~/talk

Joining The Dots: How Span Links And Fake Traces...

links:none on file
links:none on file
slides:none on file

Engineers build supertraces to represent 12‑day deployments as a single logical trace by emitting a synthetic root span (created via a risky reflection hack in .NET Activity) and linking high‑volume, sampled event traces with span links. Pipeline uses RabbitMQ, SQL Server and SMB mounts; OpenTelemetry Collector applies ~1:1000 sampling for events while keeping all deployment traces. A 10‑second forced emit marks stuck work. Root cause for long gaps is slow network file I/O; switching to HTTP file ops and payload-on-disk reduces pauses and validates the approach.

AI-written summary · about

  1. 0:00Introduction and Kanizsa triangle
  2. 1:03OTel limitations for long deployments
  3. 2:46Challenges with automatic instrumentation
  4. 4:10Deployment as a trace structure
  5. 5:57Root span memory constraints
  6. 7:01Hacking .NET Activity API
  7. 8:44Backwards emission of deployment traces
  8. 9:26Span links for event traces
  9. 10:10Deployment duration surprises
  10. 11:12SQL Server and RabbitMQ choice
  11. 12:37Diagnosing file system bottlenecks
  12. 14:00Halting problem in deployments
  13. 16:32Timers for stuck deployments
  14. 17:36Future work and randomness value
  15. 18:40Q&A and acknowledgments
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 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
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
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.