Sporadic Behavior With Linux 3.16 vs. 3.17 vs. 3.18 Test Results

Written by Michael Larabel in Linux Kernel on 7 December 2014 at 09:39 AM EST. 8 Comments
Here's some more Linux 3.18 kernel benchmarks I did with the final release due out likely today. However, these results seem to be a bit odd.

With an Intel Core i7 5960X Haswell-E system on an ASRock X99 Extreme3 motherboard with 16GB of DDR4 memory, 256GB Corsair Force LX SSD, and NVIDIA GeForce GTX 770 graphics I did some fresh benchmarks using the stable Linux 3.16 and 3.17 kernels. The stable vanilla kernels were compared to Linux 3.18 Git -- all kernels obtained from the Ubuntu Mainline Kernel PPA.
Linux 3.18 Haswell-E Intel Performance

The performance results are weird to say the least and haven't yet been able to reproduce some of the performance changes on other hardware. This Core i7 5960X setup was part of a new build with the ASRock X99 Extreme3 board that wasn't used in earlier Phoronix tests. My two other LGA-2011v3 (i7-5960X and Intel Xeons) + X99 motherboard systems haven't shown such odd results between Linux 3.16~3.18 with some of the performance changes shown on this system.
Linux 3.18 Haswell-E Intel Performance

So take the results as you wish for now. If you've seen similar performance swings out of your hardware on recent kernels, feel free to contact me or post in the forums. Sans a hardware issue, the only immediate possibility that comes to mind would be weird behavior out of the Intel P-State CPU frequency scaling driver on this system. At least going forward, this is one of the systems being added to the test farm for daily kernel benchmarking. Find these odd Linux kernel performance results via OpenBenchmarking.org.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week