MySQL 5.6 Performance

1
Copyright © 2012, Oracle and/or its affiliates. All rights reserved.

Insert Information Protection Policy Classification from Slide 12

MySQL 5.6 Performance:
Tuning and “Best” Practices..

Dimitri KRAVTCHUK
MySQL Performance Architect @Oracle

2
Copyright © 2012, Oracle and/or its affiliates. All rights reserved.

Insert Information Protection Policy Classification from Slide 12

Insert Picture Here

The following is intended to outline our general product
direction. It is intended for information purposes only, and
may not be incorporated into any contract.
It is not a commitment to deliver any material, code, or
functionality, and should not be relied upon in making
purchasing decisions. The development, release, and timing
of any features or functionality described for Oracle’s
products remains at the sole discretion of Oracle.

Are you Dimitri?..
§ Yes, it's me :-)
§ Hello from Paris! ;-)
§ Passionated by Systems and Databases Performance
§ Previous 15 years @Sun Benchmark Center
§ Started working on MySQL Performance since v3.23
§ But during all that time just for fun only ;-)
§ Since last years officially @MySQL Performance full time now
§ http://dimitrik.free.fr/blog / @dimitrik_fr

Agenda
§ Overview
§ Analyzing MySQL Workload
§ Analyzing and Understanding of MySQL Internals
§ Performance improvements in MySQL 5.6 (and 5.7)
§ Benchmark results
§ Pending issues..
§Q&A

Why benchmarking MySQL?..
●

Any solution may look “good enough”...

●

Until it did not reach its limit..

●

And even improved solution may not resist to increasing load..

●

And reach a similar limit..

●

A good benchmark testing may help you understand ahead the
resistance of your solution to incoming potential problems ;-)

●

But keep it in mind:
●

Even a very powerful solution but
leaved in wrong hands may still be
easily broken!... :-)

The Main MySQL Performance Tuning
#1 Best Practice is... ???..

USE YOUR BRAIN !!! :-)

USE YOUR BRAIN !!! :-)
AND THIS IS THE
AND THIS IS THE
MAIN SLIDE! ;-))
MAIN SLIDE! ;-))

Before we started..
●

Please, keep in mind:
●

NOBODY knows everything ;-))

●

There is no absolute true in any topic around..

●

The best answer in most cases will be probably “It depends..” ;-))

●

So, again, “USE YOUR BRAIN!” is the best advice and the best option

●

Also, knowledge and understanding of problems are changing all the
time..

●

And probably even what I'll tell you today is already obsolete. ;-))

●

Enjoy thinking and digging problems deeply ;-))

●

MySQL Performance is a very fun topic (specially current days ;-))

Different Approach for different problems
●

You are discovering a production workload..
●

●

You are trying to understand why your production is running
slower time to time..
●

●

Tracing, debugging, analyzing, discovering of new problems ;-)

You are looking for a new platform for existing production
workload (or new apps under dev.)..
●

●

Full discovery..

Workload simulation, benchmarking, discovering of the next level
issues..

etc...

They all have something in common!
●

Monitoring !..
●

Choose a tool you're familiar with (or install one and become familiar)

●

Use a tool you can completely trust ;-)

●

●

●

●

Keep in mind that sometimes you may need a 5-10sec interval
measurements (or even less).. - not every tool is allowing..
Keep a history of your monitoring to be able to compare “good” and
“bad” cases..
When something is starting to go wrong, usually it'll be not in the place
which was always problematic, but in the place started to have a
different behavior.. - and your goal is to find it ;-)
Always monitor your HW and OS !!!

MySQL Enterprise Monitor (MEM) v.3.0
●

Absolutely fantastic product!
●

Try it! (and buy it if you like it! ;-) - improve your daily work experience!)

Monitoring & Analyzing with dim_STAT (as you ask ;)
●

All my graphs are built with it (download: http://dimitrik.free.fr)
●

All System load stats (CPU, I/O, Network, RAM, Processes,...)

●

Manly for Solaris & Linux, but any other UNIX too :-)

●

Add-Ons for Oracle, MySQL, PostgreSQL, Java, etc.

●

MySQL Add-Ons:
–
–

mysqlLOAD : compact data, multi-host monitoring oriented

–

mysqlWAITS : top wait events from Performance SCHEMA

–

InnodbSTAT : most important data from “show innodb status”

–

innodbMUTEX : monitoring InnoDB mutex waits

–
●

mysqlSTAT : all available data from “show status”

innodbMETRICS : all counters from the METRICS table

And any other you want to add! :-)

Think “Database Performance” from the beginning!
●

Server:
●

●

OS is important! - Linux, Solaris, etc.. (and Windows too!)

●

●

Having faster CPU is still better! 32 cores is good enough ;-)
Right malloc() lib!! (Linux: jemalloc, Solaris: libumem)

Storage:
●

●

SSD helping random access! (index/data) more and more cheaper

●

FS is important! - ZFS, UFS, QFS, VxFS, EXT3, EXT4, XFS, etc..

●

O_DIRECT or not O_DIRECT, AIO or not AIO, and be aware of bugs! ;-)

●

●

Don't use slow disks! (except if this is a test validation goal :-))

Do some generic I/O tests first (Sysbench, IObench, iozone, etc.)

Don't forget network !! :-) (faster is better, 10Gbit is great!)

Seek for your best option..

Performance

Lower Price
Security

What to monitor on Linux?..
●

First of all use the best Linux for you!
●

●

Install & use “jemalloc”; if XFS has problems, use EXT4 (nobarrier!)

●

●

Or ORACLE Linux if you don't know which one to choose ;-)
Use AIO + O_DIRECT, don't use “cfq” IO scheduler!..

Always keep an eye on:
●

RunQueue(!), CPU, RAM, Swap in/outProcesses: vmstat, top, psSTAT

●

Storage level: iostat, ..

●

Network: netLOAD, nicstat, …

●

Overall system activity: # perf top -z
–

●

perf: excellent profiler!

IMPORTANT : system monitoring usually helps to dig DB issues!

Know/ test/ check your platform limits / “features”..
●

My backup is finished on Linux faster than on Solaris same HW
●

●

●

Be sure first there is really no more I/O activity once backup is “finished”
Keep in mind Linux buffering..

Linux distro: MySQL Performance has x4 regression! Fix it!
●

How did you see it? – Our QA test is taking x4 times more time..

●

Which engine? – InnoDB..

●

What is innodb_flush_log_at_trx_commit value? – set to 1.. why?

●

Tried innodb_flush_log_at_trx_commit=2 ?.. – Oh! You fixed it!! Thanks!!

●

Wait, what did you “improve” recently in distro? – FS flushing, why?..

●

Well, the test in fact is proving that you did not “sync” on every fsync()
before, that's all.. But now in your FS flushing you get it fixed ;-)

The Infinitive Loop of Database Tuning...

Application
Application
DB Engine
DB Engine
OS
OS
Server
Server
Storage
Storage

#1 Monitoring
●#1 Monitoring
●#2 Tuning
●#2 Tuning
●#3 Optimization
●#3 Optimization
●#4 Improvement(s)
●#5 …
●#5 …
●...
●...
●goto #1
●goto #1
●

The Infinitive Loop of Database Tuning...
Even if in
Even if in
95% cases
95% cases
the problem
the problem
Is here!!! :-)
Is here!!! :-)

Application
Application
DB Engine
DB Engine

OS
OS
Server
Server
Storage
Storage

#1 Monitoring
●#1 Monitoring
●#2 Tuning
●#2 Tuning
●#3 Optimization
●#3 Optimization
●#5 …
●#5 …
●...
●...
●goto #1
●goto #1
●

MySQL Design

Storage Engines!

MySQL Design
●

Multi-Threaded database
●

●

Simplified data access!

●

●

Fast context switch!
Concurrent access?.. Scalability?..

Storage Engines
●

Initially: MyISAM only

●

Then, with InnoDB: started to match expectations of a “true RDBMS” ;-)

●

Many other engines (MEMORY, CSV, NDB, PBXT, etc.)

●

CREATE TABLE ... ENGINE=<NAME_OF_ENGINE>

●

ALTER TABLE ... ENGINE=<NAME_OF_ENGINE>

●

Did you choose a right Engine?..

MyISAM Engine (since 1994)
●

Non-transactional! / No fast recovery! :-)

●

Cache
●

●

Data => FS cache

●

●

Index only
mysql> flush tables;

Single Writer @Table
●

Main bottleneck! => single writer

●

Solutions: delayed inserts, low priority

●

Query plan: Index forcing may be necessary (hint)

●

Extremely simple and lightweight

Why MySQL + MyISAM was successful ?..
●

Full Text search queries out-of-the-box!

●

SELECT count(*) ... :-))

●

Extremely SIMPLE!
●

my.conf => configuration parameters; mysql.server start / stop

●

Database => directory

●

Table => directory/Table.MYD, Table.MYI, Table.frm

●

$ cp Base1/Table.* /other/mysql/Base2

●

Data binary compatibility! (ex: reports via NFS)

●

Replication ready!

●

Very FAST! (until some limit :-))

●

RW workload is killing.. (but on 2CPU servers it was ok ;-))

RW Benchmark MyISAM vs PostgreSQL (in 2000)

TPS

MySQL

PostgreSQL

Sessions

InnoDB changing the game (since 2001)
●

Row-level locking

●

Index-only reads

●

True transactions / UNDO

●

Auto recovery

●

Double write / Checksums

●

Tablespaces or File-per-Table option

●

Buffer pool

●

Multi-threaded

●

Currently the fastest transactional disk-based MySQL Storage
Engine!

MySQL Performance (traditionally, in the past)
●

Choose the right Engine for each of your table/database
●

Read-Only / Text search => MyISAM

●

Read+Write / Transactions => InnoDB

●

Short/Small Transactions + DB fits in RAM => NDB

●

Tune / Optimize your queries

●

Once scalability limit is reached => go for Distributed:
●

●

Master / Slave(s) => role-based workload

●

●

Sharding
Any other similar :-)

Scalability = Main Performance Problem!...
●

But with Big Users on that time anyway: Google, Facebook, Amazon..

Things are changing constantly, stay tuned ;-)
●

MySQL/InnoDB Scalability:
●

●

2008 : up to 4CPU cores

●

2009 : up to 16CPU cores (+Sun)

●

2010 : up to 32CPU cores (+Oracle)

●

2012 : up to 48CPU cores..

●

2014 : …?? ;-)

●

●

2007 : up to 2CPU...

NOTE: on the same HW performance is better from version to version!

InnoDB today:
●

At least x4-8 times better performance than 2-3 years ago ;-)

●

Capable of over 100K 300K 500K QPS(!) + FTS & Memcached

Hope you did not miss it ;-) (2)

Hope you did not miss it ;-) (3)

How easy is to see the same
in Production now?.. ;-)

Starting points
●

What are your network limits?..
●

●

●

Latency? Max throughput? What CPU% is spent just for network?
Do you use prepared statements? (reducing traffic)

Can you use persistent connections?
●

●

Greatly improved in 5.6, yet more in 5.7 (55K Connect/s in 5.7 currently)

●

Higher QPS if more queries executed before disconnect!

●

●

Connect / Disconnect has its limits..

Thread cache size matters!

Do you use transactions on read-only requests?..
●

●

QPS is improved since 5.6 and yet more in 5.7
But you cannot get a rid from a traffic overhead due BEGIN / COMMIT
exchanges

Analyzing MySQL Workload
●

Understand the load first :
●

Hot queries <== could be improved?..

●

Hot tables / files <== storage ok? DB design?..

●

Bad query execution plans.. <== improve, force index, etc.

●

Row Lock contentions due Application Design <== will not scale..

●

Deadlocks due Application Logic.. <== will not scale..

●

NOTE: be sure you're not hitting some HW / OS limits (and MySQL is in
fact out of scope ;-))

Performance Schema since MySQL 5.6: Gold Mine!
●

Query digest (enabled by default) :
●

●

SELECT all queries having > N rows read

●

●

SELECT all queries with execution time > N ms
SELECT queries having table scans, not using indexes, etc..

FILE_IO (enabled by default) :
●

●

●

Time spent on every IO operation for every database file
Amount of each kind of IO operations for every file

Table Locks (enabled by default) :
●

●

See which tables are the most accessed

==> Just with these 3 metrics you already have an idea if things
are still going well or not.. - and MEM is excellent here! ;-)

Classic MySQL Monitoring
●

SHOW Commands:
●

●

mysql> show global status ;

●

mysql> show processlist ;

●

mysql> show engine innodb status ;

●

mysql> show engine innodb mutex ;

●

●

mysql> status ;

INFORMATION_SCHEMA.* , InnoDB METRICS table, etc..

Important :
●

only PFS instrumentation / query is truly lock free..

●

every query during its execution uses 1 CPU core full time!

●

excessive requesting may significantly lower an overall performance!

So far, what do you have to look on?..
●

MySQL Server general:
●

●

Query/sec, Select/sec, Commit/sec, Connect/sec, Connections, Abort...

InnoDB:
●

BP usage/ dirty%/ page hit%

●

Checkpoint Age, REDO logs rates (MB/sec, Writes/sec, Sync time/sec)

●

Adaptive Flushing rates, Sync Flushing rates, Sync Flushing waits

●

LRU Flushing stats, User Threads LRU Flushing, ..

●

History List Length (purge)

●

Mutex Waits (InnoDB, PFS)

●

File IO Waits (PFS)

●

etc...

Suspecting a problem?.. - Benchmark!
●

Have a clear goal!
●

●

Otherwise: I've obtained all these results, and now... so what?..

Want to simulate your production workload?..
●

●

●

Then just simulate it! (many SW available, not always OSS/free)
Hard to simulate? - adapt some generic tests

Want to know capacity limits of a given platform?
●

●

Still try to focus on the test which are most significant for you!

Want just to validate config settings impacts?
●

●

●

Focus on tests which are potentially depending on these settings
Or any, if the goal to prove there are not depending ;-)

Well, just keep thinking about what you're doing ;-)

Test Workload
●

Before to do something complex...
●

Be sure first you're comfortable with
“basic” operations!

●

●

Many tables?

●

Short queries?

●

●

Single table?

Long queries?

Remember: any complex load just
represents a mix of simple operations..
●

So, start from as simple as possible..

●

And then increase complexity progressively..

Popular “Generic” Test Workloads @MySQL
●

Sysbench
●

●

OLTP, RO/RW, 1-table, since v0.5 N-table, lots load options, deadlocks

DBT2 / TPCC-like
●

●

●

OLTP, RW, very complex, growing db, no options, deadlocks
In fact using mostly only 2 tables! (thanks Performance Schema ;-))

dbSTRESS
●

●

linkbench (Facebook)
●

●

OLTP, RO/RW, several tables, one most hot, configurable, no deadlocks
OLTP, RW, very intensive

DBT3
●

DWH, complex heavy query, loved by Optimizer Team ;-)

MySQL Performance: No Silver Bullet !!!
Internal Limits..
Internal Limits..

There is
There is
No Silver
No Silver
Bullet!!!
Bullet!!!

MySQL
MySQL
Configuration Settings..
Configuration Settings..

InnoDB
InnoDB

Server, OS, FS
Server, OS, FS

Query Optimization..
Query Optimization..

Storage
Storage
BBU, SSD
BBU, SSD

Application Contentions..
Application Contentions..

MySQL Config settings
●

Ask yourself right questions and start with some basic params:
●

●

Double write buffer? Checksums?

●

innodb_flush_log_at_trx_commit= 1 / 2 ??

●

Flush Method = O_DIRECT + ASYNC

●

Binlog Sync? - binlog group commit is since MySQL 5.6 only!

●

File per table?

●

IO capacity = 2000

●

●

Buffer Pool size / Buffer Pool Instances

Etc..

Then adapt then to discovered your HW/OS and MySQL
Internal limits!..

Example: Sort Buffer Size
●

OLTP_RO Point-Selects 8-tables
●

Sort Buffer Size: 32K, 256K, 1M, 2M, 4M

Example: Sort Buffer Size (2)
●

OLTP_RO 8-tables
●

Sort Buffer Size: 32K, 256K, 1M, 2M, 4M

Example: Buffer Pool Instances
●

RW intensive workload:
●

BP instances = 1/ 2/ 4/ 8

Workload: Read-Only oriented
●

Bigger Buffer Pool (BP) is better
●

BP < dataset = IO-bound

●

TRX list (kernel_mutex, since 5.6: trx_sys mutex)

●

Read view

●

Auto-commit or transactions?..
●

●

Prepared statements
●

●

Grouping many queries within a single transaction may also largely
reduce MDL locking, but still keep them short ! (check with PFS)
Observed 10% performance improvement in 5.6 (while Parser time is
not more than 3% according to profiler)..

Read-Only transactions!

InnoDB: Read-Only Transactions in 5.6
●

Sysbench OLTP_RO Point-Selects:
●

Concurrent user sessions: 1, 2, 4 .. 1024

●

Using of transactions in sysbench = 0 / 1

InnoDB: Read-Only Transactions in 5.6 (Apr.2013)
●

Sysbench OLTP_RO Point-Selects:
●

Concurrent user sessions: 1, 2, 4 .. 1024

●

Using of transactions in sysbench = 0

InnoDB : false sharing of cache-line = true killer
●

RO or RW Workloads
●

Same symptoms in 5.5 & 5.6 : no QPS improvement between 16 and 32
user sessions:

InnoDB : false sharing of cache-line fixed!
●

RO or RW Workloads
●

“G5” patch! :-)

●

Over x2(!) times better on Sysbench OLTP_RO,

●

x6(!) times better on SIMPLE-Ranges!

●

NOTE: the fix is not applicable on 5.5..

MySQL Internals: “killer” LOCK_open mutex
●

MySQL 5.5 and before:
●

Keep “table_open_cache” setting big enough!

●

Monitor global status for '%opened%'

●

●

Once this contention become the most hot – well, time to upgrade to
5.6 ;-))

Since MySQL 5.6:
●

Fixed: several table open cache instances

●

But it doesn't mean you can use a small “table_open_cache” either ;-)

●

Monitor PFS Waits!

●

Monitor “table_open_cache%” status variables!

●

Keep “table_open_cache_instances” at least bigger than 1

MySQL 5.6 Internals : low table_open_cache
●

MySQL 5.6 :
●

Not big enough “table_open_cache” setting

MySQL 5.6 Internals : low table_open_cache (2)
●

MySQL 5.6 :
●

Not big enough “table_open_cache” setting

●

PFS Waits monitoring: LOCK_table_cache become the most hot:

●

Table_open_cache% status:

MySQL 5.6 Internals : table_open_cache_instances
●

MySQL 5.6 :
●

When LOCK_table_cache wait is on top, the gain is usually well visible:

Workload: Read-Write
●

RW activity
●

●

Updates only? Insert? Delete? R/W %ratio?

Bigger Buffer Pool (BP) is still better
●

BP < dataset = IO-bound Reads(!) or R+W

●

BP > dataset = CPU-bound or IO-bound Writes(!)

●

REDO size matters a lot! (up to 2TB in 5.6)

●

Adaptive Flushing matters a lot!

●

LRU flushing matters a lot as well!

●

Tip: Neighbor Pages flushing = off / on

But let me tell you now the
whole story first! ;-)

Jan.2009 : Long RW Intensive Test
●

RW Workload:
●

128 concurrent users, 500M REDO, dirty pages= 15%

●

But let's get a look on the real state of BP:

InnoDB Internals: Dirty pages
●

How does it work?..
●

●

SQL> show innodb
status G

But why my dirty
pages% setting
is ignored?...
●

●

Buffer pool
> free
> data
innodb_buffer_pool_size = M

> dirty

innodb_max_dirty_pages_pct = 15%

Mystery?...
All votes:
it's impossible ;-)
REDO
DATA / INDEX

innodb_log_file_size = 500M

InnoDB Internals: Dirty pages and REDO?..
●

What if I'll reduce REDO size now?..
●

REDO: 500M => 128M

Buffer pool
> free
> data

> dirty


REDO
DATA / INDEX


InnoDB Internals: Dirty pages and REDO?..
●

What if I'll reduce REDO size now?..
●

●

REDO: 500M => 128M
Forcing lower
Dirty Pages Amount!

Buffer pool
> free
> data

> dirty


REDO
DATA / INDEX


Any Changes on RW Test now?..
●

REDO = 500M

●

REDO = 128M

Fine, but..
●

Remained questions:
●

Why finally Dirty Pages% setting is completely ignored?...

●

While, after all, any dangers to have many dirty pages?...

●

And what is the impact of REDO logs size?..

InnoDB Internals: Impact of REDO size
●

RW Intensive Load
●

REDO size = 128M

●

RW Intensive Load
●

REDO size = 1024M

●

RW Intensive Load
●

●

Result: 6000 TPS => 8000 TPS! 30% better!!!

●

●

REDO size = 128M => 1024M
For such an improvement we may ignore Dirty Pages% ;-))

But : WHY these TPS drops?...

InnoDB Internals: Analyzing the code..
●

Master thread logic:

Master Thread
loop: //Main loop
...
if( dirty pct > limit)
flush_batch( 100% IO);
...
do {
pages= trx_purge();
if( 1sec passed ) flush_log();
} while (pages);
...
goto loop;

Buffer pool
> free
> data
> dirty

REDO
DATA / INDEX

●

Master thread may never leave purge loop!!!

Master Thread
loop: //Main loop
...
...
do {
pages= trx_purge();
if( 1sec passed ) flush_log();
} while (pages);
...
goto loop;

Buffer pool
> free
> data
> dirty

REDO
DATA / INDEX

●

But if Master thread is never leave purge loop...

●

Who is then flushing Dirty Pages?...
Buffer pool
> free
> data
> dirty

REDO
DATA / INDEX

●

But if Master thread is never leave purge loop...
●

●

Who is then flushing Dirty Pages?...

Redo log constraints:
●

●

●

●

Cyclic, need free space
Checkpoint Age: diff between the
current LSN in redo and the oldest
dirty page LSN
Checkpoint Age cannot out-pass the max
checkpoint age (redo log size)

Buffer pool
> free
> data
> dirty

If Checkpoint Age >= 7/8 of Max Age
=> Flush ALL dirty pages regardless IO capacity!!!
REDO

(“Furious Flushing”)
DATA / INDEX

InnoDB Internals: Introducing Purge Thread
●

Purge Thread is the MUST !!!

Master Thread
loop: //Main loop
...
sleep( 1 );
...
...
flush_log();
...
goto loop;

Purge Thread
loop:
sleep( ... );
do { pages=
trx_purge();
} while (pages);
goto loop;

Buffer pool
> free
> data
> dirty

REDO
DATA / INDEX

Performance with Purge Thread
●

MySQL 5.4 :

●

MySQL 5.4 + purge fix :

Performance with Purge Thread
●

MySQL 5.5 :

InnoDB Purge since MySQL 5.5
●

Purging has a cost! (similar to Garbage Collecting)
●

●

●

Since MySQL 5.5: single purge thread (off by default)
Since MySQL 5.6: several purge thread(s) (up to 32)

However, Purge may lag and do not follow workload..
●

●

Ex.: On aggressive RW got 400GB of undo records within few hours(!)

●

●

This is very bad when happens...
Then it took days to reach zero in History Length..

The main problem is the past – how to dose purging?..
●

●

Since 5.6: with many threads, Purge become auto-stable itself
Still missing a dynamic config option to say how many purge threads to
run in parallel right now (but it'll be fixed soon ;-))

InnoDB : Purge improvement in 5.6
●

Several Purge Threads :
●

NOTE: activation is auto-magical (I'm serious ;-))

InnoDB : Purge improvement in 5.6
●

Fixed max purge lag code!
●

●

●

innodb_max_purge_lag
innodb_max_purge_lag_delay <= configurable!

Setting innodb_max_purge_lag=1M:

InnoDB Internals: “Furious Flushing”
●

Direct dependence on REDO log size

●

NOTE:
●

●

●

●

No direct dependence
on amount of dirty
pages and REDO size!
Depends on workload!

Buffer pool
> free
> data

> dirty

innodb_max_dirty_pages_pct = N

However, bigger REDO
allows more dirty pages..
And recovery is way
faster today!
REDO
DATA / INDEX

innodb_log_file_size = L

InnoDB: REDO log constraints
●

REDO log constraints: (Always monitor Checkpoint Age!!!)
●

●

●

Cyclic, need free space
Buffer pool
Checkpoint age: diff between the current LSN in REDO
> free
and the oldest dirty page LSN

Checkpoint age cannot out-pass the max checkpoint
age (redo log size)

●

●

●

If Checkpoint age >= 7/8 of Max age => Flush ALL dirty!

> data
> dirty

=> AKA “furious flushing”...

Adaptive Flushing:
●

Keep REDO under Max age

●

Respecting IO capacity limit

REDO
DATA / INDEX

InnoDB: Adaptive Flushing
●

MySQL 5.5:
●

●

●

Estimation based
Sometimes works ;-)

MySQL 5.6 :
●

●

●

Based on REDO write rate + I/O capacity Max
Involving batch flushing with N pages to flush (progressive, depending
on REDO %free) + page age limit (according REDO rate)

Tuning:
●

innodb_io_capacity / innofb_io_capacity_max

●

innodb_adaptive_flushing_lwm / innodb_max_dirty_pages_pct_lwm

●

ALL are dynamic!

●

Monitor Checkpoint Age..

Adaptive Flushing: MySQL 5.6 vs 5.5
●

OLTP_RW Workload:
●

Same IO capacity

●

Different logic..

InnoDB : Resisting to activity spikes in 5.6
●

dbSTRESS R+W with spikes

InnoDB Adaptive Flushing: Fine Tuning
●

Monitor your Flushing rate / capabilities..
●

Adapt IO capacity and REDO size :

InnoDB and I/O Performance
●

Keep in mind the nature of I/O operation!
●

●

Sequential Read (SR)

●

Random Write (RW)

●

●

Sequential Write (SW)

Random Read (RR)

InnoDB

Buffer pool
> free
> data

●

Data files <= SW,SR,RW,RR

●

Redo log <= SW

●

Bin log <= SW

●

Double write <= SW

> dirty

BINLOG
DATA / INDEX
double write buffer

REDO

InnoDB and I/O Performance
●

Avoid a hot-mix of I/O operations!
●

Random Read (RR) <= most painful & costly!!!

●

Place REDO on different LUNs/disks

●

●

Place BINLOG on a separated
storage array!

I/O Settings
●

I/O write threads

●

> data

I/O capacity

●

Buffer pool
> free

I/O read threads

> dirty

BINLOG
DATA / INDEX
double write buffer

REDO

InnoDB: Doublewrite Buffer
●

Protecting from partially written pages
●

Data first written into Doublewrite buffer (sys.tablespace)

●

Then flushed to the datafiles

●

●

On recovery: if partially written page discovered => use its image from
doublewrite buffer

What is the cost?..
●

Doublewrite I/O is sequential, so should be fast

●

Writes will do less sync calls:
–

Instead of sync on every page write

–

Sync once on doublewrite buffer write

–

Then once on the datafile(s) for the same chunk of pages

InnoDB: Doublewrite buffer real impact?
●

Usually:
●

●

●

performance remains the same (or better)
+ recovery guarantee!

In some cases:
●

Up to 30% performance degradation...

●

Why?...

InnoDB: Doublebuffer and I/O dependency
●

Random Reads are killing!
●

RR = ~5ms wait per operation on HD

●

Example:
–

Application is doing 30.000 IO op/s

–

All operations are SW/RW

–

Now 5% of Writes become RR

–

What about performance?..

Buffer pool
> free
> data
> dirty

BINLOG
DATA / INDEX
double write buffer

REDO

●

Random Reads are killing!
●

RR = 5ms wait per operation

●

Example:
–

Application is doing 30.000 IO op/s

–

All operations are SW/RW

–

Now 5% of Writes become RR

–

Performance => 10.000 IO ops/s...

–

x3 times degradation!

–

100 SW= 100 x 0.1ms = 10ms

–

95 SW + 5 RR = 9.5ms + 25ms

Buffer pool
> free
> data
> dirty

BINLOG
DATA / INDEX
double write buffer

REDO

●

Workaround: move doublewrite buffer on REDO disks
●

Have to set innodb_file_per_table initially for DB

●

Move system tablespace on REDO disks:
$ mv /DATA/ibdata1 /LOG
$ ln -s /LOG/ibdata1 /DATA

Buffer pool
> free
> data

●

Or just use SSD !!! ;-)

> dirty

BINLOG
DATA / INDEX
double write buffer

REDO

User Concurrency scenarios
●

Single user?..
●

●

●

With a bigger code path today 5.6 simply cannot be faster than 5.5
But then, why you're not considering Query Cache? ;-)

More users?..
●

●

●

Up to 8-16 concurrent users all internal contention are not yet hot
So, 5.6 will not be better yet..

More than 16 users?..
●

●

●

Then you'll feel a real difference, but if you have at least 16cores ;-)
Or if you have really a lot of concurrent users

But don't forget other 5.6 improvements either!
●

On-line DDL, Binlog group commit, Memcached, etc..

High Concurrency Tuning
●

●

If bottleneck is due a concurrent access on the same data (due
application design) – ask dev team to re-design ;-)
If bottleneck is due MySQL/InnoDB internal contentions, then:
●

If you cannot avoid it, then at least don't let them grow ;-)

●

Try to increase InnoDB spin wait delay (dynamic)

●

Try innodb_thread_concurrency=N (dynamic)

●

CPU taskset / prcset (Linux / Solaris, both dynamic)

●

Thread Pool

●

NOTE: things with contentions may radically change since 5.7, so stay
tuned ;-)

InnoDB Spin Wait Delay
●

RO/RW Workloads:
●

With more CPU cores internal contentions become more hot..

●

Bind mysqld to less cores helps, but the goal is to use more cores ;-)

●

Using innodb_thread_concurrency is not helping here anymore..

●

So, innodb_spin_wait_delay is entering in the game:

Tune InnoDB Spin Wait Delay
●

Notes :
●

is the max random delay on “sleep” within a spin loop in wait for lock..

●

Ideally should be auto.. while the same tuning works for 5.5 as well ;-)

●

General rule: default is 6, may need an increase with more cores

●

Test: 32-HT/ 32/ 24/ 16cores, spin delay = 6 / 96 :

Thread Pool @MySQL
●

None of these solutions will help to increase performance!
●

●

it'll just help to keep the peak level constant (and you yet need to
discover on which level of concurrency you're reaching your peak ;-))

ThreadPool in MySQL 5.5 and 5.6 is aware if I/O are involved!
●

So, better than innodb thread concurrency setting or taskset

●

May still require spin wait delay tuning!

●

The must for high concurrency loads!

●

●

May still start to show a difference since 32-128 concurrent users! (all
depends on workload)..
Keep in mind that OS scheduler is not aware how to manage user
threads most optimally, but ThreadPool does ;-)

Thread Pool in MySQL 5.6
●

OLTP_RO:

Thread Pool in MySQL 5.6
●

OLTP_RW:

Thread Pool in MySQL 5.7 @Heavy OLTP_RW

InnoDB High Concurrency: AHI
●

Adaptive Hash Index (AHI)
●

Helps a lot on Read-Only workloads

●

In fact it helps always until itself become not actively modified

●

AHI contention is seen as its btr_search_latch RW-lock contetnion

●

So, on Read+Write become a huge bottleneck..

●

In many cases on RW the result is better with AHI=off..

●

NOTE: there is still a big mystery around AHI when it's having
btr_search_latch contention even when there is no changes at all (pure
RO in memory).. - expected to be fixed in 5.7 ;-)

Testing Apples-to-Apples...
●

Comparing MySQL 5.6 vs 5.5 :
●

Don't have G5: dead..

●

Don't have open table cache instances: bad..

●

Don't have improved Adaptive Flushing; bad..

●

Don't have fixed Purge & Lag: danger!..

●

Don't have binlog group commit and use binlog: dead..

●

Etc. etc. etc.

●

●

NOTE: some “improvement” are also fixes which are making stuff
working properly, but coming with additional overhead (like Purge)..
NOTE: when comparing 5.6 and 5.5 keep in mind that Performance
Schema is enabled by default in 5.6, and not in 5.5, so think to disable it
in both (as 5.5 also has a way less PFS instrumentation)..

Sysbench OLTP_RO @8cores-HT (Apr.2013)

Sysbench OLTP_RO-trx @32cores-HT (Apr.2013)

Sysbench OLTP_RO 8-tab @32cores-HT (Apr.2013)

Sysbench OLTP_RO-trx 8-tab @32cores-HT (Apr.2013)

Sysbench OLTP_RW @8cores-HT (Apr.2013)

Sysbench OLTP_RW 8-tab @32cores-HT (Apr.2013)

MySQL 5.6: Pending issues
●

Index lock..

●

Lock_sys contention..

●

Trx_sys contention..

●

MDL scalability..

●

Flushing limits..

●

LRU flushing..

●

Design bug on block locking.. (was here from the beginning)

●

Not able yet to use 100% I/O capacity on a powerful storage..

●

“Mysterious” contentions on dbSTRESS..

●

etc..

MySQL 5.7: Work in progress.. ;-)
●

Index lock.. <== fixed !

●

Lock_sys contention.. <== lowered !

●

Trx_sys contention.. <== improved a lot !!!

●

MDL scalability.. <== in progress..

●

Flushing limits.. <== in progress..

●

LRU flushing.. <== in progress..

●

Design bug on block locking.. (was here from the beginning)

●

Not able yet to use 100% I/O capacity on a powerful storage..

●

“Mysterious” contentions on dbSTRESS..

●

Etc.. <== well, ALL in progress / investigation ;-)

MySQL 5.7: DMR2 (Sep.2013)
●

OLTP_RO Point-Selects 8-tables: 500K QPS !!!
●

UNIX socket, sysbench 0.4.8 (older, using less CPU)

●

OLTP_RO Point-Selects 8-tables: 440K QPS
●

IP port, sysbench 0.4.13 (“common”, using more CPU)

●

OLTP_RO Point-Selects-TRX 8-tables: 200K QPS
●


●

OLTP_RO Point-Selects 8-tables: Scalability..
●

UNIX socket, sysbench 0.4.8 (older, using less CPU)

●

OLTP_RO Point-Selects 8-tables: Scalability..
●

IP port, sysbench 0.4.13 (using more CPU)

●

OLTP_RO Point-Selects-TRX 8-tables: Scalability..
●

IP port, sysbench 0.4.13 (using more CPU)

●

OLTP_RO 8-tables: 280K QPS
●


●

OLTP_RO 1-table: lower than 5.6...
●

Due higher MDL contentions, work in progress..

●

OLTP_RW 8-tables: 265K QPS
●


●

OLTP_RW 1-table: lower than 5.6
●

MDL contention, work in progress..

THANK YOU !!!
●

All details about presented materials you may find on:
●

http://dimitrik.free.fr - dim_STAT, Benchmark Reports

●

http://dimitrik.free.fr/blog - Articles about MySQL Performance

MySQL 5.6 Performance

Related slideshows

More Related Content

MySQL 5.6 Performance