Zipkin and OSI PI Integration

Input and output integration overview

The Zipkin Input Plugin allows for the collection of tracing information and timing data from microservices. This capability is essential for diagnosing latency troubles within complex service-oriented environments.

This setup converts Telegraf into a lightweight PI Web API publisher, letting you push any Telegraf metric into the OSI PI System with a simple HTTP POST.

Integration details

Zipkin

This plugin implements the Zipkin HTTP server to gather trace and timing data necessary for troubleshooting latency issues in microservice architectures. Zipkin is a distributed tracing system that helps gather timing data across various microservices, allowing teams to visualize the flow of requests and identify bottlenecks in performance. The plugin offers support for input traces in JSON or thrift formats based on the specified Content-Type. Additionally, it utilizes span metadata to track the timing of requests, enhancing the observability of applications that adhere to the OpenTracing standard. As an experimental feature, its configuration and schema may evolve over time to better align with user requirements and advancements in distributed tracing methodologies.

OSI PI

OSI PI is an data management and analytics platform used in energy, manufacturing, and critical infrastructure. The PI Web API is its REST interface, exposing endpoints such as /piwebapi/streams/{WebId}/value that accept JSON payloads containing a Timestamp and Value. By pairing Telegraf’s flexible HTTP output with this endpoint, any metric Telegraf collects—SNMP counters, Modbus readings, Kubernetes stats—can be written directly into PI without installing proprietary interfaces. The configuration above authenticates with Basic or Kerberos, serializes each batch to JSON, and renders a minimal body template that aligns with PI Web API’s single-value write contract. Because Telegraf already supports batching, TLS, proxies, and custom headers, this approach scales from edge gateways to cloud VMs, allowing organizations to back-fill historical data, stream live telemetry, or mirror non-PI sources (e.g., Prometheus) into the PI data archive. It also sidesteps older SDK dependencies and enables hybrid architectures where PI remains on-prem while Telegraf agents run in containers or IIoT devices.

Configuration

Zipkin

[[inputs.zipkin]]
  ## URL path for span data
  # path = "/api/v1/spans"

  ## Port on which Telegraf listens
  # port = 9411

  ## Maximum duration before timing out read of the request
  # read_timeout = "10s"
  ## Maximum duration before timing out write of the response
  # write_timeout = "10s"

OSI PI

[[outputs.http]]
  ## PI Web API endpoint for writing a single value to a PI Point by Web ID
  url = "https://${PI_HOST}/piwebapi/streams/${WEB_ID}/value"

  ## Use POST for each batch
  method       = "POST"
  content_type = "application/json"

  ## Basic-auth header (base64-encoded "DOMAIN\\user:password")
  headers = { Authorization = "Basic ${BASIC_AUTH}" }

  ## Serialize Telegraf metrics as JSON
  data_format           = "json"
  json_timestamp_units  = "1ms"

  ## Render the JSON body that PI Web API expects
  body_template = """
  {{ range .Metrics -}}
  { "Timestamp": "{{ .timestamp | formatDate \"2006-01-02T15:04:05Z07:00\" }}", "Value": {{ index .fields 0 }} }
  {{ end -}}
  """

  ## Tune networking / batching if needed
  # timeout     = "10s"
  # batch_size  = 1

Input and output integration examples

Zipkin

1. Latency Monitoring in Microservices: Use the Zipkin Input Plugin to capture and analyze tracing data from a microservices architecture. By visualizing the request flow and pinpointing latency sources, development teams can optimize service interactions, improve response times, and ensure a smoother user experience across services.

2. Performance Optimization in Essential Services: Integrate the plugin within critical services to monitor not only the response times but also track specific annotations that could highlight performance issues. The ability to gather span data can help prioritize areas needing performance enhancements, leading to targeted improvements.

3. Dynamic Service Dependency Mapping: With the collected trace data, automatically map service dependencies and visualize them in dashboards. This helps teams understand how different services interact and the impact of failures or slowdowns, ultimately leading to better architectural decisions and faster resolutions of issues.

4. Anomaly Detection in Service Latency: Combine Zipkin data with machine learning models to detect unusual patterns in service latencies and request processing times. By automatically identifying anomalies, operations teams can respond proactively to emerging issues before they escalate into critical failures.

OSI PI

1. Remote Pump Stations Telemetry Bridge: Install Telegraf on edge gateways at oil-field pump stations, gather flow-meter and vibration readings over Modbus, and POST them to the PI Web API. Operations teams view real-time data in PI Vision without deploying heavyweight PI interfaces, while bandwidth-friendly batching keeps satellite links economical.

2. Green-Energy Micro-Grid Dashboard: Export inverter, battery, and weather metrics from MQTT into Telegraf, which relays them to PI. PI AF analytics can calculate real-time power balance and feed a campus dashboard; historical deltas inform sustainability reports.

3. Brownfield SCADA Modernization: Legacy PLCs logged to CSV are ingested by Telegraf’s tail input; each row is parsed and immediately sent to PI via HTTP, creating a live data stream that co-exists with archival files while the SCADA upgrade proceeds incrementally.

4. Synthetic Data Generator for Training: Telegraf’s exec input can run a script that emits simulated sensor patterns. Posting those metrics to a non-production PI server through the Web API supplies realistic datasets for PI Vision training sessions without risking production tags.

Feedback

Thank you for being part of our community! If you have any general feedback or found any bugs on these pages, we welcome and encourage your input. Please submit your feedback in the InfluxDB community Slack.