1 / 22

Failure Detectors

Failure Detectors. Slides by I. Gupta, modified by N. Vaidya. Two Different System Models. S ynchronous Distributed System Each message is received within bounded time Each step in a process takes lb < time < ub Each local clock’s drift has a known bound Asynchronous Distributed System

wyanet
Télécharger la présentation

Failure Detectors

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Failure Detectors Slides by I. Gupta, modified by N. Vaidya

  2. Two Different System Models • Synchronous Distributed System • Each message is received within bounded time • Each step in a process takes lb < time < ub • Each local clock’s drift has a known bound • Asynchronous Distributed System • No bounds on process execution • No bounds on message transmission delays • The drift rate of a clock is arbitrary Internet is an asynchronous distributed system

  3. Failure Model • Process omission failure • Crash-stop (fail-stop) – a process halts and does not execute any further operations • Crash-recovery – a process does not execute operations for a while • Crash-stop failures can be detected in synchronous systems • Next: detecting crash-stop failures in asynchronous systems

  4. What’s a failure detector? pi pj

  5. What’s a failure detector? Crash-stop failure pi pj X

  6. What’s a failure detector? needs to know about pj’s failure Crash-stop failure pi pj X

  7. I. Heartbeating Protocol needs to know about pj’s failure heartbeat pi pj - pj maintains a sequence number - pj sends pi a heartbeat with incremented seq. number after every T’(=T) time units • if pi has not received a heartbeat for the • past T time units, pi declares pj as failed

  8. II. Ping-Ack Protocol needs to know about pj’s failure (within 2T ms) ping pi pj ack - pi queries pj once every T time units - if pj does not respond within T time units, pi marks pj as failed - pj replies

  9. Failure Detector Properties • Completeness = every process failure is eventually detected • Accuracy = every detected failure corresponds to a crashed process • Given a failure detector that satisfies both Completeness and Accuracy • Consensus is achievable (why?) • FLP => one cannot design a failure detector (for an asynchonrous system) that guarantees both above properties

  10. Completeness or Accuracy? • Most failure detector implementations are willing to tolerate some inaccuracy, but require 100% Completeness • Heartbeating – satisfies completeness but not accuracy (why?) • Ping-Ack – satisfies completeness but not accuracy (why?) • Plenty of distributed apps designed assuming 100% completeness, e.g., p2p systems

  11. Failure Detection in a Distributed System • Difference from original failure detection is • we want all processes to know about failure •  May need combine failure detection with a dissemination protocol • What’s an example of a dissemination protocol?

  12. Centralized Heartbeating pj … pj, Heartbeat Seq. l++ pi Needs a separate dissemination component

  13. Ring Heartbeating pj pj, Heartbeat Seq. l++ pi … … Needs a separate dissemination component

  14. All-to-All Heartbeating pj pj, Heartbeat Seq. l++ … pi Does not need a separate dissemination component

  15. Failure Detector Metrics • Measuring Speed: Detection Time • Time between a process crash and its detection • Determines speed of failure detector • Measuring Accuracy: depends on distributed application App1: Failure detection => unavailability, e.g., read-only replicated database with no updates App2: Failure detection => exclusion from group, e.g., replicated database with updates

  16. Accuracy metrics for App1 • App1: Failure detection => unavailability, e.g., read-only replicated database with no updates • Tmr: Mistake recurrence time • Time between two consecutive mistakes • Tm: Mistake duration time • Length of time for which correct process is marked as failed pj up FD for pj at pi Tm Tmr pj is down pj is up

  17. Accuracy metrics for App2 • App2: Failure detection => exclusion from group, e.g., replicated database with updates Possible metrics: • Number of false failure detections per time unit • Fraction of failure detections that are false

  18. Processes and Channels

  19. Other Failure Types • Communication omission failures • Send-omission: loss of messages between the sending process and the outgoing message buffer • Channel omission: loss of message in the communication channel. • Receive-omission: loss of messages between the incoming message buffer and the receiving process

  20. Other Failure Types Arbitrary failures • Arbitrary process failure: arbitrarily omits intended processing steps or takes unintended processing steps. • Arbitrary channel failures: messages may be corrupted, duplicated, delivered out of order, incurs extremely large delays; or non-existent messages may be delivered. • Above are Byzantine failures

  21. Class of failure Affects Description Fail-stop Process Process halts and remains halted. Other processes may detect this state. Crash Process Process halts and remains halted. Other processes may not be able to detect this state. Omission Channel A message inserted in an outgoing message buffer never arrives at the other end’s incoming message buffer. Send-omission Process A process completes a send, but the message is not put in its outgoing message buffer. Receive-omission Process A message is put in a process’s incoming message buffer, but that process does not receive it. Arbitrary Process or Process/channel exhibits arbitrary behaviour: it may (Byzantine) channel send/transmit arbitrary messages at arbitrary times, commit omissions; a process may stop or take an incorrect step. Omission and Arbitrary Failures

  22. Summary • Failure detectors required in distributed systems to maintain liveness in spite of process crashes • Properties – completeness & accuracy, together unachievable • Most apps require 100% completeness, but can tolerate inaccuracy • Heartbeating and Ping • Distributed FD through heartbeating: Centralized, Ring, All-to-all • Accuracy metrics • Other Types of Failures

More Related