96MB Low End VPS Review Part XXVIII – VMPort
It has been a while since I review various low end VPS providers online, and one of the more contentious topic in the low end VPS community is whether Xen or OpenVZ could perform better with similar specifications. One of the Xen providers who I have reviewed before had a friendly discussion with Ashley in VMPort on the Xen Vs. OpenVZ issue and asked me to provide a review on their OpenVZ VPS to see how the performance is.
General Information and Set Up
VMPort has recently updated their website and according to Ashley, it was the first time she has tried to play around building a website and apparently it went really well, the new design is actually really good:
Compare to their original design (thanks to LowEndBox.com), this new design is definitely a lot more elegant and right to the point.
For GBP 3.10 per month, here is what you get:
Although with promo code: WHT10OFF, you get 10% off one time discount, which brings the price down to 2.79GBP for the first month.
Sign up process via HTTPS connection is pretty straight forward and there are quite a few OS choices available:
Note that there are actually templates with Nginx web server, which is my favourite website and what is used to host this blog, although many providers offers LAMP out of box as one of their OS templates, offering LNMP is definitely a great option on the low end VPS. There is also Shoutcast and OpenVPN templates available as well.
By default, the server is not managed, and management option is available for GBP 4 per month.
Addon options are pretty standard:
Provision of the VPS was instant and my VPS was online the minute I have received the Paypal receipt.
The welcome email is different from what the standard template emails that most of the providers give, and contains a lot more information.
For example, at the very beginning, it has the links to documentations on how to get started:
At the end of the email, there are also some very detailed descriptions on the management options and what they entitles to:
Although the last line of the email is pretty interesting, you will be fined for 5 bucks if you put your ticket as a top priority when your VPS is not down, although how strictly they would enforce such policy to those non-abusers would be something I would be curious to know.
After login to the WHMCS control panel (which by the way, has a really nice icon set), via HTTP connection, the details of the VPS could be found under My Services:
Note that all usage graphs and percentage bars are available, and standard functionalities to control the VPS are available as well. I have tried to reset the Hostname and Root Password, both of which worked.
SolusVM is on non-standard HTTP port and once logged in, a pretty standard user interface is shown:
Both backup options are not available, there is no instant rDNS and nowhere I can see IPv6 addresses as well.
There are quite a few OS templates available, although the most impressive part is their collection of CentOS templates that has things like CentOS + Nginx and CentOS + OpenVPN:
Furthermore, there is also documentations in their knowledgebase for Nginx set up, which is really great. Many unmanaged providers failed to see the importance of providing documentations, and therefore ended up having customers who does not know a lot about Linux unsatisfied for the services because βnothing worksβ. In that regard, VMPort has done a far more better job than many unmanaged providers.
Test on the VPS
As mentioned above, the test VPS that I have has 256MB of dedicated memory and 512MB of swap memory, I have put Debian 6 32 bit for testing purposes and the VPS is located in Wholesale Internet in Kansas, MO, in US.
When doing a fresh OS install, about 12MB of memory were used:
free -m total used free shared buffers cached Mem: 512 16 495 0 0 0 -/+ buffers/cache: 16 495 Swap: 0 0 0
Corresponding top output showing the processes running:
top - 06:55:42 up 4 min, 1 user, load average: 0.05, 0.11, 0.05 Tasks: 14 total, 2 running, 12 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 524288k total, 17008k used, 507280k free, 0k buffers Swap: 0k total, 0k used, 0k free, 0k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 1631 root 16 0 8756 3116 2468 R 0.0 0.6 0:00.23 sshd 1383 root 18 0 5132 2432 1180 S 0.0 0.5 0:00.00 apache2 1384 www-data 25 0 5132 1844 584 S 0.0 0.4 0:00.00 apache2 1633 root 15 0 2956 1612 1292 S 0.0 0.3 0:00.00 bash 1588 root 18 0 9964 1548 496 S 0.0 0.3 0:00.00 sendmail-mta 1641 root 15 0 2324 1064 872 R 0.0 0.2 0:00.00 top 1603 root 18 0 5484 988 600 S 0.0 0.2 0:00.00 sshd 1405 root 18 0 2284 844 660 S 0.0 0.2 0:00.00 cron 1558 root 25 0 2388 836 668 S 0.0 0.2 0:00.00 xinetd 1354 root 18 0 8664 784 448 S 0.0 0.1 0:00.00 saslauthd 1 root 15 0 2024 676 584 S 0.0 0.1 0:00.69 init 1369 root 15 0 1732 608 504 S 0.0 0.1 0:00.00 syslogd 1373 root 18 0 1676 548 456 S 0.0 0.1 0:00.00 anacron 1355 root 18 0 8664 500 164 S 0.0 0.1 0:00.00 saslauthd
And a little more than 400MB of hard drive spaces were used:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 20G 413M 20G 3% / tmpfs 256M 0 256M 0% /lib/init/rw tmpfs 256M 0 256M 0% /dev/shm
And htop output for those htop fans:
With the full LNMP stack installed, 61MB of memory were used:
free -m total used free shared buffers cached Mem: 512 61 450 0 0 0 -/+ buffers/cache: 61 450 Swap: 0 0 0
And the corresponding top output:
top - 21:29:30 up 10:37, 1 user, load average: 0.00, 0.00, 0.00 Tasks: 21 total, 2 running, 19 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 524288k total, 63660k used, 460628k free, 0k buffers Swap: 0k total, 0k used, 0k free, 0k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 28111 www 25 0 14496 10m 412 S 0.0 2.0 0:00.01 nginx 15910 mysql 19 0 34792 5828 3152 S 0.0 1.1 0:00.00 mysqld 28102 root 18 0 22700 4540 1380 S 0.0 0.9 0:00.00 php-cgi 28103 www 25 0 22700 4160 1000 S 0.0 0.8 0:00.00 php-cgi 28104 www 25 0 22700 4160 1000 S 0.0 0.8 0:00.00 php-cgi 28105 www 25 0 22700 4160 1000 S 0.0 0.8 0:00.00 php-cgi 28106 www 25 0 22700 4160 1000 S 0.0 0.8 0:00.00 php-cgi 28107 www 25 0 22700 4160 1000 S 0.0 0.8 0:00.00 php-cgi 29920 root 15 0 8752 3116 2472 R 0.0 0.6 0:00.26 sshd 29922 root 15 0 2956 1612 1292 S 0.0 0.3 0:00.00 bash 1588 root 18 0 9964 1548 496 S 0.0 0.3 0:00.05 sendmail-mta 15807 root 25 0 2680 1212 1000 S 0.0 0.2 0:00.00 mysqld_safe 29930 root 15 0 2324 1076 876 R 0.0 0.2 0:00.08 top 1603 root 18 0 5484 988 600 S 0.0 0.2 0:00.00 sshd 1405 root 15 0 2284 848 664 S 0.0 0.2 0:00.00 cron 1558 root 25 0 2388 836 668 S 0.0 0.2 0:00.00 xinetd 1354 root 18 0 8664 784 448 S 0.0 0.1 0:00.00 saslauthd
And the corresponding htop output:
Approximately 1.7GB of hard drive space were used:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 20G 1.7G 19G 9% / tmpfs 256M 0 256M 0% /lib/init/rw tmpfs 256M 0 256M 0% /dev/shm
Vmstat shows the VPS is relatively little used:
vmstat 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 460304 0 0 0 0 0 31 0 11 3 1 96 0
And similar results were shown with the uptime output:
uptime 21:11:41 up 1 day, 15:42, 1 user, load average: 0.00, 0.00, 0.00
Beancounters have pretty reasonable settings:
cat /proc/user_beancounters Version: 2.5 uid resource held maxheld barrier limit failcnt 186: kmemsize 2848349 13681884 2147483646 2147483646 0 lockedpages 0 0 999999 999999 0 privvmpages 15973 53467 131072 131072 0 shmpages 642 672 65536 65536 0 dummy 0 0 0 0 0 numproc 22 47 999999 999999 0 physpages 7238 36710 0 2147483647 0 vmguarpages 0 0 65536 2147483647 0 oomguarpages 7238 36710 65536 2147483647 0 numtcpsock 6 9 7999992 7999992 0 numflock 4 11 999999 999999 0 numpty 1 2 500000 500000 0 numsiginfo 0 6 999999 999999 0 tcpsndbuf 107352 6518192 214748160 396774400 0 tcprcvbuf 98304 1739304 214748160 396774400 0 othersockbuf 11640 29096 214748160 396774400 0 dgramrcvbuf 0 8472 214748160 396774400 0 numothersock 14 18 7999992 7999992 0 dcachesize 0 0 2147483646 2147483646 0 numfile 531 913 23999976 23999976 0 dummy 0 0 0 0 0 dummy 0 0 0 0 0 dummy 0 0 0 0 0 numiptent 14 14 999999 999999 0
Vzfree shows no sign of overselling as well:
vzfree Total Used Free Kernel: 2048.00M 2.72M 2045.28M Allocate: 512.00M 62.38M 449.62M (256M Guaranteed) Commit: 256.00M 30.97M 225.03M (45.3% of Allocated) Swap: 0.00M (0.0% of Committed)
Meminfo does not really give any new information:
cat /proc/meminfo MemTotal: 524288 kB MemFree: 460112 kB Buffers: 0 kB Cached: 0 kB SwapCached: 0 kB Active: 0 kB Inactive: 0 kB HighTotal: 0 kB HighFree: 0 kB LowTotal: 524288 kB LowFree: 460112 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 260 kB Writeback: 0 kB AnonPages: 0 kB Mapped: 0 kB Slab: 0 kB PageTables: 0 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 0 kB Committed_AS: 0 kB VmallocTotal: 0 kB VmallocUsed: 0 kB VmallocChunk: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 Hugepagesize: 2048 kB
Output of cpuinfo shows that one core was offered:
cat /proc/cpuinfo processor : 0 vendor_id : AuthenticAMD cpu family : 16 model : 4 model name : AMD Phenom(tm) II X4 965 Processor stepping : 3 cpu MHz : 1700.107 cache size : 512 KB physical id : 0 siblings : 4 core id : 0 cpu cores : 4 apicid : 0 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy s vm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw bogomips : 6800.42 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: ts ttp tm stc 100mhzsteps hwpstate [8]
And the time sync info:
time sync real 0m0.014s user 0m0.002s sys 0m0.000s
Disk I/O, although not the best I have seen, is pretty consistent:
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, 18.5245 s, 58.0 MB/s
And running it again later on shows almost the same I/O:
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, 18.2727 s, 58.8 MB/s
The network speed of the VPS is pretty solid, I was able to get close to 10MB/s, which is not bad at all for a 100mbit connection:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2011-09-01 21:18:04-- 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 9.66M/s in 10s 2011-09-01 21:18:15 (9.84 MB/s) - `/dev/null' saved [104857600/104857600]
Upload speed varies, with my Nix Communications’ VPS in Montreal, Canada showing the slowest speed since it is at the east coast:
wget 74.91.24.59/100mb.test -O /dev/null --2011-09-01 22:53:06-- http://74.91.24.59/100mb.test Connecting to 74.91.24.59:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 1.16M/s in 90s 2011-09-01 22:54:36 (1.12 MB/s) - `/dev/null' saved [104857600/104857600]
My BuyVM VPS in San Jose, CA, showing a really good speed as it is along the west coast:
wget 74.91.24.59/100mb.test -O /dev/null --2011-09-01 10:57:53-- http://74.91.24.59/100mb.test Connecting to 74.91.24.59:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 4.75M/s in 14s 2011-09-01 10:58:07 (7.23 MB/s) - `/dev/null' saved [104857600/104857600]
And finally, my Quickweb VPS in London, UK:
wget 74.91.24.59/100mb.test -O /dev/null --2011-09-01 10:57:53-- http://74.91.24.59/100mb.test Connecting to 74.91.24.59:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 4.75M/s in 14s 2011-09-01 10:58:07 (7.23 MB/s) - `/dev/null' saved [104857600/104857600]
Correction: My big fat finger failed to hit Ctrl+C properly, here is the correct output:
wget 74.91.24.59/100mb.test -O /dev/null --2011-09-01 10:57:00-- http://74.91.24.59/100mb.test Connecting to 74.91.24.59:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 11.2M/s in 15s 2011-09-01 10:57:16 (6.48 MB/s) - `/dev/null' saved [104857600/104857600]
Finally, for the benchmarks. As a single core VPS, the unit did OK in UnixBench, although by no means impressive:
# # # # # # # ##### ###### # # #### # # # # ## # # # # # # # ## # # # # # # # # # # # ## ##### ##### # # # # ###### # # # # # # ## # # # # # # # # # # # # ## # # # # # # # ## # # # # #### # # # # # ##### ###### # # #### # # Version 5.1.3 Based on the Byte Magazine Unix Benchmark Multi-CPU version Version 5 revisions by Ian Smith, Sunnyvale, CA, USA January 13, 2011 johantheghost at yahoo period com 1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10 1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10 1 x Execl Throughput 1 2 3 1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3 1 x File Copy 256 bufsize 500 maxblocks 1 2 3 1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3 1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10 1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10 1 x Process Creation 1 2 3 1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10 1 x Shell Scripts (1 concurrent) 1 2 3 1 x Shell Scripts (8 concurrent) 1 2 3 ======================================================================== BYTE UNIX Benchmarks (Version 5.1.3) System: vmport: GNU/Linux OS: GNU/Linux -- 2.6.32-238.12.1.el5.028stab091.1 -- #1 SMP Wed Jun 1 13:20:25 MSD 2011 Machine: i686 (unknown) Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968") CPU 0: AMD Phenom(tm) II X4 965 Processor (6800.4 bogomips) Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET 21:19:35 up 1 day, 15:49, 1 user, load average: 0.00, 0.03, 0.00; runlevel 2 ------------------------------------------------------------------------ Benchmark Run: Thu Sep 01 2011 21:19:35 - 21:49:21 1 CPU in system; running 1 parallel copy of tests Dhrystone 2 using register variables 4753746.6 lps (10.0 s, 7 samples) Double-Precision Whetstone 1678.9 MWIPS (10.5 s, 7 samples) Execl Throughput 2046.7 lps (29.7 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 257057.6 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 87675.5 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 488295.4 KBps (30.0 s, 2 samples) Pipe Throughput 543844.5 lps (10.0 s, 7 samples) Pipe-based Context Switching 124690.0 lps (10.0 s, 7 samples) Process Creation 3959.5 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 1553.3 lpm (60.1 s, 2 samples) Shell Scripts (8 concurrent) 249.4 lpm (60.1 s, 2 samples) System Call Overhead 452660.2 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 4753746.6 407.3 Double-Precision Whetstone 55.0 1678.9 305.3 Execl Throughput 43.0 2046.7 476.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 257057.6 649.1 File Copy 256 bufsize 500 maxblocks 1655.0 87675.5 529.8 File Copy 4096 bufsize 8000 maxblocks 5800.0 488295.4 841.9 Pipe Throughput 12440.0 543844.5 437.2 Pipe-based Context Switching 4000.0 124690.0 311.7 Process Creation 126.0 3959.5 314.2 Shell Scripts (1 concurrent) 42.4 1553.3 366.3 Shell Scripts (8 concurrent) 6.0 249.4 415.7 System Call Overhead 15000.0 452660.2 301.8 ======== System Benchmarks Index Score 424.0
Testing again gives pretty consistent results:
# # # # # # # ##### ###### # # #### # # # # ## # # # # # # # ## # # # # # # # # # # # ## ##### ##### # # # # ###### # # # # # # ## # # # # # # # # # # # # ## # # # # # # # ## # # # # #### # # # # # ##### ###### # # #### # # Version 5.1.3 Based on the Byte Magazine Unix Benchmark Multi-CPU version Version 5 revisions by Ian Smith, Sunnyvale, CA, USA January 13, 2011 johantheghost at yahoo period com 1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10 1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10 1 x Execl Throughput 1 2 3 1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3 1 x File Copy 256 bufsize 500 maxblocks 1 2 3 1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3 1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10 1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10 1 x Process Creation 1 2 3 1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10 1 x Shell Scripts (1 concurrent) 1 2 3 1 x Shell Scripts (8 concurrent) 1 2 3 ======================================================================== BYTE UNIX Benchmarks (Version 5.1.3) System: vmport: GNU/Linux OS: GNU/Linux -- 2.6.32-238.12.1.el5.028stab091.1 -- #1 SMP Wed Jun 1 13:20:25 MSD 2011 Machine: i686 (unknown) Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968") CPU 0: AMD Phenom(tm) II X4 965 Processor (6800.4 bogomips) Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET 22:09:10 up 1 day, 16:39, 1 user, load average: 0.00, 0.08, 0.53; runlevel 2 ------------------------------------------------------------------------ Benchmark Run: Thu Sep 01 2011 22:09:10 - 22:38:54 1 CPU in system; running 1 parallel copy of tests Dhrystone 2 using register variables 4702220.3 lps (10.0 s, 7 samples) Double-Precision Whetstone 1518.3 MWIPS (9.8 s, 7 samples) Execl Throughput 1759.0 lps (30.0 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 254350.8 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 76412.0 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 402112.5 KBps (30.0 s, 2 samples) Pipe Throughput 502623.9 lps (10.0 s, 7 samples) Pipe-based Context Switching 126734.4 lps (10.0 s, 7 samples) Process Creation 3759.5 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 1988.9 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 222.8 lpm (60.2 s, 2 samples) System Call Overhead 493027.5 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 4702220.3 402.9 Double-Precision Whetstone 55.0 1518.3 276.1 Execl Throughput 43.0 1759.0 409.1 File Copy 1024 bufsize 2000 maxblocks 3960.0 254350.8 642.3 File Copy 256 bufsize 500 maxblocks 1655.0 76412.0 461.7 File Copy 4096 bufsize 8000 maxblocks 5800.0 402112.5 693.3 Pipe Throughput 12440.0 502623.9 404.0 Pipe-based Context Switching 4000.0 126734.4 316.8 Process Creation 126.0 3759.5 298.4 Shell Scripts (1 concurrent) 42.4 1988.9 469.1 Shell Scripts (8 concurrent) 6.0 222.8 371.3 System Call Overhead 15000.0 493027.5 328.7 ======== System Benchmarks Index Score 406.7
I am not sure how many people have noticed, but GeekBench for Linux has recently updated to version 2.2, I was fortunate enough to have both version 2.1 and 2.2 downloaded on this VPS and decided to run GeekBench against both versions to see the performance:
Using version 2.2, the score is significantly lower:
System Information Operating System Linux 2.6.32-238.12.1.el5.028stab091.1 i686 Model N/A Motherboard N/A Processor AMD Phenom II X4 965 Black Edition @ 0.00 Hz 1 Processor Processor ID AuthenticAMD Family 16 Model 4 Stepping 3 L1 Instruction Cache 64.0 KB L1 Data Cache 64.0 KB L2 Cache 512 KB L3 Cache 6.00 MB Memory 7.54 GB N/A BIOS N/A Integer Blowfish single-threaded scalar 1438 ||||| Text Compress single-threaded scalar 1044 |||| Text Decompress single-threaded scalar 1157 |||| Image Compress single-threaded scalar 1129 |||| Image Decompress single-threaded scalar 1149 |||| Lua single-threaded scalar 1478 ||||| Floating Point Mandelbrot single-threaded scalar 971 ||| Dot Product single-threaded scalar 1165 |||| single-threaded vector 2219 |||||||| LU Decomposition single-threaded scalar 1088 |||| Primality Test single-threaded scalar 1156 |||| Sharpen Image single-threaded scalar 4454 ||||||||||||||||| Blur Image single-threaded scalar 4015 |||||||||||||||| Memory Read Sequential single-threaded scalar 1355 ||||| Write Sequential single-threaded scalar 2047 |||||||| Stdlib Allocate single-threaded scalar 1545 |||||| Stdlib Write single-threaded scalar 1079 |||| Stdlib Copy single-threaded scalar 1426 ||||| Stream Stream Copy single-threaded scalar 1527 |||||| single-threaded vector 1850 ||||||| Stream Scale single-threaded scalar 1246 |||| single-threaded vector 1779 ||||||| Stream Add single-threaded scalar 1565 |||||| single-threaded vector 1770 ||||||| Stream Triad single-threaded scalar 1686 |||||| single-threaded vector 1309 ||||| Benchmark Summary Integer Score 1232 |||| Floating Point Score 2152 |||||||| Memory Score 1490 ||||| Stream Score 1591 |||||| Geekbench Score 1641 ||||||
Trying again gives pretty consistent results:
System Information Operating System Linux 2.6.32-238.12.1.el5.028stab091.1 i686 Model N/A Motherboard N/A Processor AMD Phenom II X4 965 Black Edition @ 0.00 Hz 1 Processor Processor ID AuthenticAMD Family 16 Model 4 Stepping 3 L1 Instruction Cache 64.0 KB L1 Data Cache 64.0 KB L2 Cache 512 KB L3 Cache 6.00 MB Memory 7.54 GB N/A BIOS N/A Integer Blowfish single-threaded scalar 1194 |||| Text Compress single-threaded scalar 912 ||| Text Decompress single-threaded scalar 1073 |||| Image Compress single-threaded scalar 1405 ||||| Image Decompress single-threaded scalar 901 ||| Lua single-threaded scalar 1475 ||||| Floating Point Mandelbrot single-threaded scalar 811 ||| Dot Product single-threaded scalar 1132 |||| single-threaded vector 2236 |||||||| LU Decomposition single-threaded scalar 1135 |||| Primality Test single-threaded scalar 1108 |||| Sharpen Image single-threaded scalar 4817 ||||||||||||||||||| Blur Image single-threaded scalar 4474 ||||||||||||||||| Memory Read Sequential single-threaded scalar 1285 ||||| Write Sequential single-threaded scalar 1948 ||||||| Stdlib Allocate single-threaded scalar 1545 |||||| Stdlib Write single-threaded scalar 1145 |||| Stdlib Copy single-threaded scalar 1202 |||| Stream Stream Copy single-threaded scalar 1614 |||||| single-threaded vector 1728 |||||| Stream Scale single-threaded scalar 1205 |||| single-threaded vector 1780 ||||||| Stream Add single-threaded scalar 1550 |||||| single-threaded vector 1851 ||||||| Stream Triad single-threaded scalar 1598 |||||| single-threaded vector 1248 |||| Benchmark Summary Integer Score 1160 |||| Floating Point Score 2244 |||||||| Memory Score 1425 ||||| Stream Score 1571 |||||| Geekbench Score 1633 ||||||
Using GeenBench 2.1, I was able to get scores as high as 1800:
System Information Platform: Linux x86 (32-bit) Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33) Operating System: Linux 2.6.32-238.12.1.el5.028stab091.1 i686 Model: Linux PC (AMD Phenom(tm) II X4 965 Processor) Motherboard: Unknown Motherboard Processor: AMD Phenom(tm) II X4 965 Processor Processor ID: AuthenticAMD Family 16 Model 4 Stepping 3 Logical Processors: 1 Physical Processors: 1 Processor Frequency: 1.70 GHz L1 Instruction Cache: 64.0 KB L1 Data Cache: 64.0 KB L2 Cache: 512 KB L3 Cache: 6.00 MB Bus Frequency: 0.00 Hz Memory: 7.54 GB Memory Type: N/A SIMD: 1 BIOS: N/A Processor Model: AMD Phenom(tm) II X4 965 Processor Processor Cores: 1 Integer Blowfish single-threaded scalar 2447 ||||||||| multi-threaded scalar 1099 |||| Text Compress single-threaded scalar 1003 |||| multi-threaded scalar 1010 |||| Text Decompress single-threaded scalar 1102 |||| multi-threaded scalar 1083 |||| Image Compress single-threaded scalar 919 ||| multi-threaded scalar 979 ||| Image Decompress single-threaded scalar 1079 |||| multi-threaded scalar 838 ||| Lua single-threaded scalar 1657 |||||| multi-threaded scalar 1499 ||||| Floating Point Mandelbrot single-threaded scalar 1005 |||| multi-threaded scalar 1075 |||| Dot Product single-threaded scalar 1462 ||||| multi-threaded scalar 1621 |||||| single-threaded vector 1686 |||||| multi-threaded vector 1805 ||||||| LU Decomposition single-threaded scalar 1872 ||||||| multi-threaded scalar 2828 ||||||||||| Primality Test single-threaded scalar 1330 ||||| multi-threaded scalar 962 ||| Sharpen Image single-threaded scalar 3848 ||||||||||||||| multi-threaded scalar 3812 ||||||||||||||| Blur Image single-threaded scalar 3930 ||||||||||||||| multi-threaded scalar 3647 |||||||||||||| Memory Read Sequential single-threaded scalar 2068 |||||||| Write Sequential single-threaded scalar 2525 |||||||||| Stdlib Allocate single-threaded scalar 1796 ||||||| Stdlib Write single-threaded scalar 1187 |||| Stdlib Copy single-threaded scalar 1507 |||||| Stream Stream Copy single-threaded scalar 2808 ||||||||||| single-threaded vector 3477 ||||||||||||| Stream Scale single-threaded scalar 2986 ||||||||||| single-threaded vector 3239 |||||||||||| Stream Add single-threaded scalar 2846 ||||||||||| single-threaded vector 3288 ||||||||||||| Stream Triad single-threaded scalar 3292 ||||||||||||| single-threaded vector 2504 |||||||||| Integer Score: 1226 |||| Floating Point Score: 2205 |||||||| Memory Score: 1816 ||||||| Stream Score: 3055 |||||||||||| Overall Geekbench Score: 1869 |||||||
Trying again shows slightly lower score, but is still reasonable:
System Information Platform: Linux x86 (32-bit) Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33) Operating System: Linux 2.6.32-238.12.1.el5.028stab091.1 i686 Model: Linux PC (AMD Phenom(tm) II X4 965 Processor) Motherboard: Unknown Motherboard Processor: AMD Phenom(tm) II X4 965 Processor Processor ID: AuthenticAMD Family 16 Model 4 Stepping 3 Logical Processors: 1 Physical Processors: 1 Processor Frequency: 1.70 GHz L1 Instruction Cache: 64.0 KB L1 Data Cache: 64.0 KB L2 Cache: 512 KB L3 Cache: 6.00 MB Bus Frequency: 0.00 Hz Memory: 7.54 GB Memory Type: N/A SIMD: 1 BIOS: N/A Processor Model: AMD Phenom(tm) II X4 965 Processor Processor Cores: 1 Integer Blowfish single-threaded scalar 2464 ||||||||| multi-threaded scalar 1160 |||| Text Compress single-threaded scalar 1098 |||| multi-threaded scalar 1043 |||| Text Decompress single-threaded scalar 1274 ||||| multi-threaded scalar 1017 |||| Image Compress single-threaded scalar 982 ||| multi-threaded scalar 1091 |||| Image Decompress single-threaded scalar 654 || multi-threaded scalar 618 || Lua single-threaded scalar 1311 ||||| multi-threaded scalar 1404 ||||| Floating Point Mandelbrot single-threaded scalar 928 ||| multi-threaded scalar 1033 |||| Dot Product single-threaded scalar 1347 ||||| multi-threaded scalar 1346 ||||| single-threaded vector 1362 ||||| multi-threaded vector 1635 |||||| LU Decomposition single-threaded scalar 2893 ||||||||||| multi-threaded scalar 2949 ||||||||||| Primality Test single-threaded scalar 1105 |||| multi-threaded scalar 829 ||| Sharpen Image single-threaded scalar 3780 ||||||||||||||| multi-threaded scalar 3344 ||||||||||||| Blur Image single-threaded scalar 4797 ||||||||||||||||||| multi-threaded scalar 4423 ||||||||||||||||| Memory Read Sequential single-threaded scalar 1614 |||||| Write Sequential single-threaded scalar 2428 ||||||||| Stdlib Allocate single-threaded scalar 1561 |||||| Stdlib Write single-threaded scalar 901 ||| Stdlib Copy single-threaded scalar 1354 ||||| Stream Stream Copy single-threaded scalar 2795 ||||||||||| single-threaded vector 1852 ||||||| Stream Scale single-threaded scalar 2871 ||||||||||| single-threaded vector 2998 ||||||||||| Stream Add single-threaded scalar 2689 |||||||||| single-threaded vector 3085 |||||||||||| Stream Triad single-threaded scalar 2985 ||||||||||| single-threaded vector 2306 ||||||||| Integer Score: 1176 |||| Floating Point Score: 2269 ||||||||| Memory Score: 1571 |||||| Stream Score: 2697 |||||||||| Overall Geekbench Score: 1789 |||||||
Customer Service and Support
Despite that Ashley seems to be the only one running the show, support is definitely very impressive. My request to enable TUN/TAP was updated barely 3 minutes after I submitted the request on a Saturday (although I was told before that the support was only open during business hours) and was completed within 6 minutes after the initial request was submitted. The next ticket submitted at 11:37AM on a Sunday was resolved by 11:39AM as well. Although none of the ticket were high priority ticket (I do not want to be fined since my server is up and running!), it was definitely replied extremely quickly.
Furthermore, VMPort has an impressive list of documentations in their knowledgebase, which is very helpful in both ways, on one hand, VMPort managed to save a lot of time addressing those types of βnoobβ questions, but on the other hand, the users will benefit by getting the issues resolved by themselves, which would be a good learning experience for them as well.
Conclusion
Although it would be difficult for me to judge whether Xen or OpenVZ is better and quite frankly speaking, the performance of VMPort VPS are just average using the standard of low end box (although network speed seems really good for 100mbit port), the service they provide is really something that makes them stand out. Excellent documentation and really fast customer service makes VMPort an ideal candidate for people who are new to VPS and who would like to use their VPS as a starting point to learn about virtual servers.
Thanks for the in-depth review π
I would love for you to come back in a month or whenever your free to test out our new boxes, your VPS was on one of our first machines and our new line is a lot better.
Kansas – i5 2400s with hardware RAID
Germany – Xeon E3-1240 with hardware RAID
The DD tests were quite good to say that node is at full capacity with only RAID1, good HDDs though π
Only other thing i want to point out is im a he not a she haha π and we are a small team of 3 you just happend to get the pleasure of having me answer your tickets π
Many, many thanks for the review and i expect to see you back testing our new machines next time and if you give me the heads up or tell me after the review i can refund you.
Cheers,
Ashley Hawkridge
The I5-2400 is a Desktop grade processor that has NO support for ECC memory. Why would you use this as a node hosting many vps’?
I have nothing against using a i5 as a dedicated server but as a node hosting many customers data? Even in the budget vps that does not seem right. Many budget providers are using quad core Xeons and even dual quad core Xeons.
@Luma: I am not sure about the performance of i5, but I have seen some providers here using i7 processors for VPS and the performance is, in fact, better than some of the providers using Xeon processors π Just an observation.
Because they are a budget provider, you buffoon. Many budget providers do this — though, sure, some use ECC memory.
Ramhost uses (or did for a long time) “desktop grade” CPUs with non-ECC memory and they are rated as one of the top LEB hosts.
If your data is so valuable that you can’t risk a few bit errors per year, you should probably be looking for a VPS that costs 5 bucks a month, chief.
There are quad-core xeons far less powerful than the i5 2400, the xeon name does not make them anything special.
And we don’t host anywhere near as many as most providers host per node.
I don’t see hardly any difference in performance with our xeon E3-1240s.
Agree
You don’t need ECC memory, come on xD
@Yomero: Mmm…why is that so?
The wget upload tests from your BuyVM and Quickweb VPS posted above are the same π
@Kuro: Very sharp eyes you have, I have already made the correction, apologies for the error…
works very BAD
i request my many back after 3 days
and have answear “we dont refund”
you have too refund ITS LAW
i will sue you
I agree they should refund you BUT I would love to see someone sue a company over 3 Euro, This would be great!
If the above user is actually Serg thats going round bashing anything with our name on it, here are the facts.
1. He sent in a ticket regarding his VPS been down, it was not a node-wide issue and was out of our business hours been in the UK.
2. He started a dispute with us because we did not responded to the ticket until 4 hours after.
If your going to open a dispute over a 4 hour reply time then why would we have the gratitude to refund you, when it states clearly in our TOS we offer a 24 hour refund period. If you would have given us a chance to actually look into your case, the output would have been different.
And FYI there is no law stating we have to refund you, you agreed to it when you signed up.
Could you jump in a taxi and ask for a refund if you got out half way? No.
Used these guys a good year or less ago for a UK mail server, must say, I had a pretty good time + live support give me a hot discount and tickets were replied to fast.
The server performed perfectly!
@Paul: Good to hear! π
Pingback: 96MB Low End VPS Review Part 48 – VMPort KVM | | 96MB.com96MB.com