STH nginx CDN Performance
On the nginx CDN test, we are using an old snapshot and access patterns from the STH website, with DRAM caching disabled, to show what the performance looks like fetching data from disks. This requires low latency nginx operation but an additional step of low-latency I/O access which makes it interesting at a server level. Here is a quick look at the distribution:
This is a case that was actually not great for Milan-X, and frankly is not taking advantage of all of the new instructions and features of the new chips. This is just running real-world website traffic patterns through the system and over the network so this is a longer chain. Still, the performance gap relative to the older generation parts is astounding. If you have early 2021 systems (the Gold 6258R), we are getting more than 3x the performance. 3:1 consolidation ratios in less than 24 months is almost unheard of in the industry.
MariaDB Pricing Analytics
This is a personally very interesting one for me. The origin of this test is that we have a workload that runs deal management pricing analytics on a set of data that has been anonymized from a major data center OEM. The application effectively is looking for pricing trends across product lines, regions, and channels to determine good deal/ bad deal guidance based on market trends to inform real-time BOM configurations. If this seems very specific, the big difference between this and something deployed at a major vendor is the data we are using. This is the kind of application that has moved to AI inference methodologies, but it is a great real-world example of something a business may run in the cloud.
On the MariaDB pricing analytics side, this is another real-world enterprise workload. Here we can see around 3.5:1 consolidation over the top-bin dual-socket server CPUs that one could have purchased in 2022.
STH STFB KVM Virtualization Testing
One of the other workloads we wanted to share is from one of our DemoEval customers. We have permission to publish the results, but the application itself being tested is closed source. This is a KVM virtualization-based workload where our client is testing how many VMs it can have online at a given time while completing work under the target SLA. Each VM is a self-contained worker. This is very akin to a VMware VMark in terms of what it is doing, just using KVM to be more general.
There are a lot of bars on this chart. The top end looks compressed just because those VMs are so big that we are not getting enough resolution due to the large VM sizes. Instead, let us focus on some of the smaller VM sizes.
This is where things get really interesting. We get fairly massive changes between the AMD EPYC 9654 and the top-bin 3rd Gen Xeon Scalable processors. If you have a dual-socket Intel Xeon Platinum 8380 or a quad-socket Intel Xeon Platinum 8380H, you can get huge consolidation ratios moving to the new EPYC chips.
Moving up to the medium size VMs, we get a similar view of consolidation. This is one where if AMD had stuck with 8-channel DDR5 instead of 12-channel, the performance gap would have closed.
Even with this, folks are going to be noting higher TDPs on the chips. As such, next, we wanted to address power consumption observations on the new Genoa platforms to put the performance increases into a performance-per-watt context at a system level.