SlackwareThis Forum is for the discussion of Slackware Linux.
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
Worth reading Intel's official performance impact benchmarks after applying the "mitigation" on Win10 - not effectively describing what, but presumably firmware + SW patch:
Worth reading Intel's official performance impact benchmarks after applying the "mitigation" on Win10 - not effectively describing what, but presumably firmware + SW patch:
They're referencing desktop PeeCee and Laptop Performance Hits.
What they skilfully neglect to say in that marketing piece it is MUCH Worse on Servers, even on Microsoft Servers.
One anecdote I can provide ...
We've been running a CentOS-Based Server Application on AWS for five years or so.
Before Amazon did their forced reboots last week, the load averages ran consistently less than 1.00 ...
After the AWS forced reboot, our load averages skyrocketed to between 7.00 and 9.00 and our Server App took a dump -- it could no longed accept Client Connections and all hell broke loose.
Amazon's advice: buy a bigger instance -- a pisser after running on that Server since 2013 !
So we spent the weekend scrambling to move our hand-rolled server-side application to 'a bigger instance'.
It runs fine now but it cost us the entire weekend to migrate and then to clean up the aftermath in the DataBase Tables.
Not to mention our AWS Monthly Fees will increase proportionally.
And then there are our Client Apps Servers ( Data Conversion && Transfer Boxen ) which took a 38% dive on our Intel NUC Model after applying Intel's BIOS Updates and the CentOS 6 Kernel Updates.
I've not measured the effects on our Zotac ZBOXen ... Still waiting for a BIOS Update there, but I don't expect any better results.
And if you consider that these are the "latest generation processors" and that, as reported my Redmond: https://www.linuxquestions.org/quest...ml#post5804447
the performance impact on older "generations" - Haswell downwards will be higher, I'm afraid that Mr. Schneier was right:
"The security of pretty much every computer on the planet has just gotten a lot worse, and the only real solution -- which of course is not a solution -- is to throw them all away and buy new ones." https://www.schneier.com/blog/archiv...and_mel_1.html
@abga and @Kjhambrick The information about performance after microcode AND kernel updates is more directly related to Greg K-H's thread on Meltdown, Spectre and other threats https://www.linuxquestions.org/quest...el-4175621133/. Please move the discussion on mitigation to that thread or the security thread. This thread is intended as a "howto" for microcode update and not intended to replace the security thread(s) or Greg K-H's thread.
Some may feel that readers should understand the performance impact of these latest microcode updates, OR the possibility that doing an update may actually be futile and simply getting a different processor is the only solution. However, there are some of us who wish to continue using our existing CPU's and want to know what is the proper procedure to be successful.
@bamunds
My mistake in considering that some of you might care not only about the result, but also about its quality.
Please, do carry on and sorry for the interference.
@abga Thank you for understanding the intent of this thread. This will be marked SOLVED once I have captured the process for "Howto upgrade Intel microcode" with examples of what tools to use and how to measure success of the installation. That needs to include what errors one might get. Cheers.
Does anyone knows how to load microcode for AMD processors?
Unlike Intel, AMD's microcode has a licence that allows it to be redistributed. So it comes with the Linux firmware blobs (in Slackware that's the kernel-firmware package) and is loaded automatically on boot. See your /lib/firmware/amd-ucode/ directory.
Also, unlikely Intel, the AMD does NOT add or remove CPU features via microcode, then its microcode is safely to be loaded later, if the operating system survive until that, i.e. does not try to execute some faulty instruction or command.
Also, unlikely Intel, the AMD does NOT add or remove CPU features via microcode, then its microcode is safely to be loaded later, if the operating system survive until that, i.e. does not try to execute some faulty instruction or command.
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.