pixie
pixie copied to clipboard
pixie-io
Instant Kubernetes-Native Application Observability
See video. This is more noticeable for longer time periods because it's harder for the mouse to avoid the plotted line in the timeseries. 1. Go to px/node for any...
![sync-by-unito[bot] avatar](https://avatars.githubusercontent.com/in/64202?v=4 "sync-by-unito[bot] avatar"){kind=avatar}
Intermittently getting the following error message when I try to run the attached script: ``` Failed to execute script Compiler error on line 342, column 23: UDF 'ip_to_pod_id' must execute...
The following code (with start_time == `1s`) returns an empty table. Since we don't allow future start_times, we should error. import px df = px.DataFrame(table='http_events', start_time='1s') px.display() ┆Issue is synchronized...
Expected behavior: stream all data captured after the `start_time` and into future. Actual behavior: data is streamed from the `start_time` to the present time, and then streaming ends. ┆Issue is...
According to [~accountid:5e26aeb0db3c400c9ddecd9e] 's report: I have the demo app from src/stirling/source_connectors/socket_tracer/protocols/pgsql/testing/ running on my cluster. At first stirling will trace the pgsql traffic from it, but if I leave...
I deployed `src/stirling/source_connectors/socket_tracer/protocols/pgsql/testing/postgres.yaml` and `src/stirling/source_connectors/socket_tracer/protocols/pgsql/testing/demo.yaml` to a namespace called stirling-testing. After 1-2minutes no traffic is traced from the postgres demo pod to postgres anymore. Deleting the demo pod and restarting...
This is due to the way memory_source_node.cc handles not finding the start time. Any streaming query with a start time in the future, will run forever outputting Zero row row...
We want to be able to track the operator version and current pod status like we do with Vizier version and pods. Currently, the operator is in a different namespace....
We need to make kafka tracing more robust to lost or mis-aligned events. This includes: * Hardening FindFrameBoundary, especially for responses, which need to have already matched with a request...
We use limit nodes for both implicit and explicit table truncation. * Explicit truncation is done via `px.head` in the script. * Implicit truncation is done via the `max_output_rows_per_table` flag....