Language Selection

English French German Italian Portuguese Spanish

Graphics/Benchmarks

Radeon RX 5700 XT: A Handful Of Early Linux Gaming Benchmarks On Ubuntu 18.04

Filed under
Graphics/Benchmarks
Linux
Gaming
Ubuntu

I've already published my thoughts on AMD's new 7nm Navi graphics card lineup. Both the RX 5700 and RX 5700 XT punch above their weight class on Windows and are a compelling alternative to Nvidia's new SUPER series. But how is their performance looking on Linux? Well, that's a bit more difficult to answer since widespread Linux support is still largely absent.

Still, I wanted to fire up the RX 5700 XT on my Ubuntu 18.04 and Ryzen 9 3900X test bench and see how things are shaping up.

The official AMDGPU 19.30 driver package (i.e. from AMD itself) only supports Ubuntu 18.04.2 LTS, while solid widespread support for the RX 5700 cards won't arrive until MESA 19.3. However, development is moving very quickly on this.

Your mileage may vary, but I found the "easiest" solution was to install Ubuntu 18.04 LTS, install the official AMD 19.30 packaged driver, then add the Oibaf PPA. A quick sudo apt update / upgrade later, and you should have Mesa 19.2-git which will enable Vulkan support. The situation may have changed over the last several days, but this is how I got mine up and running with performance that is mostly expected.

Read more

7-Way Linux Distribution Benchmarks For July 2019, Including LTO'ed openSUSE Tumbleweed

Filed under
Graphics/Benchmarks

As it's been a few weeks since last hosting any Linux distribution comparison and now with the rolling-release openSUSE Tumbleweed enabling LTO by default, here are some fresh Linux distribution comparison results plus tossing the newly-released Debian 10.0 into the mix as well. This round of testing included Ubuntu 18.04 LTS, Ubuntu 19.04, Fedora Workstation 30, openSUSE Leap 15.1, openSUSE Tumbleweed, Clear Linux 30450, and Debian 10.0.

This round of benchmarking was done on an Intel Core i9 7980XE with ASUS PRIME X299-A motherboard, 16GB of RAM, NVIDIA GeForce GTX TITAN X graphics, and Samsung 970 EVO 500GB NVMe solid-state drive.

The Ubuntu, openSUSE, Fedora, Clear Linux, and Debian releases were all tested following clean installations with all stable release updates present as of testing. Manjaro/Arch isn't in this round of testing due to Manjaro running into issues with Nouveau on the GTX TITAN X present in this test system. Unfortunately I didn't have any very recent openSUSE Tumbleweed benchmark results handy pre-LTO-by-default and with not being aware of any other way to roll-back/archive the Tumbleweed system state, there are just Tumbleweed tests from the latest build after they began defaulting to Link Time Optimizations on their packages. System details below in full for this default/out-of-the-box Linux performance experience comparison.

Read more

The Status of Fractional Scaling (HiDPI) Between Windows & Linux

Filed under
GNU
Graphics/Benchmarks
Linux

There’s a special type of displays commonly called “HiDPI“, which means that the number of pixels in the screen is doubled (vertically and horizontally), making everything drawn on the screen look sharper and better. One of the most common examples of HiDPI are Apple’s Retina displays, which do come with their desktops and laptops.

However, one issue with HiDPI is that the default screen resolutions are too small to be displayed on them, so we need what’s called as “scaling”; Which is simply also doubling the drawn pixels from the OS side so that they can match that of the display. Otherwise, displaying a 400×400 program window on a 3840×2160 display will give a very horrible user experience, so the OS will need to scale that window (and everything) by a factor of 2x, to make it 800×800, which would make it better.

Fractional scaling is the process of doing the previous work, but by using fractional scaling numbers (E.g 1.25, 1.4, 1.75.. etc), so that they can be customized better according to the user’s setup and needs.

Now where’s the issue, you may ask? Windows operating system has been supporting such kind of displays natively for a very long time, but Linux distributions do lack a lot of things in this field. There are many drawbacks, issues and other things to consider. This article will take you in a tour about that.

Read more

Also: Vulkan 1.1.116 Published With Subgroup Size Control Extension

Graphics and Games: DXVK, Overload and Songs of Syx

Filed under
Graphics/Benchmarks
  • Lima Gallium3D Gets A Reworked Scheduler

    Landing this week in Mesa 19.2 for the Lima Gallium3D driver for Arm Mali 400/450 series hardware is a reworked GPIR regiaster scheduler.

    The change to their existing scheduler is that the scheduling is now done at value register allocation time and other improvements made in the process.

  • DXVK 1.3.1 Brings Logging Improvements, GPU Load Monitoring In The HUD

    Just one week after releasing DXVK 1.3, lead developer Philip Rebohle has released DXVK 1.3.1 with a few more features plus a number of bug fixes -- including performance work.

    The two principal new features of DXVK 1.3.1 are logging improvements and GPU load monitoring support in the DXVK HUD. The GPU load monitoring are estimates based on Vulkan timing information within DXVK as opposed to using driver-specific queries; Philip acknowledges that the number may be inaccurate when CPU load is very high. Those wanting to try out that GPU load monitoring in the heads-up display can do so via the DXVK_HUD=gpuload environment variable.

  • The six-degree-of-freedom shooter "Overload" has a new Community Level Pack offering a fresh challenge

    Overload is possibly the best six-degree-of-freedom shooter I've played in the past few years, sadly it has been overlooked by a lot of gamers.

    It's limping on though, with a new Community Level Pack available for around £3.99. This includes nine single player levels, stitched together to form an entirely new mission. It includes progression, unlocks and a secret level. There's also twelve new challenge mode levels and online leaderboard support.

  • Songs of Syx, a city-builder with empire management, tactical battles and RPG elements

    Here's a fun recent discovery, Songs of Syx an in-development title from Swedish developer Jakob de Laval. It's a city-builder with empire management, tactical battles and rpg-elements and it's looking good.

    With an interesting pixel-art top-down view, Songs of Syx reminds me a little of Rise to Ruins, another great pixel-art builder. It's been in development since 2014, with an Early Access release due sometime in March next year with support for Linux, Mac and Windows.

Graphics: Weston 7.0 Reaches Alpha and RadeonSI Gallium3D Driver Adds Navi Wave32 Support

Filed under
Graphics/Benchmarks
  • weston 6.0.91
    This is the alpha release for weston 7.0.  A lot of new features and
    fixes are shipped in this release, including:
    
    - New internal debug scopes and logging framework
    - Improved documentation
    - HDCP support
    - A new PipeWire plugin
    
    Thanks to all contributors!
    
    We've moved to Meson as our only build system, autotools support has
    been removed.  Package maintainers: please report any issues you have
    with Meson before the stable release.
    
    Full commit history below.
    
  • Weston 7.0 Reaches Alpha With PipeWire, HDCP, EGL Partial Updates & Mores

    Wayland release manager Simon Ser announced the alpha release of the Weston 7.0 reference compositor on Friday that also marks the feature freeze for this Wayland compositor update.

    Some of the major changes to Weston 7.0 include HDCP content protection support, better documentation, new debugging and logging framework support, and the just-added PipeWire plug-in for remote streaming. There are also less prominent additions like EGL partial update support, various DRM compositor back-end restructuring, build system updates, and a variety of libweston updates.

  • RadeonSI Gallium3D Driver Adds Navi Wave32 Support

    One of the new features to the RDNA architecture with Navi is support for single cycle issue Wave32 execution on SIMD32. Up to now the RadeonSI code was using just Wave64 but now there is support in this AMD open-source Linux OpenGL driver for Wave32.

    Well known AMD open-source developer Marek Olšák landed this Wave32 support on Friday for the RadeonSI driver. The Wave32 support landed over several commits to Mesa 19.2-devel and is enabled for vertex, geometry, and tessellation shaders. Wave32 isn't enabled for pixel shaders but rather Wave64. Additionally, Wave32 isn't yet enabled for compute shaders due to Piglit OpenGL test case failures.

Graphics: Nouveau, Wayland's Weston and Libinput

Filed under
Graphics/Benchmarks
Linux
  • The Open-Source NVIDIA "Nouveau" Driver Gets A Batch Of Fixes For Linux 5.3

    Originally on Thursday was finally the Nouveau-next 5.3 pull request that offered improvements to the display color management, fixes to Secure Boot on newer hardware, and Turing TU116 mode-setting support. But that was rejected by the DRM maintainers for being way too late as usually the cut-off for new feature material is when hitting RC6 on the previous cycle, just not days before the end of the current merge window. Not that those changes were all too exciting or notable, but this pushes back the color management and other work to Linux 5.4.

    Nouveau DRM maintainer Ben Skeggs of Red Hat as a result today sent in Nouveau-fixes 5.3. This pull request has support still for the TU116 GPU since that shouldn't regress any existing support as well as having fixes around KMS, a memory leak, and a few other basic fixes.

  • Wayland's Weston Lands A Pipewire Plug-In As New Remote Desktop Streaming Option

    Wayland's Weston compositor for the past year has provided a remoting plug-in for virtual output streaming that was built atop RTP/GStreamer. Now though a new plug-in has landed in the Weston code-base making use of Red Hat's promising PipeWire project.

    The PipeWire plug-in was merged into Weston today and is similar to the GStreamer-powered remoting plug-in but instead leverages PipeWire. The compositor's frames are exported to PipeWire and the same virtual output API is shared between these plug-ins. The virtual outputs can be configured using the weston.ini configuration file. Any PipeWire client in turn can read these frames.

  • Libinput 1.14 RC Arrives With Better Thumb Detection & Dell Canvas Totem Support

    Linux input expert Peter Hutterer of Red Hat shipped the much anticipated release candidate today for libinput 1.14, the open-source input handling library used by both X.Org and Wayland systems.

  • libinput 1.13.901
    The first RC for libinput 1.14 is now available.
    
    We have new and improved thumb detection for touchpads, thanks to Matt
    Mayfield. On Clickpad devices this should make interactions where a thumb is
    resting on the touchpad or dropped during an interaction more reliable. A
    summary of the changes can be found here:
    https://who-t.blogspot.com/2019/07/libinputs-new-thumb-detection-code.html
    
    The Dell Canvas Totem is now supported by libinput. It is exposed as a new
    tool type through the tablet interface along with two new axes. Note that
    this is only low-level support, the actual integration of the totem needs
    Wayland protocol changes and significant changes in all applications that
    want to make use of it. A summary of the changes can be found here:
    https://who-t.blogspot.com/2019/06/libinput-and-dell-canvas-totem.html
    
    Touch-capable tablets now tie both devices together for rotation. If you set
    the tablet to left-handed, the touchpad will be rotated along with the
    tablet. Note that this does not affect the left-handed-ness of the touchpad,
    merely the rotation. 
    
    Tablet proximity out handling for tablets that are unreliably sending
    proximity out events is now always timeout-based. It is no longer necessary
    to add per-device quirks to enable this feature and it is completely
    transparent on devices that work correctly anyway. A summar of the
    changes can be found here:
    https://who-t.blogspot.com/2019/06/libinput-and-tablet-proximity-handling.html
    
    Tablets that send duplicate tools (BTN_TOOL_PEN and BTN_TOOL_ERASER) now
    ignore the latter. This is an intermediate fix only but at least makes those
    tablets more usable than they are now. Issue #259 is the tracker for this
    particular behaviour if you are affected by it.
    
    The handling of kernel fuzz has been slightly improved. Where our udev rule
    fails to reset the fuzz on the kernel device, we disable the hysteresis and
    rely on the kernel now to handle it. Previously our hysteresis would take
    effect on top of the kernel's, causing nonresponsive behaviour.
    
    Note to distribitors: the python-evdev dependency has been dropped, the
    tools that used it are now using python-libevdev instead.
    
    And of course a random assortment of fixes, improvements, etc. Many thanks
    to all contributors and testers.
    
    As usual, the git shortlog is below.
    

Corsair Force MP600 PCIe 4.0 NVMe SSD Benchmarks On Linux

Filed under
Graphics/Benchmarks

One of the first PCIe Gen 4 NVMe SSDs to market has been the Corsair Force MP600. AMD included the Corsair MP600 2TB NVMe PCIe4 SSD with their Ryzen 3000 reviewer's kit and for those interested in this speedy solid-state storage here are some benchmarks compared to various other storage devices on Ubuntu Linux.

The 2TB Force Series Gen 4 MP600 SSD is rated for sequential reads up to 4950MB/s and sequential writes up to 4250MB/s and 600k IOPS random writes and 680k IOPS random reads. The MP600 relies upon 3D TLC NAND and relies upon a Phison PS5016-E16 controller. This 2TB PCIe 4.0 SSD will set you back $450 USD while a 1TB version is a modest $250 USD.

Read more

These Windows 10 Vs Pop OS Benchmarks Reveal A Surprising Truth About Linux Gaming Performance

Filed under
Graphics/Benchmarks
Linux
Gaming

Having a game run on Linux that isn't built for Linux? That's certainly a cool thing. Performance is another thing entirely. It's not a compelling enough argument for Linux enthusiasts to tell their Windows-using friends that "hey, but the games you play run on Linux!" They have to run well. Maybe the notion of switching to Linux is an enticing one for the stability and increased privacy control, but you can't show me an enthusiast gamer who'll willingly trade that for a 20% drop in the framerates they're used to on their hardware, right?

That 20% is an important number, albeit not a scientific one. When I got into Linux last year, that's the figure I kept seeing thrown around. "Sure, it runs on Linux but about 15% to 20% lower FPS." With constant improvements to the kernel, Vulkan drivers and Steam Proton, however, I think the situation has changed.

Enough of my rambling. Here's what we're looking at today...

Read more

CompuLab Turns An 8-Core/16-Thread Xeon, 64GB RAM, NVIDIA Quadro RTX 4000 Into Fan-Less Computer

Filed under
Graphics/Benchmarks

Three years ago we checked out the CompuLab Airtop as a high-performance fanless PC. Back then it was exciting to passively cool an Intel Core i7 5775C, 16GB of RAM, SATA 3.0 SSD, and a GeForce GTX 950 graphics card. But now in 2019 thanks to the continued design improvements by CompuLab and ever advancing tech, their newly-launched CompuLab 3 can accommodate an eight-core / sixteen-thread Xeon CPU, 64GB of RAM, NVMe SSD storage, and a NVIDIA Quadro RTX 4000 graphics card without any fans!

The Airtop 3 just arrived from Israel earlier this month and I've begun putting it through its paces with our Linux benchmarks. Over the weeks ahead I'll begin posting more benchmarks from this passively-cooled, industrial-grade PC with Intel Xeon E-2288G processor and RTX 4000 Turing graphics, but given the reader interest when CompuLab announced the Airtop 3 back in April, I'm just sharing some initial impressions and first round of performance data today.

Read more

Graphics: Vulkan, AMDGPU and AMDVLK

Filed under
Graphics/Benchmarks
  • A Vulkan Extension Is Being Worked On To Acquire Exclusive Control Of A Wayland Display

    Drew DeVault of Sway/WLROOTS fame has been dabbling with his first Vulkan extension as part of work with other upstream Wayland developers on DRM lease support and better supporting VR headsets under Wayland.

    Being worked on in-step with DRM lease protocol support for Wayland, Drew is also drafting a "VK_EXT_acquire_wl_display" extension for Vulkan. That new extension is akin to VK_EXT_acquire_xlib_display for X11 but for working on Wayland. The existing VK_EXT_acquire_xlib_display extension allows a Vulkan application / game engine to take exclusive control of a display currently associated with an X11 screen. This goes along with the DRM lease support and was spearheaded by Red Hat, Valve, NVIDIA, and Intel as part of Steam VR support on Linux.

  • AMDGPU DC Gets A Number Of Fixes For Navi & Other Clean-Ups

    The past few weeks while AMD open-source developers were busy getting their Navi enablement code public and aligned for the Linux 5.3 merge window, the display core "DC" frequent code drops ceased. Every so often AMD developers volley their DC patches from their internal development trees to the public mailing list for queuing ahead of the next cycle. Now that Navi is out there and getting stabilized, they've issued a new set of DC patches and it's coming in heavy.

    Given that it's been a while during Navi review and upstreaming, the AMDGPU DC patches sent out on Monday are 87 patches that add nearly ten thousand lines of new code.

  • AMDVLK 2019.Q3.2 Released With Navi 10 Support

    Just over one week after the Radeon RX 5700/5700XT "Navi" graphics cards began shipping, the AMDVLK open-source AMD Radeon Vulkan Linux driver support is now available for these first RDNA offerings.

    AMDVLK is the official open-source AMD Vulkan Linux driver and is based on the same sources as the Windows/Linux Radeon Software Vulkan driver. The open-source AMDVLK, however, uses their LLVM-based shader compiler rather than AMD's long-standing proprietary shader compiler. AMDVLK is an alternative to the Mesa RADV Vulkan driver maintained by the "community" (principally, Red Hat, Google, and Valve) that did see launch-day support last week for Navi.

Syndicate content

More in Tux Machines

today's leftovers

  • Linux Weekly Roundup #35

    Hello and welcome to this week's Linux Roundup and what a wonderful week we had! We have plenty of Linux Distro releases and LibreOffice 6.3 RC1. The Linux distros with releases this week are Q4OS 3.8, SparkyLinux 5.8, Mageia 7.1, ArcoLinux 19.07.11, Deepin 15.11, ArchBang 2107-beta, Bluestar 5.2.1, Slackel 7.2 "Openbox" and Endeavour OS 2019.07.15. I looked at most of these Linux Distros, links below, I will look at some of them in the new week and some I will unfortunately not have a look at, for download links and more, please visit distrowatch.com Well, this is this week's Linux Roundup, thank you so much for your time! Have a great week!

  • Full Circle Magazine: Full Circle Weekly News #140
  • Christopher Allan Webber: ActivityPub Conf 2019

    That's right! We're hosting the first ever ActivityPub Conf. It's immediately following Rebooting Web of Trust in Prague. There's no admission fee to attend. (Relatedly, the conference is kind of being done on the cheap, because it is being funded by organizers who are themselves barely funded.) The venue, however, is quite cool: it's at the DOX Centre for Contemporary Art, which is itself exploring the ways the digital world is affecting our lives. If you plan on attending (and maybe also speaking), you should get in your application soon (see the flier for details). We've never done one of these, and we have no idea what the response will be like, so this is going to be a smaller gathering (about 40 people). In some ways, it will be somewhere between a conference and a gathering of people-who-are-interested-in-activitypub. As said in the flier, by attending, you are agreeing to the code of conduct, so be sure to read that.

Sysadmin Appreciation Day, IBM and Fedora

  • Gift ideas for Sysadmin Appreciation Day

    Sysadmin Appreciation Day is coming up this Friday, July 26. To help honor sysadmins everywhere, we want you to share your best gift ideas. What would be the best way a team member or customer could show their appreciation for you? As a sysadmin, what was the best gift you've ever received? We asked our writers the same question, and here are their answers: "Whilst working in the Ubuntu community on Edubuntu, I took it upon myself to develop the startup/shutdown sound scheme, which became the default in Ubuntu for, from what I can understand, the next decade. Whilst people had a love-hate relationship with my sound scheme, and rightly so, I had a love-hate relationship with my sound card during the development. At the time I had recorded all my sound samples using one sample rate, but my new sound card, as my motherboard had exploded a few days earlier, did not support it. I had two choices, resample all my samples (which I didn't really want to do) or buy a new sound card.

  • Red Hat OpenStack Platform with Red Hat Ceph Storage: Radosbench baseline performance evaluation

    Red Hat Ceph Storage is popular storage for Red Hat OpenStack Platform. Customers around the world run their hyperscale, production workloads on Red Hat Ceph Storage and Red Hat OpenStack Platform. This is driven by the high level of integration between Ceph storage and OpenStack private cloud platforms. With each release of both platforms, the level of integration has grown and performance and automation has increased. As the customer's storage and compute needs for footprints have grown, we have seen more interest towards running compute and storage as one unit and providing a hyperconverged infrastructure (HCI) layer based on OpenStack and Ceph. [...] Continuing the benchmarking series, in the next post you’ll learn performance insights of running multi-instance MySQL database on Red Hat OpenStack Platform and Red Hat Ceph Storage across decoupled and hyperconverged architectures. We’ll also compare results from a near-equal environment backed by all-flash cluster nodes.

  • The State of Java in Flathub

    For maintainers of Java-based applications in Flathub, it's worth noting that even if you consume the Latest OpenJDK extension in your application, users will not be broken by major updates because OpenJDK is bundled into your Flatpak. The implication of this for users is that they won't see updates to their Java version until the application maintainer rebuilds the application in Flathub. If you maintain a Java-based Flatpak application on Flathub, you can consume the latest version of your chosen OpenJDK stream (either LTS or Latest) simply by rebuilding; the latest version of that OpenJDK steam will be pulled in automatically.

  • Fedora Magazine: Contribute at the Fedora Test Week for kernel 5.2

    The kernel team is working on final integration for kernel 5.1. This version was just recently released, and will arrive soon in Fedora. This version has many security fixes included. As a result, the Fedora kernel and QA teams have organized a test week from Monday, Jul 22, 2019 through Monday, Jul 29, 2019. Refer to the wiki page for links to the test images you’ll need to participate. Read below for details.

Debian and Ubuntu Leftovers

  • Bootstrappable Debian BoF

    Greetings from DebConf 19 in Curitiba! Just a quick reminder that I will run a Bootstrappable Debian BoF on Tuesday 23rd, at 13.30 Brasilia time (which is 16.30 UTC, if I am not mistaken). If you are curious about bootstrappability in Debian, why do we want it and where we are right now, you are welcome to come in person if you are at DebCon or to follow the streaming.

  • Candy Tsai: Outreachy Week 6 – Week 7: Getting Code Merge

    You can’t overhear what others are doing or learn something about your colleagues through gossip over lunch break when working remotely. So after being stuck for quite a bit, terceiro suggested that we try pair programming. After our first remote pair programming session, I think there should be no difference in pair programming in person. We shared the same terminal, looked at the same code and discussed just like people standing side by side. Through our pair programming session, I found out that I had a bad habit. I didn’t run tests on my code that often, so when I had failing tests that didn’t fail before, I spent more time debugging than I should have. Pair programming gave insight to how others work and I think little improvements go a long way.

  • about your wiki page on I/O schedulers and BFQ
    Hi,
    this is basically to report outdated statements in your wiki page on
    I/O schedulers [1].
    
    The main problematic statement is that BFQ "...  is not ideal for
    devices with slow CPUs or high throughput I/O devices" because too
    heavy.  BFQ is definitely more sophisticated than any of the other I/O
    schedulers.  We have designed it that way to provide an incomparably
    better service quality, at a very low overhead.  As reported in [2],
    the execution time of BFQ on an old laptop CPU is 0.6 us per I/O
    event, against 0.2 us for mq-deadline (which is the lightest Linux I/O
    scheduler).
    
    To put these figures into context, BFQ proved to be so good for
    "devices with slow CPUs" that, e.g., Chromium OS migrated to BFQ a few
    months ago.  In particular, Google crew got convinced by a demo [3] I
    made for them, on one of the cheapest and slowest Chromebook on the
    market.  In the demo, a fast download is performed.  Without BFQ, the
    download makes the device completely unresponsive.  With BFQ, the
    device remains as responsive as if it was totally idle.
    
    As for the other part of the statement, "...  not ideal for ...  high
    throughput I/O devices", a few days ago I ran benchmarks (on Ubuntu)
    also with one of the fastest consumer-grade NVMe SSDs: a Samsung SSD
    970 PRO.  Results [4] can be summarized as follows.  Throughput with
    BFQ is about the same as with the other I/O schedulers (it couldn't be
    higher, because this kind of drives just wants the scheduler to stay
    as aside as possible, when it comes to throughput).  But, in the
    presence of writes as background workload, start-up times with BFQ are
    at least 16 times as low as with the other I/O schedulers.  In
    absolute terms, gnome-terminal starts in ~1.8 seconds with BFQ, while
    it takes at least 28.7 (!) seconds with the other I/O schedulers.
    Finally, only with BFQ, no frame gets lost in video-playing
    benchmarks.
    
    BFQ then provides other important benefits, such as from 5x to 10X
    throughput boost in multi-client server workloads [5].
    
    So, is there any chance that the outdated/wrong information on your
    wiki page [1] gets updated somehow?  If I may, I'd be glad to update
    it myself, after providing you with all the results you may ask.
    
    In addition, why doesn't Ubuntu too consider switching to BFQ as
    default I/O scheduler, for all drives that BFQ supports (namely all
    drives with a maximum speed not above ~500 KIOPS)?
    
    Looking forward to your feedback,
    Paolo
    
    
  • Should Ubuntu Use The BFQ I/O Scheduler?

    The BFQ I/O scheduler is working out fairly well these days as shown in our benchmarks. The Budget Fair Queueing scheduler supports both throughput and low-latency modes while working particularly well for consumer-grade hardware. Should the Ubuntu desktop be using BFQ by default? [...] But in addition to wanting to correct that Wiki information, Paolo pops the question of why doesn't Ubuntu switch to BFQ as the default I/O scheduler for supported drives. Though as of yet, no Ubuntu kernel developers have yet commented on the prospect of switching to BFQ.

Devices With Linux Support

  • Quest Releases KACE SDA & SMA Updates

    The update to 7.0 for KACE Systems Deployment Appliance is primarily about bringing a scope of endpoint management capabilities with new support for Linux devices to the table.

  • Rugged, Kaby Lake transport computer has a 10-port LAN switch with PoE

    Axiomtek’s Linux-ready “tBOX400-510-FL” transportation system has a 7th Gen Intel CPU and a 10-port managed switch with 8x M12-style 10/100Mbps PoE and 2x GbE ports. The rugged system also has 3x mini-PCIe slots and dual swappable SATA drives. Axiomtek has launched a fanless, Kaby Lake-U based transportation computer with a choice of power supplies designed for in-vehicle, marine, or railway applications. The rugged tBOX400-510-FL features a Qualcomm-driven, Layer 2 managed PoE switch with support for IP surveillance and video management applications. “Customers can connect IP cameras directly without installing an extra PoE switch, minimizing overall deployment costs and installation space onboard,” stated Axiomtek product manager Sharon Huang.