~/talk

Pulsar Functions Deep Dive

Talkat Data Con LA 2020 · 2020-10-23..10-25· [distributed-systems, kubernetes]
slides:none on file

Pulsar Functions implements lightweight serverless stream processing on Apache Pulsar, running function instances as threads/processes/pods (including Kubernetes) with runtimes selected per language and gRPC/protobuf used for control. Deployments require tenant/namespace/name, input/output topics, parallelism (e.g. 5–20 instances), and processing guarantees; the system uses a metadata topic as single source of truth (BookKeeper-backed) with first-writer-wins updates and an assignment topic for scheduling. Known limits: metadata growth and slow worker start. Roadmap includes function mesh, dynamic runtime selection and metadata compaction.

AI-written summary · about

  1. 0:00Intro
  2. 1:30Pulsar Functions:- A Deep Dive Agenda
  3. 2:13Pulsar Functions:- A Brief Introduction
  4. 6:53Pulsar Functions:- Submission Workflow
  5. 17:44Pulsar Functions:- Scheduling Workflow
  6. 23:16Pulsar Functions:- Execution Workflow
  7. 26:54Pulsar Functions:- Java Instance
  8. 29:00Pulsar Functions:- Future Work
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.