Deviant and irregular execution times
This is kind of related to my previous post How does cold start work?.
I've sent an in app support request showing a video on deviant execution times: #182588
We have two BuildShip workflows that we use for an AI Chatbot (a "Trigger" and a "Message" workflow). Our goal is to reach a super low latency response. Though both workflows show extraordinary response times in some cases.
My concerns are these:
1. "Get document" node sometimes takes several hundreds of milliseconds and sometimes even more than a second to retrieve a simple database line from the BuildShip database (even though there is not much data inside)
2. "Execute Workflow" node can also take several hundreds of milliseconds to be executed even though the remote workflow just runs some simple javascript code.
3. "Execute Workflow" node apparently takes up extra time to "connect" to the remote workflow which adds further unnecessary latency. Are you doing an internal REST API call with this node?
4. Several nodes like "Get document" or "Execute workflow" have very deviating execution times even though they always have the same complexity
5. REST API call of a workflow adds several hundreds of milliseconds (see attached images: upper diagram shows REST API call response time and lower diagram shows internal workflow execution time which are manually recorded by extra nodes in the beginning and end of a workflow)
6. Why are some super simple Javascript nodes running several hundreds of a milliseconds sometimes? Is every node basically adding significant delay and in best case scenario we should put most code into one node?
7. Is there something faster than a REST API call that we can do to execute a BuildShip workflow?
8. Do you have several servers running across the globe to allow the clients to connect to the server with the best ping possible?
It would be great if you can take the time and respond to every single point here.
I've sent an in app support request showing a video on deviant execution times: #182588
We have two BuildShip workflows that we use for an AI Chatbot (a "Trigger" and a "Message" workflow). Our goal is to reach a super low latency response. Though both workflows show extraordinary response times in some cases.
My concerns are these:
1. "Get document" node sometimes takes several hundreds of milliseconds and sometimes even more than a second to retrieve a simple database line from the BuildShip database (even though there is not much data inside)
2. "Execute Workflow" node can also take several hundreds of milliseconds to be executed even though the remote workflow just runs some simple javascript code.
3. "Execute Workflow" node apparently takes up extra time to "connect" to the remote workflow which adds further unnecessary latency. Are you doing an internal REST API call with this node?
4. Several nodes like "Get document" or "Execute workflow" have very deviating execution times even though they always have the same complexity
5. REST API call of a workflow adds several hundreds of milliseconds (see attached images: upper diagram shows REST API call response time and lower diagram shows internal workflow execution time which are manually recorded by extra nodes in the beginning and end of a workflow)
6. Why are some super simple Javascript nodes running several hundreds of a milliseconds sometimes? Is every node basically adding significant delay and in best case scenario we should put most code into one node?
7. Is there something faster than a REST API call that we can do to execute a BuildShip workflow?
8. Do you have several servers running across the globe to allow the clients to connect to the server with the best ping possible?
It would be great if you can take the time and respond to every single point here.
