We are experiencing poor performance with a Sunfire T2000 server with 32GB RAM, one 8 Core CPU, 1GHz processor.
The server was purchased for PX jobs however the current code has not yet been converted.
Initial benchmarks are showing drastic performance hits when compared to a Semetrical multiprocessor server (V880)
When writing to hash files over 450% degradation of performance compared to the same job and input on a Sunfire V880 with 4CPU and 8GB RAM running at 1.2GHz
When writing sequential FF to sequential FF the degradation is 40%
Do these numbers seem accurate since Server is a single threaded application that we are trying to run on a box designed for a multi-threaded app?
Poor performance on Sunfire T2000
Moderators: chulett, rschirm, roy
-
ray.wurlod
- Participant
- Posts: 54595
- Joined: Wed Oct 23, 2002 10:52 pm
- Location: Sydney, Australia
- Contact:
Welcome aboard.
Define "performance" in an ETL context. What measurements are you taking about resource consumption?
DataStage starts processes. Allocation of those processes to CPUs is a function of the operating system. Eight cores should theoretically be the same as eight single-core CPUs in standard benchmark tests (keep DataStage out of the picture) - if it's not you probably need to get Sun involved to find out why not.
Define "performance" in an ETL context. What measurements are you taking about resource consumption?
DataStage starts processes. Allocation of those processes to CPUs is a function of the operating system. Eight cores should theoretically be the same as eight single-core CPUs in standard benchmark tests (keep DataStage out of the picture) - if it's not you probably need to get Sun involved to find out why not.
IBM Software Services Group
Any contribution to this forum is my own opinion and does not necessarily reflect any position that IBM may hold.
Any contribution to this forum is my own opinion and does not necessarily reflect any position that IBM may hold.

