Big memory

Posted on By Experte

Memory (RAM ) is a large memory device that has a large memory RAM ( random-access memory ) memory. Some workloads are databases, in-memory caches, and graph analytics. [1] Now, more generally, data science and big data.

Some database systems are designed to run mostly in memory, rarely if ever retrieving data from disk or flash memory. See list of in-memory databases .

The performance of big memory systems depends on the CPU’s or CPU’s access to the memory, via a standard controller or via NUMA ( non-uniform memory access ). Performance also depends on the size and design of the CPU cache .

Performance also depends on OS design. The “Huge pages” feature in Linux can improve the efficiency of virtual memory . [2] The new “Transparent Huge Pages” feature in Linux can offer better performance for some big-memory workloads. [3] The “Large-Page Support” in Microsoft Windows allows you to set up large-page memory regions that are typically smaller than the native page size. [4]

References

  1. Jump up^ “Efficient Virtual Memory for Big Memory Servers” (PDF) . Retrieved 2016-09-24 .
  2. Jump up^ “Huge pages part 1 (Introduction)” . Retrieved 2016-09-24 .
  3. Jump up^ “Transparent huge pages in 2.6.38” . Retrieved 2016-09-24 .
  4. Jump up^ “Large-Page Support” . Retrieved 2016-09-24 .