PetaMongo: A Petabyte Database for as Little as $200

Preview:

DESCRIPTION

1,000,000,000,000,000 bytes. On demand. Online. Live. Big doesn't quite describe this data. Amazon Web Services makes it possible to construct highly elastic computing systems, and you can further increase cost efficiency by leveraging the Spot Pricing model for Amazon EC2. We showcase elasticity by demonstrating the creation and teardown of a petabyte-scale multiregion MongoDB NoSQL database cluster, using Amazon EC2 Spot Instances, for as little as $200 in total AWS costs. Oh and it offers up four million IOPS to storage via the power of PIOPS EBS. Christopher Biow, Principal Technologist at 10gen | MongoDB covers MongoDB best practices on AWS, so you can implement this NoSQL system (perhaps at a more pedestrian hundred-terabyte scale?) confidently in the cloud. You could build a massive enterprise warehouse, process a million human genomes, or collect a staggering number of cat GIFs. The possibilities are huMONGOus.

Citation preview

© 2013 Amazon.com, Inc. and its affiliates. All rights reserved. May not be copied, modified, or distributed in whole or in part without the express consent of Amazon.com, Inc.

PetaMongo: A Petabyte Database for as Little as $200

Chris Biow, MongoDB

Miles Ward, AWS

November 13, 2013

Agenda

• MongoDB on AWS review– Guidance, Storage, Architecture

• MongoDB at PetaScale on AWS

• Whitepaper• Marketplace• CloudFormation

Tools to simplify your design

http://media.amazonwebservices.com/AWS_NoSQL_MongoDB.pdf

• Easy to start a single node

• Correctly configured PIOPS EBS Storage

• No extra cost

https://aws.amazon.com/marketplace/pp/B00COAAEH8/ref=srh_res_product_title?ie=UTF8&sr=0-6&qid=1383897659043

mongodb.org/display/DOCS/Automating+Deployment+with+CloudFormation

• Nested Templates

• Nodes and Storage

• Configurable Scale

• CloudFormation: Your Infrastructure belongs in your source control

CloudFormation

AWS Storage Options

• EBS – Provisioned IOPS volumes• Deliver predictable, high performance for I/O intensive workloads• Specify IOPS required upfront, and EBS provisions for lifetime of volume– 4000 IOPS per volume, can stripe to get thousands of IOPS to an EC2 instance

• High IO Instances – hi1.4xlarge• For some applications that require tens of thousands of IOPS• Eliminates network latency/bandwidth as a performance constraint to storage

EBSPIOPS

SSD

AWS Storage OptionsTesting: random 4k reads

EBS

SSD

PIOPS+

One Volume: ~200 MongoOPS with some variability, <1mb/sLoaded instance: ~ 1000 MongoOPS with some variability <10mb/s

One Volume: 200 0 MongoOPS with <1% variability, 16mb/sLoaded Instance: 16,000 MongoOPS with <1% variability, 64mb/s

Loaded Cluster Instance: MongoOPS, 320mb/s

Hi1.4xlarge ephemeral: ~64,000 MongoOPS with low variability, ~245mb/s

4,000

80,000

Testing: random 4k reads

EBS

SSD

PIOPS+

Sta

ble

Stability Tips

• Ext4 or XFS, nodiratime, noatime

• Raise file descriptor limits

• Set disk read-ahead

• No large virtual memory pages

• SNAPSHOT SNAPSHOT SNAPSHOT

• Retain a PIOPS EBS node for snapshot backups

• Snapshots allow cross-AZ and cross-region recovery

• SSD hosts as primary

• Shard for scale

244gb cr1.8xlargeAnother option…

So, about that Petabyte

v.cheap

• Spot Market• m1.small• 1024 shards• 1TB EBS from snapshot• PowerBench reader• Aggregation queries

v.fast

• AutoScaling On-Demand• cc2.8xlarge• 44 instances x 24 shards

each• 24TBx1K PIOPS indexed• YCSB loader• Aggregation queries

The naming of parts

Amazon Terms

• Provisioned IOPS• Elastic Compute Cloud• EC2 Spot Instances• Auto Scaling groups

Nicks

• PIOPS• EC2• Here, Spot!• ASG

Players

MongoDB• Document-model,

NoSQL database

• Dev adoption is STRONG

• MongoDB Inc. trending toward zero h/w

• Scale-up with commodity h/w• Scale-out with sharding• Scale-around with replication

Dev Activity: stackoverflow.com

AWS

• PIOPS for an IO-hungry client• 40% of MongoDB customer usage• 90% of MongoDB internal usage• More ports :2701[79] than :[15]521

PB & ChocolateDifferentiators for mutual customers

• Fast time-to-solution• Easy global distribution• Document model• Secondary indexes• Geo, text, security• Fast analytic aggregation

Challenge

Motivation: IWBCI…

• Test scale-out of MongoDB beyond typical• Learn massive scale-out on AWS • Do it as cheaply as possible• Apply customer data• Break the petabarrier

m1.small us-east1 Spot Market

m1.small us-east1d Spot Market

ProposalItem Units Time Unit Cost Net Cost

m1.small Spot 1050 3hr $0.007/hr $22.05

m1.large 3 48hrs $0.056/hr $8.07

S3 1TB 1wk $95/TB/mo 23.75

EBS 1024 x 1TB 1hr $100/TB/mo 142.22

S3 EBS 1PB lazy $0/TB 0.00

Total $196.09

http://calculator.s3.amazonaws.com/G77798SS77SH72

Initial Directions

• Spot instance requests– m1.small market, mostly us-east-1 (my zone “d”)– Net: $0.007 / hour = $7 / hr / K-shard

• Perl– use Net::Amazon::EC2;– gaps: parse EC2 command-line API

• Defer Chef, Puppet, CloudFormation• YCSB• userdata.sh• t1.micro / m1.small / cr1.8xlarge

MongoDB Architecture

• 3x Config Servers– mongod --configsvr

• Routing– mongos --configdb a,b,c

• Replica sets (not used)• Shards

– mongod

• Client load – java -cp [] com.yahoo.ycsb.Client

Range-based sharding

Hash-based sharding

Process Flow

Spot Instance Request (sir-)

• Rejected• Awaiting evaluation• Awaiting fulfillment

– Partial– Launch intervals

• Fulfilled

Instances (i-)

• Requested• Initializing (i)• Config running (C)• MongoS starting (s)• MongoS running (S)• MongoD starting (D)• Failed/slow response (X)

Spot Instance Lifecycle

sir-

Config

Sharded

MongoD

Shard

MongoS

Progress

Scale Out Experience

• Sharding by magnitude: 4, 16, 64, 256, 1024• 4: functional validation• 16: startup variation, process flow• 64: full speed ahead!• 256: chunk distribution time, single Config• 1024: market dependence, client wire saturation

Lessons Learned

• Code defensively• Monitor: MongoDB Mgt Svc, top, iftop, iostat,

mongostat• Avoid sentimental attachment (i-8bad8bee)• Prototype / refactor• Make the instances do the work• Mitigate chunk migration

Refactor

• BenchPress YCSB• Auto Scaling Groups request-spot-instances • use VM::EC2; Net::Amazon::EC2 • gsh monolithic Perl• serf polling

Secure Cloud Networking

Enable customers to easily connect, manage and secure applications across VPCs, regions, and hybrid infrastructures.

Cloud-scale your VPC connectivity!

VPC 1 VPC 2

ApplicationServiceMesh

After the Session: Survey - $500 Gift CardOr schedule a demoInfo@unionbaynetworks.com

5:16:48 5:45:36 6:14:24 6:43:12 7:12:00 7:40:480

200,000,000

400,000,000

600,000,000

800,000,000

1,000,000,000

1,200,000,000

1,400,000,000

1,600,000,000

1,800,000,000

1KB Docs Loaded, 512 shards

^ 1X RAM

4:19:12 5:31:12 6:43:12 7:55:12 9:07:12 10:19:12 11:31:12 12:43:12 13:55:120

500,000,000

1,000,000,000

1,500,000,000

2,000,000,000

2,500,000,000

1KB Docs Loaded, 1035 shards, 2 jobs conflicting

^ 1X RAM

Dee-Luxe

0

500,000

1,000,000

1,500,000

2,000,000

2,500,000

3,000,000

3,500,000

cc2.8xlarge, 24 x 1TB-4K PIOPS EBS, bulk-load 64KB docs

64KB-docsus-latency

100% RAM

12:00:00 AM 02:24:00 AM 04:48:00 AM 07:12:00 AM 09:36:00 AM 12:00:00 PM 02:24:00 PM 04:48:00 PM 07:12:00 PM0

20,000,000

40,000,000

60,000,000

80,000,000

100,000,000

120,000,000

140,000,000

cc2.8xlarge, 24 x 1TB-4K PIOPS EBS, bulk-load 64KB docs

64KB-docsus-latency

Further Work

• Completion• Replication• Self-healing• MongoDB-appropriate benchmarks• Customer data• Self-hosting cluster

Please give us your feedback on this presentation

As a thank you, we will select prize winners daily for completed surveys!

BDT307

Recommended