96MB Low End VPS Review Part XVI – Tailored VPS
Jay from Tailored VPS emailed me and would like me to write a review about them. Although I do all my reviews for free (in fact, for some of the more notable names, I even paid out of my own pocket to purchase the VPS), I am always happy to see business requesting reviews since that shows at least the owners of those business cares and are serious about running a VPS business. Therefore, I happily agreed upon the condition that I pay and sign up the VPS just like an ordinary customer of theirs, so…here it goes:
General Information and Set Up
TailoredVPS has just had their domain registered in February 2011, and according to their domain whois information that I have obtained via this checker, is based in Port Coquitlam, British Columbia in Canada, although their servers seem to be based in Philadelphia in US.
As per Tailored VPS WHT advertisement, here are the specifications of the VPS:
I was curious to see how “Tailored” they are when it comes to Tailored VPS and the answer shows up as soon as I started the ordering process on a secured HTTP web page:
Basically, pretty much every resources on the VPS could be configured to suit your needs exactly. For example, by default, the CPU is one core, however you can add it to 4 cores maximum, memory by default is 256MB, however it could go as high as 4096MB dedicated for an extra 52 dollars per months. The only major part that can not be upgraded here is the port speed, where you have to use the 100Mbit port.
It is also interesting to note that they have a pretty strict SLA, which will give 1 day of credit for more than an hour of unexpected downtime, which is seems to be rather assuring.
Provision is instant. I paid via Paypal at 1:48PM and the VPS information email, which contained all the password in plain text, came in the same minute (a good sign since I really don’t want to be treated any differently than other customers).
After login through their secured HTTPs interface, here is what I see the information related to my VPS, note that besides the basic control and resources usage percentage bars, the Tailored VPS Control actually give the resources graphs as well, which does not really happen that frequently among the providers.
The SolusVM login is using HTTPS on a non-standard HTTPS port and after login using the assigned username. It is a standard SolusVM set up with no instant rDNS and both backup functionalities are not enabled:
They have a pretty “standard” list of OS template as well, covering most of the major Linux distributions and is pretty up to date considering it has Debian 6, although I would say the latest major OS release in Linux world is CentOS 6, which they do not have here:
Test on the VPS
The VPS that I have received has 1 CPU core, 256 dedicated/384 burstable RAM and is located Philadelphia, US in the data centre of Telecom Colocation.
Without any application installed, the default Debian template uses about 16MB of RAM:
free -m
total used free shared buffers cached
Mem: 384 16 367 0 0 0
-/+ buffers/cache: 16 367
Swap: 0 0 0
And the corresponding top output shows a pretty much default setup:
top - 22:00:10 up 11 min, 1 user, load average: 0.00, 0.00, 0.00
Tasks: 18 total, 2 running, 16 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: 393216k total, 20020k used, 373196k free, 0k buffers
Swap: 0k total, 0k used, 0k free, 0k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1636 root 18 0 8752 3112 2468 R 0.0 0.8 0:00.12 sshd
1373 root 18 0 5132 2428 1180 S 0.0 0.6 0:00.00 apache2
1661 smmsp 22 0 8216 2396 1684 S 0.0 0.6 0:00.00 sendmail-msp
1374 www-data 25 0 5132 1836 580 S 0.0 0.5 0:00.00 apache2
1638 root 15 0 2956 1628 1304 S 0.0 0.4 0:00.00 bash
1566 root 15 0 9960 1536 496 S 0.0 0.4 0:00.00 sendmail-mta
1646 smmsp 22 0 2936 1468 1000 S 0.0 0.4 0:00.01 sendmail
1644 root 18 0 2828 1112 844 S 0.0 0.3 0:00.00 cron
1664 root 15 0 2324 1064 872 R 0.0 0.3 0:00.00 top
1645 smmsp 22 0 2612 1060 912 S 0.0 0.3 0:00.00 sh
1581 root 18 0 5484 988 600 S 0.0 0.3 0:00.00 sshd
1395 root 18 0 2284 844 660 S 0.0 0.2 0:00.00 cron
1540 root 25 0 2388 836 668 S 0.0 0.2 0:00.00 xinetd
1351 root 18 0 8664 788 448 S 0.0 0.2 0:00.00 saslauthd
1363 root 18 0 1888 776 648 S 0.0 0.2 0:00.00 anacron
1 root 18 0 2024 676 584 S 0.0 0.2 0:01.32 init
1359 root 15 0 1732 632 504 S 0.0 0.2 0:00.00 syslogd
Once the LNMP stack is installed, memory usage goes up to 65MB, which is pretty good:
free -m
total used free shared buffers cached
Mem: 384 65 318 0 0 0
-/+ buffers/cache: 65 318
Swap: 0 0 0
And again, the corresponding top output:
top - 04:00:59 up 2:12, 1 user, load average: 0.00, 0.00, 0.00 Tasks: 25 total, 2 running, 23 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: 393216k total, 67064k used, 326152k free, 0k buffers Swap: 0k total, 0k used, 0k free, 0k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 27927 www 25 0 14492 10m 412 S 0.0 2.7 0:00.01 nginx 15744 mysql 18 0 34792 5828 3152 S 0.0 1.5 0:00.01 mysqld 27915 root 15 0 22700 4540 1380 S 0.0 1.2 0:00.01 php-cgi 27916 www 24 0 22700 4160 1000 S 0.0 1.1 0:00.00 php-cgi 27917 www 25 0 22700 4160 1000 S 0.0 1.1 0:00.00 php-cgi 27918 www 25 0 22700 4160 1000 S 0.0 1.1 0:00.00 php-cgi 27922 www 25 0 22700 4160 1000 S 0.0 1.1 0:00.00 php-cgi 27923 www 25 0 22700 4160 1000 S 0.0 1.1 0:00.00 php-cgi 28087 root 16 0 8752 3116 2472 R 0.0 0.8 0:00.12 sshd 28084 smmsp 24 0 8212 2420 1708 S 0.0 0.6 0:00.00 sendmail-msp 28089 root 15 0 2956 1612 1292 S 0.0 0.4 0:00.00 bash 1566 root 15 0 9960 1540 500 S 0.0 0.4 0:00.00 sendmail-mta 28069 smmsp 21 0 2936 1472 1000 S 0.0 0.4 0:00.01 sendmail 15641 root 25 0 2672 1204 1000 S 0.0 0.3 0:00.01 mysqld_safe 28067 root 15 0 2828 1112 844 S 0.0 0.3 0:00.00 cron 28095 root 15 0 2324 1076 876 R 0.0 0.3 0:00.00 top 28068 smmsp 15 0 2612 1056 912 S 0.0 0.3 0:00.00 sh
vmfree shows the RAM is not oversold:
vzfree
Total Used Free
Kernel: 2048.00M 2.93M 2045.07M
Allocate: 384.00M 62.14M 321.86M (256M Guaranteed)
Commit: 256.00M 30.94M 225.06M (45.1% of Allocated)
Swap: 0.00M (0.0% of Committed)
df commands shows the hard drive space is not oversold:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 5242880 69565 5173315 2% / tmpfs 49152 4 49148 1% /lib/init/rw tmpfs 49152 1 49151 1% /dev/shm
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 10G 1.7G 8.4G 17% / tmpfs 192M 0 192M 0% /lib/init/rw tmpfs 192M 0 192M 0% /dev/shm
vmstat actually shows the idle percentage time is pretty low:
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 329392 0 0 0 0 0 242 0 679 19 5 76 0
However, I suspect it was due to the initial set up that I ran, the usage stabilized soon after I ran uptime:
uptime 04:02:18 up 2:13, 1 user, load average: 0.00, 0.00, 0.00
And re-running vmstat after a while showed a much better picture:
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 328156 0 0 0 0 0 12 0 91 1 0 99 0
And the corresponding uptime seems to show the box is very lightly used:
20:05:08 up 5 days, 6:16, 1 user, load average: 0.00, 0.00, 0.00
Beancounters have pretty “standard” values considering the size of the VPS:
cat /proc/user_beancounters
Version: 2.5
uid resource held maxheld barrier limit failcnt
170: kmemsize 3057997 3635606 2147483646 2147483646 0
lockedpages 0 0 999999 999999 0
privvmpages 15913 37524 98304 98304 0
shmpages 642 672 65536 65536 0
dummy 0 0 0 0 0
numproc 22 30 999999 999999 0
physpages 7176 34834 0 2147483647 0
vmguarpages 0 0 65536 2147483647 0
oomguarpages 7176 34834 65536 2147483647 0
numtcpsock 6 8 7999992 7999992 0
numflock 4 10 999999 999999 0
numpty 1 2 500000 500000 0
numsiginfo 0 3 999999 999999 0
tcpsndbuf 107352 212376 214748160 396774400 0
tcprcvbuf 98304 3731504 214748160 396774400 0
othersockbuf 11640 30400 214748160 396774400 0
dgramrcvbuf 0 8472 214748160 396774400 0
numothersock 14 19 7999992 7999992 0
dcachesize 244140 261981 2147483646 2147483646 0
numfile 522 615 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
Hard drive I/O was a little lagging:
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, 36.3871 s, 29.5 MB/s
And the repeated test did not show any better result:
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, 36.1456 s, 29.7 MB/s
After being told that my I/O priority was upgraded, there did not seem to be too much change to disk 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, 39.6171 s, 27.1 MB/s
One CPU core is offered in this particular VPS, and the CPU is an Opteron 285:
cat /proc/cpuinfo processor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 33 model name : Dual Core AMD Opteron(tm) Processor 285 stepping : 2 cpu MHz : 2589.421 cache size : 1024 KB physical id : 0 siblings : 2 core id : 0 cpu cores : 2 apicid : 0 fpu : yes fpu_exception : yes cpuid level : 1 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 lm 3dnowext 3d now pni lahf_lm cmp_legacy bogomips : 5178.84 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts fid vid ttp
And the meminfo indicated the RAM are not oversold:
cat /proc/meminfo MemTotal: 393216 kB MemFree: 329204 kB Buffers: 0 kB Cached: 0 kB SwapCached: 0 kB Active: 0 kB Inactive: 0 kB HighTotal: 0 kB HighFree: 0 kB LowTotal: 393216 kB LowFree: 329204 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 94120 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
For a 100Mbps port, the download speed from Cachefly is just OK:
wget cachefly.cachefly.net/100mb.test --2011-07-30 04:07:26-- 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: `100mb.test' 100%[======================================>] 104,857,600 5.20M/s in 19s 2011-07-30 04:07:45 (5.31 MB/s) - `100mb.test' saved [104857600/104857600]
The upload speed are comparable to the download speed:
From my BuyVM box from Fremont, CA:
wget 69.55.14.79/100mb.test --2011-07-30 05:19:36-- http://69.55.14.79/100mb.test Connecting to 69.55.14.79:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `100mb.test' 100%[======================================>] 104,857,600 3.70M/s in 29s 2011-07-30 05:20:06 (3.44 MB/s) - `100mb.test' saved [104857600/104857600]
Nix Communications VPS from Montreal, Canada seems to be a little better:
wget 69.55.14.79/100mb.test --2011-07-30 01:21:02-- http://69.55.14.79/100mb.test Connecting to 69.55.14.79:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `100mb.test' 100%[======================================>] 104,857,600 4.86M/s in 19s 2011-07-30 01:21:22 (5.22 MB/s) - `100mb.test' saved [104857600/104857600]
Finally, Quickweb VPS in London, UK, being the furthest from US, gave the slowest speed among all three that I have tested.
wget 69.55.14.79/100mb.test --2011-07-29 17:22:09-- http://69.55.14.79/100mb.test Connecting to 69.55.14.79:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `100mb.test' 100%[======================================>] 104,857,600 5.03M/s in 38s 2011-07-29 17:22:48 (2.62 MB/s) - `100mb.test' saved [104857600/104857600]
Finally, for the Benchmarks, the VPS delivered a pretty low score, especially considering that 256MB of RAM is already in the “high” end of the low end VPS:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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: tailoredvps: GNU/Linux
OS: GNU/Linux -- 2.6.32-238.9.1.el5.028stab089.1 -- #1 SMP Thu Apr 14 14:06:01 MSD 2011
Machine: i686 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Dual Core AMD Opteron(tm) Processor 285 (5178.8 bogomips)
Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
04:09:02 up 2:20, 1 user, load average: 0.02, 0.08, 0.04; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Sat Jul 30 2011 04:09:02 - 04:37:23
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 9939383.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2194.1 MWIPS (10.0 s, 7 samples)
Execl Throughput 2768.9 lps (29.4 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 207897.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 75750.6 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 453733.8 KBps (30.0 s, 2 samples)
Pipe Throughput 565675.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 159217.7 lps (10.0 s, 7 samples)
Process Creation 6938.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2668.5 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 359.7 lpm (60.1 s, 2 samples)
System Call Overhead 759592.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 9939383.2 851.7
Double-Precision Whetstone 55.0 2194.1 398.9
Execl Throughput 43.0 2768.9 643.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 207897.1 525.0
File Copy 256 bufsize 500 maxblocks 1655.0 75750.6 457.7
File Copy 4096 bufsize 8000 maxblocks 5800.0 453733.8 782.3
Pipe Throughput 12440.0 565675.0 454.7
Pipe-based Context Switching 4000.0 159217.7 398.0
Process Creation 126.0 6938.2 550.6
Shell Scripts (1 concurrent) 42.4 2668.5 629.4
Shell Scripts (8 concurrent) 6.0 359.7 599.4
System Call Overhead 15000.0 759592.8 506.4
========
System Benchmarks Index Score 551.0
And running the tests again does not seem to show a lot better 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: tailoredvps: GNU/Linux
OS: GNU/Linux -- 2.6.32-238.9.1.el5.028stab089.1 -- #1 SMP Thu Apr 14 14:06:01 MSD 2011
Machine: i686 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Dual Core AMD Opteron(tm) Processor 285 (5178.8 bogomips)
Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
04:40:27 up 2:51, 1 user, load average: 0.21, 1.71, 1.40; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Sat Jul 30 2011 04:40:27 - 05:08:41
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 9743976.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2194.4 MWIPS (10.0 s, 7 samples)
Execl Throughput 2641.0 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 224038.8 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 74032.5 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 438154.3 KBps (30.0 s, 2 samples)
Pipe Throughput 570675.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 161256.9 lps (10.0 s, 7 samples)
Process Creation 7054.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2675.2 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 369.8 lpm (60.1 s, 2 samples)
System Call Overhead 742809.1 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 9743976.8 835.0
Double-Precision Whetstone 55.0 2194.4 399.0
Execl Throughput 43.0 2641.0 614.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 224038.8 565.8
File Copy 256 bufsize 500 maxblocks 1655.0 74032.5 447.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 438154.3 755.4
Pipe Throughput 12440.0 570675.0 458.7
Pipe-based Context Switching 4000.0 161256.9 403.1
Process Creation 126.0 7054.4 559.9
Shell Scripts (1 concurrent) 42.4 2675.2 630.9
Shell Scripts (8 concurrent) 6.0 369.8 616.4
System Call Overhead 15000.0 742809.1 495.2
========
System Benchmarks Index Score 550.8
Although sometimes GeekBench score and UnixBench score do deviate greatly, this time the GeekBench score did not show any better results than UnixBench:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Linux 2.6.32-238.9.1.el5.028stab089.1 i686
Model: Linux PC (AMD Opteron 285)
Motherboard: Unknown Motherboard
Processor: AMD Opteron 285
Processor ID: AuthenticAMD Family 15 Model 33 Stepping 2
Logical Processors: 1
Physical Processors: 1
Processor Frequency: 2.59 GHz
L1 Instruction Cache: 64.0 KB
L1 Data Cache: 64.0 KB
L2 Cache: 1.00 MB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 15.4 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: AMD Opteron 285
Processor Cores: 1
Integer
Blowfish
single-threaded scalar 1809 |||||||
multi-threaded scalar 1940 |||||||
Text Compress
single-threaded scalar 1719 ||||||
multi-threaded scalar 1705 ||||||
Text Decompress
single-threaded scalar 1670 ||||||
multi-threaded scalar 1708 ||||||
Image Compress
single-threaded scalar 1448 |||||
multi-threaded scalar 1417 |||||
Image Decompress
single-threaded scalar 1124 ||||
multi-threaded scalar 1152 ||||
Lua
single-threaded scalar 2000 ||||||||
multi-threaded scalar 1959 |||||||
Floating Point
Mandelbrot
single-threaded scalar 1805 |||||||
multi-threaded scalar 1843 |||||||
Dot Product
single-threaded scalar 2634 ||||||||||
multi-threaded scalar 2780 |||||||||||
single-threaded vector 2800 |||||||||||
multi-threaded vector 3168 ||||||||||||
LU Decomposition
single-threaded scalar 1791 |||||||
multi-threaded scalar 1814 |||||||
Primality Test
single-threaded scalar 2227 ||||||||
multi-threaded scalar 1759 |||||||
Sharpen Image
single-threaded scalar 5821 |||||||||||||||||||||||
multi-threaded scalar 5839 |||||||||||||||||||||||
Blur Image
single-threaded scalar 7606 ||||||||||||||||||||||||||||||
multi-threaded scalar 7645 ||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 1523 ||||||
Write Sequential
single-threaded scalar 1693 ||||||
Stdlib Allocate
single-threaded scalar 2693 ||||||||||
Stdlib Write
single-threaded scalar 582 ||
Stdlib Copy
single-threaded scalar 1017 ||||
Stream
Stream Copy
single-threaded scalar 1133 ||||
single-threaded vector 1220 ||||
Stream Scale
single-threaded scalar 1171 ||||
single-threaded vector 1182 ||||
Stream Add
single-threaded scalar 1130 ||||
single-threaded vector 1265 |||||
Stream Triad
single-threaded scalar 1228 ||||
single-threaded vector 935 |||
Integer Score: 1637 ||||||
Floating Point Score: 3538 ||||||||||||||
Memory Score: 1501 ||||||
Stream Score: 1158 ||||
Overall Geekbench Score: 2227 ||||||||
And finally, GeekBench for the second time:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Linux 2.6.32-238.9.1.el5.028stab089.1 i686
Model: Linux PC (AMD Opteron 285)
Motherboard: Unknown Motherboard
Processor: AMD Opteron 285
Processor ID: AuthenticAMD Family 15 Model 33 Stepping 2
Logical Processors: 1
Physical Processors: 1
Processor Frequency: 2.59 GHz
L1 Instruction Cache: 64.0 KB
L1 Data Cache: 64.0 KB
L2 Cache: 1.00 MB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 15.4 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: AMD Opteron 285
Processor Cores: 1
Integer
Blowfish
single-threaded scalar 1817 |||||||
multi-threaded scalar 1958 |||||||
Text Compress
single-threaded scalar 1756 |||||||
multi-threaded scalar 1695 ||||||
Text Decompress
single-threaded scalar 1671 ||||||
multi-threaded scalar 1713 ||||||
Image Compress
single-threaded scalar 1449 |||||
multi-threaded scalar 1422 |||||
Image Decompress
single-threaded scalar 1130 ||||
multi-threaded scalar 1147 ||||
Lua
single-threaded scalar 1998 |||||||
multi-threaded scalar 2004 ||||||||
Floating Point
Mandelbrot
single-threaded scalar 1824 |||||||
multi-threaded scalar 1855 |||||||
Dot Product
single-threaded scalar 2650 ||||||||||
multi-threaded scalar 2808 |||||||||||
single-threaded vector 2717 ||||||||||
multi-threaded vector 3147 ||||||||||||
LU Decomposition
single-threaded scalar 1777 |||||||
multi-threaded scalar 1800 |||||||
Primality Test
single-threaded scalar 2252 |||||||||
multi-threaded scalar 1785 |||||||
Sharpen Image
single-threaded scalar 5790 |||||||||||||||||||||||
multi-threaded scalar 5832 |||||||||||||||||||||||
Blur Image
single-threaded scalar 7596 ||||||||||||||||||||||||||||||
multi-threaded scalar 7646 ||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 1588 ||||||
Write Sequential
single-threaded scalar 1693 ||||||
Stdlib Allocate
single-threaded scalar 2687 ||||||||||
Stdlib Write
single-threaded scalar 592 ||
Stdlib Copy
single-threaded scalar 1038 ||||
Stream
Stream Copy
single-threaded scalar 1138 ||||
single-threaded vector 1229 ||||
Stream Scale
single-threaded scalar 1196 ||||
single-threaded vector 1187 ||||
Stream Add
single-threaded scalar 1132 ||||
single-threaded vector 1273 |||||
Stream Triad
single-threaded scalar 1239 ||||
single-threaded vector 949 |||
Integer Score: 1646 ||||||
Floating Point Score: 3534 ||||||||||||||
Memory Score: 1519 ||||||
Stream Score: 1167 ||||
Overall Geekbench Score: 2233 ||||||||
In conclusion, although the CPU is not capped and RAM does not show any signs of overselling, the low disk I/O speed basically affected greatly the performance of the VPS, resulting in relatively low benchmark scores.
Customer Service and Support
TailoredVPS advertise 24x7x365 support on their website, like many others:
However, Jay seems to be the only one I have ever been in touch with regarding my tickets. Although the initial response regarding the issue I have raised (low disk I/O speed) was answered in a little more than an hour (ticket opened at 10:40PM, response received at 11:40PM) with the solution, with is pretty good especially considering it was a Saturday. The follow-up request, after seeing no improvement with the disk I/O speed although my I/O priority was adjusted, was not answered until almost a day later (response sent at 13:50 and was not answered until 11:35) saying that they will need higher level admin to work on the issue. Since then, I have not heard anything nor there was any improvement in the disk I/O nor the disk I/O has shown any improvements at the time I put in the cancellation request 4 days later.
Conclusion
Although there is no evidence suggesting the VPS is heavily oversold in memory, the fact that disk I/O is pretty low makes it unfortunately having a relatively benchmark scores. Although the fact that it has one Opteron core with 2.6GHz make it a possible consideration for some computational work. However, support could be slow at times, making it perhaps better for QA/testing purposes than for actual production.
I would like to note that we have recently upgraded all of our nodes which will result in significantly faster I/O compared to our older nodes. These new nodes utilize 3ware Raid cards.
@Tailored VPS: Glad to hear! I will probably show up once a while in your WHMCS and grab a VPS just to see the performance!