Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Finagle, linkerd, and Mesos
Magic Operability Sprinkles for Microservices

Finagle, linkerd, and Mesos
Magic Operability Sprinkles for Microservices

Finagle and Mesos are two core technologies used by Twitter and many other companies to scale application infrastructure to high traffic workloads. In this talk, we describe how these two technologies work together to form applications that are both highly scalable and resilient to failure. We introduce linkerd, an open-source proxy form of Finagle, which extends Finagle's operational model to non-JVM or polyglot microservices. Finally, we show how linkerd can be used to "wrap" applications running on Mesos to provide higher-level, service-based semantics around scalability, reliability, and fault-tolerance for microservices---even in the presence of unpredictable traffic volumes and unreliable hardware.

625beff353c7c2b068b26d1a57566e05?s=128

Oliver Gould

June 02, 2016
Tweet

Transcript

  1. Finagle, linkerd, and Mesos
 Magic Operability Sprinkles for Microservices oliver

    gould
 cto, buoyant MesosCon North America, June 2 2016 from
  2. oliver gould • founding cto @ buoyant
 open-source microservice infrastructure

    • previously, tech lead @ twitter:
 observability, traffic • core contributor: finagle • creator: linkerd • likes: dogs • dislikes: being woken up by a pager @olix0r
 ver@buoyant.io
  3. overview • 2010: A Failwhale Odyssey • Automating the Datacenter

    • Microservices: A Silver Bullet • Finagle: The Once and Future Layer 5 • Introducing linkerd • Demo • Q&A
  4. 2010 A FAILWHALE ODYSSEY

  5. Twitter, 2010 107 users 107 tweets/day 102 engineers 101 services

    101 deploys/week 102 hosts 0 datacenters 101 user-facing outages/week https://blog.twitter.com/2010/measuring-tweets
  6. None
  7. None
  8. Events https://blog.twitter.com/2013/new-tweets-per-second-record-and-how

  9. Asymmetry Photo by Troy Holden

  10. Provisioning

  11. automating the datacenter

  12. mesos.apache.org UC Berkeley, 2010 Twitter, 2011 Apache, 2012 Abstracts compute

    resources Promise: don’t worry about the hosts
  13. aurora.apache.org Twitter, 2011 Apache, 2013 Schedules processes on Mesos Promise:

    no more puppet, monit, etc
  14. timelines Aurora (or Marathon, or …) host Mesos host host

    host host host users notifications x800 x300 x1000
  15. microservices A SILVER BULLET

  16. scaling teams growing software

  17. flexibility

  18. performance correctness monitoring debugging efficiency security operability
 resilience

  19. there are no magic sprinkles. (sorry.)

  20. Resilience is an imperative: our software runs on the truly

    dismal computers we call datacenters. Besides being heinously
 complex… they are unreliable and prone to
 operator error. Marius Eriksen @marius
 RPC Redux
  21. resilience in microservices software you didn’t write hardware you can’t

    touch network you can’t configure break in new and surprising ways and your customers shouldn’t notice
  22. resilient microservices means resilient communication

  23. datacenter [1] physical [2] link [3] network [4] transport aurora,

    marathon, … mesos 
 canal, weave, … aws, azure, digitalocean, gce, … business languages, libraries [7] application rpc [5] session [6] presentation json, protobuf, thrift, … http/2, mux, …
  24. layer 5 dispatches requests onto layer 4 connections

  25. finagle THE ONCE AND FUTURE LAYER 5

  26. github.com/twitter/finagle RPC library (JVM) asynchronous built on Netty scala functional

    strongly typed first commit: Oct 2010
  27. used by…

  28. programming finagle val users = Thrift.newIface[UserSvc](“/s/users”)
 val timelines = Thrift.newIface[TimelineSvc](“/s/timeline”)

    Http.serve(“:8080”, Service.mk[Request, Response] { req => for { user <- users.get(userReq(req)) timeline <- timelines.get(user) } yield renderHTML(user, timeline) })
  29. operating finagle transport security service discovery circuit breaking backpressure deadlines

    retries tracing metrics keep-alive multiplexing load balancing per-request routing service-level objectives Observe Session timeout Retries Request draining Load balancer Monitor Observe Trace Failure accrual Request timeout Pool Fail fast Expiration Dispatcher
  30. layer 5 naming

  31. layer 5 naming applications refer to logical names
 requests are

    bound to concrete names
 delegations express routing /s/users /#/io.l5d.zk/prod/users /s => /#/io.l5d.zk/prod/http
  32. per-request routing: staging GET / HTTP/1.1
 Host: mysite.com
 Dtab-local: /s/B

    => /s/B2
  33. per-request routing: debug proxy GET / HTTP/1.1
 Host: mysite.com
 Dtab-local:

    /s/E => /s/P/s/E
  34. tracing

  35. tracing

  36. tracing

  37. “It’s slow”
 is the hardest problem you’ll ever debug. Jeff

    Hodges @jmhodges
 Notes on Distributed Systems for Young Bloods
  38. the more components you deploy, the more problems you have

  39. the more components you deploy, the more problems you have

  40. the more components you deploy, the more problems you have

  41. lb algorithms: • round-robin • fewest connections • queue depth

    • exponentially-weighted moving average (ewma) • aperture load balancing at layer 5
  42. timeouts & retries timelines users web db timeout=400ms retries=3 timeout=400ms

    retries=2 timeout=200ms retries=3 timelines users web db
  43. timeouts & retries timelines users web db timeout=400ms retries=3 timeout=400ms

    retries=2 timeout=200ms retries=3 timelines users web db 800ms! 600ms!
  44. deadlines timelines users web db timeout=400ms deadline=323ms deadline=210ms 77ms elapsed

    113ms elapsed
  45. retries typical: retries=3

  46. retries typical: retries=3 worst-case: 300% more load!!!

  47. budgets typical: retries=3 better:
 retryBudget=20% worst-case: 300% more load!!! worst-case:

    20% more load
  48. so all i have to do is rewrite my app

    in scala?
  49. linkerd

  50. github.com/buoyantio/linkerd microservice rpc proxy layer-5 router aka l5d built on

    finagle & netty pluggable http, thrift, … etcd, consul, kubernetes, marathon, zookeeper, … …
  51. magic resiliency sprinkles transport security service discovery circuit breaking backpressure

    deadlines retries tracing metrics keep-alive multiplexing load balancing per-request routing service-level objectives Service B instance linkerd Service C instance linkerd Service A instance linkerd
  52. namerd released in March centralized routing policy delegates logical names

    to service discovery pluggable etcd kubernetes zookeeper …
  53. namerd

  54. demo: gob’s microservice

  55. web word gen l5d l5d l5d

  56. web word gen gen-v2 l5d l5d l5d l5d

  57. web word gen gen-v2 l5d l5d l5d l5d namerd

  58. master dc/os marathon zookeeper node node public node node …

    ELB ELB
  59. master dc/os marathon zookeeper node node public node node …

    linkerd linkerd linkerd linkerd ELB ELB namerd
  60. master dc/os marathon zookeeper node node public node node …

    linkerd linkerd linkerd linkerd ELB ELB namerd web (x1) gen (x3) word (x3) word-growthhack (x3) gen-growthhack (x3)
  61. github.com/buoyantio/linkerd-examples

  62. linkerd roadmap • Netty4.1 • HTTP/2+gRPC linkerd#174 • TLS client

    certs, SPIFEE • Deadlines • Announcers • All configurable everything
  63. more at linkerd.io slack: slack.linkerd.io email: ver@buoyant.io twitter: • @olix0r

    • @linkerd thanks!