From d468efe031b7b569d8a9d67cf3d838c8cb0cdfeb Mon Sep 17 00:00:00 2001 From: David Eliahu Date: Thu, 25 Jun 2020 13:09:21 -0700 Subject: [PATCH 1/2] Add troubleshooting docs for API request errors --- docs/summary.md | 1 + docs/troubleshooting/api-request-errors.md | 9 +++++++++ 2 files changed, 10 insertions(+) create mode 100644 docs/troubleshooting/api-request-errors.md diff --git a/docs/summary.md b/docs/summary.md index 10c2b8bdea..eba49cf519 100644 --- a/docs/summary.md +++ b/docs/summary.md @@ -46,6 +46,7 @@ ## Troubleshooting * [API is stuck updating](troubleshooting/stuck-updating.md) +* [404/503 API responses](troubleshooting/api-request-errors.md) * [NVIDIA runtime not found](troubleshooting/nvidia-container-runtime-not-found.md) * [TF session in predict()](troubleshooting/tf-session-in-predict.md) diff --git a/docs/troubleshooting/api-request-errors.md b/docs/troubleshooting/api-request-errors.md new file mode 100644 index 0000000000..7d26827704 --- /dev/null +++ b/docs/troubleshooting/api-request-errors.md @@ -0,0 +1,9 @@ +# 404 or 503 error responses from API requests + +_WARNING: you are on the master branch, please refer to the docs on the branch that matches your `cortex version`_ + +When making prediction requests to your API, it's possible to get a `{"message":"Not Found"}` error message (with HTTP status code `404`), or a `no healthy upstream` error message (with HTTP status code `503`). This means that there are currently no live replicas running for your API. This could happen for a few reasons: + +1. It's possible that your API is simply not ready yet. You can check the status of your API with `cortex get API_NAME`, and stream the logs with `cortex logs API_NAME`. +1. Your API may have errored. `cortex get API_NAME` will show the status of your API, and you can view the logs with `cortex logs API_NAME`. +1. If `cortex get API_NAME` shows your API's status as "updating" for a while and if `cortex logs API_NAME` doesn't shed any light onto what may be wrong, please see the [API is stuck updating](stuck-updating.md) troubleshooting guide. From c440dbecd21ecc845a5e7f9ba6aa698d9a345045 Mon Sep 17 00:00:00 2001 From: David Eliahu Date: Thu, 25 Jun 2020 16:06:03 -0700 Subject: [PATCH 2/2] Update api-request-errors.md --- docs/troubleshooting/api-request-errors.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/troubleshooting/api-request-errors.md b/docs/troubleshooting/api-request-errors.md index 7d26827704..41288c2832 100644 --- a/docs/troubleshooting/api-request-errors.md +++ b/docs/troubleshooting/api-request-errors.md @@ -5,5 +5,5 @@ _WARNING: you are on the master branch, please refer to the docs on the branch t When making prediction requests to your API, it's possible to get a `{"message":"Not Found"}` error message (with HTTP status code `404`), or a `no healthy upstream` error message (with HTTP status code `503`). This means that there are currently no live replicas running for your API. This could happen for a few reasons: 1. It's possible that your API is simply not ready yet. You can check the status of your API with `cortex get API_NAME`, and stream the logs with `cortex logs API_NAME`. -1. Your API may have errored. `cortex get API_NAME` will show the status of your API, and you can view the logs with `cortex logs API_NAME`. +1. Your API may have errored during initialization or while responding to a previous request. `cortex get API_NAME` will show the status of your API, and you can view the logs with `cortex logs API_NAME`. 1. If `cortex get API_NAME` shows your API's status as "updating" for a while and if `cortex logs API_NAME` doesn't shed any light onto what may be wrong, please see the [API is stuck updating](stuck-updating.md) troubleshooting guide.