Announcement

Collapse
No announcement yet.

A Look At The MDS Cost On Xeon, EPYC & Xeon Total Impact Of Affected CPU Vulnerabilities

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • max0x7ba
    replied
    These are the types of benchmarks where one wants to see percentages, not the raw unscaled numbers.

    Leave a comment:


  • nuetzel
    replied
    After current mitigation is before next...

    Leave a comment:


  • Alex/AT
    replied
    > A datacenter down 25% in perf would need some rapid upgrades of more of the same.
    Or more of the AMD.

    Leave a comment:


  • msroadkill612
    replied
    It seems too self evident to be fresh, but I have not seen it said that it would explain intel's surprising mini boom in server sales that propped up their numbers and shares recently.

    A datacenter down 25% in perf would need some rapid upgrades of more of the same.

    Its sad for retail investors. The more tech savvy and insiders have had a great opportunity to flip out of their shares at inflated prices.

    Leave a comment:


  • Alex/AT
    replied
    Thanks a lot for the article. Given this one - https://openbenchmarking.org/embed.p...ha=30a8bc6&p=2 - I think we can safely assume multiple cores need a full stop for the buffer clear operation, because the hit is surely improportional to the context switch time growth here if compared with lesser core CPU. Not as much as I expected, but probably only single CPU needs to stop (or even a part of it consisting of some cores), so it's yet to be found.

    Leave a comment:


  • DoMiNeLa10
    replied
    Originally posted by sa666666 View Post
    And with that comment you point out that the Intel shills are already here.

    Can't this analysis be done objectively, keeping to the facts and without resorting to calling anyone you don't agree with a shill? Pointing out that AMD is doing better in a certain area isn't shilling; it's simply stating what is being proven to be a fact.
    The fact that you aren't a shill doesn't mean that there will be shills out there posting in this thread. I'm just saying that this is perfect shill fuel.

    In fact, I'm considering putting an AMD chip into my next computer.

    Leave a comment:


  • Apokalypz
    replied
    You know what's funny? These CPU security flaws keep popping up just often enough to keep further CPU development relevant. Thus, in a way, Intel and AMD both benefit from these hardware bugs. The reason is that they get to churn out new chips with hardware mitigations, bringing the effective speed back up with the new architecture as opposed to implementing new optimizations to improve performance.

    I'd put on my tinfoil hat, but I don't think it has the latest mitigations.

    Leave a comment:


  • Spacefish
    replied
    Why use Cascade Lake CPUs with hardware mitigations? The Skylake Xeons arenĀ“t hit that hard by the mitigations either.. Furthermore some of the benchmarks are far from realworld workloads.. For example Sockperf, it just saturates the network link, most load is inside the kernel without context switchting..

    The Postgres Benchmark is the only relevant IMHO..
    Where are the nginx, apache or Maria DB benchmarks?
    Where are the Hypervisor Benchmarks? A lot of enterprises run ESXi Clusters to virtualize their servers.

    Furthermore a lot of existing enterprise server hardware is still Haswell / Broadwell based..
    For example Google Cloud compute still has active clusters with Sandy Bridge CPUs: https://cloud.google.com/compute/docs/cpu-platforms

    Leave a comment:


  • ThoreauHD
    replied
    Ahh.. Intel will be fine.

    I look at it this way. The next root kit will install 20% slower. Bonus!

    Leave a comment:


  • chithanh
    replied
    Originally posted by phoronix View Post
    PostMark mostly exercises fsync and for this testing the EPYC server saw a 3.5% hit from its relevant Spectre mitigations while the Xeon Platinum 8280 saw a 4% performance hit from its relevant mitigations. The Xeon Gold 6138 server was most impacted with a 18% hit to the performance due to not seeing any hardware mitigations unlike the brand new Cascadelake processors.
    Originally posted by phoronix View Post
    PostgreSQL is one of the server workloads being affected a lot by Spectre/Meltdown/Zombieload and especially so if disabling HT/SMT. In this particular run, the Xeon Gold 6138 server had been outperforming the EPYC 7601 2P server unmitigated but once mitigated fell behind the AMD server being tested.
    Are the numbers between AMD and Intel even comparable here? If I understand correctly, the systems use different storage:
    AMD uses "120GB SSDSCKJB120G7R + 20 x 500GB Samsung SSD 860" while Intel uses "Samsung SSD 970 PRO 512GB" according to the table

    Leave a comment:

Working...
X