#17
下面是關於smp和mpp的介紹,如果你的數據量夠到n個G,機器有m個cpu的unix,內存有?個G,倒是想跟你交流下
Parallel-Processing Environments: SMP and Cluster/MPP
The environment in which you run your Orchestrate applications is defined by your system’s architecture
and hardware resources. All parallel-processing environments are categorized as one of the
following:
• SMP (symmetric multiprocessing), in which some hardware resources may be shared among
processors
• Cluster or MPP (massively parallel processing), also known as shared-nothing, in which each
processor has exclusive access to hardware resources
SMP systems allow you to scale up the number of CPUs, which may improve application
performance. The performance improvement depends on whether your application is CPU-,
memory-, or I/O-limited. In CPU-limited applications, the memory, memory bus, and disk I/O
spend a disproportionate amount of time waiting for the CPU to finish its work. Running a CPUlimited
application on more processing units can shorten the waiting time of other resources and
thereby speed up overall performance.
Some SMP systems allow scalability of disk I/O, so that throughput improves as the number of
processors increases. A number of factors contribute to the I/O scalability of an SMP, including the
number of disk spindles, the presence or absence of RAID, and the number of I/O controllers
In a cluster or MPP environment, you can use the multiple CPUs and their associated memory and
disk resources in concert to tackle a single application. In this environment, each CPU has its own
dedicated memory, memory bus, disk, and disk access. In a shared-nothing environment, parallelization
of your application is likely to improve the performance of CPU-limited, memory-limited,
or disk I/O-limited applications.
:)