So in fact, your change does not remove multiple fast models except on one server, fastmodels02.
Perhaps the solution is to have a new device type, rtsm_ve-armv8-single which is guaranteed to run on a single node, and only provide one of those.
My main issue here is that if we have to have a server per fast model instance, then to support the current load and spread, and future new fast model types, I need 10 servers, at $2000 each, one per fast model instance. That seems rather excessive.
You will need to get authorisation from Mark Orvek for that sort of spend.
So, previous to this change we had:
fastmodels01 foundation- armv8_01 ve-a15x1- a7x1_01 ve-a15x4- a7x4_01 ve-a15x4- a7x4_02 foundation- armv8_02
rtsm_
rtsm_
rtsm_
rtsm_
rtsm_ve-armv8_03
rtsm_ve-armv8_04
fastmodels02
rtsm_ve-armv8_01
rtsm_ve-armv8_02
fastmodels03
rtsm_
rtsm_ve-armv8_05
And after this change we would have:
fastmodels01 foundation- armv8_01 ve-a15x1- a7x1_01 ve-a15x4- a7x4_01 ve-a15x4- a7x4_02
rtsm_
rtsm_
rtsm_
rtsm_
rtsm_ve-armv8_01
fastmodels02
rtsm_ve-armv8_02
fastmodels03 foundation- armv8_02
rtsm_
rtsm_ve-armv8_03
So in fact, your change does not remove multiple fast models except on one server, fastmodels02.
Perhaps the solution is to have a new device type, rtsm_ve- armv8-single which is guaranteed to run on a single node, and only provide one of those.
My main issue here is that if we have to have a server per fast model instance, then to support the current load and spread, and future new fast model types, I need 10 servers, at $2000 each, one per fast model instance. That seems rather excessive.
You will need to get authorisation from Mark Orvek for that sort of spend.