Host information:
sh-jp ipv6 (ct)
CPU Cores: 1
Amount Of RAM: 1G
Disk Space: 10G
IPV4: 0
IPV6: 1
Bandwidth: 500G (in+out)
Network Rate: 1000Mbps (Shared)
Price: ¥100/month, National Day promo ¥60/month; this unit was bought second-hand from someone else; PUSH fee ¥10. The ingress is an independent Shanghai Telecom IPv6, the egress is NAT IPv4, and it is VM Silo (Stacks)'s own data center.
[!INFO]
BestVM’s Shanghai-Japan IEPL outbound data center is the same as this model, both STACKS; the ingress is Shanghai Telecom IPv6; traffic, price, and hardware are also identical, so these two products are likely the same. If you want to buy BestVM’s Shanghai-Japan IEPL, you should be able to reference this article as well.
The machine itself should be in Japan. The latency data in the image includes intra-network latency; for example, Shanghai Mobile measured latency of 32 ms, and this 32 ms includes the latency from Shanghai Mobile to the Shanghai Telecom entry point plus from the Shanghai Telecom entry point to Japan’s exit. Overall the ping is green, not bad. The intra-network latency is estimated to be around 26 ms. It feels like a viable replacement for Shinagawa, after all the latency is lower, the access is looser, and the price is cheaper. However, there may be cross-network QoS considerations.
I bought this machine mainly because the education network provides IPv6 for free, so I need IPv6. Other Shanghai-Japan options mostly only have IPv4; I also need to use Tencent Cloud Shanghai Ruichi Transit to relay, which costs an extra ¥40 per month and adds a few milliseconds of latency.
The exit is in our own data center; the connections are as shown.
Latency to the US direction is shown in the figure. Buyers of the Shanghai-Japan option should either route to Japan or to the West Coast of the Americas; probably not useful for other destinations.
Latency to DMIT TYO T1 is 0.65ms, iperf3 tests are as follows:
[ ID] Interval Transfer Bitrate
[ 5] 0.00-1.00 sec 104 MBytes 868 Mbits/sec
[ 5] 1.00-2.00 sec 104 MBytes 871 Mbits/sec
[ 5] 2.00-3.00 sec 104 MBytes 876 Mbits/sec
[ 5] 3.00-4.00 sec 104 MBytes 870 Mbits/sec
[ 5] 4.00-5.00 sec 103 MBytes 865 Mbits/sec
[ 5] 5.00-6.00 sec 103 MBytes 867 Mbits/sec
[ 5] 6.00-7.00 sec 104 MBytes 873 Mbits/sec
[ 5] 7.00-8.00 sec 102 MBytes 858 Mbits/sec
[ 5] 8.00-9.00 sec 102 MBytes 856 Mbits/sec
[ 5] 9.00-10.00 sec 101 MBytes 844 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.04 sec 1.01 GBytes 864 Mbits/sec 21 sender
[ 5] 0.00-10.00 sec 1.01 GBytes 865 Mbits/sec receiver
Latency to DMIT TYO T1 is 0.57ms, iperf3 tests are as follows:
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 127 MBytes 1.07 Gbits/sec 8584 421 KBytes
[ 5] 1.00-2.00 sec 125 MBytes 1.05 Gbits/sec 7265 503 KBytes
[ 5] 2.00-3.00 sec 125 MBytes 1.05 Gbits/sec 8647 413 KBytes
[ 5] 3.00-4.00 sec 126 MBytes 1.06 Gbits/sec 7130 410 KBytes
[ 5] 4.00-5.00 sec 124 MBytes 1.04 Gbits/sec 8076 399 KBytes
[ 5] 5.00-6.00 sec 125 MBytes 1.05 Gbits/sec 7456 411 KBytes
[ 5] 6.00-7.00 sec 126 MBytes 1.05 Gbits/sec 8123 427 KBytes
[ 5] 7.00-8.00 sec 126 MBytes 1.05 Gbits/sec 8304 396 KBytes
[ 5] 8.00-9.00 sec 124 MBytes 1.04 Gbits/sec 7870 396 KBytes
[ 5] 9.00-10.00 sec 126 MBytes 1.05 Gbits/sec 6941 352 KBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.04 sec 1.22 GBytes 1.05 Gbits/sec 78396 sender
[ 5] 0.00-10.00 sec 1.22 GBytes 1.05 Gbits/sec receiver
Latency to DMIT LAX T1 is 99ms, iperf3 tests are as follows:
[ ID] Interval Transfer Bitrate
[ 5] 0.00-1.00 sec 7.88 MBytes 66.0 Mbits/sec
[ 5] 1.00-2.00 sec 37.9 MBytes 318 Mbits/sec
[ 5] 2.00-3.00 sec 38.5 MBytes 323 Mbits/sec
[ 3] 3.00-4.00 sec 38.4 MBytes 322 Mbits/sec
[ 5] 4.00-5.00 sec 38.1 MBytes 320 Mbits/sec
[ 5] 5.00-6.00 sec 38.5 MBytes 323 Mbits/sec
[ 5] 6.00-7.00 sec 38.1 MBytes 320 Mbits/sec
[ 5] 7.00-8.00 sec 38.2 MBytes 321 Mbits/sec
[ 5] 8.00-9.00 sec 38.0 MBytes 319 Mbits/sec
[ 5] 9.00-10.00 sec 38.6 MBytes 324 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.10 sec 421 MBytes 350 Mbits/sec 0 sender
[ 5] 0.00-10.00 sec 352 MBytes 295 Mbits/sec receiver
From Tencent Cloud Shanghai Ruichi to this machine, iperf3 test as follows. Tencent Cloud rate-limits to 200 Mbps, and it is already maxed out.
[ ID] Interval Transfer Bitrate Retr Cwnd
[ 5] 0.00-1.00 sec 47.6 MBytes 399 Mbits/sec 5464 3.58 MBytes
[ 5] 1.00-2.00 sec 22.5 MBytes 189 Mbits/sec 8113 1.43 MBytes
[ 5] 2.00-3.00 sec 27.5 MBytes 231 Mbits/sec 4699 1.88 MBytes
[ 5] 3.00-4.00 sec 23.8 MBytes 199 Mbits/sec 8183 1.82 MBytes
[ 4] 4.00-5.00 sec 23.8 MBytes 199 Mbits/sec 0 1.70 MBytes
[ 5] 5.00-6.00 sec 25.0 MBytes 210 Mbits/sec 1164 1.28 MBytes
[ 5] 6.00-7.00 sec 25.0 MBytes 210 Mbits/sec 7449 1.77 MBytes
[ 5] 7.00-8.00 sec 26.2 MBytes 220 Mbits/sec 5062 1.80 MBytes
[ 5] 8.00-9.00 sec 25.0 MBytes 210 Mbits/sec 0 1.72 MBytes
[ 5] 9.00-10.00 sec 25.0 MBytes 210 Mbits/sec 2356 2.51 MBytes
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate Retr
[ 5] 0.00-10.00 sec 271 MBytes 228 Mbits/sec 42490 sender
[ 5] 0.00-10.03 sec 269 MBytes 225 Mbits/sec receiver
From my local network (Liaoning, Dalian Education Network) to this machine, iperf3 tests are as follows. It seems this is cross-network QoS’d? But in normal use I didn’t encounter any QoS; speed tests are below.
This test is for local upload; the test was wrong; please ignore; see corrected speed test below.
[ ID] Interval Transfer Bitrate
[ 5] 0.00-1.00 sec 31.4 MBytes 262 Mbits/sec
[ 5] 1.00-2.00 sec 33.2 MBytes 280 Mbits/sec
[ 5] 2.00-3.01 sec 19.0 MBytes 158 Mbits/sec
[ 5] 3.01-4.01 sec 13.4 MBytes 113 Mbits/sec
[ 5] 4.01-5.00 sec 9.88 MBytes 83.2 Mbits/sec
[ 5] 5.00-6.01 sec 7.25 MBytes 60.2 Mbits/sec
[ 5] 6.01-7.01 sec 6.38 MBytes 53.7 Mbits/sec
[ 5] 7.01-8.01 sec 5.12 MBytes 43.0 Mbits/sec
[ 5] 8.01-9.00 sec 2.88 MBytes 24.3 Mbits/sec
[ 5] 9.00-10.02 sec 2.88 MBytes 23.8 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate
[ 5] 0.00-10.02 sec 131 MBytes 110 Mbits/sec sender
[ 5] 0.00-10.08 sec 124 MBytes 103 Mbits/sec receiver
From my local network (Liaoning, Dalian Education Network) to this machine, iperf3 tests are as follows:
[ ID] Interval Transfer Bitrate
[ 5] 0.00-1.00 sec 8.62 MBytes 72.3 Mbits/sec
[ 5] 1.00-2.01 sec 33.1 MBytes 274 Mbits/sec
[ 5] 2.01-3.01 sec 31.8 MBytes 268 Mbits/sec
[ 5] 3.01-4.00 sec 30.1 MBytes 254 Mbits/sec
[ 5] 4.00-5.01 sec 27.8 MBytes 230 Mbits/sec
[ 5] 5.01-6.01 sec 30.4 MBytes 256 Mbits/sec
[ 6] 6.01-7.00 sec 30.1 MBytes 254 Mbits/sec
[ 7] 7.00-8.01 sec 31.6 MBytes 262 Mbits/sec
[ 8] 8.01-9.01 sec 31.6 MBytes 265 Mbits/sec
[ 9] 9.01-10.01 sec 30.2 MBytes 255 Mbits/sec
- - - - - - - - - - - - - - - - - - - - - - - - -
[ ID] Interval Transfer Bitrate
[ 5] 0.00-10.10 sec 288 MBytes 239 Mbits/sec 71 sender
[ 5] 0.00-10.01 sec 285 MBytes 239 Mbits/sec receiver
This machine, if connected directly to my West US home broadband, goes via NTT with higher latency; routing via DMIT / Bage uses GSL with lower latency. So I used Bage’s LA as a transit once.
The final result is below; it can reliably hit West US with a landing around 180 ms. If you’re in Shanghai, it should be under about 140 ms.
