Recomendados
Recomendados
Mais conteúdo relacionado
Semelhante a Pinterest arch summit august 2012 - scaling pinterest
Semelhante a Pinterest arch summit august 2012 - scaling pinterest (20)
Mais de drewz lin
Mais de drewz lin (20)
Último
Último (20)
Pinterest arch summit august 2012 - scaling pinterest
- 1. 感谢您参加本次Ar h u c S mmi全球架构师峰会！ t 大会官方网站与资料下载地址： www. c um m i . om ar hs tc
- 2. Scaling Marty Weiner Evrhet Milam Krypton Batcave 12年8月10⽇日星期五 TODO: Title page names Pass on page title consistency Fill out numbers Put "always test in production" pin in screenshot of website
- 3. Pinterest is . . . An online pinboard to organize and share what inspires you. Scaling Pinterest 12年8月10⽇日星期五 Talking points should be presented with any key phrases in bold, and everything else regular weight. All text should always be centered.
- 4. 12年8月10⽇日星期五 Talking points should be presented with any key phrases in bold, and everything else regular weight. All text should always be centered.
- 5. 12年8月10⽇日星期五 Images should be full-bleed when possible. Captions should be succinct and appear in bold in the bottom right corner. If necessary, you can make this white to make it legible (like this one).
- 6. 12年8月10⽇日星期五 Talking points should be presented with any key phrases in bold, and everything else regular weight. All text should always be centered.
- 7. Relationships Marty Weiner Grayskull, Eternia Yashh Nelapati Gotham City Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 8. Page Views / Day · RackSpace · 1 small Web Engine · Mar 2010 Jan 2011 Jan 2012 1 small MySQL DB · 1 Engineer Mar 2010 Jan 2011 Jan 2012 May 2012 Scaling Pinterest 12年8月10⽇日星期五 4-5 mts.
- 9. · Amazon EC2 + Page Views / Day S3 + CloudFront · 1 NGinX, 4 Web Engines · 1 MySQL DB + 1 Read Slave · 1 Task Queue + 2 Task Processors · 1 MongoDB Mar 2010 · 2 Engineers Jan 2011 Jan 2012 May 2012 Scaling Pinterest 12年8月10⽇日星期五 TODO: Show total somewhere
- 10. · Amazon EC2 + S3 + CloudFront · 2 NGinX, 16 Web Engines + 2 API Engines Page Views / Day · 5 Functionally Sharded MySQL DB + 9 read slaves · 4 Cassandra Nodes · 15 Membase Nodes (3 separate clusters) · 8 Memcache Nodes · 10 Redis Nodes Mar 2010· Mar 2010 3 Task Routers + 4 Task Processors Jan 2011 Jan 2011 Jan 2012 Jan 2012 May 2012 · 4 Elastic Search Nodes · 3 Mongo Clusters · 3 Engineers Scaling Pinterest 12年8月10⽇日星期五
- 11. Lesson Learned #1 It will fail. Keep it simple. Scaling Pinterest 12年8月10⽇日星期五 Talking points should be presented with any key phrases in bold, and everything else regular weight. All text should always be centered.
- 12. · Amazon EC2 + S3 + Akamai, ELB Page Views / Day · 90 Web Engines + 50 API Engines · 66 MySQL DBs (m1.xlarge) + 1 slave each · 59 Redis Instances · 51 Memcache Instances · 1 Redis Task Manager + 25 Task Processors Mar 2010 · Sharded Solr Jan 2011 Jan 2012 May 2012 · 6 Engineers Scaling Pinterest 12年8月10⽇日星期五
- 13. · Amazon EC2 + S3 + Edge Cast, ELB Page Views / Day · 135 Web Engines + 75 API Engines · 80 MySQL DBs (m1.xlarge) + 1 slave each · 110 Redis Instances · 60 Memcache Instances · 2 Redis Task Manager + 60 Task Processors Mar 2010 · Sharded Solr Jan 2011 Jan 2012 May 2012 · 25 Engineers Scaling Pinterest 12年8月10⽇日星期五
- 14. Why Amazon EC2/S3? · Very good reliability, reporting, and support · Very good peripherals, such as managed cache, DB, load balancing, DNS, map reduce, and more... · New instances ready in seconds · Con: Limited choice · Pro: Limited choice Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 15. Why MySQL? · Extremely mature · Well known and well liked · Rarely catastrophic loss of data · Response time to request rate increases linearly · Very good software support - XtraBackup, Innotop, Maatkit · Solid active community · Very good support from Percona · Free Scaling Pinterest 12年8月10⽇日星期五 TODO: Animate in a money bag
- 16. Why Memcache? · Extremely mature · Very good performance · Well known and well liked · Never crashes, and few failure modes · Free Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 17. Why Redis? · Variety of convenient data structures · Has persistence and replication · Well known and well liked · Consistently good performance · Few failure modes · Free Scaling Pinterest 12年8月10⽇日星期五 Data structures -- list, set, sorted set, pubsub, string. All support atomic operations. All support pipelining.
- 18. Clustering vs Sharding Scaling Pinterest 12年8月10⽇日星期五 clustered = automatically managed nodes with autoscaling, sharding = engineer assigns how data is distributed, splits databases, and writes code to redistribute data (if that option is supported)
- 19. Clustering · Data distributed automatically · Data can move · Rebalances to distribute capacity · Nodes communicate with each othe Sharding Scaling Pinterest 12年8月10⽇日星期五 clustered = automatically managed nodes with autoscaling, sharding = engineer assigns how data is distributed, splits databases, and writes code to redistribute data (if that option is supported). Clustered nodes gossip with each other to determine if rebalancing is needed
- 20. Clustering · Data distributed manually · Data does not move · Split data to distribute load · Nodes are not aware of each other Sharding Scaling Pinterest 12年8月10⽇日星期五 clustered = automatically managed nodes with autoscaling, sharding = engineer assigns how data is distributed, splits databases, and writes code to redistribute data (if that option is supported). Clustered nodes gossip with each other to determine if rebalancing is needed
- 21. Why Clustering? · Examples: Cassandra, MemBase, HBase, Riak · Automatically scale your datastore · Easy to set up · Spatially distribute and colocate your data · High availability · Load balancing · No single point of failure Scaling Pinterest 12年8月10⽇日星期五 What could go wrong?
- 22. What could possibly go wrong? source: thereifixedit.com Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 23. Why Not Clustering? · Still fairly young · Fundamentally complicated · Less community support · Fewer engineers with working knowledge · Difficult and scary upgrade mechanisms · And, yes, there is a single point of failure. A BIG one. Scaling Pinterest 12年8月10⽇日星期五 I lied, there is major single point of failure. The cluster management system. What if it fails? When will it fail? How will you, a non DB developer, fix it? Clustering is a pipe dream. Maybe someday it will work -- same day when there's a perfect makefile system, version control, bug management
- 24. Clustering Single Point of Failure Cluster Management Algorithm Scaling Pinterest 12年8月10⽇日星期五 joke (without names) about how when the cluster manager fails, load balancing may stop one night and keep you up til 6am, or the cluster manager sprays bad data to all nodes and teh CEO of the cluster company contacts you telling you your data is gone and can he buy you a pizza.
- 25. Cluster Manager · Same complex code replicated over all nodes · Failure modes: · Data rebalance breaks · Data corruption across all nodes · Improper balancing that cannot be fixed (easily) · Data authority failure Scaling Pinterest 12年8月10⽇日星期五 What could go wrong?
- 26. Lesson Learned #2 Clustering is scary. Scaling Pinterest 12年8月10⽇日星期五 Swap speakers after this slide
- 27. Why Sharding? · Can split your databases to add more capacity · Spatially distribute and colocate your data · High availability · Load balancing · Algorithm for placing data is very simple · ID generation is simplistic Scaling Pinterest 12年8月10⽇日星期五 ID management is a single point of failure too, but much simpler and easy to test/debug.
- 28. When to shard? · Sharding makes schema design harder · Solidify site design and backend architecture · Remove all joins and complex queries, add cache · Functionally shard as much as possible · Still growing? Shard. Scaling Pinterest 12年8月10⽇日星期五 Maybe a pictograph here showing sharding early = faster transition, but unnecessary complexity. later = slower transition
- 29. Our Transition 1 DB + Foreign Keys + Joins 1 DB + Denormalized + Cache + Read slaves + 1 DB Cache Several functionally sharded DBs + Read slaves + Cache ID sharded DBs + Backup slaves + Cache Scaling Pinterest 12年8月10⽇日星期五 Another possible splitting point
- 30. Watch out for... · Cannot perform most JOINS · No transaction capabilities · Extra effort to maintain unique constraints · Schema changes requires more planning · Reports require running same query on all shards Scaling Pinterest 12年8月10⽇日星期五 Another possible splitting point
- 31. How we sharded Scaling Pinterest 12年8月10⽇日星期五
- 32. Sharded Server Topology db00001 db00513 db03072 db03584 db00002 db00514 db03073 db03585 ....... ....... ....... ....... db00512 db01024 db03583 db04096 Initially, 8 physical servers, each with 512 DBs Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 33. High Availability db00001 db00513 db03072 db03584 db00002 db00514 db03073 db03585 ....... ....... ....... ....... db00512 db01024 db03583 db04096 Multi Master replication Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 34. Increased load on DB? db00001 db00002 ....... db00256 db00001 db00002 ....... db00257 db00512 db00258 ....... db00512 To increase capacity, a server is replicated and the new replica becomes responsible for some DBs Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 35. ID Structure 64 bits Shard ID Type Local ID · A lookup data structure has physical server to shard ID range (cached by each app server process) · Shard ID denotes which shard · Type denotes object type (e.g., pins) · Local ID denotes position in table Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 36. Lookup Structure {“sharddb001a”: ( 1, 512), “sharddb002b”: ( 513, 1024), “sharddb003a”: (1025, 1536), ... “sharddb008b”: (3585, 4096)} sharddb003a DB01025 users users 1 ser-data user_has_boards 2 ser-data boards 3 ser-data Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 37. ID Structure · New users are randomly distributed across shards · Boards, pins, etc. try to be collocated with user · Local ID’s are assigned by auto-increment · Enough ID space for 65536 shards, but only first 4096 opened initially. Can expand horizontally. Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 38. · Object tables (e.g., pin, board, user, comment) Objects and Mappings · Local ID MySQL blob (JSON / Serialized thrift) · Mapping tables (e.g., user has boards, pin has likes) · Full ID Full ID (+ timestamp) · Naming schema is noun_verb_noun · Queries are PK or index lookups (no joins) · Data DOES NOT MOVE · All tables exist on all shards · No schema changes required (index = new Scaling Pinterest table) 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 39. Loading a Page · Rendering user profile SELECT body FROM users WHERE id=<local_user_id> SELECT board_id FROM user_has_boards WHERE user_id=<user_id> SELECT body FROM boards WHERE id IN (<board_ids>) SELECT pin_id FROM board_has_pins WHERE board_id=<board_id> SELECT body FROM pins WHERE id IN (pin_ids) · Most of these calls will be a cache hit · Omitting offset/limits and mapping sequence id sort Scaling Pinterest 12年8月10⽇日星期五
- 40. Scripting · Must get old data into your shiny new shard · 500M pins, 1.6B follower rows, etc · Build a scripting farm · Spawn more workers and complete the task faster · Pyres - based on Github’s Resque queue Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 41. Future · Sharded MySQL is here to stay · Auto-sharding on top of MySQL becoming viable · Clustering may become hardened in 5 to 10 years Scaling Pinterest 12年8月10⽇日星期五 If you have to use a list, do this. But remember, the less stuff on a slide, the better
- 42. In The Works · Service Based Architecture · Connection limits · Isolation of functionality · Isolation of access (security) · Scaling the Team Scaling Pinterest 12年8月10⽇日星期五 Connection limits + Isolation of functionality = service oriented architecture
- 43. Lesson Learned #3 Keep it fun. Scaling Pinterest 12年8月10⽇日星期五 Swap speakers after this slide
- 44. We are Hiring! jobs@pinterest.com Scaling Pinterest 12年8月10⽇日星期五 Connection limits + Isolation of functionality = service oriented architecture
- 45. Questions? marty@pinterest.com yashh@pinterest.com evrhet@pinterest.com Scaling Pinterest 12年8月10⽇日星期五 Talking points should be presented with any key phrases in bold, and everything else regular weight. All text should always be centered.
- 46. 杭州站·2012年 10月 25日 ~27日 大会官网：www.c n a g h uc m q o h n z o .o