SlideShare a Scribd company logo
1 of 38
Download to read offline
PostgreSQL and Benchmarks
Jignesh Shah – Staff Engineer,
ISV Engineering, Sun Microsystems Inc
PostgreSQL East Conference March 2008
About Me
• Working with Sun Microsystems for about 7 1/2 years
> Primarily responsibility at Sun is to make ISV and Open Source
Community Software applications work better on Solaris
• Prior to Sun worked as ERP Consultant
• Worked with various databases (DB2 UDB, PostgreSQL,
MySQL, Progress OpenEdge, Oracle)
• Worked with various ERP (QAD, Lawson) and CRM
(Dispatch-1), etc
• Previous responsibilities also included : Low Cost BIDW
Agenda
• Industry Standard Benchmarks
> SPECjAppServer2004™
> EAStress2004
> TPC-E
> TPC-H
SPECjAppServer2004
SPECjAppServer2004
• SPECjAppServer2004 is the current version
• Review by SPEC required before publishing the result (published on spec.org)
• Metric is JOPS = jAppServer Operations Per Second
• Fine workload to use to measure impacts of database from one version to another (rather
than compare systems, operating systems and/or other databases)
SPECjAppServer2004 Characteristics
• J2EE Application with Database Backend
• Response times do depend on Database
Performance among other things
• Not a micro benchmark for Database but not
exhaustive also
• Typical Single row queries/updates/inserts
• No stored procedures
• Mostly highlighting performance combining J2EE
and database performance together
PostgreSQL's SPECjAppServer2004
Setup
PostgreSQL's SPECjAppServer2004
Performance
• Two published SPECjAppServer2004 result using
Glassfish and PostgreSQL 8.2 on Solaris
> 778.14 JOPS with Glassfish v1
> 813.73 JOPS with Glassfish v2
• PostgreSQL is in top category in terms of overall
low price and price/performance
Mandatory Disclosure:
SPECjAppServer2004 JOPS@standard
Sun Fire X4200 M2 (4 chips, 8 cores) - 813.73 SPECjAppServer2004 JOPS@Standard
Sun Fire X4200 M2 (6 chips, 12cores) - 778.14 SPECjAppServer2004 JOPS@Standard
SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. All results from www.spec.org as of Jan 8,2008
PostgreSQL Conf Parameters
Used in SPECjAppServer2004 (v8.2)
shared_buffers=3500MB
temp_buffers = 1000
work_mem=100MB
maintenance_work_mem = 512MB
wal_sync_method = fdatasync
full_page_writes = off
wal_buffers = 2300
commit_delay = 10
checkpoint_segments = 256
enable_seqscan = off
random_page_cost = 1.5
cpu_tuple_cost = 0.001
cpu_index_tuple_cost = 0.0005
cpu_operator_cost = 0.00025
effective_cache_size = 40GB
stats_start_collector = off
default_transaction_isolation = read committed
deadlock_timeout = 1000
EAStress2004
EAStress2004
• EAStress2004 is RESEARCH mode of SPECjAppServer2004
• No review from SPEC required
• Metric of EAStress2004 (HASOPM) is not equivalent and hence should not be compared to
metric of SpecJAppServer2004 (JOPS)
• Fine workload to use to measure impacts of database from one version to another (rather
than compare systems, operating systems and/or other databases)
EAStress2004 Characteristics
• In lot of ways subset to SPECjAppServer2004 but
not equivalent as SPECjAppserver2004 has more
added workload tasks
• Has potential to be put into regression test suite for
PostgreSQL
• Stresses IO, Scalability, Response times
PostgreSQL's EAStress2004
Performance
EAStress2004 HASOPM – Hundreds of Application Server Operations Per Minute
SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation.
PostgreSQL 8.2 (32-bit)
PostgreSQL 8.3 (64-bit)
0 100 200 300 400 500 600 700
EAStress2004 with PostgreSQL
EAStress Metric (HASOPM)
46% improvement just by
changing the database
underneath it
Highlights database
performance impact to
EAStress
Differences between 8.3/8.2:
• 64-bit vs 32-bit
• sync_commit=false
• Higher shared_buffers
**Missing data point with 8.3
(32-bit) which could have
been very helpful
PostgreSQL Conf Parameters
Used in EAStress2004 (v8.3)
shared_buffers=8000MB
temp_buffers = 8MB
work_mem=1MB
maintenance_work_mem = 512MB
wal_sync_method = fdatasync
full_page_writes = off
wal_buffers = 2500
commit_delay = 10
checkpoint_segments = 256
synchronous_commit=false
enable_seqscan = off
random_page_cost = 1.5
cpu_tuple_cost = 0.001
cpu_index_tuple_cost = 0.0005
cpu_operator_cost = 0.00025
effective_cache_size = 4GB
update_process_title=off
default_transaction_isolation = read committed
deadlock_timeout = 1000
TPC-E
TPC-E Highlights
● Complex schema
● Referential Integrity
● Less partitionable
● Increase # of trans
● Transaction Frames
● Non-primary key access
to data
● Data access
requirements (RAID)
● Complex transaction
queries
●
Extensive foreign key
relationships
● TPC provided core
components
TPC-E Sample Setup
System Under Test
Driver Tier A Tier B
Data
Data
Data
Database Server
App. Server
App. Server
App. Server
Mandatory
Network
between
Driver and
Tier A
Network
System Under Test
Driver Tier A Tier B
DataData
DataData
DataData
Database ServerDatabase Server
App. ServerApp. Server
App. ServerApp. Server
App. ServerApp. Server
Mandatory
Network
between
Driver and
Tier A
Network
Image From: http://www.tpc.org/tpce/spec/TPCEpresentation.ppt
TPC-E Characteristics
• Brokerage House workload
• Scale factor in terms of active customers to be used
dependent on target performance (roughly Every 1K
customer = 7.1GB raw data to be loaded)
• Lots of Constraints and Foreign keys
• Business logic (part of system) can be implemented
via Stored Procedures or other mechanisms
• Can be used to stress multiple features of database:
Random IO reads/writes, Index performance, stored
procedure performance, response times, etc
How PostgreSQL is behaving right
now with TPC-E?
• Setup process very slow with PostgreSQL
• Table with few rows hot for update (Broker)
• High Random reads which blocks (trade and
trade_history)
• Adding index hurts trade update performance and
less index hurts trade lookup performance
• More contention if client streams are increased
even slightly resulting in drop in performance
How PostgreSQL is behaving right
now with TPC-E?
• With some work, it could be possible to publish a
competitive TPC-E with PostgreSQL
TPC-H
TPC-H
• Industry Standard TPC Benchmark
• Data Warehousing / Decision Support
• Simulates ad hoc environment where there is little
pre-knowledge of the queries
• Simple Schema
> 8 Tables
> 3NF, not Star
TPC-H
• Different scale factors: 100GB, 300GB, 1000GB,
3000GB
• 22 queries
• 2 refresh functions (insert, delete)
• Single-stream component . . . power
• Multi-stream component . . . throughput
• Ad-hoc enforced by implemention rules
> Indexes only on primary key, foreign key and date
colums.
How PostgreSQL Behaves
• Power run actually runs a single stream of queries
> Since PostgreSQL can only use one core for query, it is
difficult to use the capabilities of multi-core systems.
• For research purposes, its useful to see how
PostgreSQL performs even in single stream
How PostgreSQL Behaves
• Current runs indicate that without right index(es) it is
hard for PostgreSQL Optimizer to suggest good
plans.
> However index on such huge tables are slow to create, plus you
can never guess the next index required (in realworld BIDW)
> COPY took 02:12:06 while INDEX creations took 11:33:47
> Commercial databases have figured good ways to just live with few
index for this type of workload
• Range Partitioning, Table Partitioning, Clustering
are more important
> Hard to provide single logical view of partitioned table for
inserts/updates. Plus very hard to setup table partitioning which can
be compliant with run rules
How PostgreSQL Behaves
• Query profiles without range-partitioning or Clustering but
with many indexes:
> Queries which are user CPU(core) bound = 1,7,8,12,13,15,19,21
> Queries which are user+sys CPU (core bound)= 2,3,11,15,18
> Queries which are suspiciously idle = 9,17, 20, 22
> Queries return 0 rows immediately = 4, 5, 6,10,14
Summary/Next Step
• Good overall status with SPECjAppServer2004 and EAStress
• EAStress good load for regression testing
• TPC-E with PostgreSQL has room for improvements.
> Highlights hot contention with BROKER table
> Need to work with community to see if it is a schema
problem or some inherent problem in PostgreSQL
• TPC-H with PostgreSQL will require more detailed
investigation
> Figure out problems with broken queries
> Optimizer plan key to performance
> Need to work with community
Acknowledgements
• Performance and Benchmark Team, Sun
> Vince Carbone (TPC-H)
> Glenn Fawcett (TPC-E)
> John Fowler Jr
• ISV- Engineering, Sun
> Tom Daly (SpecJAppServer / EAStress )
More Information
• PostgreSQL Question: <postgresql-question@sun.com>
• Blogs on PostgreSQL
> Josh Berkus: http://blogs.ittoolbox.com/database/soup
> Jignesh Shah: http://blogs.sun.com/jkshah/
> Tom Daly: http://blogs.sun.com/tomdaly/
> Robert Lor: http://blogs.sun.com/robertlor/
• PostgreSQL on Solaris Wiki:
http://wikis.sun.com/display/DBonSolaris/PostgreSQL
• OpenSolaris databases community:
databases-discuss@opensolaris.org
Q & A
Backup Slides/
Additional Information
TPC-E Scaling Design
● DBMS size and metric scales with the number of emulated
customers in the database
● Transactions designed for consistent scaling; independent of
architecture
● Transactions designed to access “any row, any where”.
Increases cross-node & cross schema communications.
● “Any customer emulation” - Any driver can emulate any
customer at any time, and possibly the same customer
simultaneously across drivers.
● All results are comparable
Settlement
Commission
Rate
Account
Permission
Holding
Customer
Taxrate
Customer
Customer
Account
Holding
History
Cash
Transaction
Broker
Watch
Item
Watch
List
Charge
Trade
History
Trade
Trade
Request
Company
Industry
Company
Competitor
Trade
Type
Company
Daily
Market
Last
Trade
Industry
Exchange
Financial
News
Item
Status
Type
Security
News
Xref
Sector
ZipcodeTaxrateAddress
Customer Broker Market
TPC-E Transaction Overview
● Broker Volume – Total potential volume for a subset of brokers of
all Trades in a given sector for a specific customer tier – Single
Frame
● Customer Position – Reports the current market value for each
account of a customer – Single Frame
● Security Detail – Returns all information pertaining to a specific
security; financial, news, stock performance ... - Single Frame
● Trade Status – Status of the most recent trade for a customer –
Single Frame
● Market Watch – Calculates the percentage change in value of the
market capitalization for a set of securities – Multiple Independent
Single Frames
TPC-E Transaction Overview – Con't
●
Trade Lookup – Return all information relating to a specific trade
determined by either: 1) trade-id, or 2) customer-id and a timestamp –
Multiple Independent Frames
● Trade-Update – Same as Trade-Lookup, but modifies the data returned,
i.e. “Settle cash transactions” - Multiple Independent Frames
● Trade Order – Request to buy/sell a quantity of a security for a customer
account either via a market or limit order – Single Multi Frame
Transaction
● Trade Result – The completion of a confirmed Trade Order from the
“Market” - Single Multi Frame Transaction
● Market Feed – Update the last traded values for a security from the
“ticker” (Market Exchange Emulator) – Single Multi Frame Transaction
TPC-E Reported Metrics
● Primary Metrics
● tpsE : qualified throughput metric; total number of
Trade-Result transactions completed in the
measurement interval divided by the measurement
interval in seconds
● $/tpsE : Total 3 year cost divided by the throughput
metric
● Additional Reported Metric
● # of processors, cores and threads
● Durability Redundancy Level
● Database Recovery Time
TPC-H Reporting Requirements
● Scale factor, e.g., @1000GB
● Composite performance metric QphH
● Price/performance . . . $/ QphH
● System availability date
● Results at different scale factors are not
comparable . . . per TPC
TPC-H Reported Metric
● Primary Metrics
● Composite Metric (QphH@size)
● Composite of Power and Throughput metric
● Price/Performance Metric ($/QphH@size)
● Secondary Metrics
● Power Numerical Quantity (QppH@size)
● How fast a single stream of queries perform
● Throughput Numerical Quantity(QthH@size)
● How fast multiple stream of queries perform

More Related Content

What's hot

PostgreSQL HA
PostgreSQL   HAPostgreSQL   HA
PostgreSQL HAharoonm
 
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...Nelson Calero
 
Tanel Poder - Scripts and Tools short
Tanel Poder - Scripts and Tools shortTanel Poder - Scripts and Tools short
Tanel Poder - Scripts and Tools shortTanel Poder
 
(BDT303) Running Spark and Presto on the Netflix Big Data Platform
(BDT303) Running Spark and Presto on the Netflix Big Data Platform(BDT303) Running Spark and Presto on the Netflix Big Data Platform
(BDT303) Running Spark and Presto on the Netflix Big Data PlatformAmazon Web Services
 
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...Flink Forward
 
Presto best practices for Cluster admins, data engineers and analysts
Presto best practices for Cluster admins, data engineers and analystsPresto best practices for Cluster admins, data engineers and analysts
Presto best practices for Cluster admins, data engineers and analystsShubham Tagra
 
PostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldPostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldJignesh Shah
 
PostgreSQL Replication High Availability Methods
PostgreSQL Replication High Availability MethodsPostgreSQL Replication High Availability Methods
PostgreSQL Replication High Availability MethodsMydbops
 
Dynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisationDynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisationOri Reshef
 
Understanding my database through SQL*Plus using the free tool eDB360
Understanding my database through SQL*Plus using the free tool eDB360Understanding my database through SQL*Plus using the free tool eDB360
Understanding my database through SQL*Plus using the free tool eDB360Carlos Sierra
 
PostgreSQL Administration for System Administrators
PostgreSQL Administration for System AdministratorsPostgreSQL Administration for System Administrators
PostgreSQL Administration for System AdministratorsCommand Prompt., Inc
 
Performance Tuning With Oracle ASH and AWR. Part 1 How And What
Performance Tuning With Oracle ASH and AWR. Part 1 How And WhatPerformance Tuning With Oracle ASH and AWR. Part 1 How And What
Performance Tuning With Oracle ASH and AWR. Part 1 How And Whatudaymoogala
 
Oracle Enterprise Manager Cloud Control 13c for DBAs
Oracle Enterprise Manager Cloud Control 13c for DBAsOracle Enterprise Manager Cloud Control 13c for DBAs
Oracle Enterprise Manager Cloud Control 13c for DBAsGokhan Atil
 
PostgreSQL on EXT4, XFS, BTRFS and ZFS
PostgreSQL on EXT4, XFS, BTRFS and ZFSPostgreSQL on EXT4, XFS, BTRFS and ZFS
PostgreSQL on EXT4, XFS, BTRFS and ZFSTomas Vondra
 
What to Expect From Oracle database 19c
What to Expect From Oracle database 19cWhat to Expect From Oracle database 19c
What to Expect From Oracle database 19cMaria Colgan
 
What is new in PostgreSQL 14?
What is new in PostgreSQL 14?What is new in PostgreSQL 14?
What is new in PostgreSQL 14?Mydbops
 
Best Practices for Becoming an Exceptional Postgres DBA
Best Practices for Becoming an Exceptional Postgres DBA Best Practices for Becoming an Exceptional Postgres DBA
Best Practices for Becoming an Exceptional Postgres DBA EDB
 
Mastering PostgreSQL Administration
Mastering PostgreSQL AdministrationMastering PostgreSQL Administration
Mastering PostgreSQL AdministrationEDB
 
Parquet performance tuning: the missing guide
Parquet performance tuning: the missing guideParquet performance tuning: the missing guide
Parquet performance tuning: the missing guideRyan Blue
 

What's hot (20)

PostgreSQL HA
PostgreSQL   HAPostgreSQL   HA
PostgreSQL HA
 
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...
Automate Oracle database patches and upgrades using Fleet Provisioning and Pa...
 
Tanel Poder - Scripts and Tools short
Tanel Poder - Scripts and Tools shortTanel Poder - Scripts and Tools short
Tanel Poder - Scripts and Tools short
 
MyRocks Deep Dive
MyRocks Deep DiveMyRocks Deep Dive
MyRocks Deep Dive
 
(BDT303) Running Spark and Presto on the Netflix Big Data Platform
(BDT303) Running Spark and Presto on the Netflix Big Data Platform(BDT303) Running Spark and Presto on the Netflix Big Data Platform
(BDT303) Running Spark and Presto on the Netflix Big Data Platform
 
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...
Introducing BinarySortedMultiMap - A new Flink state primitive to boost your ...
 
Presto best practices for Cluster admins, data engineers and analysts
Presto best practices for Cluster admins, data engineers and analystsPresto best practices for Cluster admins, data engineers and analysts
Presto best practices for Cluster admins, data engineers and analysts
 
PostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldPostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized World
 
PostgreSQL Replication High Availability Methods
PostgreSQL Replication High Availability MethodsPostgreSQL Replication High Availability Methods
PostgreSQL Replication High Availability Methods
 
Dynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisationDynamic filtering for presto join optimisation
Dynamic filtering for presto join optimisation
 
Understanding my database through SQL*Plus using the free tool eDB360
Understanding my database through SQL*Plus using the free tool eDB360Understanding my database through SQL*Plus using the free tool eDB360
Understanding my database through SQL*Plus using the free tool eDB360
 
PostgreSQL Administration for System Administrators
PostgreSQL Administration for System AdministratorsPostgreSQL Administration for System Administrators
PostgreSQL Administration for System Administrators
 
Performance Tuning With Oracle ASH and AWR. Part 1 How And What
Performance Tuning With Oracle ASH and AWR. Part 1 How And WhatPerformance Tuning With Oracle ASH and AWR. Part 1 How And What
Performance Tuning With Oracle ASH and AWR. Part 1 How And What
 
Oracle Enterprise Manager Cloud Control 13c for DBAs
Oracle Enterprise Manager Cloud Control 13c for DBAsOracle Enterprise Manager Cloud Control 13c for DBAs
Oracle Enterprise Manager Cloud Control 13c for DBAs
 
PostgreSQL on EXT4, XFS, BTRFS and ZFS
PostgreSQL on EXT4, XFS, BTRFS and ZFSPostgreSQL on EXT4, XFS, BTRFS and ZFS
PostgreSQL on EXT4, XFS, BTRFS and ZFS
 
What to Expect From Oracle database 19c
What to Expect From Oracle database 19cWhat to Expect From Oracle database 19c
What to Expect From Oracle database 19c
 
What is new in PostgreSQL 14?
What is new in PostgreSQL 14?What is new in PostgreSQL 14?
What is new in PostgreSQL 14?
 
Best Practices for Becoming an Exceptional Postgres DBA
Best Practices for Becoming an Exceptional Postgres DBA Best Practices for Becoming an Exceptional Postgres DBA
Best Practices for Becoming an Exceptional Postgres DBA
 
Mastering PostgreSQL Administration
Mastering PostgreSQL AdministrationMastering PostgreSQL Administration
Mastering PostgreSQL Administration
 
Parquet performance tuning: the missing guide
Parquet performance tuning: the missing guideParquet performance tuning: the missing guide
Parquet performance tuning: the missing guide
 

Viewers also liked

PostgreSQL performance improvements in 9.5 and 9.6
PostgreSQL performance improvements in 9.5 and 9.6PostgreSQL performance improvements in 9.5 and 9.6
PostgreSQL performance improvements in 9.5 and 9.6Tomas Vondra
 
PostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldPostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldJignesh Shah
 
PostgreSQL and Linux Containers
PostgreSQL and Linux ContainersPostgreSQL and Linux Containers
PostgreSQL and Linux ContainersJignesh Shah
 
PostgreSQL 9.6 Performance-Scalability Improvements
PostgreSQL 9.6 Performance-Scalability ImprovementsPostgreSQL 9.6 Performance-Scalability Improvements
PostgreSQL 9.6 Performance-Scalability ImprovementsPGConf APAC
 
Best Practices of HA and Replication of PostgreSQL in Virtualized Environments
Best Practices of HA and Replication of PostgreSQL in Virtualized EnvironmentsBest Practices of HA and Replication of PostgreSQL in Virtualized Environments
Best Practices of HA and Replication of PostgreSQL in Virtualized EnvironmentsJignesh Shah
 
SFPUG - DVDStore Performance Benchmark and PostgreSQL
SFPUG - DVDStore Performance Benchmark and PostgreSQLSFPUG - DVDStore Performance Benchmark and PostgreSQL
SFPUG - DVDStore Performance Benchmark and PostgreSQLJignesh Shah
 
OLTP Performance Benchmark Review
OLTP Performance Benchmark ReviewOLTP Performance Benchmark Review
OLTP Performance Benchmark ReviewJignesh Shah
 
Introduction to PgBench
Introduction to PgBenchIntroduction to PgBench
Introduction to PgBenchJoshua Drake
 
The Great Debate: PostgreSQL vs MySQL
The Great Debate: PostgreSQL vs MySQLThe Great Debate: PostgreSQL vs MySQL
The Great Debate: PostgreSQL vs MySQLEDB
 
High Availability PostgreSQL with Zalando Patroni
High Availability PostgreSQL with Zalando PatroniHigh Availability PostgreSQL with Zalando Patroni
High Availability PostgreSQL with Zalando PatroniZalando Technology
 
Ten Reasons Why You Should Prefer PostgreSQL to MySQL
Ten Reasons Why You Should Prefer PostgreSQL to MySQLTen Reasons Why You Should Prefer PostgreSQL to MySQL
Ten Reasons Why You Should Prefer PostgreSQL to MySQLanandology
 
PostgreSQL Portland Performance Practice Project - Database Test 2 Howto
PostgreSQL Portland Performance Practice Project - Database Test 2 HowtoPostgreSQL Portland Performance Practice Project - Database Test 2 Howto
PostgreSQL Portland Performance Practice Project - Database Test 2 HowtoMark Wong
 
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"Yandex
 
Elephants vs. Dolphins: Comparing PostgreSQL and MySQL for use in the DoD
Elephants vs. Dolphins:  Comparing PostgreSQL and MySQL for use in the DoDElephants vs. Dolphins:  Comparing PostgreSQL and MySQL for use in the DoD
Elephants vs. Dolphins: Comparing PostgreSQL and MySQL for use in the DoDJamey Hanson
 
Tuning DB2 in a Solaris Environment
Tuning DB2 in a Solaris EnvironmentTuning DB2 in a Solaris Environment
Tuning DB2 in a Solaris EnvironmentJignesh Shah
 

Viewers also liked (20)

PostgreSQL performance improvements in 9.5 and 9.6
PostgreSQL performance improvements in 9.5 and 9.6PostgreSQL performance improvements in 9.5 and 9.6
PostgreSQL performance improvements in 9.5 and 9.6
 
PostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized WorldPostgreSQL High Availability in a Containerized World
PostgreSQL High Availability in a Containerized World
 
PostgreSQL and Linux Containers
PostgreSQL and Linux ContainersPostgreSQL and Linux Containers
PostgreSQL and Linux Containers
 
PostgreSQL 9.6 Performance-Scalability Improvements
PostgreSQL 9.6 Performance-Scalability ImprovementsPostgreSQL 9.6 Performance-Scalability Improvements
PostgreSQL 9.6 Performance-Scalability Improvements
 
Best Practices of HA and Replication of PostgreSQL in Virtualized Environments
Best Practices of HA and Replication of PostgreSQL in Virtualized EnvironmentsBest Practices of HA and Replication of PostgreSQL in Virtualized Environments
Best Practices of HA and Replication of PostgreSQL in Virtualized Environments
 
TPC-H in MongoDB
TPC-H in MongoDBTPC-H in MongoDB
TPC-H in MongoDB
 
SFPUG - DVDStore Performance Benchmark and PostgreSQL
SFPUG - DVDStore Performance Benchmark and PostgreSQLSFPUG - DVDStore Performance Benchmark and PostgreSQL
SFPUG - DVDStore Performance Benchmark and PostgreSQL
 
OLTP Performance Benchmark Review
OLTP Performance Benchmark ReviewOLTP Performance Benchmark Review
OLTP Performance Benchmark Review
 
Introduction to PgBench
Introduction to PgBenchIntroduction to PgBench
Introduction to PgBench
 
The Great Debate: PostgreSQL vs MySQL
The Great Debate: PostgreSQL vs MySQLThe Great Debate: PostgreSQL vs MySQL
The Great Debate: PostgreSQL vs MySQL
 
PostgreSQL and MySQL
PostgreSQL and MySQLPostgreSQL and MySQL
PostgreSQL and MySQL
 
High Availability PostgreSQL with Zalando Patroni
High Availability PostgreSQL with Zalando PatroniHigh Availability PostgreSQL with Zalando Patroni
High Availability PostgreSQL with Zalando Patroni
 
Ten Reasons Why You Should Prefer PostgreSQL to MySQL
Ten Reasons Why You Should Prefer PostgreSQL to MySQLTen Reasons Why You Should Prefer PostgreSQL to MySQL
Ten Reasons Why You Should Prefer PostgreSQL to MySQL
 
Tpc h benchmarking no mysql
Tpc h benchmarking no mysqlTpc h benchmarking no mysql
Tpc h benchmarking no mysql
 
Trabalhando com Logs no PostgreSQL
Trabalhando com Logs no PostgreSQLTrabalhando com Logs no PostgreSQL
Trabalhando com Logs no PostgreSQL
 
PostgreSQL Portland Performance Practice Project - Database Test 2 Howto
PostgreSQL Portland Performance Practice Project - Database Test 2 HowtoPostgreSQL Portland Performance Practice Project - Database Test 2 Howto
PostgreSQL Portland Performance Practice Project - Database Test 2 Howto
 
Postgres Big data
Postgres Big dataPostgres Big data
Postgres Big data
 
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"
Виталий Харисов "История создания БЭМ. Кратко, сбивчиво и неполно"
 
Elephants vs. Dolphins: Comparing PostgreSQL and MySQL for use in the DoD
Elephants vs. Dolphins:  Comparing PostgreSQL and MySQL for use in the DoDElephants vs. Dolphins:  Comparing PostgreSQL and MySQL for use in the DoD
Elephants vs. Dolphins: Comparing PostgreSQL and MySQL for use in the DoD
 
Tuning DB2 in a Solaris Environment
Tuning DB2 in a Solaris EnvironmentTuning DB2 in a Solaris Environment
Tuning DB2 in a Solaris Environment
 

Similar to PostgreSQL and Benchmarks

Problems with PostgreSQL on Multi-core Systems with MultiTerabyte Data
Problems with PostgreSQL on Multi-core Systems with MultiTerabyte DataProblems with PostgreSQL on Multi-core Systems with MultiTerabyte Data
Problems with PostgreSQL on Multi-core Systems with MultiTerabyte DataJignesh Shah
 
Presentación Oracle Database Migración consideraciones 10g/11g/12c
Presentación Oracle Database Migración consideraciones 10g/11g/12cPresentación Oracle Database Migración consideraciones 10g/11g/12c
Presentación Oracle Database Migración consideraciones 10g/11g/12cRonald Francisco Vargas Quesada
 
Oracle ebs capacity_analysisusingstatisticalmethods
Oracle ebs capacity_analysisusingstatisticalmethodsOracle ebs capacity_analysisusingstatisticalmethods
Oracle ebs capacity_analysisusingstatisticalmethodsAjith Narayanan
 
Performance Scenario: Diagnosing and resolving sudden slow down on two node RAC
Performance Scenario: Diagnosing and resolving sudden slow down on two node RACPerformance Scenario: Diagnosing and resolving sudden slow down on two node RAC
Performance Scenario: Diagnosing and resolving sudden slow down on two node RACKristofferson A
 
30334823 my sql-cluster-performance-tuning-best-practices
30334823 my sql-cluster-performance-tuning-best-practices30334823 my sql-cluster-performance-tuning-best-practices
30334823 my sql-cluster-performance-tuning-best-practicesDavid Dhavan
 
Database Fundamental Concepts- Series 1 - Performance Analysis
Database Fundamental Concepts- Series 1 - Performance AnalysisDatabase Fundamental Concepts- Series 1 - Performance Analysis
Database Fundamental Concepts- Series 1 - Performance AnalysisDAGEOP LTD
 
Adding Value in the Cloud with Performance Test
Adding Value in the Cloud with Performance TestAdding Value in the Cloud with Performance Test
Adding Value in the Cloud with Performance TestRodolfo Kohn
 
Technical Introduction to PostgreSQL and PPAS
Technical Introduction to PostgreSQL and PPASTechnical Introduction to PostgreSQL and PPAS
Technical Introduction to PostgreSQL and PPASAshnikbiz
 
ebs-performance-tuning-part-1-470542.pdf
ebs-performance-tuning-part-1-470542.pdfebs-performance-tuning-part-1-470542.pdf
ebs-performance-tuning-part-1-470542.pdfElboulmaniMohamed
 
Performance Stability, Tips and Tricks and Underscores
Performance Stability, Tips and Tricks and UnderscoresPerformance Stability, Tips and Tricks and Underscores
Performance Stability, Tips and Tricks and UnderscoresJitendra Singh
 
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...Daniel Martin
 
Extreme Availability using Oracle 12c Features: Your very last system shutdown?
Extreme Availability using Oracle 12c Features: Your very last system shutdown?Extreme Availability using Oracle 12c Features: Your very last system shutdown?
Extreme Availability using Oracle 12c Features: Your very last system shutdown?Toronto-Oracle-Users-Group
 
Migration to ClickHouse. Practical guide, by Alexander Zaitsev
Migration to ClickHouse. Practical guide, by Alexander ZaitsevMigration to ClickHouse. Practical guide, by Alexander Zaitsev
Migration to ClickHouse. Practical guide, by Alexander ZaitsevAltinity Ltd
 
OOW09 Ebs Tuning Final
OOW09 Ebs Tuning FinalOOW09 Ebs Tuning Final
OOW09 Ebs Tuning Finaljucaab
 
Oracle Database Performance Tuning Basics
Oracle Database Performance Tuning BasicsOracle Database Performance Tuning Basics
Oracle Database Performance Tuning Basicsnitin anjankar
 
How should I monitor my idaa
How should I monitor my idaaHow should I monitor my idaa
How should I monitor my idaaCuneyt Goksu
 
Powering GIS Application with PostgreSQL and Postgres Plus
Powering GIS Application with PostgreSQL and Postgres Plus Powering GIS Application with PostgreSQL and Postgres Plus
Powering GIS Application with PostgreSQL and Postgres Plus Ashnikbiz
 
Whitepaper: Where did my CPU go?
Whitepaper: Where did my CPU go?Whitepaper: Where did my CPU go?
Whitepaper: Where did my CPU go?Kristofferson A
 

Similar to PostgreSQL and Benchmarks (20)

Problems with PostgreSQL on Multi-core Systems with MultiTerabyte Data
Problems with PostgreSQL on Multi-core Systems with MultiTerabyte DataProblems with PostgreSQL on Multi-core Systems with MultiTerabyte Data
Problems with PostgreSQL on Multi-core Systems with MultiTerabyte Data
 
Presentación Oracle Database Migración consideraciones 10g/11g/12c
Presentación Oracle Database Migración consideraciones 10g/11g/12cPresentación Oracle Database Migración consideraciones 10g/11g/12c
Presentación Oracle Database Migración consideraciones 10g/11g/12c
 
Oracle ebs capacity_analysisusingstatisticalmethods
Oracle ebs capacity_analysisusingstatisticalmethodsOracle ebs capacity_analysisusingstatisticalmethods
Oracle ebs capacity_analysisusingstatisticalmethods
 
Performance Scenario: Diagnosing and resolving sudden slow down on two node RAC
Performance Scenario: Diagnosing and resolving sudden slow down on two node RACPerformance Scenario: Diagnosing and resolving sudden slow down on two node RAC
Performance Scenario: Diagnosing and resolving sudden slow down on two node RAC
 
30334823 my sql-cluster-performance-tuning-best-practices
30334823 my sql-cluster-performance-tuning-best-practices30334823 my sql-cluster-performance-tuning-best-practices
30334823 my sql-cluster-performance-tuning-best-practices
 
Database Fundamental Concepts- Series 1 - Performance Analysis
Database Fundamental Concepts- Series 1 - Performance AnalysisDatabase Fundamental Concepts- Series 1 - Performance Analysis
Database Fundamental Concepts- Series 1 - Performance Analysis
 
Adding Value in the Cloud with Performance Test
Adding Value in the Cloud with Performance TestAdding Value in the Cloud with Performance Test
Adding Value in the Cloud with Performance Test
 
Technical Introduction to PostgreSQL and PPAS
Technical Introduction to PostgreSQL and PPASTechnical Introduction to PostgreSQL and PPAS
Technical Introduction to PostgreSQL and PPAS
 
ebs-performance-tuning-part-1-470542.pdf
ebs-performance-tuning-part-1-470542.pdfebs-performance-tuning-part-1-470542.pdf
ebs-performance-tuning-part-1-470542.pdf
 
Performance Stability, Tips and Tricks and Underscores
Performance Stability, Tips and Tricks and UnderscoresPerformance Stability, Tips and Tricks and Underscores
Performance Stability, Tips and Tricks and Underscores
 
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...
IBM Insight 2013 - Aetna's production experience using IBM DB2 Analytics Acce...
 
Extreme Availability using Oracle 12c Features: Your very last system shutdown?
Extreme Availability using Oracle 12c Features: Your very last system shutdown?Extreme Availability using Oracle 12c Features: Your very last system shutdown?
Extreme Availability using Oracle 12c Features: Your very last system shutdown?
 
Migration to ClickHouse. Practical guide, by Alexander Zaitsev
Migration to ClickHouse. Practical guide, by Alexander ZaitsevMigration to ClickHouse. Practical guide, by Alexander Zaitsev
Migration to ClickHouse. Practical guide, by Alexander Zaitsev
 
OOW09 Ebs Tuning Final
OOW09 Ebs Tuning FinalOOW09 Ebs Tuning Final
OOW09 Ebs Tuning Final
 
Oracle Database Performance Tuning Basics
Oracle Database Performance Tuning BasicsOracle Database Performance Tuning Basics
Oracle Database Performance Tuning Basics
 
OOW13 Exadata and ODI with Parallel
OOW13 Exadata and ODI with ParallelOOW13 Exadata and ODI with Parallel
OOW13 Exadata and ODI with Parallel
 
How should I monitor my idaa
How should I monitor my idaaHow should I monitor my idaa
How should I monitor my idaa
 
Oracle SQL Tuning
Oracle SQL TuningOracle SQL Tuning
Oracle SQL Tuning
 
Powering GIS Application with PostgreSQL and Postgres Plus
Powering GIS Application with PostgreSQL and Postgres Plus Powering GIS Application with PostgreSQL and Postgres Plus
Powering GIS Application with PostgreSQL and Postgres Plus
 
Whitepaper: Where did my CPU go?
Whitepaper: Where did my CPU go?Whitepaper: Where did my CPU go?
Whitepaper: Where did my CPU go?
 

More from Jignesh Shah

PostgreSQL Extensions: A deeper look
PostgreSQL Extensions:  A deeper lookPostgreSQL Extensions:  A deeper look
PostgreSQL Extensions: A deeper lookJignesh Shah
 
Deep Dive into RDS PostgreSQL Universe
Deep Dive into RDS PostgreSQL UniverseDeep Dive into RDS PostgreSQL Universe
Deep Dive into RDS PostgreSQL UniverseJignesh Shah
 
Best Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisBest Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisJignesh Shah
 
My experience with embedding PostgreSQL
 My experience with embedding PostgreSQL My experience with embedding PostgreSQL
My experience with embedding PostgreSQLJignesh Shah
 
Best Practices of running PostgreSQL in Virtual Environments
Best Practices of running PostgreSQL in Virtual EnvironmentsBest Practices of running PostgreSQL in Virtual Environments
Best Practices of running PostgreSQL in Virtual EnvironmentsJignesh Shah
 
Understanding PostgreSQL LW Locks
Understanding PostgreSQL LW LocksUnderstanding PostgreSQL LW Locks
Understanding PostgreSQL LW LocksJignesh Shah
 
Introduction to PostgreSQL for System Administrators
Introduction to PostgreSQL for System AdministratorsIntroduction to PostgreSQL for System Administrators
Introduction to PostgreSQL for System AdministratorsJignesh Shah
 

More from Jignesh Shah (7)

PostgreSQL Extensions: A deeper look
PostgreSQL Extensions:  A deeper lookPostgreSQL Extensions:  A deeper look
PostgreSQL Extensions: A deeper look
 
Deep Dive into RDS PostgreSQL Universe
Deep Dive into RDS PostgreSQL UniverseDeep Dive into RDS PostgreSQL Universe
Deep Dive into RDS PostgreSQL Universe
 
Best Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on SolarisBest Practices with PostgreSQL on Solaris
Best Practices with PostgreSQL on Solaris
 
My experience with embedding PostgreSQL
 My experience with embedding PostgreSQL My experience with embedding PostgreSQL
My experience with embedding PostgreSQL
 
Best Practices of running PostgreSQL in Virtual Environments
Best Practices of running PostgreSQL in Virtual EnvironmentsBest Practices of running PostgreSQL in Virtual Environments
Best Practices of running PostgreSQL in Virtual Environments
 
Understanding PostgreSQL LW Locks
Understanding PostgreSQL LW LocksUnderstanding PostgreSQL LW Locks
Understanding PostgreSQL LW Locks
 
Introduction to PostgreSQL for System Administrators
Introduction to PostgreSQL for System AdministratorsIntroduction to PostgreSQL for System Administrators
Introduction to PostgreSQL for System Administrators
 

Recently uploaded

Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...SelfMade bd
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrandmasabamasaba
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfproinshot.com
 
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfonteinmasabamasaba
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfkalichargn70th171
 
BUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptxBUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptxalwaysnagaraju26
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension AidPhilip Schwarz
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is insideshinachiaurasa2
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech studentsHimanshiGarg82
 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfonteinmasabamasaba
 
Define the academic and professional writing..pdf
Define the academic and professional writing..pdfDefine the academic and professional writing..pdf
Define the academic and professional writing..pdfPearlKirahMaeRagusta1
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfryanfarris8
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
ManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxComplianceQuest1
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
 

Recently uploaded (20)

Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdf
 
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
 
BUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptxBUS PASS MANGEMENT SYSTEM USING PHP.pptx
BUS PASS MANGEMENT SYSTEM USING PHP.pptx
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
The title is not connected to what is inside
The title is not connected to what is insideThe title is not connected to what is inside
The title is not connected to what is inside
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students
 
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
%in kaalfontein+277-882-255-28 abortion pills for sale in kaalfontein
 
Define the academic and professional writing..pdf
Define the academic and professional writing..pdfDefine the academic and professional writing..pdf
Define the academic and professional writing..pdf
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
ManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide Deck
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
 

PostgreSQL and Benchmarks

  • 1. PostgreSQL and Benchmarks Jignesh Shah – Staff Engineer, ISV Engineering, Sun Microsystems Inc PostgreSQL East Conference March 2008
  • 2. About Me • Working with Sun Microsystems for about 7 1/2 years > Primarily responsibility at Sun is to make ISV and Open Source Community Software applications work better on Solaris • Prior to Sun worked as ERP Consultant • Worked with various databases (DB2 UDB, PostgreSQL, MySQL, Progress OpenEdge, Oracle) • Worked with various ERP (QAD, Lawson) and CRM (Dispatch-1), etc • Previous responsibilities also included : Low Cost BIDW
  • 3. Agenda • Industry Standard Benchmarks > SPECjAppServer2004™ > EAStress2004 > TPC-E > TPC-H
  • 5. SPECjAppServer2004 • SPECjAppServer2004 is the current version • Review by SPEC required before publishing the result (published on spec.org) • Metric is JOPS = jAppServer Operations Per Second • Fine workload to use to measure impacts of database from one version to another (rather than compare systems, operating systems and/or other databases)
  • 6. SPECjAppServer2004 Characteristics • J2EE Application with Database Backend • Response times do depend on Database Performance among other things • Not a micro benchmark for Database but not exhaustive also • Typical Single row queries/updates/inserts • No stored procedures • Mostly highlighting performance combining J2EE and database performance together
  • 8. PostgreSQL's SPECjAppServer2004 Performance • Two published SPECjAppServer2004 result using Glassfish and PostgreSQL 8.2 on Solaris > 778.14 JOPS with Glassfish v1 > 813.73 JOPS with Glassfish v2 • PostgreSQL is in top category in terms of overall low price and price/performance Mandatory Disclosure: SPECjAppServer2004 JOPS@standard Sun Fire X4200 M2 (4 chips, 8 cores) - 813.73 SPECjAppServer2004 JOPS@Standard Sun Fire X4200 M2 (6 chips, 12cores) - 778.14 SPECjAppServer2004 JOPS@Standard SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. All results from www.spec.org as of Jan 8,2008
  • 9. PostgreSQL Conf Parameters Used in SPECjAppServer2004 (v8.2) shared_buffers=3500MB temp_buffers = 1000 work_mem=100MB maintenance_work_mem = 512MB wal_sync_method = fdatasync full_page_writes = off wal_buffers = 2300 commit_delay = 10 checkpoint_segments = 256 enable_seqscan = off random_page_cost = 1.5 cpu_tuple_cost = 0.001 cpu_index_tuple_cost = 0.0005 cpu_operator_cost = 0.00025 effective_cache_size = 40GB stats_start_collector = off default_transaction_isolation = read committed deadlock_timeout = 1000
  • 11. EAStress2004 • EAStress2004 is RESEARCH mode of SPECjAppServer2004 • No review from SPEC required • Metric of EAStress2004 (HASOPM) is not equivalent and hence should not be compared to metric of SpecJAppServer2004 (JOPS) • Fine workload to use to measure impacts of database from one version to another (rather than compare systems, operating systems and/or other databases)
  • 12. EAStress2004 Characteristics • In lot of ways subset to SPECjAppServer2004 but not equivalent as SPECjAppserver2004 has more added workload tasks • Has potential to be put into regression test suite for PostgreSQL • Stresses IO, Scalability, Response times
  • 13. PostgreSQL's EAStress2004 Performance EAStress2004 HASOPM – Hundreds of Application Server Operations Per Minute SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. PostgreSQL 8.2 (32-bit) PostgreSQL 8.3 (64-bit) 0 100 200 300 400 500 600 700 EAStress2004 with PostgreSQL EAStress Metric (HASOPM) 46% improvement just by changing the database underneath it Highlights database performance impact to EAStress Differences between 8.3/8.2: • 64-bit vs 32-bit • sync_commit=false • Higher shared_buffers **Missing data point with 8.3 (32-bit) which could have been very helpful
  • 14. PostgreSQL Conf Parameters Used in EAStress2004 (v8.3) shared_buffers=8000MB temp_buffers = 8MB work_mem=1MB maintenance_work_mem = 512MB wal_sync_method = fdatasync full_page_writes = off wal_buffers = 2500 commit_delay = 10 checkpoint_segments = 256 synchronous_commit=false enable_seqscan = off random_page_cost = 1.5 cpu_tuple_cost = 0.001 cpu_index_tuple_cost = 0.0005 cpu_operator_cost = 0.00025 effective_cache_size = 4GB update_process_title=off default_transaction_isolation = read committed deadlock_timeout = 1000
  • 15. TPC-E
  • 16. TPC-E Highlights ● Complex schema ● Referential Integrity ● Less partitionable ● Increase # of trans ● Transaction Frames ● Non-primary key access to data ● Data access requirements (RAID) ● Complex transaction queries ● Extensive foreign key relationships ● TPC provided core components
  • 17. TPC-E Sample Setup System Under Test Driver Tier A Tier B Data Data Data Database Server App. Server App. Server App. Server Mandatory Network between Driver and Tier A Network System Under Test Driver Tier A Tier B DataData DataData DataData Database ServerDatabase Server App. ServerApp. Server App. ServerApp. Server App. ServerApp. Server Mandatory Network between Driver and Tier A Network Image From: http://www.tpc.org/tpce/spec/TPCEpresentation.ppt
  • 18. TPC-E Characteristics • Brokerage House workload • Scale factor in terms of active customers to be used dependent on target performance (roughly Every 1K customer = 7.1GB raw data to be loaded) • Lots of Constraints and Foreign keys • Business logic (part of system) can be implemented via Stored Procedures or other mechanisms • Can be used to stress multiple features of database: Random IO reads/writes, Index performance, stored procedure performance, response times, etc
  • 19. How PostgreSQL is behaving right now with TPC-E? • Setup process very slow with PostgreSQL • Table with few rows hot for update (Broker) • High Random reads which blocks (trade and trade_history) • Adding index hurts trade update performance and less index hurts trade lookup performance • More contention if client streams are increased even slightly resulting in drop in performance
  • 20. How PostgreSQL is behaving right now with TPC-E? • With some work, it could be possible to publish a competitive TPC-E with PostgreSQL
  • 21. TPC-H
  • 22. TPC-H • Industry Standard TPC Benchmark • Data Warehousing / Decision Support • Simulates ad hoc environment where there is little pre-knowledge of the queries • Simple Schema > 8 Tables > 3NF, not Star
  • 23. TPC-H • Different scale factors: 100GB, 300GB, 1000GB, 3000GB • 22 queries • 2 refresh functions (insert, delete) • Single-stream component . . . power • Multi-stream component . . . throughput • Ad-hoc enforced by implemention rules > Indexes only on primary key, foreign key and date colums.
  • 24. How PostgreSQL Behaves • Power run actually runs a single stream of queries > Since PostgreSQL can only use one core for query, it is difficult to use the capabilities of multi-core systems. • For research purposes, its useful to see how PostgreSQL performs even in single stream
  • 25. How PostgreSQL Behaves • Current runs indicate that without right index(es) it is hard for PostgreSQL Optimizer to suggest good plans. > However index on such huge tables are slow to create, plus you can never guess the next index required (in realworld BIDW) > COPY took 02:12:06 while INDEX creations took 11:33:47 > Commercial databases have figured good ways to just live with few index for this type of workload • Range Partitioning, Table Partitioning, Clustering are more important > Hard to provide single logical view of partitioned table for inserts/updates. Plus very hard to setup table partitioning which can be compliant with run rules
  • 26. How PostgreSQL Behaves • Query profiles without range-partitioning or Clustering but with many indexes: > Queries which are user CPU(core) bound = 1,7,8,12,13,15,19,21 > Queries which are user+sys CPU (core bound)= 2,3,11,15,18 > Queries which are suspiciously idle = 9,17, 20, 22 > Queries return 0 rows immediately = 4, 5, 6,10,14
  • 27. Summary/Next Step • Good overall status with SPECjAppServer2004 and EAStress • EAStress good load for regression testing • TPC-E with PostgreSQL has room for improvements. > Highlights hot contention with BROKER table > Need to work with community to see if it is a schema problem or some inherent problem in PostgreSQL • TPC-H with PostgreSQL will require more detailed investigation > Figure out problems with broken queries > Optimizer plan key to performance > Need to work with community
  • 28. Acknowledgements • Performance and Benchmark Team, Sun > Vince Carbone (TPC-H) > Glenn Fawcett (TPC-E) > John Fowler Jr • ISV- Engineering, Sun > Tom Daly (SpecJAppServer / EAStress )
  • 29. More Information • PostgreSQL Question: <postgresql-question@sun.com> • Blogs on PostgreSQL > Josh Berkus: http://blogs.ittoolbox.com/database/soup > Jignesh Shah: http://blogs.sun.com/jkshah/ > Tom Daly: http://blogs.sun.com/tomdaly/ > Robert Lor: http://blogs.sun.com/robertlor/ • PostgreSQL on Solaris Wiki: http://wikis.sun.com/display/DBonSolaris/PostgreSQL • OpenSolaris databases community: databases-discuss@opensolaris.org
  • 30. Q & A
  • 32. TPC-E Scaling Design ● DBMS size and metric scales with the number of emulated customers in the database ● Transactions designed for consistent scaling; independent of architecture ● Transactions designed to access “any row, any where”. Increases cross-node & cross schema communications. ● “Any customer emulation” - Any driver can emulate any customer at any time, and possibly the same customer simultaneously across drivers. ● All results are comparable
  • 34. TPC-E Transaction Overview ● Broker Volume – Total potential volume for a subset of brokers of all Trades in a given sector for a specific customer tier – Single Frame ● Customer Position – Reports the current market value for each account of a customer – Single Frame ● Security Detail – Returns all information pertaining to a specific security; financial, news, stock performance ... - Single Frame ● Trade Status – Status of the most recent trade for a customer – Single Frame ● Market Watch – Calculates the percentage change in value of the market capitalization for a set of securities – Multiple Independent Single Frames
  • 35. TPC-E Transaction Overview – Con't ● Trade Lookup – Return all information relating to a specific trade determined by either: 1) trade-id, or 2) customer-id and a timestamp – Multiple Independent Frames ● Trade-Update – Same as Trade-Lookup, but modifies the data returned, i.e. “Settle cash transactions” - Multiple Independent Frames ● Trade Order – Request to buy/sell a quantity of a security for a customer account either via a market or limit order – Single Multi Frame Transaction ● Trade Result – The completion of a confirmed Trade Order from the “Market” - Single Multi Frame Transaction ● Market Feed – Update the last traded values for a security from the “ticker” (Market Exchange Emulator) – Single Multi Frame Transaction
  • 36. TPC-E Reported Metrics ● Primary Metrics ● tpsE : qualified throughput metric; total number of Trade-Result transactions completed in the measurement interval divided by the measurement interval in seconds ● $/tpsE : Total 3 year cost divided by the throughput metric ● Additional Reported Metric ● # of processors, cores and threads ● Durability Redundancy Level ● Database Recovery Time
  • 37. TPC-H Reporting Requirements ● Scale factor, e.g., @1000GB ● Composite performance metric QphH ● Price/performance . . . $/ QphH ● System availability date ● Results at different scale factors are not comparable . . . per TPC
  • 38. TPC-H Reported Metric ● Primary Metrics ● Composite Metric (QphH@size) ● Composite of Power and Throughput metric ● Price/Performance Metric ($/QphH@size) ● Secondary Metrics ● Power Numerical Quantity (QppH@size) ● How fast a single stream of queries perform ● Throughput Numerical Quantity(QthH@size) ● How fast multiple stream of queries perform