BMD: Best practice for virtualisation and hardware recommendations

Virtualisation has evolved steadily over the past few years and has become an integral part of today's IT infrastructure. Below, you will find a few useful tips and tricks on how to get the most out of the BMD software in your virtual environment. This guide is based on an HP ProLiant Gen9 Server with Intel Xeon E5 v3 processor technology and DDR4 RAM under VMWare ESXi 6.0.

Recommendations for CPUs

The BMD software is a single-core application, which means that it benefits more from a processor with a higher frequency than from a processor with many cores. We therefore do not recommend using so-called entry-level and low-voltage CPUs. Modern processors also have various energy-saving mechanisms which, however, significantly limit the performance. Therefore, these power options should always be set to maximum performance.

Recommendations for RAM

As for RAM, the BMD software does not have special requirements. However, experience has shown that an even distribution over all memory channels and the use of dual-rank modules offer the best performance. Any "overcommitment" of the RAM should be avoided.

Recommendations for drives

Drives are supposedly the most important factor for optimal operation. The more virtual machines need to share the available memory, the faster it should be.Using SSDs contributes to a significant increase in performance. However, there are some additional aspects that are of importance. 

When using SAS hard drives:

• Type of array: 
  as a rule of thumb, use RAID 10 for optimal performance
• Number of drives:
  as a rule of thumb, the more drives the faster
• Use of 10k and 15k drives:
  the increased performance usually does not justify the price difference. We recommend investing in more 10k drives rather than in expensive 15k drives.

When using SSDs:

When used for servers, SSDs are generally divided into different price/performance categories:

• Read Intensive
• Mixed Use
• Write Intensive

If you want to use an SSD as both a read and write cache, only the models of the categories "Mixed Use" and "Write Intensive" are recommended. 

In the test scenario below, we compare RAID5, RAID50 and RAID10 in combination with an SSD as a cache to their counterparts. The only aspect measured was random access (random I/O). The transfer rate (sequential I/O) is not conclusive enough for a practical comparison and is therefore not listed.

As for reading, the result is clear: there is a major increase in performance due to the SSD.  Furthermore, it is apparent that performance is also related to the different RAID levels as well as the number of hard drives (RAID5 > RAID50 > RAID 10). 

When it comes to the write access, we have to take a closer look. Although the SSD does not respond as quickly as the array controller's cache itself, performance does profit noticeably from the higher cache size of the SSD. The difference in performance between the various configurations is even more visible when writing rather than reading: RAID5 is the slowest, RAID50 offers a good balance between performance and capacity, and RAID10 is always the fastest.

Conclusion

We do not necessarily agree with the statement that an installation in a virtual environment is always slower than a physical installation. 

Based on our experience, however, it can be said that with appropriately dimensioned hardware only very little performance is lost.

In view of the many advantages of VMWare, Hyper-V and similar hypervisors, we can definitely recommend the use of a bare metal virtualisation solution.