Web20expo Filesystems

Beyond the File System

Designing Large Scale File Storage and Serving

Cal Henderson

Web 2.0 Expo, 17 April 2007 2

Hello!


Big file systems?

• Too vague!• What is a file system?• What constitutes big?• Some requirements would be nice


ScalableLooking at storage and serving infrastructures1


ReliableLooking at redundancy, failure rates, on the fly changes2


CheapLooking at upfront costs, TCO and lifetimes3


Four buckets

Storage

Serving

BCP

Cost


Storage


The storage stack

File system

Block protocol

RAID

Hardware

ext, reiserFS, NTFS

SCSI, SATA, FC

Mirrors, Stripes

Disks and stuff

File protocol NFS, CIFS, SMB


Hardware overview

The storage scale

Internal DAS SAN NAS

Lower Higher


Internal storage

• A disk in a computer– SCSI, IDE, SATA

• 4 disks in 1U is common• 8 for half depth boxes


DAS

Direct attached storage

Disk shelf, connected by SCSI/SATA

HP MSA30 – 14 disks in 3U


SAN

• Storage Area Network• Dumb disk shelves• Clients connect via a ‘fabric’• Fibre Channel, iSCSI, Infiniband

– Low level protocols


NAS

• Network Attached Storage• Intelligent disk shelf• Clients connect via a network• NFS, SMB, CIFS

– High level protocols


Of course, it’s more confusing than that


Meet the LUN

• Logical Unit Number• A slice of storage space• Originally for addressing a single drive:

– c1t2d3– Controller, Target, Disk (Slice)

• Now means a virtual partition/volume– LVM, Logical Volume Management


NAS vs SAN

With a SAN, a single host (initiator) owns a single LUN/volume

With NAS, multiple hosts own a single LUN/volume

NAS head – NAS access to a SAN


SAN Advantages

Virtualization within a SAN offers some nice features:

• Real-time LUN replication• Transparent backup• SAN booting for host replacement


Some Practical Examples

• There are a lot of vendors• Configurations vary • Prices vary wildly

• Let’s look at a couple– Ones I happen to have experience with– Not an endorsement ;)


NetApp Filers

Heads and shelves, up to 500TB in 6 Cabs

FC SAN with 1 or 2 NAS heads


Isilon IQ

• 2U Nodes, 3-96 nodes/cluster, 6-600 TB

• FC/InfiniBand SAN with NAS head on each node


Scaling

Vertical vs Horizontal


Vertical scaling

• Get a bigger box

• Bigger disk(s) • More disks

• Limited by current tech – size of each disk and total number in appliance


Horizontal scaling

• Buy more boxes

• Add more servers/appliances

• Scales forever*

*sort of


Storage scaling approaches

• Four common models:

• Huge FS• Physical nodes• Virtual nodes• Chunked space


Huge FS

• Create one giant volume with growing space– Sun’s ZFS– Isilon IQ

• Expandable on-the-fly?• Upper limits

– Always limited somewhere


Huge FS

• Pluses– Simple from the application side– Logically simple– Low administrative overhead

• Minuses– All your eggs in one basket– Hard to expand– Has an upper limit


Physical nodes

• Application handles distribution to multiple physical nodes– Disks, Boxes, Appliances, whatever

• One ‘volume’ per node• Each node acts by itself• Expandable on-the-fly – add more nodes• Scales forever


Physical Nodes

• Pluses– Limitless expansion– Easy to expand– Unlikely to all fail at once

• Minuses– Many ‘mounts’ to manage– More administration


Virtual nodes

• Application handles distribution to multiple virtual volumes, contained on multiple physical nodes

• Multiple volumes per node• Flexible• Expandable on-the-fly – add more nodes• Scales forever


Virtual Nodes

• Pluses– Limitless expansion– Easy to expand– Unlikely to all fail at once– Addressing is logical, not physical– Flexible volume sizing, consolidation

• Minuses– Many ‘mounts’ to manage– More administration


Chunked space

• Storage layer writes parts of files to different physical nodes

• A higher-level RAID striping

• High performance for large files– read multiple parts simultaneously


Chunked space

• Pluses– High performance– Limitless size

• Minuses– Conceptually complex– Can be hard to expand on the fly– Can’t manually poke it


Real Life

Case Studies


GFS – Google File System

• Developed by … Google• Proprietary• Everything we know about it is based on

talks they’ve given• Designed to store huge files for fast

access



• Single ‘Master’ node holds metadata– SPF – Shadow master allows warm swap

• Grid of ‘chunkservers’– 64bit filenames– 64 MB file chunks



1(a) 2(a)

1(b)

Master



• Client reads metadata from master then file parts from multiple chunkservers

• Designed for big files (>100MB)

• Master server allocates access leases

• Replication is automatic and self repairing– Synchronously for atomicity



• Reading is fast (parallelizable)– But requires a lease

• Master server is required for all reads and writes


MogileFS – OMG Files

• Developed by Danga / SixApart

• Open source

• Designed for scalable web app storage



• Single metadata store (MySQL)– MySQL Cluster avoids SPF

• Multiple ‘tracker’ nodes locate files

• Multiple ‘storage’ nodes store files



Tracker

Tracker

MySQL



• Replication of file ‘classes’ happens transparently

• Storage nodes are not mirrored – replication is piecemeal

• Reading and writing go through trackers, but are performed directly upon storage nodes


Flickr File System

• Developed by Flickr

• Proprietary

• Designed for very large scalable web app storage


Flickr File System

• No metadata store– Deal with it yourself

• Multiple ‘StorageMaster’ nodes

• Multiple storage nodes with virtual volumes


Flickr File System

SM

SM

SM


Flickr File System

• Metadata stored by app– Just a virtual volume number– App chooses a path

• Virtual nodes are mirrored– Locally and remotely

• Reading is done directly from nodes


Flickr File System

• StorageMaster nodes only used for write operations

• Reading and writing can scale separately


Amazon S3

• A big disk in the sky• Multiple ‘buckets’• Files have user-defined keys• Data + metadata


Amazon S3

Servers Amazon


Amazon S3

Servers Amazon

Users


The cost

• Fixed price, by the GB

• Store: $0.15 per GB per month• Serve: $0.20 per GB


The cost

S3


The cost

S3

Regular Bandwidth


End costs

• ~$2k to store 1TB for a year

• ~$63 a month for 1Mb

• ~$65k a month for 1Gb


Serving


Serving files

Serving files is easy!

ApacheDisk


Serving files

Scaling is harder

ApacheDisk

ApacheDisk

ApacheDisk


Serving files

• This doesn’t scale well

• Primary storage is expensive– And takes a lot of space

• In many systems, we only access a small number of files most of the time


Caching

• Insert caches between the storage and serving nodes

• Cache frequently accessed content to reduce reads on the storage nodes

• Software (Squid, mod_cache)• Hardware (Netcache, Cacheflow)


Why it works

• Keep a smaller working set

• Use faster hardware– Lots of RAM– SCSI– Outer edge of disks (ZCAV)

• Use more duplicates– Cheaper, since they’re smaller


Two models

• Layer 4– ‘Simple’ balanced cache– Objects in multiple caches– Good for few objects requested many times

• Layer 7– URL balances cache– Objects in a single cache– Good for many objects requested a few times


Replacement policies

• LRU – Least recently used• GDSF – Greedy dual size frequency• LFUDA – Least frequently used with

dynamic aging

• All have advantages and disadvantages• Performance varies greatly with each


Cache Churn

• How long do objects typically stay in cache?

• If it gets too short, we’re doing badly– But it depends on your traffic profile

• Make the cached object store larger


Problems

• Caching has some problems:

– Invalidation is hard– Replacement is dumb (even LFUDA)

• Avoiding caching makes your life (somewhat) easier


CDN – Content Delivery Network

• Akamai, Savvis, Mirror Image Internet, etc

• Caches operated by other people– Already in-place– In lots of places

• GSLB/DNS balancing


Edge networks

Origin


Edge networks

Origin

Cache

Cache

Cache

CacheCache

Cache

CacheCache


CDN Models

• Simple model– You push content to them, they serve it

• Reverse proxy model– You publish content on an origin, they proxy

and cache it


CDN Invalidation

• You don’t control the caches– Just like those awful ISP ones

• Once something is cached by a CDN, assume it can never change– Nothing can be deleted– Nothing can be modified


Versioning

• When you start to cache things, you need to care about versioning

– Invalidation & Expiry– Naming & Sync


Cache Invalidation

• If you control the caches, invalidation is possible

• But remember ISP and client caches

• Remove deleted content explicitly– Avoid users finding old content– Save cache space


Cache versioning

• Simple rule of thumb:– If an item is modified, change its name (URL)

• This can be independent of the file system!


Virtual versioning• Database indicates

version 3 of file

• Web app writes version number into URL

• Request comes through cache and is cached with the versioned URL

• mod_rewrite converts versioned URL to path

Version 3

example.com/foo_3.jpg

Cached: foo_3.jpg

foo_3.jpg -> foo.jpg


Authentication

• Authentication inline layer– Apache / perlbal

• Authentication sideline– ICP (CARP/HTCP)

• Authentication by URL– FlickrFS


Auth layer

• Authenticator sits between client and storage

• Typically built into the cache software

Cache

Authenticator

Origin


Auth sideline

• Authenticator sits beside the cache

• Lightweight protocol used for authenticator

Cache

Authenticator

Origin


Auth by URL

• Someone else performs authentication and gives URLs to client (typically the web app)

• URLs hold the ‘keys’ for accessing files

Cache OriginWeb Server


BCP


Business Continuity Planning

• How can I deal with the unexpected?– The core of BCP

• Redundancy• Replication


Reality

• On a long enough timescale, anything that can fail, will fail

• Of course, everything can fail

• True reliability comes only through redundancy


Reality

• Define your own SLAs

• How long can you afford to be down?• How manual is the recovery process?• How far can you roll back?• How many $node boxes can fail at once?


Failure scenarios

• Disk failure• Storage array failure• Storage head failure• Fabric failure• Metadata node failure• Power outage• Routing outage


Reliable by design

• RAID avoids disk failures, but not head or fabric failures

• Duplicated nodes avoid host and fabric failures, but not routing or power failures

• Dual-colo avoids routing and power failures, but may need duplication too


Tend to all points in the stack

• Going dual-colo: great

• Taking a whole colo offline because of a single failed disk: bad

• We need a combination of these


Recovery times

• BCP is not just about continuing when things fail

• How can we restore after they come back?

• Host and colo level syncing– replication queuing

• Host and colo level rebuilding


Reliable Reads & Writes

• Reliable reads are easy– 2 or more copies of files

• Reliable writes are harder– Write 2 copies at once– But what do we do when we can’t write to

one?


Dual writes

• Queue up data to be written– Where?– Needs itself to be reliable

• Queue up journal of changes– And then read data from the disk whose write

succeeded

• Duplicate whole volume after failure– Slow!


Cost


Judging cost

• Per GB?

• Per GB upfront and per year

• Not as simple as you’d hope– How about an example


Hardware costs

Cost of hardware

Usable GB

Single Cost


Power costs

Cost of power per year

Usable GB

Recurring Cost


Power costs

Power installation cost

Usable GB

Single Cost


Space costs

Cost per U

Usable GB

[ ]U’s needed (inc network)x

Recurring Cost


Network costs

Cost of network gear

Usable GB

Single Cost


Misc costs

Support contracts + spare disks

Usable GB

+ bus adaptors + cables[ ]Single & Recurring Costs


Human costs

Admin cost per node

Node countx

Recurring Cost

Usable GB

[ ]


TCO

• Total cost of ownership in two parts– Upfront– Ongoing

• Architecture plays a huge part in costing– Don’t get tied to hardware– Allow heterogeneity– Move with the market

(fin)

Web 2.0 Expo, 17 April 2007 100

Photo credits

• flickr.com/photos/ebright/260823954/• flickr.com/photos/thomashawk/243477905/• flickr.com/photos/tom-carden/116315962/• flickr.com/photos/sillydog/287354869/• flickr.com/photos/foreversouls/131972916/• flickr.com/photos/julianb/324897/• flickr.com/photos/primejunta/140957047/• flickr.com/photos/whatknot/28973703/• flickr.com/photos/dcjohn/85504455/

Web 2.0 Expo, 17 April 2007 101

You can find these slides online:

iamcal.com/talks/

Web20expo Filesystems

Technology