Intel Xeon E7 Processor Generational Performance Comparison

Intel has a fairly recent document titled Accelerated Operations for Telecom and Financial Services which is also listed under Accelerate OLTP Database Performance with Intel TSX. It describes the “performance” increases seen with the AsiaInfo ADB from moving from 2.8GHz Intel Xeon E7-4890 v2 (Ivy Bridge-EX), to 2.5GHz Intel Xeon E7-8890 v3 (Haswell-EX), and finally to 2.2GHz Intel Xeon E7-8890 v4 (Broadwell-EX) processors, as shown in Figure 1.

 

Figure 1: Speedup from Successive Processor Generations

 

This workload is described as “AsiaInfo ADB Database OCS k-tpmC”, while the AsiaInfo ADB is described as “a scalable OLTP database that targets high performance and mission critical businesses such as online charge service (OCS) in the telecom industry”, that runs on Linux.

The reason I have performance in quotes above is because what they are really measuring is closer to what I would call capacity or scalability. Their topline result is “Thousands of Transactions per Minute” as measured with these different hardware and storage configurations.

The key point to keep in mind with these types of benchmarks is whether they are actually comparing relatively comparable systems or not. In this case, the systems are quite similar, except for the core counts of the successive processor models (and the DD3 vs. DDR4 memory support). Here are the system components, as listed in the footnotes of the document:

Baseline: Four-sockets, 15-core Intel Xeon E7-4890 v2, 256GB DDR3/1333 DIMM, Intel DC S3700 SATA for OS, (2) 2TB Intel DC P3700 PCIe NVMe for storage, 10GbE Intel X540-AT2 NIC

Next Generation: Four-sockets, 18-core Intel Xeon E7-8890 v3, 256GB DDR4/1600 LVDIMM, Intel DC S3700 SATA for OS, (2) 2TB Intel DC P3700 PCIe NVMe for storage, 10GbE Intel X540-AT2 NIC

New: Four-sockets, 24-core Intel Xeon E7-8890 v4, 256GB DDR4/1600 LVDIMM, Intel DC S3700 SATA for OS, (2) 2TB Intel DC P3700 PCIe NVMe for storage, 10GbE Intel X540-AT2 NIC

The baseline system has a total of 60 physical cores, running at 2.8GHz, using the older Ivy Bridge-EX microarchitecture. The next generation system has a total of 72 physical cores, running at 2.5GHz, using the slightly newer Haswell-EX microarchitecture. Finally, the new system has a total of 96 physical cores, running at 2.2GHz, using the current Broadwell-EX microarchitecture. These differences in core counts, base clock speeds, and microarchitecture make it a little harder to fully understand their benchmark results in a realistic manner.

Table 1 shows some relevant metrics for these three system configurations. The older generation processors have fewer cores, but run at a higher base clock speed. The newer generation processors would be faster than the older generation processors at the same clock speed, but the base clock speed is lower as the core counts have increased with each successive generation flagship processor. The improvements in IPC and single-threaded performance are obscured by lower base clock speeds as the core counts increase, which makes the final score increase less impressive.

 

ProcessorBase ClockTotal System CoresRaw ScoreScore/Core
Xeon E7-4890 v22.8GHz6072512.08
Xeon E7-8890 v32.5GHz72102114.18
Xeon E7-8890 v42.2GHz96129413.48

Table 1: Analysis of ADB Benchmark Results

 

Table 2 shows some metrics from an analysis of some actual and estimated TPC-E benchmark results for those same three system configurations, plus an additional processor choice that I added. The results are pretty similar, which supports the idea that both of these benchmarks are CPU-limited. From a SQL Server 2016 perspective, you are going to be better off from a performance/license cost perspective if you purposely choose a lower core count “frequency-optimized” processor (at the cost of less total system capacity per host).

This is somewhat harder to do with the Intel Xeon E7 v4 family, because of your limited SKU choices. A good processor choice for many workloads would be the 10-core Intel Xeon E7-8891 v4 processor, which has a base clock speed of 2.8GHz and a 60MB L3 cache that is shared by only 10 cores.

If you could spread your workload across two database servers, you would be much better off with two, four-socket servers with the 10-core Xeon E7-8891 v4 rather than one four-socket server with the 24-core Xeon E7-8890 v4. You would have more total system processor capacity, roughly 27% better single-threaded CPU performance, twice the total system memory capacity, and twice the total number of PCIe 3.0 expansion slots. You would also only need 80 SQL Server 2016 Enterprise Edition core licenses rather than 96 core licenses, which would save you about $114K in license costs. That license savings would probably pay for both database servers, depending on their exact configuration.

 

ProcessorBase ClockTotal System CoresEst TPC-E ScoreScore/Core
Xeon E7-4890 v22.8GHz605576.2792.94
Xeon E7-8890 v32.5GHz726964.7596.73
Xeon E7-8890 v42.2GHz969068.0094.46
Xeon E7-8891 v42.8GHz404808.79120.22

Table 2: Analysis of Estimated TPC-E Benchmark Results

 

The Intel document also discusses the “performance” increases seen from moving from Intel DC S3700 SATA drives to Intel DC P3700 PCIe NVMe drives. This is going to be primarily influenced by the advantages of being connected directly to the PCIe bus and the lower latency and overhead of the NVMe protocol compared to the older AHCI protocol.

Finally, they talk about the “performance” increases they measured from enabling the Intel Transactional Synchronization Extensions (TSX) instruction set and the Intel AVX 2.0 instruction set on current generation Intel E7-8800 v4 series processors.

SQL Server 2016 already has hardware support for older SSE/AVX instructions as discussed here and here. I really hope that Microsoft decides to add even more support for newer instruction sets (such as TSX) in SQL Server vNext.

 

 

Intel Xeon E7 v3 Product Family Released

On May 5, 2015, Intel announced the new E7 v3 Product Family, which is also known as the Haswell-EX, which is meant for four and eight-socket servers. This 22nm processor is a Tock release (which means that it is using a new processor microarchitecture compared to the previous 22nm Ivy Bridge-EX). An updated graphic that outlines the Tick-Tock development history for the Xeon 7xxx and E7 families is shown in Figure 1.

intel-xeon-tick-tock-model

Figure 1: Intel Tick-Tock Development Model

Intel only has 12 different processors in this product family, and of these, only four are really good choices from a licensing cost and performance perspective for SQL Server 2012 and newer. These are shown in Table 1.

ProcessorCoresBase ClockTurbo ClockL3 SizeQPI Speed
E7-8893 v343.2 GHz3.5 GHz45 MB9.6 GT/s
E7-8891 v3102.8 GHz3.5 GHz45 MB9.6 GT/s
E7-8867 v3162.5 GHz3.3 GHz45 MB9.6 GT/s
E7-8890 v3182.5 GHz3.3 GHz45 MB9.6 GT/s

Table 1: Preferred Xeon E7 v3 Family Processors for SQL Server 2012/2014/2016

I make this assertion because of how SQL Server 2012 and newer core-based licensing works. You pay for the number of physical cores in your system (on non-virtualized servers), and Microsoft does not care whether your processor cores are slow or fast, the license price is the same either way. Given this basic fact, you really should pick processors with faster cores (better single-threaded performance) at the same physical core count, to get the most performance possible for a given licensing cost. In some cases, you may be able get away with a lower core count processor that has faster individual cores, and still be able to support a similar overall total workload at a much lower SQL Server licensing cost.

The other eight processors in the E7 v3 Product Family all have lower specifications (at the same core count) than the four in my preferred list, so they are bad choices in my opinion. If you or someone else in your organization picks one of those other eight processors, you are not making a good choice. I am guessing that some people may argue that the slower processors at a given core count are less expensive, so they make sense in some situations.

My response would be that when you are talking about four or eight, high core count processors, the SQL Server 2012 and newer license costs are going to far outweigh the relatively small difference in the cost of a given processor. The single-threaded performance difference between a 2.1 GHz Xeon E7-8870 v3 ($7,175 each) and a 2.5 GHz Xeon E7-8890 v3 ($4,672 each) is likely to be about 20%, while the difference in total system cost will be much less than 20%.

You may notice that all of my recommended E7 v3 processors are E7-88xx processors, which means they are designed for eight-socket servers. That does not mean that you have to use them in an eight-socket server. You can actually use those E7-88xx processors in four-socket servers, which are much more common and much less expensive.