Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Sign In Register

Quick Links


Shells Virtual Desktop
BMail.ag - Secure Email Service
Server.net
CPLicense.net
VPS Server
Buy VPN
Vultr
VMs for AI
HostDare
ReliableSite White-Label Dedicated Hosting for Resellers
InterServer VPS
BMail.ag - Secure Email Service
Best VPN
High-Performance Bare Metal Server Solutions
Karvl.com
Server Mania Cloud Hosting
DataWagon Hosting
AlphaVPS Hosting
Evoxt.com
Clouvider
VPS Hosting with NVMe
Residential IPs in the US & 4G Mobile Proxies in EU & US with Unlimited Bandwidth
ReliableSite White-Label Dedicated Hosting for Resellers
Rabisu - Hosting Solutions
Shells Virtual Desktop

Categories

In this Discussion

Home › Offers
New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

★ VirMach ★ RYZEN ★ NVMe ★★ $8.88/YR- 384MB ★★ $21.85/YR- 2.5GB ★ Instant ★ Japan Pre-order ★ & More

1…5051535556…339

Comments

  • miumiu Member
    edited March 2022

    @VirMach said:

    With Eco Mode: CB20 6523 multi & 505 single core @ 59W
    Without Eco Mode: 7166 multi & 505 single core @ 110W

    So around 45% less power (=less heat) while losing less than 10% performance. For me and my use case (24x7) this was a given win.

    Interesting finding: I am using 5950X in my workstation and CPU performance are too practically the same both (multi and single) in PERFORMANCE vs. ECO MODE. (Asus main board) Larger differences seems to be while eco mode try throttle down cpu frequency more strictly at lower load, perfo try keep it higher permanently and also main board automatically adjust (up) voltages for cpu, northbridge and southbridge (this may be cause of higher power consumption u mentioned). FAN load and CPU heat i am not able good compare bcs using water coolling with large radiator. In conclusion - i agree with your finding (especially at these really high performance AMD CPUs) that is more sane use normal or eco modes instead performance if server is not under regular peak load near to 100% (and its MB support/allow such settings/modes). BTW: Nowadays AMD processors really they are good at coping with a high load. Is X reasons for me stay at AMD and no reason return back to intel (imo, personally), very satisfied from time while working on new generation AMD processors.

  • reb0rnreb0rn Member

    I sorted my Ubuntu 20.04 install
    On San Jose imagine worked
    On Seattle it does not as there where some issue with partition and file system error so I used netbootin to install clean ubuntu 20.04 from network and it worked

  • VirMachVirMach Member, Patron Provider
    edited March 2022

    Shipment update

    I'm delaying these by a day to re-evaluate, and make sure any that have similar brand NVMe are tested further. I also got sidetracked by the ongoing situation with TYOC040 so I fell behind on the shipments and couldn't meet my target (which is good I suppose, as I have to unpack some servers now and if more were ready, that'd be more work.)

    I'll see if I can go back and review my records and rule any of these out and see if I can try to send something out today but I'm still working on node configurations too, we'll see how it goes!

    Thanked by 4Xrmaddness SakuraCat FAT32 noisycode
  • miumiu Member

    @VirMach said:

    any ETAs when larger AMD plans are planned to be available pls?

  • miumiu Member

    (mean more cores & larger disks) thanks

  • VirMachVirMach Member, Patron Provider

    @reb0rn said:
    I sorted my Ubuntu 20.04 install
    On San Jose imagine worked
    On Seattle it does not as there where some issue with partition and file system error so I used netbootin to install clean ubuntu 20.04 from network and it worked

    This is still on the list as well, I'm trying to prioritize going through all templates, modifying and generating improved compatibility versions, and clean up the syncs across all nodes so they're uniform.

  • VirMachVirMach Member, Patron Provider

    @miu said:

    @VirMach said:

    any ETAs when larger AMD plans are planned to be available pls?

    I actually was about to post the 8GB package earlier yesterday and then everything else happened which took away my time. I completely forgot, let me see if I can work that into today's schedule.

    Thanked by 1miu
  • miumiu Member
    edited March 2022

    @VirMach said:

    @miu said:

    @VirMach said:

    any ETAs when larger AMD plans are planned to be available pls?

    I actually was about to post the 8GB package earlier yesterday and then everything else happened which took away my time. I completely forgot, let me see if I can work that into today's schedule.

    Sure. Thanks, good new, take your time for it. And looking fwd - Virmach got absolutely new dimension of performance with this Ryzen lines, excited :+1:

  • smarty24smarty24 Member

    @smarty24 said:

    @VirMach said:

    @Davis said:
    @VirMach
    Hello, can you help me change the location to Tokyo?Thanks a lot!
    Invoice：1404755

    Changed, but I can't change any future ones, only if people requested it in the past, so please quote your old posts if you posted the request and I didn't get to it.

    @smarty24 said:

    @VirMach said:
    Any requests to switch locations I haven't processed yet, please post it again now and be clear about the details. Most if not all should be done, so any left I missed.

    Hi @VirMach - I think you missed my older request as I didn't get a short confirmation from you. I asked for a location switch from Tokyo to LA. No worries about any waiting time. Appreciate your help 😀 (Invoice #1397608 - Order ID is 652865 - "LargeWorried-VM")

    I hope now you´ll get it :-) Thanks, appreciate it.

    Sorry, another try - but @VirMach asked everyone to post an older request again to bring it to his attention. Hope you will confirm it now, @VirMach. Thanks!

  • foitinfoitin Member

    Currently all provisioned VMs are on TYOC040?
    IIRC there’s another server shipped. What about that one?

  • VirMachVirMach Member, Patron Provider

    @foitin said:
    Currently all provisioned VMs are on TYOC040?
    IIRC there’s another server shipped. What about that one?

    There's 6 other servers shipped, set to arrive this week, yes. All provisioned are on TYOC040, I was running into issues with TOC039 yesterday hence why it got delayed. I finally got it functional and then ran into another weird issue today, I may have to re-install. Weird issue is because I'm still redoing the setup documentation for these particular builds and some steps are iffy.

  • VirMachVirMach Member, Patron Provider

    @smarty24 said:

    @smarty24 said:

    @VirMach said:

    @Davis said:
    @VirMach
    Hello, can you help me change the location to Tokyo?Thanks a lot!
    Invoice：1404755

    Changed, but I can't change any future ones, only if people requested it in the past, so please quote your old posts if you posted the request and I didn't get to it.

    @smarty24 said:

    @VirMach said:
    Any requests to switch locations I haven't processed yet, please post it again now and be clear about the details. Most if not all should be done, so any left I missed.

    Hi @VirMach - I think you missed my older request as I didn't get a short confirmation from you. I asked for a location switch from Tokyo to LA. No worries about any waiting time. Appreciate your help 😀 (Invoice #1397608 - Order ID is 652865 - "LargeWorried-VM")

    I hope now you´ll get it :-) Thanks, appreciate it.

    Sorry, another try - but @VirMach asked everyone to post an older request again to bring it to his attention. Hope you will confirm it now, @VirMach. Thanks!

    Already set to Tokyo.

    Thanked by 1smarty24
  • smarty24smarty24 Member

    @VirMach said:

    @smarty24 said:

    @smarty24 said:

    @VirMach said:

    @Davis said:
    @VirMach
    Hello, can you help me change the location to Tokyo?Thanks a lot!
    Invoice：1404755

    Changed, but I can't change any future ones, only if people requested it in the past, so please quote your old posts if you posted the request and I didn't get to it.

    @smarty24 said:

    @VirMach said:
    Any requests to switch locations I haven't processed yet, please post it again now and be clear about the details. Most if not all should be done, so any left I missed.

    Hi @VirMach - I think you missed my older request as I didn't get a short confirmation from you. I asked for a location switch from Tokyo to LA. No worries about any waiting time. Appreciate your help 😀 (Invoice #1397608 - Order ID is 652865 - "LargeWorried-VM")

    I hope now you´ll get it :-) Thanks, appreciate it.

    Sorry, another try - but @VirMach asked everyone to post an older request again to bring it to his attention. Hope you will confirm it now, @VirMach. Thanks!

    Already set to Tokyo.

    @VirMach: It should be changed from Tokyo to LA.

  • leendonleendon Member

    @VirMach What is the situation when the node is locked? After the system is reinstalled, the server is offline, and it can't handle it by itself.

  • SonnyCUISonnyCUI Member

    @SonnyCUI said:

    @SonnyCUI said:

    @VirMach said:

    @SonnyCUI said:

    @VirMach said:

    @SonnyCUI said:

    @VirMach said:

    @SonnyCUI said:
    I have Placed the 4 VPS orders, the system automatic split each one to sub account, when I purchase new vps.

    Create support ticket, the support team said they will merge them to my main account, but finial someone refund my 3 VPS without notice me or the agreement they settle.

    And I wait weeks, no one give me any updates. it's really unacceptable.

    @VirMach Ticket #509751

    The ticket you provided, I don't see that one being cancelled/refunded, it's pending.

    Invoice #1399104 - Ryzen Special 384 LA
    Invoice #1400321 - Ryzen Special 2560 JP
    Invoice #1401040 - STORAGE-250G JP

    already been refunded in my sub account, and money had back, when I wait the support team merge VPS. and wait to now.

    Merge ticket is unrelated to that. Check other ticket, if you have other ticket that may be why.

    I only create merge ticket to avoid any mis understanding, I did not create other ones.

    the support team reply me as:

    "Hi, please provide the order or invoice ID for each of these purchases so that we can track the accounts and merge them into your main account.

    Qi G."

    then I provided the all four invoices (16th MAR), the next day all 3 VPS in sub account had been refunded. and no one reply me or update me on ticket. I know it a week ago.

    @VirMach please help on this, thanks a lot.

    I need other ticket IDs you created.

    @VirMach I only created Ticket #509751 for merge my VPS to my main account.

    Now I create #114194 #498498 #940526 asked recreate invoice to process. thanks a lot.

    I saw you route #114194 #498498 to billing department

    940526 have not yet route to billing department, btw when these can be fixed?

    @VirMach thanks agian.

    @VirMach all the ticket not update, could you please help to push, it's really unacceptable, agreed to merge VPS, but refund the paid invoice indeed.

    the tickets need to follow:#114194 #498498 #940526

  • Tom2019Tom2019 Member

    @VirMach said:

    @smarty24 said:

    @smarty24 said:

    @VirMach said:

    @Davis said:
    @VirMach
    Hello, can you help me change the location to Tokyo?Thanks a lot!
    Invoice：1404755

    Changed, but I can't change any future ones, only if people requested it in the past, so please quote your old posts if you posted the request and I didn't get to it.

    @smarty24 said:

    @VirMach said:
    Any requests to switch locations I haven't processed yet, please post it again now and be clear about the details. Most if not all should be done, so any left I missed.

    Hi @VirMach - I think you missed my older request as I didn't get a short confirmation from you. I asked for a location switch from Tokyo to LA. No worries about any waiting time. Appreciate your help 😀 (Invoice #1397608 - Order ID is 652865 - "LargeWorried-VM")

    I hope now you´ll get it :-) Thanks, appreciate it.

    Sorry, another try - but @VirMach asked everyone to post an older request again to bring it to his attention. Hope you will confirm it now, @VirMach. Thanks!

    Already set to Tokyo.

    @VirMach Has the request to change the location to Tokyo been accepted? The location of my order has not changed.Please help me take a look.

    Order Number 1783999301
    Invoice ID 1405804

  • VirMachVirMach Member, Patron Provider
    edited March 2022

    TYOC040 update - I managed to find some information on the issue and apparently some NVMe SSDs have issues on Linux with certain specific configurations related to the CPU and motherboard. I applied a few fixes, and I've ran a few sets of benchmarks on it without it dying as @FAT32 previously mentioned happened when he tried.

    So far it's stable, but that's not a guarantee it will remain that way. I'm going to try to bring everyone's VM back online, and create the rest on the other node just to be safe and see how it goes. It's very possible a drive will just get knocked off again as soon as VMs start powering on, especially if everyone benchmarks at once and if there's other issues related to the SVM bug and creations.

    (edit) Andddd it broke.

    (edit2) Trying one last thing.

    Thanked by 10shinzi xpreboun FAT32 tototo FrankZ noisycode fan taizi JabJab nick_
  • VirMachVirMach Member, Patron Provider

    New issue appearing now. Alright folks, this one's going to be considered toast.

    The server is going to be powered down/removed from SolusVM. Anyone who has important data (I'm guessing you shouldn't since it was barely online) can make a ticket and I'll retrieve it for them. Otherwise I'm recreating everyone on the other node once I do more testing and make sure this doesn't repeat on that as well.

    Thanked by 12Xrmaddness noisycode FAT32 nightcat sanvit countra FrankZ tototo JabJab nick_ tooyoung ZA_capetown
  • DoucheBagzDoucheBagz Member

    Sorry to post here about this @VirMach , but is there any chance for you to look into my ticket please? #994620 - it has been almost 6 days since I have had a reply. It says updating my ticket could result in a delay so I am posting here. The VPS hasn't worked since it was delivered. Thank you for the assistance!

  • manxsecmanxsec Member

    @VirMach said:
    New issue appearing now. Alright folks, this one's going to be considered toast.

    The server is going to be powered down/removed from SolusVM. Anyone who has important data (I'm guessing you shouldn't since it was barely online) can make a ticket and I'll retrieve it for them. Otherwise I'm recreating everyone on the other node once I do more testing and make sure this doesn't repeat on that as well.

    Can you predict delivery this Friday?

  • yaya_yaya_ Member

    Go Go VIRMACH

  • sangatsetiasangatsetia Member

    Go... Go.... @VirMach
    I respectfully request, I beg you very much,
    please follow up on my ticket #309737
    please please....
    I'm waiting

  • KuYeHQKuYeHQ Member
    edited March 2022

    virmach, please let me join the server stability test, my Invoice #1397721 :)

  • riofredinandriofredinand Member

    @VirMach said:
    New issue appearing now. Alright folks, this one's going to be considered toast.

    The server is going to be powered down/removed from SolusVM. Anyone who has important data (I'm guessing you shouldn't since it was barely online) can make a ticket and I'll retrieve it for them. Otherwise I'm recreating everyone on the other node once I do more testing and make sure this doesn't repeat on that as well.

    Oh no BBQ le

  • elliotcelliotc Member

    @VirMach said:

    @TimboJones said:

    @VirMach said:

    @TimboJones said: Your heatsink likely isn't rated for the TDP of the CPU or it sucks.

    https://www.anandtech.com/show/16214/amd-zen-3-ryzen-deep-dive-review-5950x-5900x-5800x-and-5700x-tested/8

    It's funny because the heatsink rated for 95 TDP functions better than those advertised for 105+ but that's a whole other can of worms.

    With these rackmounts the fans end up being more important in most cases I've noticed though and even with excessive fans (as in fans all over, even ones that would not fit in normal use) the same problem I'm describing exists. So at this point it doesn't really seem to be a "problem" and more of a "feature" on how these function. As in, AMD wants it to get hot and maximize performance and then cut it off however they want by default unless you do a custom configuration as we've done.

    There's a difference between throttling down below base frequency due to inadequate heat sinking and having limited time boost window ABOVE the base frequency. I don't call coming down from the boost frequency as throttling and I don't think others do, either.

    So if you're actually throttling below base frequency, something ain't right.

    I think something important to note is that my testing is extreme, to make sure it's the absolute worst case possible scenario. In these cases, that means the node was purposefully overloaded to a situation similar to a node about to crash with load in at least the hundreds. The only time this would be potentially close to being replicated is if something is seriously messed up, and maybe this does paint an incorrect picture.

    But the 3000 series can put up with this better, perhaps because it's never allowed or designed to reach the performance level of the 5000 series.

    What I can assure you is that in these tests, no one would be able to bend the laws of physics any further. As in, with everything else kept exactly the same between 3000 and 5000 series, down all the way to the thermal paste used, there isn't any 1U chassis that could accommodate the level of cooling I provided to attempt to alleviate the throttling in these tests, even if it's up to spec. Yes, perhaps moving the 5000 series to 2U instead could help a little bit when it comes specifically to the heatsink and fans (and nothing else) but these processors are advertised as the same TDP and in many benchmarks the 5000 series actually may actually stay cooler. As in, the temperatures definitely do seem to be lower in some of these burst scenarios. And to add to that, there will be less throttling if the cooling is extreme. However, when it comes to 24x7 operation, the 5000 series definitely has more periods of time where it does throttle below the frequency of similar 3000 series (and it also has more periods of time where it goes much higher above the base frequency.)

    Trust me, I've done more testing than I care to admit and ruled out pretty much everything else. I've used different boards, heatsinks, changed airflow, changed chassis, looked into different static pressure fans and physical configurations of the air shrouds, used processors from different batches, modified the ambient temperature, and even tested these on extreme liquid cooling, and the similar differences in pattern remain.

    I'm not saying that the 5000 series cannot be used, only that I have some concerns, especially when it comes to 5000 series versus 3000 series or 5950X versus 5900X.

    Have you taken into account that Tokyo is hotter than other location?

    Thanked by 2FrankZ noisycode
  • VirMachVirMach Member, Patron Provider

    @manxsec said:

    @VirMach said:
    New issue appearing now. Alright folks, this one's going to be considered toast.

    The server is going to be powered down/removed from SolusVM. Anyone who has important data (I'm guessing you shouldn't since it was barely online) can make a ticket and I'll retrieve it for them. Otherwise I'm recreating everyone on the other node once I do more testing and make sure this doesn't repeat on that as well.

    Can you predict delivery this Friday?

    Yes, I'm a seer.

    Thanked by 3Xrmaddness FrankZ skorous
  • VirMachVirMach Member, Patron Provider

    @DoucheBagz said:
    Sorry to post here about this @VirMach , but is there any chance for you to look into my ticket please? #994620 - it has been almost 6 days since I have had a reply. It says updating my ticket could result in a delay so I am posting here. The VPS hasn't worked since it was delivered. Thank you for the assistance!

    You have an ISO mounted which doesn't work.

  • VirMachVirMach Member, Patron Provider

    @sangatsetia said:
    Go... Go.... @VirMach
    I respectfully request, I beg you very much,
    please follow up on my ticket #309737
    please please....
    I'm waiting

    I don't understand why you'd think that posting a ticket for your rDNS request here would result in it being prioritized.

    Thanked by 1FrankZ
  • VirMachVirMach Member, Patron Provider

    @elliotc said:

    @VirMach said:

    @TimboJones said:

    @VirMach said:

    @TimboJones said: Your heatsink likely isn't rated for the TDP of the CPU or it sucks.

    https://www.anandtech.com/show/16214/amd-zen-3-ryzen-deep-dive-review-5950x-5900x-5800x-and-5700x-tested/8

    It's funny because the heatsink rated for 95 TDP functions better than those advertised for 105+ but that's a whole other can of worms.

    With these rackmounts the fans end up being more important in most cases I've noticed though and even with excessive fans (as in fans all over, even ones that would not fit in normal use) the same problem I'm describing exists. So at this point it doesn't really seem to be a "problem" and more of a "feature" on how these function. As in, AMD wants it to get hot and maximize performance and then cut it off however they want by default unless you do a custom configuration as we've done.

    There's a difference between throttling down below base frequency due to inadequate heat sinking and having limited time boost window ABOVE the base frequency. I don't call coming down from the boost frequency as throttling and I don't think others do, either.

    So if you're actually throttling below base frequency, something ain't right.

    I think something important to note is that my testing is extreme, to make sure it's the absolute worst case possible scenario. In these cases, that means the node was purposefully overloaded to a situation similar to a node about to crash with load in at least the hundreds. The only time this would be potentially close to being replicated is if something is seriously messed up, and maybe this does paint an incorrect picture.

    But the 3000 series can put up with this better, perhaps because it's never allowed or designed to reach the performance level of the 5000 series.

    What I can assure you is that in these tests, no one would be able to bend the laws of physics any further. As in, with everything else kept exactly the same between 3000 and 5000 series, down all the way to the thermal paste used, there isn't any 1U chassis that could accommodate the level of cooling I provided to attempt to alleviate the throttling in these tests, even if it's up to spec. Yes, perhaps moving the 5000 series to 2U instead could help a little bit when it comes specifically to the heatsink and fans (and nothing else) but these processors are advertised as the same TDP and in many benchmarks the 5000 series actually may actually stay cooler. As in, the temperatures definitely do seem to be lower in some of these burst scenarios. And to add to that, there will be less throttling if the cooling is extreme. However, when it comes to 24x7 operation, the 5000 series definitely has more periods of time where it does throttle below the frequency of similar 3000 series (and it also has more periods of time where it goes much higher above the base frequency.)

    Trust me, I've done more testing than I care to admit and ruled out pretty much everything else. I've used different boards, heatsinks, changed airflow, changed chassis, looked into different static pressure fans and physical configurations of the air shrouds, used processors from different batches, modified the ambient temperature, and even tested these on extreme liquid cooling, and the similar differences in pattern remain.

    I'm not saying that the 5000 series cannot be used, only that I have some concerns, especially when it comes to 5000 series versus 3000 series or 5950X versus 5900X.

    Have you taken into account that Tokyo is hotter than other location?

    I heard the drift there is fast and furious, good airflow.

    Thanked by 3Xrmaddness FrankZ bark
  • riofredinandriofredinand Member

    @VirMach said:

    @elliotc said:

    @VirMach said:

    @TimboJones said:

    @VirMach said:

    @TimboJones said: Your heatsink likely isn't rated for the TDP of the CPU or it sucks.

    https://www.anandtech.com/show/16214/amd-zen-3-ryzen-deep-dive-review-5950x-5900x-5800x-and-5700x-tested/8

    It's funny because the heatsink rated for 95 TDP functions better than those advertised for 105+ but that's a whole other can of worms.

    With these rackmounts the fans end up being more important in most cases I've noticed though and even with excessive fans (as in fans all over, even ones that would not fit in normal use) the same problem I'm describing exists. So at this point it doesn't really seem to be a "problem" and more of a "feature" on how these function. As in, AMD wants it to get hot and maximize performance and then cut it off however they want by default unless you do a custom configuration as we've done.

    There's a difference between throttling down below base frequency due to inadequate heat sinking and having limited time boost window ABOVE the base frequency. I don't call coming down from the boost frequency as throttling and I don't think others do, either.

    So if you're actually throttling below base frequency, something ain't right.

    I think something important to note is that my testing is extreme, to make sure it's the absolute worst case possible scenario. In these cases, that means the node was purposefully overloaded to a situation similar to a node about to crash with load in at least the hundreds. The only time this would be potentially close to being replicated is if something is seriously messed up, and maybe this does paint an incorrect picture.

    But the 3000 series can put up with this better, perhaps because it's never allowed or designed to reach the performance level of the 5000 series.

    What I can assure you is that in these tests, no one would be able to bend the laws of physics any further. As in, with everything else kept exactly the same between 3000 and 5000 series, down all the way to the thermal paste used, there isn't any 1U chassis that could accommodate the level of cooling I provided to attempt to alleviate the throttling in these tests, even if it's up to spec. Yes, perhaps moving the 5000 series to 2U instead could help a little bit when it comes specifically to the heatsink and fans (and nothing else) but these processors are advertised as the same TDP and in many benchmarks the 5000 series actually may actually stay cooler. As in, the temperatures definitely do seem to be lower in some of these burst scenarios. And to add to that, there will be less throttling if the cooling is extreme. However, when it comes to 24x7 operation, the 5000 series definitely has more periods of time where it does throttle below the frequency of similar 3000 series (and it also has more periods of time where it goes much higher above the base frequency.)

    Trust me, I've done more testing than I care to admit and ruled out pretty much everything else. I've used different boards, heatsinks, changed airflow, changed chassis, looked into different static pressure fans and physical configurations of the air shrouds, used processors from different batches, modified the ambient temperature, and even tested these on extreme liquid cooling, and the similar differences in pattern remain.

    I'm not saying that the 5000 series cannot be used, only that I have some concerns, especially when it comes to 5000 series versus 3000 series or 5950X versus 5900X.

    Have you taken into account that Tokyo is hotter than other location?

    I heard the drift there is fast and furious, good airflow.

    Wow you guys are chatting with videos,that's COOOOOOOOL.

This discussion has been closed.