Does CAS latency and RAM frequency affect virtualization performance?

[backup_account]

Does CAS latency and RAM frequency affect virtual machine performance by a moderate to significant degree?

 

[ondooy]

size over timing...

 

[backup_account]

size over timing...

If I can get the size already, would it be worth topping up that extra to get a noticeable difference in performance?

 

[IPmansg]

I would say it can be quite significant.

 

[Ark Law]

I'm not a memory expert, just quoting stuff from a source;

Loaded latency is the latency when the memory subsystem is saturated with memory request and that’s where bandwidth has a positive impact on real world latency.

Under loaded conditions memory requests spend time in the queue, the more bandwidth speed the memory has, the more quickly the memory controller can process the queued commands. For example, memory running at 1600 MHz has about 20% lower loaded latency than memory running at 1333 MHz.

Loaded latency is the real world measurement of performance applications will experience, having bandwidth speed to reduce loaded latency is important when reviewing the DPC configuration (part 4) of your server configuration.

CAS latencies (CL) increase with each new generation of memory, but as mentioned before latency is a factor of clock speed as well as the CAS latency. Generally a lower CL will be better, however they are only better when using the same base clock.

If you have faster memory, higher CL could end up better. When DDR3 was released it offered two speeds, 1066MHz CL7 and 1333 MHz CL8. Today servers are equipped with 1600 MHz CL9 memory.DDR4 was released with 2133 MHz CL13. However 2133 MHz CL15 is available at the major server vendors. To work out the unloaded latency is: (CL/Frequency) * 2000.

This means that 1600 MHz CL9 provides an unloaded latency of 11.25ns, while 2133 MHz CL15 provides an unloaded latency of 14.06ns. A drop of 24.9%. However DDR4 latency will drop when bandwidth increases faster then the increase of CAS latency.

At the time of writing “prosumer” DDR4 memory is available at higher speeds than the server vendors offer, but it’s just a matter of time before those modules become available for server hardware. Many memory vendors offer DDR4 2800 MHz CL14 to CL 16. When using the same calculation, 2800 MHz CL16 provides an unloaded latency of (16/2800) * 2000 = 11.42ns. Almost the same latency at DDR3 1600 MHz CL9! 2800 MHZ CL14 provides an unloaded latency of 10ns, meaning that CL14 beating CL9 with a lower latency while providing more than 75% bandwidth.

SRC: http://frankdenneman.nl/2015/02/25/memory-deep-dive-ddr4/

 

[yusoffb01]

Doesn't matter. That's not the bottleneck

 

[klap_hanz]

Doesn't really matter...

If your VMs are running mission critical stuffs, i suggest that you use ECC registered/buffered memory instead...

 

[satria_neo_2014]

Doesn't matter

 

[backup_account]

Doesn't matter. That's not the bottleneck

I have a sata ssd, if I change to NVME, will it uncap my bottle?