Howdy, Stranger!

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


★ VirMach ★ RYZEN ★ NVMe ★★ $8.88/YR- 384MB ★★ $21.85/YR- 2.5GB ★ Instant ★ Japan Pre-order ★ & More - Page 182
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

1179180182184185339

Comments

  • @VirMach said:

    @qzydustin said:

    @VirMach said:
    Around 150~ services have been created today in Tokyo. I'm letting it cool off now. Most of these were previously broken ones.

    There are 109 services remaining pending from this sale, per a database query.

    Will the Japanese network improve in the future? On node 37, there is packet loss on the global network. I think this is abnormal. If this is due to MJJs, there should only be packet loss in China.

    If this is due to a technical issue and it will be fixed in the future. I can wait.

    If you think this is going to be the norm in the future, I'm disappointed in this.

    It's from too many people using it as a VPN. The NIC isn't handling it well, too many packets and tiny transactions going on. We can definitely improve it and have improved it, but it's not something we anticipated or have dealt with before so it will take some more time to tweak it to be perfect.

    Some nodes are doing better than others and I'm applying the settings that work best, and removing the ones that do not.

    Got it. I suggest you to update the progress on https://virmach.com/ryzen-special-offer-news-updates/.

  • @JabJab said:

    @VirMach said: That's actually brilliant.

    Is it? I would rather go that way:
    You didn't send stuff for months, 7 days ago we had a premium/big/long term client asking for new cabinet, we gave him yours hoping we will re-deploy it before you send servers. Didn't work out, we f&cked up. As a sorry we will setup new cabinet within 5 days, give you 2 months free and 2 hours of remote hands. We are sorry again.

    Would you be MAD enough to go find other DC after a message like that?

    The cover up is usually worse than the crime. I think Virmach would appreciate them saying, "we fucked up" rather than the ridiculous excuses that makes no sense. At least with human errors, you can sell the story you've learned from it and won't happen again. Having a crazy excuse just prepares him for future let down with crazy excuse.

    Thanked by 1Tokyom
  • @VirMach said:

    @JabJab said:

    @VirMach said: xTom was able to accommodate us very quickly so luckily the timeline isn't completely thrown off. It'll probably be ready by early next week. They're picking up the hardware from Psychz for us tomorrow and also setting up the cabinet in 1 business day. Theoretically it could be sooner than early next week but I won't push it.

    Time to vote xTom top provider this year, even with 0 services from them (-:

    And Psychz as "most professional"

    Holy shit, LET totally needs an annual Razzies.

    @raindog308 @jbiloh

  • alvinalvin Member
    edited April 2022

    Node : ATLKVM11 status DOWN on 2022-04-27 15:11:04 UTC+0
    @VirMach Please take a look. Thanks

  • I remember reading about it earlier, but was there ever a definitive answer to the constant 50-80KiB/s downloading that these Tokyo VPS are doing? Is it just spam or what?

  • My VPS was shipped yesterday. But port 22 is closed after reinstalling Ubuntu v.20.
    Thank Virmach.

  • @VirMach said:

    @jickur said:
    I want return to Tokyo in advance,the ticket #266828 which named switch from tokyo to sanjose has been closed and can't be replied,

    We can't do these right now, San Jose is having problems.

    When can I migrate

  • RecDRecD Member

    @VirMach said:

    xTom was able to accommodate us very quickly so luckily the timeline isn't completely thrown off. It'll probably be ready by early next week. They're picking up the hardware from Psychz for us tomorrow and also setting up the cabinet in 1 business day. Theoretically it could be sooner than early next week but I won't push it.

    When will Frankfurt be available?
    Any ETA?

  • @RecD said:
    When will Frankfurt be available?
    Any ETA?

    Virmach mentioned that it's not included as part of THIS sale, so I don't think you'll be able to buy it using LET/LES special at this moment.

    Thanked by 1RecD
  • @xpreboun said:

    @RecD said:
    When will Frankfurt be available?
    Any ETA?

    Virmach mentioned that it's not included as part of THIS sale, so I don't think you'll be able to buy it using LET/LES special at this moment.

    What I suspect is that @RecD is combining some stuff said in this thread about maybe moving the Amsterdam servers to a Frankfurt location.

    That was one of the options for the Amsterdam servers - latest said is that they most likely go to a xTom location, and xTom has multiple locations (also in Amsterdam/Haarlem and Frankfurt). Since I've seen the statement that xTom will pick up the servers I'd expect that it'll be Amsterdam or Haarlem (both called "Amsterdam" by xTom).

    Thanked by 1RecD
  • How to send Yabs test results? Please send a detailed tutorial, thank you.

  • Is there a chance for the vm created yesterday to participate in the lottery?

  • @passwa said:
    Is there a chance for the vm created yesterday to participate in the lottery?

    Let's wait for the next lottery. I don't know if it will be held.

  • YYSDYYSD Member
    edited April 2022

    Node 29 has intermittent packet loss for a whole day, please fix it.

  • PilotseyePilotseye Member
    edited April 2022

    Anyone else having recent issues with their VM on NY10GKVM48 ?
    "An error occurred processing your request. The host is currently unavailable. Please try again later"

  • BTW, have you ever consider to isolate the subnet to minimal the ARP or broadcast packet? I think that might be helpful because those small packets could drop a lot so server NIC doesn't need to forward/handle such amount of packets, and what about the NIC upgrade or perf opt to make the networking better?

  • @serverfunlet said:
    BTW, have you ever consider to isolate the subnet to minimal the ARP or broadcast packet? I think that might be helpful because those small packets could drop a lot so server NIC doesn't need to forward/handle such amount of packets, and what about the NIC upgrade or perf opt to make the networking better?

    smaller VLAN may be useful

  • @saosangmo said:
    My VPS was shipped yesterday. But port 22 is closed after reinstalling Ubuntu v.20.
    Thank Virmach.

    Port 22 was lost in shipping.

    Thanked by 2bdl saosangmo
  • FrankZFrankZ Veteran

    @serverfunlet said:
    BTW, have you ever consider to isolate the subnet to minimal the ARP or broadcast packet? I think that might be helpful because those small packets could drop a lot so server NIC doesn't need to forward/handle such amount of packets, and what about the NIC upgrade or perf opt to make the networking better?

    smaller VLAN may be useful

    I though about this earlier and you are most likely correct, but then VirMach would need to change the VPS IP every time a VPS was moved to a different Node. Which at least in the beginning stages of Tokyo would have been a major headache to say the least.

  • FrankZFrankZ Veteran
    edited April 2022

    @YYSD said: Node 29 has intermittent packet loss for a whole day, please fix it.

    I am not seeing any packet loss from node 29 to Sydney, AU.

      1. AS23959 45.66.128.1.static.xtom.com                       0.0%    10    1.7  22.8   1.4  96.4  38.3
      2. AS23959 45.149.159.1                                      0.0%    10   23.7  30.6  13.8  66.5  18.1
      3. AS9607  AS23959.xe-0-1-6.tedge0503.newote.bbtower.ad.jp   0.0%    10    0.6   4.7   0.3  12.9   4.2
      4. AS9607  xe-0-1-2.tedge0504.newote.bbtower.ad.jp          10.0%    10   10.7   5.0   0.4  25.8   8.4
      5. AS9607  et-100-0-19.core0501.newote.bbtower.ad.jp         0.0%    10    1.1   5.8   0.5  31.4  10.5
      6. AS???   172.25.0.9                                        0.0%    10    0.7   9.3   0.6  56.7  18.9
      7. AS3356  8.244.128.201                                    90.0%    10    1.4   1.4   1.4   1.4   0.0
      8. AS3356  ae1.3505.edge2.Tokyo4.level3.net                  0.0%    10    4.1   6.4   1.3  17.2   5.8
      9. AS???   ???                                              100.0    10    0.0   0.0   0.0   0.0   0.0
     10. AS174   be3011.ccr21.hkg02.atlas.cogentco.com             0.0%    10  172.5 169.3 141.3 209.9  23.0
     11. AS174   be2923.ccr31.sin01.atlas.cogentco.com             0.0%    10  224.4 200.2 180.8 263.2  27.0
     12. AS174   154.18.32.82                                      0.0%    10  361.7 258.5 223.0 361.7  42.5
     13. AS63956 ae3.cr1.sg3.sg.coloau.net.au                      0.0%    10  223.9 223.8 223.2 225.8   0.6
     14. AS63956 103.52.119.70                                     0.0%    10  232.0 230.8 229.2 234.9   1.8
     15. AS63956 103.52.119.65                                     0.0%    10  290.4 243.2 228.9 298.0  27.0
     16. AS63956 103.52.116.139                                    0.0%    10  313.7 241.6 228.8 313.7  26.3
     17. AS63956 45.112.245.88                                     0.0%    10  265.0 235.4 228.7 265.0  11.7
     18. AS136557core-a.sy4.nsw.hostuniversal.com.au              10.0%    10  273.0 241.8 228.6 273.0  16.9
     19. AS136557144.48.36.161                                    10.0%    10  235.7 252.1 229.3 280.4  20.7
     20. AS136557144.48.36.155                                     0.0%    10  223.2 240.9 223.2 273.7  19.0
    

    udp port 53 from four locations for today.

    Larger Image

  • fanfan Veteran

    @FrankZ said: packet loss from node 29

    It's more likely ping spikes up to 1000+ms, found that by comparing it with my other VPS in the same DC.

    Thanked by 1FrankZ
  • Yeah, I'm on Node 28 and I don't see any packet loss, however latency spikes up a lot and the StDev is high.

    Thanked by 1FrankZ
  • FrankZFrankZ Veteran
    edited April 2022

    @fan said: It's more likely ping spikes up to 1000+ms, found that by comparing it with my other VPS in the same DC.

    --

    @JeDaYoshi said: Yeah, I'm on Node 28 and I don't see any packet loss, however latency spikes up a lot and the StDev is high.

    I would agree with both of you on the spikes and StDev and this shows in the graph above. Although from my point of view it has been generally improving over time. I expect it is something that VirMach is aware of, and already working to correct long term.

  • VirMachVirMach Member, Patron Provider
    edited April 2022

    @YYSD said:
    Node 29 has intermittent packet loss for a whole day, please fix it.

    Please provide some details. This node looks very healthy.

    @FrankZ said:

    @serverfunlet said:
    BTW, have you ever consider to isolate the subnet to minimal the ARP or broadcast packet? I think that might be helpful because those small packets could drop a lot so server NIC doesn't need to forward/handle such amount of packets, and what about the NIC upgrade or perf opt to make the networking better?

    smaller VLAN may be useful

    I though about this earlier and you are most likely correct, but then VirMach would need to change the VPS IP every time a VPS was moved to a different Node. Which at least in the beginning stages of Tokyo would have been a major headache to say the least.

    This was actually one of our concerns when we did it the way we did, and if other locations start having issues as well we'll come up with a plan to move people around and/or change their IP addresses with proper notice.

    I don't think this is the main issue though from what I've looked at, it just seems more affected by the quantity of packets in general, because we can make some drastic improvements by changing some stuff around on ethtool.

    @JeDaYoshi said:
    Yeah, I'm on Node 28 and I don't see any packet loss, however latency spikes up a lot and the StDev is high.

    38? We don't have a 28 right now.

    Thanked by 2FrankZ DP
  • VirMachVirMach Member, Patron Provider

    @fan said:

    @FrankZ said: packet loss from node 29

    It's more likely ping spikes up to 1000+ms, found that by comparing it with my other VPS in the same DC.

    Okay I'll look into this more.

    Thanked by 3FrankZ fan DP
  • VirMachVirMach Member, Patron Provider

    @saosangmo said:
    My VPS was shipped yesterday. But port 22 is closed after reinstalling Ubuntu v.20.
    Thank Virmach.

    Probably Ubuntu w/ Desktop that uses port 6000?

  • Any updates on SEAZ001. I can't even get to server details. It shows "Operation Timed Out After 90001 Milliseconds With 0 Bytes Received"

  • @monsterup said:
    Any updates on SEAZ001. I can't even get to server details. It shows "Operation Timed Out After 90001 Milliseconds With 0 Bytes Received"

    In early April, I saw it explained that that error would appear when the server is overloading. But now it may be a different.

  • yczhengyczheng Member
    edited April 2022

    @VirMach said:

    @YYSD said:
    Node 29 has intermittent packet loss for a whole day, please fix it.

    Please provide some details. This node looks very healthy.

    My VPS is also on Node 29 and saw packet loss for all routes by ping.pe

    See a larger one

    Thanked by 1Durs
  • Is there any updates about when will SEAZ001 be online?

This discussion has been closed.