2 months ago I benchmarked VMHaus servers at their London and Los Angeles locations post here. The Los Angeles location was poor in its I/O speed Which is the disk read and write speed.
Today i returned to see if things had improved. I couldn’t deploy a $3 per month server but could create a $5 per month one.
Bench.sh
CPU model : Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz Number of cores : 2 CPU frequency : 2599.998 MHz Total size of Disk : 15.0 GB (0.8 GB Used) Total amount of Mem : 992 MB (41 MB Used) Total amount of Swap : 0 MB (0 MB Used) System uptime : 0 days, 0 hour 1 min Load average : 0.10, 0.07, 0.02 OS : Ubuntu 16.04.2 LTS Arch : x86_64 (64 Bit) Kernel : 4.4.0-87-generic ---------------------------------------------------------------------- I/O speed(1st run) : 170 MB/s I/O speed(2nd run) : 621 MB/s I/O speed(3rd run) : 630 MB/s Average I/O speed : 473.7 MB/s ---------------------------------------------------------------------- Node Name IPv4 address Download Speed CacheFly 205.234.175.175 73.2MB/s Linode, Tokyo, JP 106.187.96.148 4.47MB/s Linode, Singapore, SG 139.162.23.4 6.00MB/s Linode, London, UK 176.58.107.39 13.2MB/s Linode, Frankfurt, DE 139.162.130.8 7.49MB/s Linode, Fremont, CA 50.116.14.9 68.2MB/s Softlayer, Dallas, TX 173.192.68.18 24.7MB/s Softlayer, Seattle, WA 67.228.112.250 42.7MB/s Softlayer, Frankfurt, DE 159.122.69.4 7.74MB/s Softlayer, Singapore, SG 119.81.28.170 7.38MB/s Softlayer, HongKong, CN 119.81.130.170 9.90MB/s ---------------------------------------------------------------------- Node Name IPv6 address Download Speed Linode, Atlanta, GA 2600:3c02::4b 23.2MB/s Linode, Dallas, TX 2600:3c00::4b 26.5MB/s Linode, Newark, NJ 2600:3c03::4b 19.9MB/s Linode, Singapore, SG 2400:8901::4b 5.09MB/s Linode, Tokyo, JP 2400:8900::4b 12.3MB/s Softlayer, San Jose, CA 2607:f0d0:2601:2a::4 6.76MB/s Softlayer, Washington, WA 2607:f0d0:3001:78::2 11.8MB/s Softlayer, Paris, FR 2a03:8180:1301:8::4 1.68MB/s Softlayer, Singapore, SG 2401:c900:1101:8::2 7.81MB/s Softlayer, Tokyo, JP 2401:c900:1001:16::4 7.98MB/s
Nench.sh
nench.sh v2018.04.14 -- https://git.io/nench.sh
benchmark timestamp: 2018-08-18 01:40:47 UTC
-------------------------------------------------
Processor: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz
CPU cores: 2
Frequency: 2599.998 MHz
RAM: 992M
Swap: -
Kernel: Linux 4.4.0-87-generic x86_64
Disks:
vda 15G HDD
CPU: SHA256-hashing 500 MB
4.010 seconds
CPU: bzip2-compressing 500 MB
6.520 seconds
CPU: AES-encrypting 500 MB
1.724 seconds
ioping: seek rate
min/avg/max/mdev = 39.4 us / 61.7 us / 8.10 ms / 49.7 us
ioping: sequential read speed
generated 35.3 k requests in 5.00 s, 8.61 GiB, 7.05 k iops, 1.72 GiB/s
dd: sequential write speed
1st run: 503.54 MiB/s
2nd run: 619.89 MiB/s
3rd run: 635.15 MiB/s
average: 586.19 MiB/s
IPv4 speedtests
your IPv4: 103.105.51.xxxx
Cachefly CDN: 78.48 MiB/s
Leaseweb (NL): 3.67 MiB/s
Softlayer DAL (US): 1.83 MiB/s
Online.net (FR): 9.21 MiB/s
OVH BHS (CA): 13.29 MiB/s
IPv6 speedtests
your IPv6: 2402:28c0:2:xxxx
Leaseweb (NL): 5.11 MiB/s
Softlayer DAL (US): 1.40 MiB/s
Online.net (FR): 6.48 MiB/s
OVH BHS (CA): 14.63 MiB/sThere we have it, More than triple the speed than what was previously had. Not sure if it was an overloaded server when I first tested but the results were poor. Anyway at least this time we can see that the VMHuas Los Angeles location can get decent I/O speeds.