Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Mystery Machine Overview

340 views

Published on

End-to-end Performance Analysis of Large-scale Internet Services

Published in: Software
  • Be the first to comment

  • Be the first to like this

Mystery Machine Overview

  1. 1. Nov, 2015 Review of Mystery Machine Ivan Glushkov ivan.glushkov@gmail.com @gliush
  2. 2. Why ❖ Need to debug and optimize applications ❖ Complex, heterogenous systems ❖ Different parts written in different languages ❖ Different communicative channels ❖ Different execution environments ❖ Even if individual components are optimized - the whole system might not work optimally
  3. 3. What ❖ They develop performance analysis tools ❖ They apply it to their pipeline ❖ They measure end-to-end performance: ❖ from the point of initiating a page load ❖ to the point when browser finishes rendering
  4. 4. Why not ❖ All current approaches assume you instrument your code, specify relations, etc ❖ Usually you don’t have time or ability ❖ Large systems are developed by large teams ❖ Adding instrumentation retroactively is a Herculean task
  5. 5. Overview ❖ They generate a model via large scale reasoning of logs ❖ They can confirm relationships ❖ They need only (requestId, hostId, hostTS, eventId) in each log message ❖ UberTrace gathers all the log to one point ❖ MysteryMachine conducts causality model from that traces ❖ MysteryMachine performs analyses: identifying critical paths, slack analysis, outlier detection
  6. 6. UberTrace: why ❖ No tools to analyze inter-process optimality ❖ They need to have a single end-to-end performance tracing tool for all logs
  7. 7. UberTrace: requirements ❖ Each log message should contain ❖ Unique request id ❖ Computer id (server node / client laptop) ❖ Timestamp (local clock) ❖ Event name (e.g. “start DOM arendering”) ❖ Task name (<Event,Task> should be unique) ❖ Propagate decision about logging particular request
  8. 8. UberTrace ❖ TS are from local clocks -> translated to global clock ❖ Execution time = Latest TS - Earliest TS ❖ RTT = Es - Ec ❖ Clock skew = 1/2 RTT ❖ Multiple observation,
 choose minimal one
  9. 9. Mystery Machine: casual model ❖ Split all logs into segments
 (two consecutive events
 for the same task) ❖ Create a casual model ❖ They validated this model
 for client-side js library
 (42 and 84 segments -> 2583 and 10458 casual relationships)
  10. 10. Mystery Machine: casual model
  11. 11. Mystery Machine: casual model
  12. 12. Mystery Machine: casual model
  13. 13. Mystery Machine: critical path Critical path - set of segments for which a differential increase in segments execution time would result in the same differential increase in the end-to-end latency
  14. 14. Mystery Machine: critical path
  15. 15. Mystery Machine: slack Slack - the amount by which the duration of a segment may increase without increasing the end-to-end latency of the request
  16. 16. Mystery Machine: slack validation
  17. 17. Mystery Machine: slack analyses usage
  18. 18. Links ❖ Video: https://www.usenix.org/node/186168 ❖ Slides: https://www.usenix.org/sites/default/files/ conference/protected-files/osdi14_slides_chow.pdf ❖ Paper: https://www.usenix.org/system/files/ conference/osdi14/osdi14-paper-chow.pdf

×