxio still caches the outdated version ● Partitions in cache are outdated
  • 9. Challenge #1: Realtime Partition Updates ● Solution: Add Hive latest modification time to caching key ○ Previous caching key: hdfs://<path> ○ New caching key: hdfs://<path><mod time> ■ Concatenate last modification time to the path ● New partition with latest modification gets cached ● Tradeoff: outdated partition still present in cache, wasting caching space until evicted ○ Improving eviction strategy WIP
  • 10. Challenge #2: Cluster Membership Change ● Cached bytes only present on certain nodes ○ SOFT_AFFINITY ● Presto worker nodes may go up/down due to operational activities ○ Node crash ○ Node taken down for maintenance ○ Ad-hoc Node restart ● When node changes, node selection may hit wrong nodes
  • 11. Challenge #2: Cluster Membership Change Presto Coordinator Presto Worker#0 Presto Worker#1 Presto Worker#2 key=4 Currently, simple hash mod based node lookup : key 4 % 3 nodes = worker # 1
  • 12. Challenge #2: Cluster Membership Change Presto Coordinator Presto Worker#0 Presto Worker#1 Presto Worker#2 key=4 Now node#3 goes down, new lookup: key 4 % 2 nodes = 0, but worker#0 does not have the bytes
  • 13. Challenge #2: Cluster Membership Change Solution: Node id based consistent hashing ● All nodes are placed on a virtual ring ● Relative ordering of nodes on the ring doesn’t change ● Always look up the key on the ring ○ Instead of using mode based hash ● Use replication for better robustness
  • 14. Challenge #3: Cache Size Restriction ● At Uber, PBs accessed by Presto queries >> PBs Disks space available on Worker nodes ○ 50PB of data accessed daily v.s 500GB local disk space ○ Heavy eviction can hurt overall cache performance ● Only a selected set of data can fit into cache: ○ certain tables ○ certain number of partitions
  • 15. Challenge #3: Cache Size Restriction ● Solution: Cache Filter ○ A mechanism that decide whether to cache a table and how many partitions ○ Based on a static json config that specifies: ■ which table are eligible for caching ■ how many partitions to cache for each table ● A sample configuration: { "databases": [{ "name": "database_foo", "tables": [{ "name" : "table_bar", "maxCachedPartitions": 100}]}] }
  • 16. Challenge #3: Cache Size Restriction ● Greatly increased cache hit rate ○ From ~65% to >90% ● Notes wrt Cache Filter ○ Manual, static configuration ○ Should be based on traffic pattern, e.g.: ■ Most frequently accessed tables ■ Most common # of partitions being accessed ■ Tables that do not change too frequently ■ Ideally, should be based on shadow caching numbers and table level metrics
  • 17. Monitoring/Dashboarding ● Integrated with Uber’s internal metrics platform ● Jmx metrics emitted to Grafana based dashboard
  • 18. Current Status and Next Steps ● Deployed to production cluster ○ 3 clusters of 200+ nodes each, all nodes on NVMe disks, 500GB cache space per node ○ Using cache filter to cache ~20 most frequently accessed tables ○ Initial measurement shows great improvement ■ ~1/3 of wall time for input scan (TableScanOperator and ScanFilterProjectOperator) vs no cache ● Next Steps ○ Onboard more tables/Improve process of table onboarding ■ E.g. shadow cache ○ Better support for changing partitions/Hoodie tables ○ Other optimizations ■ E.g. load balancing between nodes
  • 19. Table Level Metrics - Motivation
  • 20. Table Level Metrics - Architecture
  • 21. Table Level Metrics - Dashboard
  • 22. Persistent File Level Metadata for Local Cache ● Prevent stale caching ○ The underlying data files might be changed by the 3rd party frameworks. (This situation might be rare in hive table, but very common in hudi tables) ● Metadata should be recoverable after server restart ● File or Partition Level Eviction
  • 23. Future Work ● Performance Tuning ○ Improve cache efficiency ○ Optimized for SATA or mechanical hard drives ● Adopt Shadow Cache ○ Table-level working set estimation ○ Partition-level popularity estimation