Escolar Documentos
Profissional Documentos
Cultura Documentos
2015, Amazon Web Services, Inc. or its affiliates. All rights reserved
SQL
Transactions
Caching
Logging
Multiple layers of
functionality all on a
single box
Application
SQL
SQL
Transactions
Transactions
Caching
Caching
Logging
Logging
Application
SQL
SQL
Transactions
Transactions
Caching
Caching
Logging
Logging
Application
SQL
SQL
Transactions
Transactions
Caching
Caching
Logging
Logging
Storage
This is a problem.
For cost. For flexibility. And for availability.
Youd build something that can scale out, that is self-healing, and that
leverages existing AWS services.
Control Plane
SQL
Transactions
Caching
Amazon
DynamoDB
Logging + Storage
Amazon SWF
Amazon Route 53
Aurora preview
vCPU
Mem
Hourly Price
db.r3.large
15.25
$0.29
db.r3.xlarge
30.5
$0.58
db.r3.2xlarge
61
$1.16
db.r3.4xlarge
16
122
$2.32
db.r3.8xlarge
32
244
$4.64
Simple pricing
No licenses
No lock-in
Pay only for what you use
Discounts
connectors
work with Aurora seamlessly. Today, customers can take MariaDB Enterprise with
MariaDB MaxScale drivers and connect to Aurora, MariaDB, or MySQL without worrying about
compatibility. We look forward to working with the Aurora team in the future to further
accelerate innovation within the MySQL ecosystem. Roger Levy, VP Products, MariaDB
Business Intelligence
Data Integration
SI and Consulting
Automated patching
Continuous backups to S3
Amazon RDS
Application
SQL
Transactions
Storage
Amazon S3
Aurora storage
AZ 1
AZ 2
Automatic fallback to
3 of 4 if an AZ is unavailable
3 of 6 read quorum
SQL
Transactions
Caching
Log-structured storage
Amazon S3
AZ 3
Amazon Aurora
AZ 2
AZ 1
AZ 2
Standby
Instance
Primary
Instance
Replica
Instance
async
4/6 quorum
PiTR
Amazon Elastic
Block Store (EBS)
EBS
Sequential
write
Sequential
write
EBS
EBS
mirror
mirror
Amazon S3
Improvements
Distributed
writes
Amazon S3
Type of writes
Consistencytolerance to outliers
Log records
Binlog
Data
Double-write buffer
FRM files, metadata
AZ 3
Self-healing, fault-tolerant
AZ 2
AZ 3
AZ 1
SQL
SQL
Transaction
Transaction
Caching
Caching
Read availability
AZ 2
AZ 3
Amazon Aurora
Single-threaded in MySQL;
requires a large number of disk
accesses
Crash at T requires
a re-application of the
SQL in the redo log since
last checkpoint
Checkpointed Data
Redo Log
T0
T0
Survivable caches
SQL
SQL
SQL
Transactions
Transactions
Transactions
Caching
Caching
Caching
Aurora Master
70% Write
70% Write
30% Read
30% Read
Data Volume
Data Volume
MySQL Master
70% Write
Single-threaded
binlog apply
Page cache
invalidation
Aurora Replica
100% New
Reads
MySQL Sysbench
MySQL Sysbench
Tables
Amazon
Aurora
MySQL
I2.8XL
Local SSD
MySQL
I2.8XL
RAM Disk
RDS MySQL
30K IOPS
(Single AZ)
10
60,000
18,000
22,000
25,000
100
66,000
19,000
24,000
23,000
1,000
64,000
7,000
18,000
8,000
10,000
54,000
4,000
8,000
5,000
70
60
50
40
30
20
10
10
Write-only workload
1,000 connections
Query cache (default on for Amazon Aurora, off for MySQL)
100
1,000
Number of Tables
Aurora
MySQL on I2.8XL
MySQL on I2.8XL with RAM Disk
RDS MySQL with 30,000 IOPS (Single AZ)
10,000
Better concurrency
Write Performance and Concurrency
120
50
Amazon
Aurora
40,000
RDS MySQL
30K IOPS
(Single AZ)
10,000
500
71,000
21,000
5,000
110,000
13,000
100
Connections
80
60
40
20
OLTP Workload
Variable connection count
250 tables
Query cache (default on for Amazon Aurora, off for MySQL)
50
Aurora
500
Concurrent Connections
5,000
Amazon
Aurora
With
Caching
RDS MySQL
30K IOPS
Without
Caching
RDS MySQL
30K IOPS
With
Caching
100/0
160,000
375,000
35,000
19,000
50/50
130,000
93,000
24,000
20,000
0/100
64,000
64,000
16,000
16,000
400
Thousands of Operations/Second
R/W Ratio
Amazon
Aurora
Without
Caching
350
300
250
200
150
100
50
100/0
OLTP workload
1,000 connections
250 tables
Query cache on/off tested
50/50
Read/Write Ratio
0/100
Updates/
Second
Amazon
Aurora
RDS MySQL
30K IOPS
(Single AZ)
1,000
2.62 ms
0s
2,000
3.42 ms
1s
5,000
3.94 ms
60 s
10,000
5.38 ms
300 s
350,000
300,000
250,000
200,000
150,000
100,000
50,000
2.6
Write workload
250 tables
Query cache on for Amazon Aurora, off for MySQL (best settings)
3.4
5.4
3.9
0
1,000
2,000
5,000
10,000
SAN FRANCISCO