Quantcast
Channel: Reviews — LowEndTalk
Viewing all articles
Browse latest Browse all 9092

[REVIEW] Aggressive Networks 128MB/NAT Trial VPS

$
0
0

The Aggressive Netowrks ( @aggressivenetworks ) provider has invited some beta testers to review their new product. The specifications of the provided VPS are bellow:

RAM: 128MB
Swap: 128MB
HDD: 15 GB (Raid10)
Bandwidth: 200GB@ 1 Gbps
IPv4 network: NAT 19 Ports + 1 SSH
IPv6 network: /112 ipv6

The image used to build the container is outdated and doesn't include the last libc patch. We all know how to update our servers, I think, but should be a great idea to build new images with the latest updates:

root@trial:~# apt-get upgrade
Reading package lists... Done
Building dependency tree... Done
The following packages will be upgraded:
  apt base-files debian-archive-keyring libapt-pkg4.12 libc-bin libc6 libssl1.0.0 locales multiarch-support tzdata
10 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
Need to get 16.7 MB of archives.
After this operation, 778 kB of additional disk space will be used.
Do you want to continue [Y/n]?

The container, however, has very small set of running process out of box, cutting out services like xinetd and saslauthd from the startup:

root@trial:~# ps aux
USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root         1  0.0  0.6   3140   840 ?        Ss   Feb01   0:00 init
root         2  0.0  0.0      0     0 ?        S    Feb01   0:00 [kthreadd/108]
root         3  0.0  0.0      0     0 ?        S    Feb01   0:00 [khelper/108]
root       112  0.0  0.2   2396   352 ?        S    Feb01   0:00 upstart-udev-bridge --daemon
root       120  0.0  0.4   2364   648 ?        Ss   Feb01   0:00 /sbin/udevd --daemon
root       167  0.0  0.3   2360   404 ?        S    Feb01   0:00 /sbin/udevd --daemon
root       168  0.0  0.3   2360   404 ?        S    Feb01   0:00 /sbin/udevd --daemon
root       336  0.0  0.1   2388   244 ?        S    Feb01   0:00 upstart-socket-bridge --daemon
root      1546  0.0  0.7  33852   980 ?        Sl   Feb01   0:00 /usr/sbin/rsyslogd -c5
root      1626  0.0  0.4   6340   584 ?        Ss   Feb01   0:00 /usr/sbin/sshd
root      1647  0.0  0.4   1976   616 tty1     Ss+  Feb01   0:00 /sbin/getty 38400 console
root      1649  0.0  0.4   1976   616 tty2     Ss+  Feb01   0:00 /sbin/getty 38400 tty2
root      2086  0.0  1.6   9280  2100 ?        Ss   06:28   0:00 sshd: root@pts/0
root      2088  0.0  0.9   3044  1276 pts/0    Ss   06:28   0:00 -bash
root      3041  0.0  0.7   2692   976 pts/0    R+   06:39   0:00 ps aux

Memory and swap is just what should be:

root@trial:~# free -m
             total       used       free     shared    buffers     cached
Mem:           128          7        120          0          0          5
-/+ buffers/cache:          1        126
Swap:          128          4        123

You have 4 cores to use and this is very interesting. I don't know if we will keep with the 4 cores after trial but this is a good point to choose this server over the competitors:

root@trial:~# nproc
4

Each core comes from a Intel(R) Xeon(R) CPU E3-1230 v3 @ 3.30GHz as you can see bellow:

root@trial:~# cat /proc/cpuinfo
processor   : 0
vendor_id   : Genu
cpu family  : 6
model       : 60
model name  : Intel(R) Xeon(R) CPU E3-1230 v3 @ 3.30GHz
stepping    : 3
microcode   : 16
cpu MHz     : 3292.615
cache size  : 8192 KB
physical id : 0
siblings    : 8
core id     : 0
cpu cores   : 4
apicid      : 0
initial apicid  : 0
fpu     : yes
fpu_exception   : yes
cpuid level : 13
wp      : yes
flags       : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf cpuid_faulting pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm ida arat epb pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase bmi1 hle avx2 smep bmi2 erms invpcid rtm
bogomips    : 6585.23
clflush size    : 64
cache_alignment : 64
address sizes   : 39 bits physical, 48 bits virtual
power management:

All the other 3 cores are the same as this one (obviouslly). The CPU has performed very well on some tests:

root@trial:~# wget dl.getipaddr.net/speedtest.sh 2>/dev/null -O- | bash
---------------CPU test--------------------
CPU: 4 x Intel(R) Xeon(R) CPU E3-1230 v3 @ 3.30GHz
Time taken to generate PI to 5000 decimal places with a single thread: 0m21.527s

root@trial:~# openssl speed sha1
Doing sha1 for 3s on 16 size blocks: 8379526 sha1's in 2.99s
Doing sha1 for 3s on 64 size blocks: 6913999 sha1's in 3.00s
Doing sha1 for 3s on 256 size blocks: 4157273 sha1's in 3.00s
Doing sha1 for 3s on 1024 size blocks: 1652443 sha1's in 3.00s
Doing sha1 for 3s on 8192 size blocks: 262372 sha1's in 3.00s
The 'numbers' are in 1000s of bytes per second processed.
type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
sha1             44840.27k   147498.65k   354753.96k   564033.88k   716450.47k

root@trial:~# openssl speed sha256
Doing sha256 for 3s on 16 size blocks: 7529214 sha256's in 2.99s
Doing sha256 for 3s on 64 size blocks: 4584302 sha256's in 3.00s
Doing sha256 for 3s on 256 size blocks: 1991055 sha256's in 3.00s
Doing sha256 for 3s on 1024 size blocks: 614873 sha256's in 3.00s
Doing sha256 for 3s on 8192 size blocks: 82313 sha256's in 3.00s
The 'numbers' are in 1000s of bytes per second processed.
type             16 bytes     64 bytes    256 bytes   1024 bytes   8192 bytes
sha256           40290.11k    97798.44k   169903.36k   209876.65k   224769.37k

Disk I/O is pretty good too:

root@trial:~# dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 0.711218 s, 1.5 GB/s

Network speed is OK, but UP/DOWN for/from some locations is really slow:

root@trial:~# wget dl.getipaddr.net/speedtest.sh 2>/dev/null -O- | bash
-------------Speed test--------------------
Testing North America locations
Speedtest from Portland, Oregon, USA [ generously donated by http://bonevm.com ] on a shared 100 Mbps port
    Download Speed: 9.90 MB/sec
    Upload speed: 5.18 MB/sec
Speedtest from Seattle, Washington, USA on a shared 100 Mbps port
    Download Speed: 9.39 MB/sec
    Upload speed: 3.67 MB/sec
Speedtest from Los Angeles, CA, USA [ generously donated by http://maximumvps.net ] on a shared 1 Gbps port
    Download Speed: 19.74 MB/sec
    Upload speed: 11.41 MB/sec
Speedtest from Los Angeles, CA, USA [ generously donated by TeraFire, LLC ] on a shared 1 Gbps port
    Download Speed: 13.70 MB/sec
    Upload speed: 8.00 MB/sec
Speedtest from Denver, CO, USA on a shared 100 Mbps port
    Download Speed: 5.48 MB/sec
    Upload speed: 15.34 MB/sec
Speedtest from Kansas City, MO, USA [ generously donated by http://megavz.com ] on a shared 1 Gbps port
    Download Speed: 5.09 MB/sec
    Upload speed: 8.98 MB/sec
Speedtest from Dallas, TX, USA [ generously donated by http://cloudshards.com ] on a shared 1 Gbps port
    Download Speed: 38.85 MB/sec
    Upload speed: 18.30 MB/sec
Speedtest from Chicago, IL, USA [ generously donated by http://vortexservers.com ] on a shared 1 Gbps port
    Download Speed: 34.68 MB/sec
    Upload speed: 25.18 MB/sec
Speedtest from Beauharnois, Quebec, Canada [ generously donated by http://mycustomhosting.net ] on a shared 1000 Mbps port in / 500 Mbps port out
    Download Speed: 10.40 MB/sec
    Upload speed: 3.14 MB/sec
Speedtest from Beauharnois, Quebec, Canada [ generously donated by http://hostnun.net/ ] on a shared 500 Mbps port
    Download Speed: 11.38 MB/sec
    Upload speed: 2.55 MB/sec
Speedtest from Buffalo, NY, USA on a shared 1 Gpbs port (location may be slow):
    Download Speed: 6.49 MB/sec
    Upload speed: 2.16 MB/sec
Speedtest from Atlanta, GA, USA [ generously donated by http://hostus.us ] on a shared 1 Gbps port
    Download Speed: 65.67 MB/sec
    Upload speed: 25.13 MB/sec
Speedtest from Lenoir, NC, USA [ generously donated by http://megavz.com ] on a shared 1 Gbps port
    Download Speed: 19.68 MB/sec
    Upload speed: 27.75 MB/sec
Speedtest from Jacksonville, FL, USA [ generously donated by http://maximumvps.net ] on a shared 1 Gbps port
    Download Speed: 61.73 MB/sec
    Upload speed: 16.82 MB/sec

Testing EU locations
Speedtest from Tallinn, Estonia on a shared 1 Gbps port
    Download Speed: 4.49 MB/sec
    Upload speed: 7.04 MB/sec
Speedtest from Paris, France on a shared 1 Gbps port
    Download Speed: 6.09 MB/sec
    Upload speed: 3.66 MB/sec
Speedtest from Milan, Italy [ generously donated by http://www.prometeus.net ] on a shared 1 Gbps port
    Download Speed: 15.31 MB/sec
    Upload speed: 6.62 MB/sec
Speedtest from Dusseldorf, Germany [ generously donated by http://megavz.com ] on a shared 1 Gbps port
    Download Speed: 8.30 MB/sec
    Upload speed: 7.37 MB/sec
Speedtest from Falkenstein, Germany [ generously donated by http://megavz.com ] on a shared 1 Gbps port
    Download Speed: 0 MB/sec
    Upload speed: 0 MB/sec
Speedtest from Bucharest, Romania [ generously donated by http://www.prometeus.net ] on a semi-dedicated 1 Gbps port
    Download Speed: 9.08 MB/sec
    Upload speed: 2.09 MB/sec

Testing Asian locations
Speedtest from Tokyo, Japan on a shared 1 Gbps port
    Download Speed: 2.65 MB/sec
    Upload speed: 3.01 MB/sec

Testing Australian locations
Speedtest from Sydney, Australia on a shared 1 Gbps port
    Download Speed: 2.29 MB/sec
    Upload speed: 1.08 MB/sec

I've stressed the container using:

root@trial:~# stress --cpu 4 --io 1 --vm 1 --vm-bytes 128M --hdd 1 --timeout 180s --verbose

This was the result:

stress-test

Without hangs, drops, locks or anything. But I think that a load limit should be imposed over the containers to stop abusers from running the node out of resources.

I've managed to compile and run a full web stack on the containeir (web server, php, sqlite) using monkeyServer.sh and it is running the Linfo script (that show details of the host running the script) and can be viewed from http://trial.alexteles.com:10602/, a set of PHP benchmark scripts that can be accessed from http://trial.alexteles.com:10602/bench.php and the phpinfo() output from http://trial.alexteles.com:10602/phpinfo.php.

I will release the ServerBear benchmark link when it get ready.


Viewing all articles
Browse latest Browse all 9092

Trending Articles