Back in March I benchmarked the Linux Kernel Runtime Guard (LKRG) as a means of achieving additional security safeguards for a ~5% performance hit. With LKRG 0.8 having been released a few days ago, here is a fresh look at the LKRG performance compared to the stock kernel on Ubuntu 20.04 LTS.

One of the security improvements being worked on in recent months by Intel's open-source team has been FGKASLR. But how is the performance overhead compared to just traditional KASLR? Here are benchmarks looking at the performance impact of FGKASLR on top, just KASLR, and then no address space layout randomization.

Slated for Linux 5.9 is finally mainlining the FSGSBASE patches that have been floating around the kernel mailing list for years. Testing last week showed the tentative x86/fsgsbase patches helping Intel Xeon Linux performance but with AMD also supporting this instruction set extension going back to Bulldozer, how is it looking on the likes of AMD? Here are some benchmarks.

After covering the Linux patches for FSGSBASE for years, it's looking like Linux 5.9 will finally land the support for this CPU capability present since Ivy Bridge on the Intel side and more recently on AMD CPUs with Bulldozer and Zen. Here are benchmarks looking at some of the performance benefits the Linux FSGSBASE patches can provide for an Intel Xeon Cascade Lake Refresh server.

Linus Torvalds is expected to release Linux 5.8-rc1 following the two week long Linux 5.8 kernel merge window. Here is our overview of all the big changes coming with this next version of the Linux kernel.

Following yesterday's disclosure of CrossTalk / SRBDS after a nearly two year embargo period for this Special Register Buffer Data Sampling vulnerability, I have been running benchmarks on multiple systems for the past nearly 24 hours. Here are some preliminary data points for both synthetic and real-world workloads on various Intel CPUs before/after mitigating SRBDS with the updated Intel microcode.

This morning I noted CrossTalk / SRBDS as the newest side-channel vulnerability following Intel's monthly security advisories being sent out. It turns out Intel broke their own embargo on the disclosure and I happened to spot it quickly before they retracted it. In the hours since, the university researchers behind this CrossTalk vulnerability reached out and have provided an embargoed copy of the whitepaper. As of now, the formal disclosure time has passed so information on this new side-channel Intel CPU vulnerability is public and it shows for the first time that speculative execution can enable attackers to leak sensitive information across physical cores on Intel CPUs.

Given the recent releases of Chrome 83 and Firefox 77 while Firefox 78 was promoted to beta, here are some current web browser benchmarks from the Linux desktop for these different browser releases.

With the PHP 8.0 schedule putting the first alpha release for the middle of June, I've been trying out its latest Git state in recent days for looking at its performance as well as when enabling its brand new JIT (Just In Time) compiler support that is new to PHP8. The results are quite compelling and here are metrics going back to the days of PHP 5.4 for comparison.

Given the release last week of GraalVM 20.1 as well as last month's release of Eclipse OpenJ9 0.20, here are some fresh JVM benchmarks up against multiple OpenJDK releases.

We delivered many benchmarks of Clang 10.0 on various CPUs following that updated LLVM compiler stack release earlier this year. With GCC 10 released earlier this month, we have begun our benchmarking of this annual feature release to the GNU Compiler Collection. First up is a look at the GCC 9 vs. GCC 10 vs. LLVM Clang 10 compiler performance on AMD Zen 2 and Intel Cascade Lake systems.

FSGSBASE patches for the Linux kernel have been available for years albeit not mainlined to date. However, thankfully, a Microsoft Linux developer has taken up the cause to get them upstreamed given the performance benefits they are even seeing. Here are some benchmarks of the Linux kernel patches for FSGSBASE on both Intel and AMD CPUs.

Following new Intel Ice Lake CPU microcode being published on Friday without any change-log and not updating prior Intel CPU family microcodes, I've begun looking at the performance as this first Intel CPU microcode update for Linux users since November. From my initial weekend testing there does seem to be some small but measurable and consistent performance impairments for Ice Lake from this microcode upgrade.

OpenCL 3.0 is being released today in provisional form. OpenCL 3.0 is making OpenCL 2.x functionality now optional to make it better suited for a range of devices plus there is new functionality introduced like subgroups, extensions for asynchronous data copies, and more.

Earlier this month I looked at the X.Org vs. Wayland browser performance with Firefox and Chrome. Mozilla Firefox in particular was showing better performance on Wayland, so here are fresh tests of Firefox with using Fedora 32 and testing various X.Org/Wayland desktops.

With Linux 5.7 the kernel is preparing to use the Schedutil governor more often on Intel systems. That change affects the CPUfreq default as well as the Intel P-State driver when in passive mode. While Schedutil holds a lot of hope, at least on Linux 5.7 with the testing I've done thus far the results show the raw performance slipping while testing on more platforms is forthcoming.

Linus Torvalds is expected to deliver an Easter day kernel release in the form of Linux 5.7-rc1. After a two week merge window, Linux 5.7 feature development formally ends today. Here is a look at the many exciting improvements and new features to find with Linux 5.7.

Given the release of Firefox 75 with Wayland improvements and also Firefox 76 now being in beta with even more work on the Wayland front, here are some web browser benchmarks under Wayland and the X.Org Server session with GNOME Shell 3.36 on Ubuntu 20.04. Additionally, Google Chrome benchmarks on Wayland and X.Org were also carried out.

Last week Intel released an initial set of micro-benchmarks for their oneAPI Level Zero and with L0 support being plumbed into their open-source Intel Compute Runtime, this weekend I started toying around with some Level Zero benchmarks on a variety of Intel processors.

On Friday I posted some initial numbers looking at the LVI mitigation impact when using the LLVM Clang compiler with that open-source, multi-platform compiler having landed its mitigation this week for Intel's Load Value Injection (LVI) vulnerability that was disclosed in March. Through the weekend I have been running some additional tests of this compiler-based mitigation and in this article are some numbers off Cascade Lake Refresh, which while recently released is reported by Intel to still be vulnerable to this new disclosure.

Made public in March was the Load Value Injection (LVI) attack affecting Intel CPUs with SGX capabilities. LVI combines Spectre-style code gadgets with Meltdown-type illegal data flows to bypass existing defenses and allow injecting data into a victim's transient execution. While mitigations on the GNU side quickly landed, the LLVM compiler mitigations were just merged today.

With last week's release of LLVM/Clang 10.0, here are our first benchmarks looking at the stable release of the Clang 10.0 C/C++ compiler compared to its previous (v9.0.1) release on various Intel and AMD processors under Ubuntu Linux.

Following last week's benchmarks of OpenJDK 8 through the newly-released OpenJDK 14 JVM benchmarks, some Phoronix readers expressed interest in seeing Java benchmarks with Oracle's GraalVM as well as Amazon's Corretto JVM implementations. Here are some benchmarks of those benchmarks up against OpenJDK both for Java 8 and Java 11 releases.

Given this week's general availability release of OpenJDK 14, here are some fresh benchmarks looking at all the major releases from OpenJDK 8 through 14 while looking at the JVM performance across multiple workloads.

On Tuesday the Load Value Injection (LVI) attack was disclosed by Intel and security researchers as a new class of transient-execution attacks and could lead to injecting data into a victim program and in turn stealing data, including from within SGX enclaves. While Intel has publicly stated they don't believe the LVI attack to be practical, one of their open-source compiler wizards did go ahead and add mitigation options to the GNU Assembler as part of the GCC toolchain. Here are benchmarks showing the performance impact of enabling those new LVI mitigation options and the significant impact they can cause on run-time performance in real-world workloads.

Following recent discussions about Openwall's Linux Kernel Runtime Guard (LKRG) and the Whonix spin on LKRG for Debian systems and more, here are some benchmarks showing the performance overhead to this run-time integrity checking of the Linux kernel that aims to fend off security vulnerability exploits.

Phoronix Test Suite 9.4-Vestby is now available as one of our largest updates in recent years for our open-source, cross-platform automated benchmarking framework. Almost wanting to rebrand it as Phoronix Test Suite 10, sticking to conventional versioning the Phoronix Test Suite 9.4 release brings numerous result viewer improvements, a lot of polishing to the PDF result exporting, various Microsoft Windows support improvements, new statistics capabilities, some useful new sub-commands, and much more as the latest quarterly feature release.

Given this week's release of Firefox 73 stable that also puts Firefox 74 into beta state, here are fresh Firefox browser benchmarks of Firefox 72/73/74 on Ubuntu Linux with and without WebRender as well as how it compares to the current state of Google Chrome.

Given this week's release of Google Chrome 80, here are fresh benchmarks of Chrome 80 against Firefox 72 on Linux plus also a run with Firefox's WebRender option being enabled. This round of tests was under an Ubuntu 20.04 snapshot with AMD Ryzen processor and AMD Radeon VII graphics.

Last month were benchmarks of RAID benchmarks on four hard drives in not visiting the Linux HDD RAID performance in a while. Stemming from that article were requests of fresh tests of the SSD RAID performance on Linux 5.5 Git, so here are those results for single drive performance and RAID0 / RAID1 / RAID5 / RAID6 / RAID10.