All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Server Cow -> 2016 version!
Hi Guys, I am a web developer/designer and I have 4 VPSs + 1 Dedi in different
Countries and with different providers and usually I review the providers for my
Customers or sometimes for my friends and never tried to share a review since
I used to say there is always someone who did review this provider or that one before.
But this time I wanted to share this experience with you since it is a little different
For me.
I was looking for another affordable but reliable VPS (aren't we all !?;) ) and while
Comparing Scaleway to another offer from another provider I stumbled upon
A review comparing Scaleway to other providers including one called ServerCow.
I noticed that this provider managed to score really good benchmark scores.
So I looked it up and found their website which was really a simple one and German!
Only then I remembered that I heared of MailCow before but I did not know they provide
VPS Too, so I contacted them via mail with a long list of questions regarding most of the
Details about there plans, hardware, SLA, fair share policies, etc ... .
I didn't wait long and got a response from them signed by André and the answers
Were very detailed and straight forward, I liked everything except the fact that they
Do not offer SLA which I consider a must, but to be honest the way this man was answering
Every question I sent hem and his offer of a free unconditioned trial of the plan
I was asking about (the highest one they have) were enough to encourage me to try
So I accepted his offer and it was maybe just few minutes and the VPS was ready
A KVM VPS (package XL) with the following specs:
6 × Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz vCores
6GB ECC DDR3 dedicated RAM
30GB SSD storage
150GB HDD storage via Storage Server (Samba, FTP)
DDos protection (NOT ADVERTISED ON THE SITE YET!)
1 IPv4 (I got an additional one)
5 IPv6
snapshots
ReverseDNS entries for IPv4 and IPv6 addresses
Almost every Linux distro out there
It costs 11 Euros per month or 29 Euros if you pay 3 months in front.
As you can see, good specs and really good price but what about the real performance ?
I tried everything I know on this poor machine ! every benchmark, I lost count of how
Many times I reinstalled! and the results were as follow :
======================================================================== BYTE UNIX Benchmarks (Version 5.1.2) System: ********************** : GNU/Linux OS: GNU/Linux -- 3.10.0-327.18.2.el7.x86_64 -- #1 SMP Thu May 12 11:03:55 UTC 2016 Machine: x86_64 (x86_64) Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8") CPU 0: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET CPU 1: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET CPU 2: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET CPU 3: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET CPU 4: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET CPU 5: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz (4200.0 bogomips) x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET 08:19:53 up 1 day, 1:54, 1 user, load average: 0.20, 0.13, 0.08; runlevel 3 ------------------------------------------------------------------------ Benchmark Run: Mon Jun 06 2016 08:19:54 - 08:48:12 6 CPUs in system; running 1 parallel copy of tests Dhrystone 2 using register variables 20476290.9 lps (10.0 s, 7 samples) Double-Precision Whetstone 2805.2 MWIPS (9.9 s, 7 samples) Execl Throughput 907.0 lps (29.8 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 390854.9 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 114698.7 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 997382.9 KBps (30.0 s, 2 samples) Pipe Throughput 927990.1 lps (10.0 s, 7 samples) Pipe-based Context Switching 141182.1 lps (10.0 s, 7 samples) Process Creation 2938.2 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2817.0 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 1146.4 lpm (60.0 s, 2 samples) System Call Overhead 1453582.2 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 20476290.9 1754.6 Double-Precision Whetstone 55.0 2805.2 510.0 Execl Throughput 43.0 907.0 210.9 File Copy 1024 bufsize 2000 maxblocks 3960.0 390854.9 987.0 File Copy 256 bufsize 500 maxblocks 1655.0 114698.7 693.0 File Copy 4096 bufsize 8000 maxblocks 5800.0 997382.9 1719.6 Pipe Throughput 12440.0 927990.1 746.0 Pipe-based Context Switching 4000.0 141182.1 353.0 Process Creation 126.0 2938.2 233.2 Shell Scripts (1 concurrent) 42.4 2817.0 664.4 Shell Scripts (8 concurrent) 6.0 1146.4 1910.6 System Call Overhead 15000.0 1453582.2 969.1 ======== System Benchmarks Index Score 711.3 ------------------------------------------------------------------------ Benchmark Run: Mon Jun 06 2016 08:48:12 - 09:17:03 6 CPUs in system; running 6 parallel copies of tests Dhrystone 2 using register variables 94066037.5 lps (10.0 s, 7 samples) Double-Precision Whetstone 15462.6 MWIPS (9.5 s, 7 samples) Execl Throughput 7347.7 lps (29.9 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 353959.5 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 94377.1 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 986650.5 KBps (30.0 s, 2 samples) Pipe Throughput 4830927.6 lps (10.0 s, 7 samples) Pipe-based Context Switching 591775.0 lps (10.0 s, 7 samples) Process Creation 16773.0 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 11700.3 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 1954.1 lpm (60.1 s, 2 samples) System Call Overhead 4541190.5 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 94066037.5 8060.5 Double-Precision Whetstone 55.0 15462.6 2811.4 Execl Throughput 43.0 7347.7 1708.8 File Copy 1024 bufsize 2000 maxblocks 3960.0 353959.5 893.8 File Copy 256 bufsize 500 maxblocks 1655.0 94377.1 570.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 986650.5 1701.1 Pipe Throughput 12440.0 4830927.6 3883.4 Pipe-based Context Switching 4000.0 591775.0 1479.4 Process Creation 126.0 16773.0 1331.2 Shell Scripts (1 concurrent) 42.4 11700.3 2759.5 Shell Scripts (8 concurrent) 6.0 1954.1 3256.9 System Call Overhead 15000.0 4541190.5 3027.5 ======== System Benchmarks Index Score 2091.0
____ _____/\ \ __ ___ _______ ____________
/\ / ___\ _ _ / / / / | / / / | / / ____/ __ \
/ \ \ / / | | / / // /| | /| / // // |/ / /_ / / / /
/ \ \// \ | |/ / __ / | |/ |/ // // /| / __/ / // /
/ _________\ |___// // |/|/___// |// _/
\ / / vHWINFO 1.1 May 2015 | https://vhwinfo.comhostname: ****************************
>
SO: CentOS Linux release 7.2.1511 (Core) N 64 bits
>
kernel: 3.10.0-327.18.2.el7.x86_64
>
virtual: KVM
>
cpu: Intel(R) Xeon(R) CPU E5-2620 v2 @ 2.10GHz
>
vcpu: 6 cores / 4199.99 bogomips
>
RAM: 5806 MB (6% used) / swap 511 MB (0% used)
>
HD: 41G (10% used) / inkling speed 829 MB/s
>
cachefly 10MB: 59.5 MB/s (probably Gigabit Port)
>
The network tests were as follow:
From Germany:
From France:
From Netherland :
From Egypt (where I am) - The network in Egypt is really bad and slow but I needed a refrence to compare to other VPSs I have--
I also tested the I/O using :
dd if=/dev/zero of=test bs=64k count=16k conv=fdatasync
and the average results were 520 MB/s
16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 1.63928 s, 655 MB/s16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 1.67352 s, 642 MB/s^[[A16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 1.76562 s, 608 MB/s^[[A16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 1.69086 s, 635 MB/s
[
16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 2.62972 s, 408 MB/s16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 2.66973 s, 402 MB/s16384+0 records in
16384+0 records out
1073741824 bytes (1.1 GB) copied, 1.81886 s, 590 MB/s
I repeated the tests many times on different times of the day but the results were
almost identical with exception of few times when the I/O first run was slower than
normal (120-300 MB/s) but only the first time run and as I said it happened few time.
I even tested the VPS after I paid them for 3 months contract (paranoiaI) to make sure
That the performance is the sames before and after paying money!
Also I have to say the all tests were done while the usual services are running except
Any caching service of course.
The results when put together with the price make a really good price/performance value
Other very Important factors:
1- UP times : I can't judge this point now as it will need weeks if not months of usage
but till now I had no down time at all.
2- Support: here I can say with confidence Superb! André was really helpful and very
responsive even when I asked him for help in issues that is not of his responsibilities
And once again this was after I pied them ! The support is really fast and caring, they
offer support via mail and ticket system (I used the mail) but he even offered me help through
Skype
**Conclusion :
Server Cow is not one of the biggest nor the most famous providers out there but
They offer really good VPS for the price and excellent support, They really need to think
About SLA and their site needs some enhancement specially an English interface but
For me I love my "cow" and if everything goes the same way its going now I will get
More and more ! if you're looking for a very good affordable VPS with excellent support
I suggest you should give ServerCow a try.
**
-- I will update the review with any new details or changes
Comments
One of the best and complete review I've ever read, well done!
Thanks a lot! it means much to me> @andreamada said:
A perfect and very helpful review!
Thank you, I am glad you found it helpful
On a side note, if you're going to say thanks, use the thanks button rather than making a post to accept it.
What's wrong with writing a "thank you" message? It seems sincere enough
Post count ftw.
Postcow
Hi, Now ServerCow is on ServerBear .com
serverbear.com/benchmark/2016/06/16/F2yY1o7ejZ3HbZMU
According to ServerBear scores the server got even slightly higher scores
Than my tests :
**>
Agagin I ran all the tests from ServerBear without stopping any normal service on the VPS