96MB Low End VPS Review Part XXVII – UrgentVPS
Bret from UrgentVPS has emailed me almost a month ago (yes, I know I have been really lagging behind on the requests, but it is getting more and more difficult to sit down and spend time to write reviews these days) to request a review on their OnApp cloud VPS lines that they have pushed out to the public recently. The idea of cloud VPS using OnApp is great, but traditionally it has been mostly restricted to the wealthier clientele with deep pockets, so let’s see how it is.
General Information and Set Up
May be a little off the topic, but the first thing that jumps into my eyes when going to the home page of UrgentVPS is their chat with us windows, which is rather unique:
Although not publicly advertised on their website, UrgentVPS actually has a low end VPS special, and here is what you get for 4.49 Euros per month or 39.95 Dollars per year:
The IP address offered are pretty generous considering the shortage of IPv4 addresses.
The ordering page accept both HTTP and HTTPS connections, which is great if someone needs to make a purchase via, mobile devices since some mobile devices do not support HTTPS connections well.
Sign up page is pretty straight forward:
There are several choices of OS available, however interestingly enough for Debian 6, only 64 bit option is available although most of the others have both 32 bit and 64 bit options:
You will need to make sure you select the correct OS during the registration stage since otherwise the only option to reload OS is to email them to rebuild the machine, which will change your IP addresses as well and is likely to take quite a few days (at least with my request to have Debian 6 32 bit OS on).
Provision for the VPS is instant (I actually received my new VPS information email one minute before the Paypal receipt), and their new VPS information email is pretty unique:
As you can see, there is absolutely no information about the VPS revealed in the email, only a link to the client area for you to log in.
After login into the WHMCS area, the details of the VPS is under My Servers tab:
Although it looks most the same as any other WHMCS interface, it actually contains one of the most important link: the control panel for your VPS.
Click on the link, it brings to you the custom panel:
As you can see, on the overview tab, you have the information and basic controls for the VPS. It is also interesting to note that your root password will be revealed if you click on the password link in the login area, which is pretty interesting.
The CPU priority is clearly indicated on the page as well. Although many providers restrict the CPU priority to make sure those who pays big bucks gets better performances, rarely anyone is willing to make the information readily available. One point for their honesty.
On the CPU usage tab. you basically get to see a graph of the CPU usage:
On the IP addresses page, you are shown with the 3 IPv4 addresses that you are assigned to and you can set them as the base IP address for your VPS:
Disk usage shows you the size of the hard drive and the swap space and you can enable and disable auto-backup as well:
And finally, needless to say, backups tab shows the backups made and has the ability to restore the VPS from the backups and delete the backups:
There is obviously no instant rDNS and the inability to trigger manual backups could be an issue when you want to experiment something and make a backup just before that (although I suppose you can disable autobackup and re-enable it to generate a backup), furthermore, reinstall OS is not possible and you will need to submit a ticket to have the entire machine rebuilt with different IP addresses, all these leaves a lot more room for development for this otherwise pretty good-looking control panel.
Tests on the VPS
As mentioned above, the VPS I have received has 256MB of RAM, 1 GB of swap and I have initially put up Debian 6 64 bit for testing but switched to Debian 5 32 bit after my VPS was rebuilt. The VPS is in Interwerk Datacentre in Frankfurt am Main in Germany.
With a fresh OS reload, Debian 6 64 bit used about 27MB of memory:
free -m
total used free shared buffers cached
Mem: 252 66 186 0 2 36
-/+ buffers/cache: 27 225
Swap: 1023 0 1023
And a pretty standard top output:
top - 13:43:05 up 23:05, 1 user, load average: 0.00, 0.00, 0.00
Tasks: 44 total, 1 running, 43 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.3%st
Mem: 258908k total, 68052k used, 190856k free, 2432k buffers
Swap: 1048568k total, 0k used, 1048568k free, 36988k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
929 root 20 0 70572 3496 2640 S 0.0 1.4 0:00.02 sshd
933 root 20 0 19216 2000 1524 S 0.0 0.8 0:00.00 bash
585 root 20 0 54156 1580 1080 S 0.0 0.6 0:00.01 rsyslogd
938 root 20 0 18932 1272 1000 R 0.0 0.5 0:00.00 top
640 root 20 0 49168 1144 592 S 0.0 0.4 0:00.01 sshd
633 root 20 0 22392 880 672 S 0.0 0.3 0:00.08 cron
1 root 20 0 8352 808 676 S 0.0 0.3 0:00.69 init
149 root 16 -4 16736 748 384 S 0.0 0.3 0:00.02 udevd
188 root 18 -2 16732 660 300 S 0.0 0.3 0:00.00 udevd
195 root 18 -2 16732 660 300 S 0.0 0.3 0:00.00 udevd
659 root 20 0 5928 632 532 S 0.0 0.2 0:00.00 getty
611 root 20 0 3916 628 488 S 0.0 0.2 0:00.00 acpid
660 root 20 0 5928 620 520 S 0.0 0.2 0:00.00 getty
661 root 20 0 5928 620 520 S 0.0 0.2 0:00.00 getty
662 root 20 0 5928 620 520 S 0.0 0.2 0:00.00 getty
664 root 20 0 5928 620 520 S 0.0 0.2 0:00.00 getty
665 root 20 0 5928 620 520 S 0.0 0.2 0:00.00 getty
About 650MB of disk space is used, which is more than what it takes to install a 32 bit Debian 6 (normally around 400MB in size):
df -h Filesystem Size Used Avail Use% Mounted on /dev/xvda1 9.9G 648M 8.8G 7% / tmpfs 127M 0 127M 0% /lib/init/rw udev 110M 80K 110M 1% /dev tmpfs 127M 0 127M 0% /dev/shm
Interesting enough though, with the full LNMP stack installed, the 64 bit installation uses almost the same amount of memory as the 32 bit OS:
free -m
total used free shared buffers cached
Mem: 252 230 22 0 6 155
-/+ buffers/cache: 67 185
Swap: 1023 2 1021
And the corresponding top output showing the full LNMP stack running:
top - 23:21:25 up 1 day, 43 min, 1 user, load average: 0.03, 0.02, 0.00
Tasks: 54 total, 1 running, 53 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 0.0%sy, 0.0%ni, 99.9%id, 0.0%wa, 0.0%hi, 0.0%si, 0.1%st
Mem: 258908k total, 236132k used, 22776k free, 7076k buffers
Swap: 1048568k total, 2848k used, 1045720k free, 159588k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
8651 www 20 0 47140 20m 748 S 0.0 8.0 0:00.02 nginx
22158 mysql 20 0 60948 5932 2104 S 0.0 2.3 0:00.01 mysqld
8641 root 20 0 106m 5608 1308 S 0.0 2.2 0:00.55 php-cgi
8642 www 20 0 106m 5172 872 S 0.0 2.0 0:00.00 php-cgi
8643 www 20 0 106m 5172 872 S 0.0 2.0 0:00.00 php-cgi
8644 www 20 0 106m 5172 872 S 0.0 2.0 0:00.00 php-cgi
8645 www 20 0 106m 5172 872 S 0.0 2.0 0:00.00 php-cgi
8646 www 20 0 106m 5172 872 S 0.0 2.0 0:00.00 php-cgi
8680 root 20 0 70572 3500 2640 S 0.0 1.4 0:00.02 sshd
8683 root 20 0 19216 2000 1520 S 0.0 0.8 0:00.01 bash
8690 root 20 0 18932 1280 1004 R 0.0 0.5 0:00.00 top
585 root 20 0 54156 1020 784 S 0.0 0.4 0:00.02 rsyslogd
8649 root 20 0 27808 944 268 S 0.0 0.4 0:00.00 nginx
1 root 20 0 8352 568 536 S 0.0 0.2 0:00.73 init
640 root 20 0 49168 568 448 S 0.0 0.2 0:00.02 sshd
22056 root 20 0 3952 528 524 S 0.0 0.2 0:00.01 mysqld_safe
633 root 20 0 22392 512 448 S 0.0 0.2 0:00.09 cron
And for this LNMP stack to be fully installed, about 2.2GB fo hard drive space was taken out:
df -h Filesystem Size Used Avail Use% Mounted on /dev/xvda1 9.9G 2.2G 7.3G 23% / tmpfs 127M 0 127M 0% /lib/init/rw udev 110M 80K 110M 1% /dev tmpfs 127M 0 127M 0% /dev/shm
With the 32 bit Debian 5 OS template installed, it is almost the same as the memory usage of Debian 6 64 bit:
free -m
total used free shared buffers cached
Mem: 270 221 49 0 16 142
-/+ buffers/cache: 61 209
Swap: 1023 3 1020
And the corresponding top output:
top - 01:21:42 up 1 day, 2:16, 1 user, load average: 0.00, 0.00, 0.00 Tasks: 47 total, 1 running, 46 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni, 99.8%id, 0.0%wa, 0.0%hi, 0.0%si, 0.2%st Mem: 276980k total, 226700k used, 50280k free, 17284k buffers Swap: 1048568k total, 3644k used, 1044924k free, 146448k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 19476 www 20 0 14876 11m 836 S 0.0 4.1 0:00.08 nginx 19480 www 20 0 26320 8620 3004 S 0.0 3.1 0:00.18 php-cgi 19481 www 20 0 25296 7880 3400 S 0.0 2.8 0:00.04 php-cgi 19483 www 20 0 24516 7660 3928 S 0.0 2.8 0:00.00 php-cgi 19482 www 20 0 24516 7556 3916 S 0.0 2.7 0:00.02 php-cgi 19597 mysql 20 0 35004 5940 3236 S 0.0 2.1 0:00.20 mysqld 19484 www 20 0 24200 5884 2592 S 0.0 2.1 0:00.00 php-cgi 19479 root 20 0 24200 4572 1408 S 0.0 1.7 0:06.54 php-cgi 20010 root 20 0 8252 2792 2272 S 0.0 1.0 0:00.00 sshd 20013 root 20 0 4368 1636 1312 S 0.0 0.6 0:00.00 bash 19494 root 20 0 4092 1276 1068 S 0.0 0.5 0:00.04 mysqld_safe 1355 root 20 0 27272 1180 872 S 0.0 0.4 0:00.31 rsyslogd 20018 root 20 0 2332 1120 904 R 0.0 0.4 0:00.00 top 19475 root 20 0 4688 700 264 S 0.0 0.3 0:00.00 nginx 1373 root 20 0 5416 308 208 S 0.0 0.1 0:00.34 sshd 5872 root 20 0 3784 160 112 S 0.0 0.1 0:00.10 cron 2237 Debian-e 20 0 6196 132 80 S 0.0 0.0 0:00.02 exim4
The htop output for htop fans:
And almost the same hard drive space was used as well:
df -h Filesystem Size Used Avail Use% Mounted on /dev/xvda1 9.9G 2.1G 7.3G 23% / tmpfs 136M 0 136M 0% /lib/init/rw udev 10M 568K 9.5M 6% /dev tmpfs 136M 0 136M 0% /dev/shm
The Inodes limit is set to pretty low, which might caused some issue if you are going to have many small files.
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/xvda1 655360 71761 583599 11% / tmpfs 34622 4 34618 1% /lib/init/rw udev 34622 1023 33599 3% /dev tmpfs 34622 1 34621 1% /dev/shm
Vmstat shows the VPS is pretty lightly 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 2848 23056 7064 159500 0 0 4 17 172 9 1 0 99 0
And the uptime shows this is pretty much the case as well:
uptime 23:22:19 up 1 day, 44 min, 1 user, load average: 0.01, 0.02, 0.00
Cpuinfo shows the VPS was assigned one single core, although it does not seems to be throttled:
cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 26 model name : Intel(R) Xeon(R) CPU E5520 @ 2.27GHz stepping : 5 cpu MHz : 2266.746 cache size : 8192 KB fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu de tsc msr pae cx8 sep cmov pat clflush mmx fxsr sse sse2 ss ht syscall nx lm constant_tsc up rep_good nonstop_tsc pni ssse3 cx16 sse4_1 sse4_2 popcnt hypervisor lahf_lm bogomips : 4533.49 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management:
And meminfo does not show anything too interesting:
cat /proc/meminfo MemTotal: 258908 kB MemFree: 3984 kB Buffers: 7272 kB Cached: 181688 kB SwapCached: 1012 kB Active: 51328 kB Inactive: 169880 kB Active(anon): 15832 kB Inactive(anon): 16428 kB Active(file): 35496 kB Inactive(file): 153452 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 1048568 kB SwapFree: 1045516 kB Dirty: 0 kB Writeback: 0 kB AnonPages: 31380 kB Mapped: 5272 kB Shmem: 12 kB Slab: 13344 kB SReclaimable: 9932 kB SUnreclaim: 3412 kB KernelStack: 448 kB PageTables: 2500 kB NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB CommitLimit: 1178020 kB Committed_AS: 115592 kB VmallocTotal: 34359738367 kB VmallocUsed: 3576 kB VmallocChunk: 34359733892 kB HardwareCorrupted: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 2048 kB DirectMap4k: 262144 kB DirectMap2M: 0 kB
So are the time sync results:
time sync real 0m0.040s user 0m0.000s sys 0m0.008s
The disk I/O is pretty standard for low end VPS these days, which is in the 50-60 range. A surprise to me since the SAN disks that they are using are supposed to produce really impressive 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, 18.1936 s, 59.0 MB/s
Testing it again does not show a lot better results:
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, 19.3107 s, 55.6 MB/s
The download speed from Cachefly is not really impressive during the first try:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2011-09-01 23:25:29-- 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 313K/s in 3m 26s 2011-09-01 23:29:00 (498 KB/s) - dev/null
However it is a lot better when I decided to give it another shot while I was typing this article:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2011-09-07 22:57:59-- 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: â/dev/nullâ 100%[======================================>] 104,857,600 4.87M/s in 18s 2011-09-07 22:58:17 (5.67 MB/s) - â/dev/nullâ
This is speed is closer to the full port speed of 50mbit.
Upload speed do varies, although they are actually almost always at the low end:
With my Nix Communications VPS in Montreal, Canada:
wget -O /dev/null 109.230.232.171/100mb.test --2011-09-06 11:14:08-- http://109.230.232.171/100mb.test Connecting to 109.230.232.171:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 1.08M/s in 90s 2011-09-06 11:15:38 (1.11 MB/s) - `/dev/null' saved [104857600/104857600]
With my BuyVM VPS in San Jose, CA:
wget -O /dev/null 109.230.232.171/100mb.test --2011-09-05 23:11:43-- http://109.230.232.171/100mb.test Connecting to 109.230.232.171:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 4.29M/s in 35s 2011-09-05 23:12:18 (2.87 MB/s) - `/dev/null' saved [104857600/104857600]
And finally, being in Europe means they definitely have the fastest connection with my Quickweb VPS in London, UK, among all 3 test machines:
wget -O /dev/null 109.230.232.171/100mb.test --2011-09-05 23:17:36-- http://109.230.232.171/100mb.test Connecting to 109.230.232.171:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 4.22M/s in 33s 2011-09-05 23:18:10 (2.99 MB/s) - `/dev/null' saved [104857600/104857600]
The UnixBench marks are pretty low, I guess mostly due to the restricted CPU priority:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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: urgentvps: GNU/Linux
OS: GNU/Linux -- 2.6.32-5-xen-amd64 -- #1 SMP Thu May 19 01:16:47 UTC 2011
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz (4533.5 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
23:42:30 up 1 day, 1:04, 1 user, load average: 0.00, 0.00, 0.00; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Thu Sep 01 2011 23:42:30 - 00:10:46
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 18790479.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2690.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 1300.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 183889.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 48961.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 614719.9 KBps (30.0 s, 2 samples)
Pipe Throughput 311232.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 61565.1 lps (10.0 s, 7 samples)
Process Creation 2638.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2777.5 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 358.5 lpm (60.1 s, 2 samples)
System Call Overhead 386989.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 18790479.5 1610.2
Double-Precision Whetstone 55.0 2690.2 489.1
Execl Throughput 43.0 1300.8 302.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 183889.0 464.4
File Copy 256 bufsize 500 maxblocks 1655.0 48961.9 295.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 614719.9 1059.9
Pipe Throughput 12440.0 311232.7 250.2
Pipe-based Context Switching 4000.0 61565.1 153.9
Process Creation 126.0 2638.3 209.4
Shell Scripts (1 concurrent) 42.4 2777.5 655.1
Shell Scripts (8 concurrent) 6.0 358.5 597.5
System Call Overhead 15000.0 386989.5 258.0
========
System Benchmarks Index Score 417.7
Testing again shows similar 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: urgentvps: GNU/Linux
OS: GNU/Linux -- 2.6.32-5-xen-amd64 -- #1 SMP Thu May 19 01:16:47 UTC 2011
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: Intel(R) Xeon(R) CPU E5520 @ 2.27GHz (4533.5 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
00:14:32 up 1 day, 1:36, 1 user, load average: 0.16, 1.74, 1.42; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Fri Sep 02 2011 00:14:32 - 00:42:50
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 19591050.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2717.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 1325.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 192631.1 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 50479.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 617637.6 KBps (30.0 s, 2 samples)
Pipe Throughput 309519.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 60644.5 lps (10.0 s, 7 samples)
Process Creation 2591.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2733.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 356.0 lpm (60.2 s, 2 samples)
System Call Overhead 375702.0 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 19591050.7 1678.8
Double-Precision Whetstone 55.0 2717.2 494.0
Execl Throughput 43.0 1325.8 308.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 192631.1 486.4
File Copy 256 bufsize 500 maxblocks 1655.0 50479.0 305.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 617637.6 1064.9
Pipe Throughput 12440.0 309519.7 248.8
Pipe-based Context Switching 4000.0 60644.5 151.6
Process Creation 126.0 2591.4 205.7
Shell Scripts (1 concurrent) 42.4 2733.6 644.7
Shell Scripts (8 concurrent) 6.0 356.0 593.4
System Call Overhead 15000.0 375702.0 250.5
========
System Benchmarks Index Score 419.9
I could not even complete the GeekBench tests, for some reason it runs half way before it stopped and the SSH session closed itself. However, even from the subscores you should be able to see how the GeekBench score is going to look like:
System Information
Operating System Linux 2.6.26-2-686-bigmem i686
Model N/A
Motherboard N/A
Processor Intel(R) Xeon(R) CPU E5520 @ 2.27GHz @ 0.00 Hz
1 Processor
Processor ID GenuineIntel Family 6 Model 26 Stepping 5
L1 Instruction Cache 32.0 KB
L1 Data Cache 32.0 KB
L2 Cache 256 KB
L3 Cache 8.00 MB
Memory 270 MB N/A
BIOS N/A
Integer
Blowfish
single-threaded scalar 1777 |||||||
Text Compress
single-threaded scalar 1727 ||||||
Text Decompress
single-threaded scalar 1844 |||||||
Image Compress
single-threaded scalar 1689 ||||||
Image Decompress
single-threaded scalar 1338 |||||
Lua
single-threaded scalar 3004 ||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 1917 |||||||
Dot Product
single-threaded scalar 2807 |||||||||||
single-threaded vector 2799 |||||||||||
LU Decomposition
single-threaded scalar 2143 ||||||||
Primality Test
single-threaded scalar 2843 |||||||||||
Sharpen Image
single-threaded scalar 7058 ||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 7442 |||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 27
Write Sequential
single-threaded scalar 34
Stdlib Allocate
single-threaded scalar 3290 |||||||||||||
Stdlib Write
single-threaded scalar 3985 |||||||||||||||
Stdlib Copy
single-threaded scalar 3926 |||||||||||||||
Stream
Stream Copy
single-threaded scalar 11
single-threaded vector 12
And testing for the second time using screen failed as well:
Integer
Blowfish
single-threaded scalar 1742 ||||||
Text Compress
single-threaded scalar 1690 ||||||
Text Decompress
single-threaded scalar 1869 |||||||
Image Compress
single-threaded scalar 1693 ||||||
Image Decompress
single-threaded scalar 1462 |||||
Lua
single-threaded scalar 2970 |||||||||||
Floating Point
Mandelbrot
single-threaded scalar 1888 |||||||
Dot Product
single-threaded scalar 2805 |||||||||||
single-threaded vector 2809 |||||||||||
LU Decomposition
single-threaded scalar 2143 ||||||||
Primality Test
single-threaded scalar 2864 |||||||||||
Sharpen Image
single-threaded scalar 6964 |||||||||||||||||||||||||||
Blur Image
single-threaded scalar 7356 |||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 25
Write Sequential
single-threaded scalar 35
Stdlib Allocate
single-threaded scalar 3502 ||||||||||||||
Stdlib Write
single-threaded scalar 3838 |||||||||||||||
Stdlib Copy
single-threaded scalar 3984 |||||||||||||||
Stream
Stream Copy
single-threaded scalar 11
single-threaded vector 12
Terminated
Overall, the performance of the VPS is really not all that great, although downloading speed could occasionally reach close to port speed and there is no trace of the oversold RAM, however, the restrictions made on the CPU and not-so-great disk I/O on the SAN storage basically made the unit unable to complete the GeekBench tests and delivered a pretty low score for the UnixBench tests.
Customer Service and Support
The support pace for UrgentVPS actually varies quite a bit, my original ticket requesting the change in OS, which was submitted at 10:32PM was answered at 5:35AM the next day, although that is not bad for a budget VPS provider, I have to wait for 2 days until the reload was completed. However, another ticket that I put in at 11:37AM was answered at 11:38AM, barely a minute later! That is really fast response.
However, UrgentVPS does not have the ability to receive replies via email though, in fact, attempt to reply the ticket email was returned with a delivery failure as the email account that used to send out the email does not exist.
Conclusion
Although VPS on SAN storage is a really great idea and the OnApp control panel seems rather fancy, the performance of the server really does not show the advantages of the cloud servers. The fact that UnixBench are pretty low and GeekBench could not even completed definitely raised a flag in terms of performances, furthermore, the network speed varies. As such, I can only recommend this VPS if you do not need any more than very light usage on the server.
Hi there,
As mentioned in the e-mail to you, our lower plans are I/O restricted to maintain performance for everyone. We’ve had issues in the past with clients abusing the disks so we’ve had to bring this in to place. Although saying that, 60MB/s is still a very nice number for a €4.49 VPS with the rest of the features / bonuses that you’re receiving 🙂
Not sure i would agree.
disk performance is not bad yes for a cheap VPS but CPU performance seems poor and network performance is not very good at all. And support seems to be lacking as well (A full day just to reinstall the OS?)
You’re allocated 1 CPU core and given 10% of it as your CPU allocation, you can, however use more than that if it is available. For a true “cloud” server running on a SAN and for €4.49 per month, we feel that this is a great product. If you require more juice, then UV-PLAN1 and upwards are the products you’ll want to go for. UV0 isn’t meant to be a ground breaker or something to run busy forums / game servers etc on 🙂 It’s more a way of letting people experience the cloud set up at a more than affordable price, as well as giving you a great platform to run some of your own sites / VOIP applications. In regards to our network performance, you’re allocated a 50Mbit port on your VPS, each hypervisor is connected at 1GBit to the outside world so there should be no issues regarding the speeds, however you must understand this is a shared environment, clients don’t receive dedicated 50Mbit ports but in most cases you’ll be able to hit the full 50Mbit. In my opinion for the price, our UV0 is a great option and will suit many people.
Regards
Interesting market the whole could VPS thing, personally I don’t belive the hardware is mature enough to truly sustain it right now.
Its great to say “oh yeah I’m hosted in the cloud” however I could take your 4.49 and buy a Xen PV VPS with 256 mb Ram gets over 100 MB/s disk writes and comes with 8 CPU cores and scores 6 times higher in Unix bench and on top of that offers nightly offsite backups and a 1000 mbit connection.
So… in conclusion (Just my own) the cloud has no business in the budget market, its pitiful performance in many areas apart from redundancy (which if you were concerned about data you would not be looking to spend peanuts anyway) evidences this.
I think that the only people that this appeals too simply don’t understand what it is and this cloud=good and who are under the illusion the cloud is a nice shiny thing to show off about.
Anyway this is starting to sound like a bashing and its not meant to be.
Pingback: urgentVPS – €25/Year 256MB Xen VPS in Germany – Low End Box
Pingback: urgentVPS – €25/Year 256MB Xen VPS in Germany | Free vps,Free vps hosting,Free vps server - Free Vps Free Webspace and Free Web Hosting Services