Initial Benchmarks Of The Performance Impact Resulting From Linux's x86 Security Changes

First up are some synthetic I/O benchmarks...

FS-Mark performance appears to be significantly slower with this latest Linux kernel Git code, at least when using faster storage as found with the Core i7 8700K setup. The i7-8700K system was using a Samsung 950 PRO NVMe SSD while the i7-6800K system was using a slower SATA 3.0 Toshiba TR150 SSD.

Compile Bench also took a performance hit on both systems. If it's not due to the x86 changes, there is some other big kernel regression in just the last week... Keep in mind these are synthetic I/O benchmarks.

While applications mostly limited to user-space activity should see minimal change (if any) in performance.

PostgreSQL took a noticeable hit on both systems with the Linux kernel Git code containing the many recent x86 changes.

Redis is also running slower.

More extensive benchmarks are coming up soon.

Update: For those wondering, gaming performance doesn't appear affected.

Update 2: Latest details in Further Analyzing The Intel CPU "x86 PTI Issue" On More Systems.