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.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
kuroit multi-location benchmark and review
First I want to thank @kuroit for generously providing me with access to VPS in 4 locations, Dallas, Ashburn, Singapore, and Chicago. THANK YOU kuroit! 
Now, on to the results and review. Dallas first.
Based on well over 50 runs.
Version 2.5.0a, (c) 2018+ jsg (->lowendtalk.com)
Machine: amd64, Arch.: amd64, Model: AMD EPYC 7571 32-Core Processor
OS, version: FreeBSD 14.1, Mem.: 1.989 GB
CPU - Cores: 2, Family/Model/Stepping: 23/1/2
Cache: 32K/64K L1d/L1i, 512K L2, 64M L3
Std. Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat
pse36 cflsh mmx fxsr sse sse2 sse3 pclmulqdq ssse3 fma cx16 sse4_1
sse4_2 popcnt aes xsave osxsave avx f16c rdrnd hypervisor
Ext. Flags: syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm lahf_lm cmp_legacy svm
cr8_legacy lzcnt sse4a misalignsse 3dnowprefetch osvw perfctr_core
AES? Yes
InNested Virt.? Yes
HW RNG? Yes
ProcMem SC [MB/s]: avg 148.6 - min 45.1 (30.4 %), max 262.5 (176.7 %)
ProcMem MA [MB/s]: avg 475.8 - min 432.3 (90.9 %), max 525.1 (110.4 %)
ProcMem MB [MB/s]: avg 481.0 - min 435.3 (90.5 %), max 568.1 (118.1 %)
ProcMem AES [MB/s]: avg 851.6 - min 786.8 (92.4 %), max 914.9 (107.4 %)
ProcMem RSA [kp/s]: avg 55.9 - min 45.1 (80.7 %), max 66.0 (118.0 %)
Not overwhelming nowadays but reasonably decent, more than good enough for my use case anyway. And all the desirable flags are there too.
Next, the disk.
--- Disk 4 KB - Buffered ---
Write seq. [MB/s]: avg 3.67 - min 3.46 (94.4%), max 3.88 (105.8%)
Write rnd. [MB/s]: avg 3.60 - min 3.36 (93.2%), max 3.85 (106.8%)
Read seq. [MB/s]: avg 11.03 - min 10.36 (94.0%), max 11.86 (107.6%)
Read rnd. [MB/s]: avg 9.88 - min 9.47 (95.8%), max 10.34 (104.6%)
--- Disk 4 KB - Sync/Direct ---
Write seq. [MB/s]: avg 3.64 - min 3.50 (96.2%), max 3.82 (104.9%)
Write rnd. [MB/s]: avg 3.56 - min 3.37 (94.8%), max 3.78 (106.3%)
Read seq. [MB/s]: avg 11.01 - min 10.21 (92.7%), max 11.52 (104.6%)
Read rnd. [MB/s]: avg 9.86 - min 9.15 (92.8%), max 10.34 (104.8%)
--- Disk 64 KB - Buffered ---
Write seq. [MB/s]: avg 31.68 - min 28.59 (90.2%), max 34.01 (107.4%)
Write rnd. [MB/s]: avg 34.93 - min 33.10 (94.7%), max 36.62 (104.8%)
Read seq. [MB/s]: avg 1250.60 - min 1079.81 (86.3%), max 1412.34 (112.9%)
Read rnd. [MB/s]: avg 130.60 - min 112.54 (86.2%), max 144.16 (110.4%)
--- Disk 64 KB - Sync/Direct ---
Write seq. [MB/s]: avg 6.57 - min 4.85 (73.8%), max 7.75 (117.9%)
Write rnd. [MB/s]: avg 4.10 - min 3.10 (75.6%), max 5.23 (127.5%)
Read seq. [MB/s]: avg 1251.87 - min 990.62 (79.1%), max 1419.95 (113.4%)
Read rnd. [MB/s]: avg 138.16 - min 132.20 (95.7%), max 147.20 (106.5%)
--- Disk 1 MB - Buffered ---
Write seq. [MB/s]: avg 44.24 - min 39.28 (88.8%), max 47.98 (108.5%)
Write rnd. [MB/s]: avg 87.13 - min 79.03 (90.7%), max 95.86 (110.0%)
Read seq. [MB/s]: avg 2012.73 - min 1755.41 (87.2%), max 2395.97 (119.0%)
Read rnd. [MB/s]: avg 666.23 - min 619.83 (93.0%), max 721.27 (108.3%)
--- Disk 1 MB - Sync/Direct ---
Write seq. [MB/s]: avg 20.30 - min 18.78 (92.5%), max 28.52 (140.5%)
Write rnd. [MB/s]: avg 28.80 - min 26.11 (90.7%), max 40.32 (140.0%)
Read seq. [MB/s]: avg 1968.62 - min 1656.66 (84.2%), max 2304.67 (117.1%)
Read rnd. [MB/s]: avg 636.98 - min 575.23 (90.3%), max 696.31 (109.3%)
--- Disk IOps (Sync/Direct) ---
Write seq. [MB/s]: avg 27.86 - min 25.36 (91.0%), max 30.87 (110.8%)
IOps : avg 7133.06 - min 6491.64 (91.0%), max 7903.89 (110.8%)
Not a speed daemon but quite good, in particular when considering the > 7000 IOps and the quite tight spread.
Let's have a look at what I personally am most interested in, connectivity.
--- Europe ---
NO OSL mirror.terrahost.no [F: 0]
DL [Mb/s]: avg 90.5 - min 90.1 (99.6%), max 91.4 (101.0%)
Ping [ms]: avg 123.2 - min 123.0 (99.8%), max 123.5 (100.2%)
Web ping [ms]: avg 123.8 - min 123.1 (99.5%), max 145.9 (117.9%)
UK LON lon.speedtest.clouvider.net [F: 0]
DL [Mb/s]: avg 101.7 - min 94.2 (92.6%), max 104.9 (103.1%)
Ping [ms]: avg 110.2 - min 109.9 (99.8%), max 113.2 (102.8%)
Web ping [ms]: avg 111.8 - min 109.9 (98.3%), max 119.3 (106.7%)
NL AMS nl.mirrors.clouvider.net [F: 0]
DL [Mb/s]: avg 95.1 - min 89.6 (94.3%), max 99.0 (104.2%)
Ping [ms]: avg 116.2 - min 113.6 (97.8%), max 124.6 (107.3%)
Web ping [ms]: avg 118.1 - min 113.7 (96.2%), max 126.4 (107.0%)
DE FRA mirror.plusline.net [F: 0]
DL [Mb/s]: avg 93.2 - min 87.2 (93.6%), max 95.5 (102.4%)
Ping [ms]: avg 120.5 - min 118.1 (98.0%), max 130.0 (107.9%)
Web ping [ms]: avg 120.9 - min 118.2 (97.7%), max 130.0 (107.5%)
FR PAR mirror.in2p3.fr [F: 0]
DL [Mb/s]: avg 91.4 - min 87.1 (95.2%), max 94.4 (103.2%)
Ping [ms]: avg 120.5 - min 118.8 (98.6%), max 134.4 (111.6%)
Web ping [ms]: avg 142.1 - min 119.1 (83.8%), max 265.0 (186.5%)
CH ZUR mirror.init7.net [F: 0]
DL [Mb/s]: avg 88.3 - min 85.2 (96.5%), max 90.3 (102.2%)
Ping [ms]: avg 126.6 - min 124.8 (98.6%), max 139.6 (110.3%)
Web ping [ms]: avg 127.8 - min 124.8 (97.6%), max 139.6 (109.2%)
IT MIL it1.mirror.vhosting-it.com [F: 1]
DL [Mb/s]: avg 79.6 - min 0.0 (0.0%), max 91.5 (114.9%)
Ping [ms]: avg 127.9 - min 121.4 (94.9%), max 174.1 (136.1%)
Web ping [ms]: avg 161.5 - min 121.5 (75.2%), max 1440.1 (891.6%)
ES MAD mirror.raiolanetworks.com [F: 0]
DL [Mb/s]: avg 100.7 - min 93.1 (92.5%), max 105.2 (104.5%)
Ping [ms]: avg 110.6 - min 107.6 (97.3%), max 117.4 (106.2%)
Web ping [ms]: avg 112.2 - min 107.8 (96.1%), max 126.7 (112.9%)
RO BUC almalinux.mirrors.orange.ro [F: 0]
DL [Mb/s]: avg 76.7 - min 74.1 (96.7%), max 79.6 (103.8%)
Ping [ms]: avg 146.3 - min 145.7 (99.6%), max 149.3 (102.1%)
Web ping [ms]: avg 167.8 - min 145.7 (86.8%), max 297.7 (177.4%)
RU MOS speedtest.hostkey.ru [F: 0]
DL [Mb/s]: avg 70.2 - min 67.1 (95.7%), max 73.7 (105.0%)
Ping [ms]: avg 158.5 - min 155.3 (98.0%), max 165.7 (104.6%)
Web ping [ms]: avg 162.5 - min 155.3 (95.6%), max 202.7 (124.7%)
--- Asia Oceania ---
RU SIB mirror.truenetwork.ru [F: 0]
DL [Mb/s]: avg 57.0 - min 51.6 (90.5%), max 61.1 (107.1%)
Ping [ms]: avg 197.0 - min 192.3 (97.6%), max 231.5 (117.5%)
Web ping [ms]: avg 197.9 - min 192.3 (97.2%), max 264.8 (133.8%)
IR SHI ir.almalinux.sindad.cloud [F: 4]
DL [Mb/s]: avg 43.2 - min 0.0 (0.0%), max 60.2 (139.3%)
Ping [ms]: avg 200.1 - min 190.9 (95.4%), max 209.8 (104.8%)
Web ping [ms]: avg 223.7 - min 195.1 (87.2%), max 1065.9 (476.5%)
IN MUM mirrors.piconets.webwerks.in [F: 0]
DL [Mb/s]: avg 42.2 - min 39.0 (92.4%), max 44.5 (105.5%)
Ping [ms]: avg 276.0 - min 262.1 (95.0%), max 342.7 (124.2%)
Web ping [ms]: avg 278.2 - min 265.1 (95.3%), max 342.7 (123.2%)
SG SGP mirror.jingk.ai [F: 0]
DL [Mb/s]: avg 54.9 - min 51.4 (93.6%), max 57.2 (104.2%)
Ping [ms]: avg 202.5 - min 195.1 (96.3%), max 236.7 (116.9%)
Web ping [ms]: avg 260.2 - min 206.1 (79.2%), max 1036.6 (398.5%)
CN HKG mirrors.xtom.hk [F: 0]
DL [Mb/s]: avg 48.4 - min 46.1 (95.1%), max 49.6 (102.4%)
Ping [ms]: avg 227.3 - min 225.5 (99.2%), max 241.6 (106.3%)
Web ping [ms]: avg 229.5 - min 225.6 (98.3%), max 266.4 (116.1%)
CN BEJ mirrors.huaweicloud.com [F: 11]
DL [Mb/s]: avg 45.4 - min 0.0 (0.0%), max 63.2 (139.2%)
Ping [ms]: avg 156.1 - min 0.0 (0.0%), max 279.6 (179.1%)
Web ping [ms]: avg 192.0 - min 0.0 (0.0%), max 1076.2 (560.6%)
JP OSA mirrors.xtom.jp [F: 0]
DL [Mb/s]: avg 78.1 - min 68.0 (87.1%), max 83.1 (106.4%)
Ping [ms]: avg 151.5 - min 150.6 (99.4%), max 164.6 (108.7%)
Web ping [ms]: avg 151.7 - min 150.6 (99.2%), max 167.1 (110.1%)
AU SYD mirror.internet.asn.au [F: 0]
DL [Mb/s]: avg 68.5 - min 67.7 (98.9%), max 69.3 (101.2%)
Ping [ms]: avg 166.4 - min 164.7 (99.0%), max 192.4 (115.6%)
Web ping [ms]: avg 166.8 - min 164.7 (98.7%), max 195.0 (116.9%)
--- Africa ---
ZA JOB mirror.datakeepers.co.za [F: 0]
DL [Mb/s]: avg 42.2 - min 41.4 (98.2%), max 43.0 (102.1%)
Ping [ms]: avg 265.1 - min 264.0 (99.6%), max 270.5 (102.1%)
Web ping [ms]: avg 266.2 - min 264.3 (99.3%), max 270.5 (101.6%)
KE NAI mirror.liquidtelecom.com [F: 0]
DL [Mb/s]: avg 35.5 - min 31.2 (88.1%), max 37.4 (105.5%)
Ping [ms]: avg 312.0 - min 302.9 (97.1%), max 460.5 (147.6%)
Web ping [ms]: avg 312.6 - min 302.9 (96.9%), max 460.5 (147.3%)
MU POL archlinux-mirror.cloud.mu [F: 0]
DL [Mb/s]: avg 37.3 - min 35.6 (95.5%), max 41.8 (112.1%)
Ping [ms]: avg 295.3 - min 291.4 (98.7%), max 313.1 (106.0%)
Web ping [ms]: avg 306.8 - min 291.5 (95.0%), max 313.1 (102.0%)
--- America ---
CA MTL speedtest.mtl2.ca.leaseweb.net [F: 0]
DL [Mb/s]: avg 266.6 - min 262.6 (98.5%), max 268.9 (100.8%)
Ping [ms]: avg 41.7 - min 41.4 (99.4%), max 42.0 (100.8%)
Web ping [ms]: avg 41.8 - min 41.4 (99.1%), max 42.8 (102.4%)
US NYC mirrors-nyj.hawkhost.com [F: 0]
DL [Mb/s]: avg 296.2 - min 291.7 (98.5%), max 304.1 (102.7%)
Ping [ms]: avg 37.4 - min 37.2 (99.4%), max 38.8 (103.7%)
Web ping [ms]: avg 38.3 - min 37.3 (97.5%), max 44.1 (115.2%)
US ASH ash.speedtest.clouvider.net [F: 0]
DL [Mb/s]: avg 308.9 - min 280.2 (90.7%), max 322.6 (104.4%)
Ping [ms]: avg 36.0 - min 34.4 (95.5%), max 39.8 (110.5%)
Web ping [ms]: avg 36.4 - min 34.5 (94.8%), max 40.8 (112.1%)
US WDC speedtest.wdc2.us.leaseweb.net [F: 0]
DL [Mb/s]: avg 232.6 - min 65.6 (28.2%), max 333.3 (143.3%)
Ping [ms]: avg 36.9 - min 33.8 (91.5%), max 43.7 (118.3%)
Web ping [ms]: avg 37.1 - min 34.0 (91.7%), max 44.1 (118.9%)
US PIB mirror.pit.teraswitch.com [F: 0]
DL [Mb/s]: avg 287.2 - min 274.4 (95.6%), max 293.6 (102.2%)
Ping [ms]: avg 38.5 - min 38.3 (99.4%), max 39.6 (102.7%)
Web ping [ms]: avg 39.0 - min 38.3 (98.3%), max 44.2 (113.4%)
US MIA speedtest.mia11.us.leaseweb.net [F: 0]
DL [Mb/s]: avg 358.1 - min 27.4 (7.6%), max 375.0 (104.7%)
Ping [ms]: avg 30.2 - min 30.0 (99.3%), max 30.8 (101.9%)
Web ping [ms]: avg 30.7 - min 30.0 (97.6%), max 33.1 (107.7%)
US CHI speedtest.chi11.us.leaseweb.net [F: 0]
DL [Mb/s]: avg 466.5 - min 456.1 (97.8%), max 476.8 (102.2%)
Ping [ms]: avg 24.3 - min 24.0 (98.6%), max 24.7 (101.4%)
Web ping [ms]: avg 24.5 - min 24.0 (98.1%), max 27.3 (111.6%)
US ATL atl.speedtest.clouvider.net [F: 0]
DL [Mb/s]: avg 523.9 - min 342.6 (65.4%), max 643.0 (122.7%)
Ping [ms]: avg 21.3 - min 17.1 (80.5%), max 30.6 (144.0%)
Web ping [ms]: avg 21.5 - min 17.1 (79.4%), max 32.8 (152.3%)
US PHO speedtest.phx1.us.leaseweb.net [F: 0]
DL [Mb/s]: avg 501.9 - min 488.9 (97.4%), max 505.6 (100.7%)
Ping [ms]: avg 22.1 - min 22.0 (99.3%), max 22.3 (100.7%)
Web ping [ms]: avg 22.2 - min 22.1 (99.4%), max 22.9 (103.0%)
US PTL mirrors.cat.pdx.edu [F: 0]
DL [Mb/s]: avg 238.5 - min 230.3 (96.5%), max 244.8 (102.6%)
Ping [ms]: avg 47.3 - min 46.5 (98.4%), max 49.4 (104.5%)
Web ping [ms]: avg 48.8 - min 46.9 (96.1%), max 66.7 (136.7%)
US LAX la.speedtest.clouvider.net [F: 0]
DL [Mb/s]: avg 345.1 - min 237.9 (68.9%), max 352.8 (102.2%)
Ping [ms]: avg 32.5 - min 31.5 (97.0%), max 46.7 (143.7%)
Web ping [ms]: avg 32.8 - min 31.5 (95.9%), max 46.8 (142.5%)
US SJO mirrors.xtom.us [F: 0]
DL [Mb/s]: avg 253.3 - min 231.9 (91.6%), max 259.6 (102.5%)
Ping [ms]: avg 44.2 - min 0.0 (0.0%), max 99.4 (224.7%)
Web ping [ms]: avg 44.9 - min 0.0 (0.0%), max 100.1 (223.1%)
US SEA speedtest.sea11.us.leaseweb.net [F: 10]
DL [Mb/s]: avg 174.3 - min 0.0 (0.0%), max 240.8 (138.1%)
Ping [ms]: avg 50.6 - min 46.7 (92.4%), max 61.8 (122.2%)
Web ping [ms]: avg 51.0 - min 46.7 (91.6%), max 61.8 (121.2%)
BR SPA mirrors.ic.unicamp.br [F: 0]
DL [Mb/s]: avg 81.9 - min 81.2 (99.2%), max 82.6 (100.9%)
Ping [ms]: avg 137.0 - min 136.1 (99.3%), max 138.3 (100.9%)
Web ping [ms]: avg 137.2 - min 136.2 (99.3%), max 139.3 (101.5%)
CL SAN elmirror.cl [F: 0]
DL [Mb/s]: avg 84.2 - min 59.4 (70.6%), max 95.2 (113.1%)
Ping [ms]: avg 137.2 - min 137.0 (99.8%), max 137.5 (100.2%)
Web ping [ms]: avg 147.7 - min 137.1 (92.8%), max 312.5 (211.5%)
As usual split into continents / regions.
Europe - Wow! I really like what I see there. All the major targets and even ES, Madrid about or not far from 100 Mb/s. and all secondary targets reached and not far off. Really nice.
Asia / Oceania - That's were I'm less happy with what I see although routing via the Pacific probably makes sense as latency is lower than via the Atlantic and Europe. But of course webwerks in India not even achieving 50 Mb/s looks weak, at least from my european perspective. Only Singapore and east of it achieve at least 50 Mb/s (or close to it) or better. China on the other hand surprises positively with well above 40 Mb/s and Japan almost looks nice with close to 80 Mb/s. Ozzyland (all 3 targets) however is below 70 Mb/s.
Africa - Hmm, I guess 30 - 40 Mb/s are OK-ish.
America - Now we're talking! Pretty much the whole East Coast above 250+ Mb/s, Miami even above 350 Mb/s suggests that South America will show decent results as well. And of course Chicago shows above 450 Mb/s and Atlanta and Phoenix even over 500 Mb/s. Very nice!
And the West coast looks quite good as well. Portland with a bit under 250 Mb/s isn't looking that great but Lax with well over 300 Mb/s is a really nice result.
And yep, Miami kept what it promised. Both Brazil and Chile over 80 Mb/s are impressive!
All in all I think I found what I was looking for, a VPS with really decent connectivity all over the USA. And this box puts very decent South America results as a cherry on top.
That said I find it a bit sad that such a nice VPS is running on a kind of weak Epyc, allthough I personally with my specific use case don't care.
All in all, well done @kuroit (but a node upgrade would be very welcome - and deserved).
Comments
Next, the Ashburn VPS.
Based on well over 50 runs.
See what I meant when looking at the Dallas VPS? An Epyc that gets surpassed by a Xeon E5v4 except wrt AES performance. On the other hand this box here also has AVX2.
I see no reason at all to complain about those results, nope, I like what I see.
Will the disk keep up?
Yes sir, it definitely does keep up! About 40 Mb/s in 4k4t and over 10k IOps is really nice! Hell, you could put a mid size DB on that box and run a serious dynamic website on that thing!
... If connectivity is adequate, that is ...
And it does!
Europe - Not surprisingly the connectivity to Europe is better than with the Dallas VPS.
Asia / Oceania - Kind of meeh again with India below 50 Mb/s, HongKong and China as well (but for China 40+ Mb/s aren't bad!), Japan under 70 Mb/s and Ozzyland even under 60 Mb/s.
Africa - OK-ish again
America - I'm truly surprised. This box achieves great results almost all over the USA, plus it shows multiple Gb/s results on the East Coast! On the west coast though the Dallas VPS clearly beats it.
And connectivity to South America is quite good as well.
Now we'll make a big jump to Singapore.
Based on well over 50 runs.
Yay! That's what I want to see with a decent VPS, well done @kuroit (hint: that would suite the Dallas VPS quite well too *g)
And the disk?
In between the Dallas VPS and the Ashburn one. But with over 7k IOps a really decent performer.
Now let's look at what probably most are interested in, connectivity ...
As usual split ...
Europe - quite meeh with just a few with about 70 Mb/s, but then one doesn't get a SGP VPS for its connectivity to Europe.
Asia / Oceania - India, Mumbai frankly not that great at well under 200 Mb/s, and slightly over 2 Gb/s within SGP (duh!) doesn't change my impression much. HongKong well above 300 Mb/s is decent though and well over 100 Mb/s to China (the one target you see, but all targets were reached and showed acceptable or even decent results) do look good. And so does Japan with (just barely) above 150 Mb/s and even all three Ozzyland targets achieve about or a bit above 110 Mb/s.
Africa - the Johannesburg result at over 90 Mb/s (!) is exceptionally good, the other targets in the 30 Mb/s range are meeh.
America - the whole East Coast and Chicago in the thirties to a bit under 50 Mb/s are meeh. Towards the West Coast it gets somewhat better but a bee stick under 70 Mb/s is the highest result. All in all meeh.
Frankly, IMO @kuroit better had that node hardware in Dallas or Ashburn because I think it's basically wasted on Singapore, because hardly anybody buys a Singapore VPS with the priority of processor and memory performance (except obviously local customers).
Finally the VPS/location that probably many will consider the best one, Chicago.
Again, based on well over 50 runs.
What a beast! Over 400 MB/s single-core, well over a GB/s multi-core, and both AES and RSA seriously fast. If processor and memory performance were what I'm after this is the VPS I'd take in the blink of an eye.
If the disk plays in the same ball park. Let's see.
Oh yes, the disk certainly won't slow down this speed daemon. Over 100 MB/s and well over 25k IOps. Holy moly, me seriously impressed.
This being Chicago I don't expect any negative surprise wrt connectivity either.
As usual ...
Europe - Almost a bit impressive with most targets showing results of about 100 Mb/s or even better. That's a good start.
Asia / Oceania - Iran basically 50 Mb/s, nice! But India just about 40 Mb/s isn't overwhelmingly good. And Singapore isn't that much better. HongKong and China showing results in the same ball park (as SGP) is impressive though. Japan with about 70 Mb/s is OK I guess, Ozzyland a bit below 60 Mb/s is OK-ish as well.
Africa - about 40 Mb/s with all targets is quite good.
America - Very decent results along the northern East Coast and, duh, in Chicago, still really decent results to Florida and Georgia, less impressive results towards the West Coast though (but still not bad).
And South America not bad either.
TL;DR Verdict: For most the Chicago VPS is likely to be the best choice with its really great processor performance, its almost unearthly great disk performance, and its overall very decent connectivity.
For me personally though the Dallas VPS is my choice; simple reason: what I'm after is well balanced (as well the US backbones allow ...) connectivity across the whole country as well as decent connectivity to Latin America and to Europe. I care little about processor and disk performance as long as it's not crappy (and it isn't). But for most the Dallas VPS probably is a significantly less attractive choice unless kuroit upgrades their nodes there.
The Singapore location didn't convince me. The Ashburn location though did impress me (but I already have a very nice Leaseweb / @HostDZire VPS there).
All in all I like what @kuroit has to offer but I wish (and suggest to them) their offers were more balanced (like e.g. Leaseweb's).
Thank you again kuroit!
Thank you @jsg for your hard work and kind words!
Your recommendations are fully taken into account, we're already working on introducing EPYCs on all locations for our AVA VPS series. SG is fully EPYC, we started with Dallas, and getting couple of nodes ready in UK too. It will take sometime to offer on all locations but yes, that the long term plan. For PRO series, we will have Ryzen 9 or Core i9 everywhere.
Thank you so much once again!