Hostigation are no newcomer to the LowEndBox scene having had several great offers over the last few years and coming in as a finalist in the past two Top Provider polls. Hostigation offer both standard KVM and OpenVZ VPS plans but also offer Dedicated Servers, Shared Hosting and specialised OpenVZ backup plans.
Disclaimer:
I am in no way affiliated with Hostigation. This review was performed on a trial VPS on a production node so results should be fairly accurate in comparison to real world cases.
Basics:
The VPS plan is based in Los Angeles, USA and comes with 256 MB of RAM (burstable to 512 MB), 1 TB of bandwidth (monthly) and 25 GB of disk space. OpenVZ plans are managed by a standard SolusVM install (with SSL) and include commonly used templates such as CentOS, Ubuntu and Debian (in both 32 and 64 bit variants). The SolusVM panel also offers integrated support for DNS hosting and reverse IP configuration for both IPv4 and IPv6. Hostigation’s TOS can be found here and disallows TOR while allowing both IRC and Torrents (Tim has told me however that this under the standard “don’t be a dick” rule so abusers need not apply).
Support:
The server was provisioned quickly after signing up (within 5 minutes) and the welcome emails contained all information necessary to get the server up and running with control panel usage information. Unfortunately the setup emails contained account and VPS passwords in plaintext, something I consider a security risk. To test support response times, a ticket was sent in asking for possible future locations and offers at 11:30 PM (GMT +10). It was replied to quickly at 11:40 PM (within 10 minutes) with relevant information.
Setup:
Once my VPS was setup I proceeded to install Debian 6 (32 bit) as normal (installing nothing but the SSH server). After it was installed I used Minstall to clean out any unneeded packages and to set up SSH login protection. The setup went without a hitch!
Note:
From now on I will be using the Minstall benchmark environment setup script to perform tests. This will ensure that all readers have access to commands used and are able to replicate tests easily.
Basic Information:
/proc/cpuinfo showed a processor matching the plan description (one core):
root@hostigation:~/benchmark# bash cpuinfo.sh processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 58 model name : Intel(R) Xeon(R) CPU E3-1230 V2 @ 3.30GHz stepping : 9 cpu MHz : 1600.000 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 mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 x2apic popcnt aes xsave avx f16c rdrand lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms bogomips : 6600.23 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management:
/proc/meminfo showed some standard results:
root@hostigation:~/benchmark# bash meminfo.sh MemTotal: 524288 kB MemFree: 359232 kB Cached: 150456 kB Active: 68596 kB Inactive: 84056 kB Active(anon): 2192 kB Inactive(anon): 4 kB Active(file): 66404 kB Inactive(file): 84052 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 0 kB Writeback: 0 kB AnonPages: 2196 kB Shmem: 2560 kB Slab: 12332 kB SReclaimable: 11140 kB SUnreclaim: 1192 kB
inode allocation was great:
root@hostigation:~/benchmark# bash inode.sh Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 13107200 17970 13089230 1% / tmpfs 65536 3 65533 1% /lib/init/rw tmpfs 65536 1 65535 1% /dev/shm
vmstat showed standard results:
root@hostigation:~/benchmark# bash vmstat.sh procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 0 0 359188 0 150464 0 0 1 305 0 25809 1 0 99 0
Tests:
Each test was run three times and the middle ranked test was picked.
The CacheFly download speed test showed excellent speeds:
root@hostigation:~/benchmark# bash wget.sh --2012-07-15 00:12:22-- http://cachefly.cachefly.net/100mb.test Resolving cachefly.cachefly.net... 205.234.175.175 Connecting to cachefly.cachefly.net|205.234.175.175|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[====>] 104,857,600 78.4M/s in 1.3s 2012-07-15 00:12:23 (78.4 MB/s) - `/dev/null' saved [104857600/104857600]
Ping Tests (IPv6 Works!):
root@hostigation:~/benchmark# bash ping.sh PING google.com (74.125.224.130) 56(84) bytes of data. 64 bytes from nuq04s09-in-f2.1e100.net (74.125.224.130): icmp_req=1 ttl=54 time=8.66 ms 64 bytes from nuq04s09-in-f2.1e100.net (74.125.224.130): icmp_req=2 ttl=54 time=8.64 ms 64 bytes from nuq04s09-in-f2.1e100.net (74.125.224.130): icmp_req=3 ttl=54 time=8.66 ms 64 bytes from nuq04s09-in-f2.1e100.net (74.125.224.130): icmp_req=4 ttl=54 time=8.81 ms 64 bytes from nuq04s09-in-f2.1e100.net (74.125.224.130): icmp_req=5 ttl=54 time=8.62 ms --- google.com ping statistics --- 5 packets transmitted, 5 received, 0% packet loss, time 4006ms rtt min/avg/max/mdev = 8.623/8.683/8.819/0.091 ms root@hostigation:~/benchmark# bash ping6.sh PING google.com(nuq04s09-in-x06.1e100.net) 56 data bytes 64 bytes from nuq04s09-in-x06.1e100.net: icmp_seq=1 ttl=54 time=9.35 ms 64 bytes from nuq04s09-in-x06.1e100.net: icmp_seq=2 ttl=54 time=9.37 ms 64 bytes from nuq04s09-in-x06.1e100.net: icmp_seq=3 ttl=54 time=9.01 ms 64 bytes from nuq04s09-in-x06.1e100.net: icmp_seq=4 ttl=54 time=8.74 ms 64 bytes from nuq04s09-in-x06.1e100.net: icmp_seq=5 ttl=54 time=14.8 ms --- google.com ping statistics --- 5 packets transmitted, 5 received, 0% packet loss, time 4006ms rtt min/avg/max/mdev = 8.741/10.266/14.843/2.301 ms
Disk IO was great (Tim now offers SSD caching on some of his nodes so that explains the speed increase):
root@hostigation:~/benchmark# bash dd.sh 16384+0 records in 16384+0 records out 1073741824 bytes (1.1 GB) copied, 3.11963 s, 344 MB/s
Disk latency was good (again probably a result of the SSD caching):
root@hostigation:~/benchmark# bash ioping.sh 4096 bytes from . (simfs /vz/private/4101): request=1 time=1.1 ms 4096 bytes from . (simfs /vz/private/4101): request=2 time=0.6 ms 4096 bytes from . (simfs /vz/private/4101): request=3 time=0.5 ms 4096 bytes from . (simfs /vz/private/4101): request=4 time=0.6 ms 4096 bytes from . (simfs /vz/private/4101): request=5 time=0.5 ms 4096 bytes from . (simfs /vz/private/4101): request=6 time=0.6 ms 4096 bytes from . (simfs /vz/private/4101): request=7 time=0.5 ms 4096 bytes from . (simfs /vz/private/4101): request=8 time=0.6 ms 4096 bytes from . (simfs /vz/private/4101): request=9 time=0.6 ms 4096 bytes from . (simfs /vz/private/4101): request=10 time=0.5 ms --- . (simfs /vz/private/4101) ioping statistics --- 10 requests completed in 9007.4 ms, 1646 iops, 6.4 mb/s min/avg/max/mdev = 0.5/0.6/1.1/0.2 ms
Geekbench results were great, up there in terms of performance. (Online View)
root@hostigation:~/benchmark# bash geekbench32.sh
Geekbench 2.1.13 : http://www.primatelabs.ca/geekbench/
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Linux 2.6.32-042stab055.16 i686
Model: Linux PC (Intel(R) Xeon(R) CPU E3-1230 V2 @ 3.30GHz)
Motherboard: Unknown Motherboard
Processor: Intel(R) Xeon(R) CPU E3-1230 V2 @ 3.30GHz
Processor ID: GenuineIntel Family 6 Model 58 Stepping 9
Logical Processors: 1
Physical Processors: 1
Processor Frequency: 1.60 GHz
L1 Instruction Cache: 0.00 B
L1 Data Cache: 0.00 B
L2 Cache: 256 KB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 512 MB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: Intel(R) Xeon(R) CPU E3-1230 V2 @ 3.30GHz
Processor Cores: 1
Integer
Blowfish
single-threaded scalar 2581 ||||||||||
multi-threaded scalar 5487 |||||||||||||||||||||
Text Compress
single-threaded scalar 3336 |||||||||||||
multi-threaded scalar 3632 ||||||||||||||
Text Decompress
single-threaded scalar 3566 ||||||||||||||
multi-threaded scalar 4437 |||||||||||||||||
Image Compress
single-threaded scalar 2791 |||||||||||
multi-threaded scalar 5458 |||||||||||||||||||||
Image Decompress
single-threaded scalar 2760 |||||||||||
multi-threaded scalar 5530 ||||||||||||||||||||||
Lua
single-threaded scalar 4902 |||||||||||||||||||
multi-threaded scalar 5139 ||||||||||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 3091 ||||||||||||
multi-threaded scalar 6187 ||||||||||||||||||||||||
Dot Product
single-threaded scalar 5087 ||||||||||||||||||||
multi-threaded scalar 10665 ||||||||||||||||||||||||||||||||||||||||||
single-threaded vector 7769 |||||||||||||||||||||||||||||||
multi-threaded vector 17541 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LU Decomposition
single-threaded scalar 3373 |||||||||||||
multi-threaded scalar 3347 |||||||||||||
Primality Test
single-threaded scalar 5554 ||||||||||||||||||||||
multi-threaded scalar 4261 |||||||||||||||||
Sharpen Image
single-threaded scalar 12834 |||||||||||||||||||||||||||||||||||||||||||||||||||
multi-threaded scalar 25716 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 9856 |||||||||||||||||||||||||||||||||||||||
multi-threaded scalar 11050 ||||||||||||||||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 9303 |||||||||||||||||||||||||||||||||||||
Write Sequential
single-threaded scalar 12349 |||||||||||||||||||||||||||||||||||||||||||||||||
Stdlib Allocate
single-threaded scalar 5892 |||||||||||||||||||||||
Stdlib Write
single-threaded scalar 9263 |||||||||||||||||||||||||||||||||||||
Stdlib Copy
single-threaded scalar 18631 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Stream
Stream Copy
single-threaded scalar 5384 |||||||||||||||||||||
single-threaded vector 7072 ||||||||||||||||||||||||||||
Stream Scale
single-threaded scalar 4118 ||||||||||||||||
single-threaded vector 6645 ||||||||||||||||||||||||||
Stream Add
single-threaded scalar 7324 |||||||||||||||||||||||||||||
single-threaded vector 7098 ||||||||||||||||||||||||||||
Stream Triad
single-threaded scalar 5238 ||||||||||||||||||||
single-threaded vector 5103 ||||||||||||||||||||
Integer Score: 4134 ||||||||||||||||
Floating Point Score: 9023 ||||||||||||||||||||||||||||||||||||
Memory Score: 11087 ||||||||||||||||||||||||||||||||||||||||||||
Stream Score: 5997 |||||||||||||||||||||||
Overall Geekbench Score: 7422 |||||||||||||||||||||||||||||UNIX Bench results were also good:
Benchmark Run: Sun Jul 15 2012 00:21:59 - 00:50:04
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 25015245.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3661.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 2572.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 810891.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 217585.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 2257645.8 KBps (30.0 s, 2 samples)
Pipe Throughput 1275068.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 75838.4 lps (10.0 s, 7 samples)
Process Creation 8207.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 3476.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 582.1 lpm (60.1 s, 2 samples)
System Call Overhead 962634.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 25015245.7 2143.6
Double-Precision Whetstone 55.0 3661.2 665.7
Execl Throughput 43.0 2572.6 598.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 810891.2 2047.7
File Copy 256 bufsize 500 maxblocks 1655.0 217585.4 1314.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 2257645.8 3892.5
Pipe Throughput 12440.0 1275068.2 1025.0
Pipe-based Context Switching 4000.0 75838.4 189.6
Process Creation 126.0 8207.2 651.4
Shell Scripts (1 concurrent) 42.4 3476.6 819.9
Shell Scripts (8 concurrent) 6.0 582.1 970.2
System Call Overhead 15000.0 962634.4 641.8
========
System Benchmarks Index Score 955.4Conclusion:
In conclusion I believe that Hostigation is a very solid host with affordable pricing, consistent, speedy performance and good support (both in terms of reply time and the quality of help given). The panel is a stock SolusVM support which, while standard, is functional and easy for the end user to use, allowing clients to easily get their services up and running. The only fault with Hostigation is the fact that it’s a one man company (although in all honesty I have never had any issues with that personally as Tim runs a tight ship and serves his customers well). Overall Hostigation is a quality host and I wouldn’t hesitate to recommend the company to people seeking low cost yet powerful servers in the US.
Please give Hostigation a try and report on findings! Thanks for reading, tips and suggestions are appreciated!
Review written by maxexcloo (contact), results may not be accurate as providers change over time.
Related Posts:
- SteadyVPS – Dedicated Server offer for $35 a month out of Los Angeles datacenter - April 25, 2020
- WindowsVPS.Host – VPS plans starting at $5.50! - March 13, 2020
- HostNOC – Dedicated VPN offer for $4.99 a month! Secure, Safe and Private! - March 9, 2020
nice review.
Thank for review. :)
What I don’t understand is
> Once my VPS was setup I proceeded to install Debian 6 (32 bit) as normal
This is OpenVZ, you don’t install an OS yourself, no?
My mistake, I should have said installed it from the Debian 6 template :)
Awesome review. I am with Hostigation (although on the KVM package plans) but its rock solid!!
I personally have a VPS on the yearly 128 MB KVM plan and the server has also been solid :P
Doesn’t know why but the I/O performance on my KVM node has dropped significantly recently…
Probably help a bit if you share which node you’re on, look inside your SolusVM panel and it should show you.
As Cheif suggested, which node? Also some things that will help disk performance, use ext4 if possible, enable virtio, and try the follow.
echo deadline > /sys/block/sda/queue/scheduler
Change deadline to noop and try both, see which works better for you. Find your winner and add to /etc/rc.local also, edit sda to hda or vda if needed.
To be fair, none of those results are anything to worry about. In fact last year or so they would have been considered high, recently people seem to be under the impression results have to have three digits when in reality a consistent 15 – 20 MB/s would be fine.
Turns out the node KLIKLI is on was doing a raid rebuild/verify, I’d be interested how it is now that everything is showing normal.
Sorry for the late reply. Sadly the speed is more or less about the same. Rebooted to clear I/O scheduler settings:
I’m on node e3la09.
Just tried dd once again before I do anything else:
ext4 and virtio are both enabled/in use so I have nothing to do with them. Next I tried the change the scheduler as suggested:
Well, that node holds all of the xmas specials, as long as your VPS is not a xmas special, open a ticket and I can move you to a different node.
Their pricing for OpenVZ is very awesome. I’m not lucky stay with them, however on near future it will.
Hostigation is one of the best hosts I’ve ever worked with.
Awesome service indeed.
Also, nice uptime:
indeed my hostigation box is fast and snappy!
Is a domain required to register for one of their VPS plans?
No, I also offer shared hosting where it is, so it sets your hostname, if you don’t really care, just make something up but keep it tasteful.
So you’re saying I can enter fake nameservers and be able to log into my server with only the IP address?
Sure, it is just cosmetic info when signing up, you can change all that yourself whenever via Solus.
I signed up for a 128MB OpenVZ plan to use as a PPTP VPN and, a few days in, I’m very satisfied! Thanks, Tim!
Thanks, this is great review.
I’m also a satisfied customer almost 6 months, and never had any problem with my vps.
Great server, awesome service. Highly recommended!
Now that the reviewed node is full, I thought it might be interesting to see how flashcache held the load
The first test creates the file, 2nd to get it read into the cache, then the 3rd shows the cache in action
wow
What is the difference between CLT and LAX?
Sorry. I forgot to check all the page. I found this :)
Thx!