96MB Low End VPS Review Part XXIV – BrightBox Cloud
Brightbox has definitely won the title of the longest free beta service providers on my list. Although it is common to see providers offering a month or two worth of beta services, having one that offered beta services for more than 6 months is something unheard of. Quite frankly speaking, I have completely forgot about the cloud VPS with them until I have received an email informing me that they will discontinue the beta services soon and put things in production mode to make some cash. How is their services? Let’s take a look.
Basic information and Set Up
I have to admit that I have never heard of Brightbox before I signed up for the beta program, and their price structure has really made me wondering if I have encountered the most expensive VPS providers. Although the specifications seems by no means beyond “low end”, the price structure is definitely is not “low end”:
As you can see, for 384MB of RAM, you are looking at 65.52 per month!
UPDATE: The above was for the Ruby on Rails hosting and here is the fee structure for the cloud hosting:
As per this fee structure, for a Nano instance, it will only cost you 18 pounds per month (+ IP charge + data charge), which is still pretty high but is reasonable.
Interesting enough, they have a managed MYSQL cluster storage which unspecific storage size, which could be pretty useful especially on the low memory versions since MySQL takes a lot of memory most of the time.
Registration for the free beta account was fairly easy, all you need to do is to go to this page, sign up with your name and email address and then patiently wait for the email containing the client ID and secret.
Unlike most of the providers, Brightbox does not provide a graphical control panel (although it was mentioned that there will be a graphical control panel coming in the next few weeks) and you will need to use a API to create and control the VPS (and delete one for that matter as well).
To install the API was fairly straight-forward, primarily due to the fact that I was using Ubuntu in the VPS that I used to install the API (yes, the client side can be installed on Linux only) and the fact that they have had a fairly complete documentations here. The only thing to take note of is that you can only create, at most, a small instance due to the limitations in the RAM offered, although with 2GB of RAM, the “small” instance is nowhere small. Furthermore, to reload an OS template, you will need to destroy and recreate the entire instance as well.
Various OS templates can be listed using a single command:
brightbox-images list id owner type created_on status size name -------------------------------------------------------------------------------------------------- img-3rb1e brightbox official 2011-04-19 public 0 Blank disk image (i686) img-715uq brightbox official 2011-04-19 public 0 Blank disk image (x86_64) img-adtke brightbox official 2011-07-20 public 0 Blank disk image (compat) (i686) img-ztdma brightbox official 2011-07-20 public 0 Blank disk image (compat) (x86_64) img-99q79 brightbox official 2010-10-02 public 10244 CentOS 5.5 server (i686) img-pnqnc brightbox official 2010-10-03 public 10240 CentOS 5.5 server (x86_64) img-qjuex brightbox official 2010-10-14 public 10244 Fedora 14 Beta Base (i686) img-vyeeg brightbox official 2010-10-15 public 10244 Fedora 14 Beta Base (x86_64) img-1okdf brightbox official 2010-11-19 public 20480 FreeBSD 8.1 minimal (i686) img-aoubd brightbox official 2010-11-19 public 20480 FreeBSD 8.1 minimal (x86_64) img-2ab98 brightbox official 2011-04-18 public 1409 Ubuntu Lucid 10.04 server (i686) img-4gqhs brightbox official 2011-05-09 public 1409 Ubuntu Lucid 10.04 server (i686) img-3ikco brightbox official 2011-05-09 public 1409 Ubuntu Lucid 10.04 server (x86_64) img-7i0fl brightbox official 2011-05-09 public 1409 Ubuntu Maverick 10.10 server (i686) img-cq4kz brightbox official 2011-05-09 public 1409 Ubuntu Maverick 10.10 server (x86_64) img-ieh3b brightbox official 2011-05-09 public 1409 Ubuntu Natty 11.04 server (i686) img-7p3wu brightbox official 2011-05-09 public 1409 Ubuntu Natty 11.04 server (x86_64) --------------------------------------------------------------------------------------------------
As you can see, there is still relatively few OS templates available at the moment, and there are only 3 Linux distributions available,although I am glad that they have a relatively complete Ubuntu collections.
There is no way, at least from what I know, to change the rDNS record using the API client and by default, they are all in cip-xxx-xxx-xxx-xxx.gb1.brightbox.com format.
Furthermore, you can only login to the VPS via SSH keys (log in as root in CentOS and ubuntu as Ubuntu user with sudo privileges) and if for any reason the keys are lost, you will need to destroy and recreate the VPS again since there is no “emergency recovery console” available.
Finally, you can take “snapshots” of the server, which works as some sort of backup feature, although I have never tried to restore from any snapshot to see how it worked.
Test on the VPS
The test VPS that I have used is a “small” instance with 2048MB of RAM, 4 CPU cores and 80GB of hard drive space, the VPS is in Manchester, UK but the exact location is not clear since they seems to own the IP block they have assigned to me (under AS51059) and the company is registered in Leeds and the datacentre provider for them has several locations in Manchester:
id:
status: active
name:
description:
created_at: 2011-05-07T13:36
deleted_at:
zone: gb1-a
type: typ-urtky
type_name: Brightbox Small Instance
type_handle: small
ram: 2048
cores: 4
disk: 81920
image: img-7n81y
image_name:
private_ips:
cloud_ips:
cloud_ip_ids:
hostname:
public_hostname:
snapshots:
There are also other types of instances available and since you are only restrcited by the total amount of resources, you can create as many VPS as you would like:
brightbox-types list id name handle ram disk cores description -------------------------------------------------------------------------------- typ-4nssg Brightbox Nano Instance nano 512 20480 2 typ-iqisj Brightbox Mini Instance mini 1024 40960 4 typ-urtky Brightbox Small Instance small 2048 81920 4 typ-qdiwq Brightbox Medium Instance medium 4096 163840 8 typ-mlbt7 Brightbox Large Instance large 8192 327680 8 --------------------------------------------------------------------------------
For example, I can create 1 small instance, or 2 mini instance, or 4 nano instances.
As mentioned above, for Ubuntu installation, you will be logged in as user “ubuntu” via key authentication, and you will need to either do “su root” or sudo to use the root privileges.
It really worth mention that every time I log in to the VPS, I was able to see the resources usage, which is something nice:
System information as of Sun Aug 28 11:29:46 CST 2011 System load: 0.0 Processes: 79 Usage of /: 3.6% of 78.80GB Users logged in: 0 Memory usage: 35% IP address for eth0: 10.67.166.34 Swap usage: 0%
When the full LNMP stack is installed, the VPS uses about 124MB of memory:
free -m
total used free shared buffers cached
Mem: 2011 1699 312 0 78 1496
-/+ buffers/cache: 124 1886
Swap: 0 0 0
Although the top output seems to indicate that I could do better by trimming a few more processes:
top - 08:14:58 up 60 days, 10:37, 1 user, load average: 0.11, 0.04, 0.05
Tasks: 78 total, 1 running, 77 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 0.0%sy, 0.0%ni, 97.3%id, 2.7%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 2060076k total, 1740608k used, 319468k free, 80172k buffers
Swap: 0k total, 0k used, 0k free, 1532424k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
19833 www 20 0 14672 10m 812 S 0 0.5 0:00.06 nginx
32078 ubuntu 20 0 8784 5992 1512 S 0 0.3 0:00.59 bash
19945 mysql 20 0 35376 5848 3172 S 0 0.3 0:00.08 mysqld
32047 root 20 0 8448 2736 2156 S 0 0.1 0:00.07 sshd
553 root 20 0 5652 2196 1772 S 0 0.1 0:21.91 sshd
1 root 20 0 2924 1704 1220 S 0 0.1 0:08.22 init
556 syslog 20 0 29632 1396 996 S 0 0.1 1:41.58 rsyslogd
32075 ubuntu 20 0 8448 1324 736 S 0 0.1 0:00.00 sshd
32175 ubuntu 20 0 2500 1084 852 R 0 0.1 0:00.00 top
629 root 20 0 2268 804 644 S 0 0.0 0:08.15 cron
270 root 16 -4 2552 768 360 S 0 0.0 0:00.05 udevd
494 root 20 0 2548 764 500 S 0 0.0 0:33.98 dhclient3
19831 root 20 0 4860 684 228 S 0 0.0 0:00.00 nginx
351 root 18 -2 2548 672 284 S 0 0.0 0:00.00 udevd
352 root 18 -2 2548 672 284 S 0 0.0 0:00.00 udevd
665 root 20 0 3156 640 500 S 0 0.0 9:50.83 irqbalance
265 root 20 0 2412 612 456 S 0 0.0 0:00.08 upstart-udev-br
Based on the recommendations from one of the readers, I have also decided to give a htop output on the box (thanks Luc!):
Yes, this box has one of the longest uptime I have, even htop is surprised with the output!
vmstats does not show too much usage on the VPS:
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 319476 80172 1532424 0 0 0 0 2 1 0 0 100 0
which is reaffirmed by the output of uptime:
uptime 11:38:18 up 112 days, 14:00, 1 user, load average: 0.01, 0.03, 0.05
There is no sign of disk space been oversold from the output of df -h:
df -h Filesystem Size Used Avail Use% Mounted on /dev/vda1 79G 1.9G 73G 3% / none 1004M 144K 1004M 1% /dev none 1006M 0 1006M 0% /dev/shm none 1006M 44K 1006M 1% /var/run none 1006M 0 1006M 0% /var/lock
And Inode was set to pretty high:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/vda1 4997120 73324 4923796 2% / none 217865 618 217247 1% /dev none 219086 1 219085 1% /dev/shm none 219086 20 219066 1% /var/run none 219086 1 219085 1% /var/lock
From the output of CPU info, KVM seems to be the virtualization technology used here and as indicated, 4 CPU cores are available with no throttling on the CPU:
cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 13 model name : QEMU Virtual CPU version (cpu64-rhel6) stepping : 3 cpu MHz : 2267.000 cache size : 4096 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 4 wp : yes flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse3 6 clflush mmx fxsr sse sse2 syscall nx lm pni cx16 hypervisor lahf_lm bogomips : 4534.00 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 13 model name : QEMU Virtual CPU version (cpu64-rhel6) stepping : 3 cpu MHz : 2267.000 cache size : 4096 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 4 wp : yes flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse3 6 clflush mmx fxsr sse sse2 syscall nx lm pni cx16 hypervisor lahf_lm bogomips : 4534.00 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 6 model : 13 model name : QEMU Virtual CPU version (cpu64-rhel6) stepping : 3 cpu MHz : 2267.000 cache size : 4096 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 4 wp : yes flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse3 6 clflush mmx fxsr sse sse2 syscall nx lm pni cx16 hypervisor lahf_lm bogomips : 4534.00 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 13 model name : QEMU Virtual CPU version (cpu64-rhel6) stepping : 3 cpu MHz : 2267.000 cache size : 4096 KB fdiv_bug : no hlt_bug : no f00f_bug : no coma_bug : no fpu : yes fpu_exception : yes cpuid level : 4 wp : yes flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse3 6 clflush mmx fxsr sse sse2 syscall nx lm pni cx16 hypervisor lahf_lm bogomips : 4534.00 clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management:
Meminfo does not seem to show overselling on the memory as well:
cat /proc/meminfo MemTotal: 2060076 kB MemFree: 92468 kB Buffers: 59080 kB Cached: 1798588 kB SwapCached: 0 kB Active: 747104 kB Inactive: 1132844 kB Active(anon): 22404 kB Inactive(anon): 72 kB Active(file): 724700 kB Inactive(file): 1132772 kB Unevictable: 0 kB Mlocked: 0 kB HighTotal: 1183732 kB HighFree: 3388 kB LowTotal: 876344 kB LowFree: 89080 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 0 kB Writeback: 0 kB AnonPages: 22296 kB Mapped: 7680 kB Shmem: 196 kB Slab: 78460 kB SReclaimable: 71992 kB SUnreclaim: 6468 kB KernelStack: 664 kB PageTables: 588 kB NFS_Unstable: 0 kB Bounce: 0 kB WritebackTmp: 0 kB CommitLimit: 1030036 kB Committed_AS: 81360 kB VmallocTotal: 122880 kB VmallocUsed: 2276 kB VmallocChunk: 118376 kB HardwareCorrupted: 0 kB HugePages_Total: 0 HugePages_Free: 0 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 2048 kB DirectMap4k: 6136 kB DirectMap2M: 907264 kB
And the output of time sync:
time sync real 0m0.062s user 0m0.000s sys 0m0.008s
Disk I/O is something that surprised me, and makes me understand why Brightbox could charge such high prices:
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, 5.22598 s, 205 MB/s
And testing again produced even 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, 4.4293 s, 242 MB/s
I have commonly seen disk I/O speed in the double digits range so normally a triple digit disk I/O is enough to get me surprised, and one that is above 200MB/s…I guess I can only say I am speechless.
The network is pretty solid too as I was able to get close to 30MB/s download:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2011-08-23 07:01:48-- http://cachefly.cachefly.net/100mb.test Resolving cachefly.cachefly.net... 140.99.94.175 Connecting to cachefly.cachefly.net|140.99.94.175|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 30.1M/s in 3.5s 2011-08-23 07:01:51 (29.0 MB/s) - `/dev/null' saved [104857600/104857600]
Upload speed varies, with BuyVM in San Jose, California has the slowest speed since their networks to Europe is normally pretty weak:
wget 109.107.36.113/100mb.test -O /dev/null --2011-08-22 21:35:28-- http://109.107.36.113/100mb.test Connecting to 109.107.36.113:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 1.75M/s in 40s 2011-08-22 21:36:08 (2.52 MB/s) - `/dev/null' saved [104857600/104857600]
Nix Communications VPS in Montreal, Canada has an upload speed that is above 5MB/s, which is pretty good:
wget 109.107.36.113/100mb.test -O /dev/null --2011-08-23 09:34:32-- http://109.107.36.113/100mb.test Connecting to 109.107.36.113:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 5.43M/s in 20s 2011-08-23 09:34:52 (5.12 MB/s) - `/dev/null' saved [104857600/104857600]
And finally, and surprisingly, the Quickweb VPS in London, UK did not give me a lot better speed than that of Nix Communications’ VPS, since both VPS are in the same country:
wget 109.107.36.113/100mb.test -O /dev/null --2011-08-22 21:36:48-- http://109.107.36.113/100mb.test Connecting to 109.107.36.113:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 4.72M/s in 19s 2011-08-22 21:37:07 (5.30 MB/s) - `/dev/null' saved [104857600/104857600]
Given the excellent VPS specifications, I was not surprised when the VPS gave really good UnixBench score:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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
4 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
4 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
4 x Execl Throughput 1 2 3
4 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
4 x File Copy 256 bufsize 500 maxblocks 1 2 3
4 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
4 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
4 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
4 x Process Creation 1 2 3
4 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
4 x Shell Scripts (1 concurrent) 1 2 3
4 x Shell Scripts (8 concurrent) 1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: srv-3uj5d: GNU/Linux
OS: GNU/Linux -- 2.6.38-8-virtual -- #42-Ubuntu SMP Mon Apr 11 07:04:38 UTC 2011
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 3: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
08:30:16 up 60 days, 10:52, 1 user, load average: 0.00, 0.13, 0.15; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Thu Jul 07 2011 08:30:16 - 08:57:43
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 12950732.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2737.2 MWIPS (7.3 s, 7 samples)
Execl Throughput 1457.3 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 745219.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 201476.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1560603.5 KBps (30.0 s, 2 samples)
Pipe Throughput 1293677.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 177125.1 lps (10.0 s, 7 samples)
Process Creation 3677.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2268.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 931.6 lpm (60.0 s, 2 samples)
System Call Overhead 2581395.6 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 12950732.0 1109.7
Double-Precision Whetstone 55.0 2737.2 497.7
Execl Throughput 43.0 1457.3 338.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 745219.0 1881.9
File Copy 256 bufsize 500 maxblocks 1655.0 201476.0 1217.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 1560603.5 2690.7
Pipe Throughput 12440.0 1293677.7 1039.9
Pipe-based Context Switching 4000.0 177125.1 442.8
Process Creation 126.0 3677.9 291.9
Shell Scripts (1 concurrent) 42.4 2268.1 534.9
Shell Scripts (8 concurrent) 6.0 931.6 1552.7
System Call Overhead 15000.0 2581395.6 1720.9
========
System Benchmarks Index Score 882.0
------------------------------------------------------------------------
Benchmark Run: Thu Jul 07 2011 08:57:43 - 09:25:20
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 52610318.2 lps (10.0 s, 7 samples)
Double-Precision Whetstone 10984.5 MWIPS (7.3 s, 7 samples)
Execl Throughput 11691.2 lps (29.8 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 342939.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 101201.9 KBps (30.1 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1075158.0 KBps (30.0 s, 2 samples)
Pipe Throughput 5177799.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 771060.3 lps (10.0 s, 7 samples)
Process Creation 34255.6 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 10322.6 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1787.1 lpm (60.1 s, 2 samples)
System Call Overhead 5839533.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 52610318.2 4508.2
Double-Precision Whetstone 55.0 10984.5 1997.2
Execl Throughput 43.0 11691.2 2718.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 342939.9 866.0
File Copy 256 bufsize 500 maxblocks 1655.0 101201.9 611.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 1075158.0 1853.7
Pipe Throughput 12440.0 5177799.0 4162.2
Pipe-based Context Switching 4000.0 771060.3 1927.7
Process Creation 126.0 34255.6 2718.7
Shell Scripts (1 concurrent) 42.4 10322.6 2434.6
Shell Scripts (8 concurrent) 6.0 1787.1 2978.5
System Call Overhead 15000.0 5839533.5 3893.0
========
System Benchmarks Index Score 2226.0
Running it almost a month later shows the score continued to be really good:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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
4 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
4 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
4 x Execl Throughput 1 2 3
4 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
4 x File Copy 256 bufsize 500 maxblocks 1 2 3
4 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
4 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
4 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
4 x Process Creation 1 2 3
4 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
4 x Shell Scripts (1 concurrent) 1 2 3
4 x Shell Scripts (8 concurrent) 1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: srv-3uj5d: GNU/Linux
OS: GNU/Linux -- 2.6.38-8-virtual -- #42-Ubuntu SMP Mon Apr 11 07:04:38 UTC 2011
Machine: i686 (i386)
Language: en_US.utf8 (charmap="UTF-8", collate="UTF-8")
CPU 0: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 1: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 2: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
CPU 3: QEMU Virtual CPU version (cpu64-rhel6) (4534.0 bogomips)
x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET
07:03:35 up 107 days, 9:26, 1 user, load average: 0.03, 0.04, 0.05; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Tue Aug 23 2011 07:03:35 - 07:31:10
4 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 13088159.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2711.2 MWIPS (7.0 s, 7 samples)
Execl Throughput 1514.3 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 651055.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 154870.2 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1364834.9 KBps (30.0 s, 2 samples)
Pipe Throughput 907680.7 lps (10.0 s, 7 samples)
Pipe-based Context Switching 166570.0 lps (10.0 s, 7 samples)
Process Creation 3426.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2273.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 893.8 lpm (60.1 s, 2 samples)
System Call Overhead 2528284.9 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 13088159.1 1121.5
Double-Precision Whetstone 55.0 2711.2 492.9
Execl Throughput 43.0 1514.3 352.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 651055.2 1644.1
File Copy 256 bufsize 500 maxblocks 1655.0 154870.2 935.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 1364834.9 2353.2
Pipe Throughput 12440.0 907680.7 729.6
Pipe-based Context Switching 4000.0 166570.0 416.4
Process Creation 126.0 3426.7 272.0
Shell Scripts (1 concurrent) 42.4 2273.9 536.3
Shell Scripts (8 concurrent) 6.0 893.8 1489.7
System Call Overhead 15000.0 2528284.9 1685.5
========
System Benchmarks Index Score 808.9
------------------------------------------------------------------------
Benchmark Run: Tue Aug 23 2011 07:31:10 - 07:58:52
4 CPUs in system; running 4 parallel copies of tests
Dhrystone 2 using register variables 52680595.4 lps (10.0 s, 7 samples)
Double-Precision Whetstone 10984.5 MWIPS (7.6 s, 7 samples)
Execl Throughput 10303.8 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 308785.7 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 84620.5 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1013008.7 KBps (30.0 s, 2 samples)
Pipe Throughput 3629454.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 693532.4 lps (10.0 s, 7 samples)
Process Creation 28795.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 10493.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1661.0 lpm (60.1 s, 2 samples)
System Call Overhead 6068445.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 52680595.4 4514.2
Double-Precision Whetstone 55.0 10984.5 1997.2
Execl Throughput 43.0 10303.8 2396.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 308785.7 779.8
File Copy 256 bufsize 500 maxblocks 1655.0 84620.5 511.3
File Copy 4096 bufsize 8000 maxblocks 5800.0 1013008.7 1746.6
Pipe Throughput 12440.0 3629454.2 2917.6
Pipe-based Context Switching 4000.0 693532.4 1733.8
Process Creation 126.0 28795.4 2285.4
Shell Scripts (1 concurrent) 42.4 10493.3 2474.8
Shell Scripts (8 concurrent) 6.0 1661.0 2768.4
System Call Overhead 15000.0 6068445.8 4045.6
========
System Benchmarks Index Score 2027.3
Geekbench shows pretty good score too:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Ubuntu Natty (development branch) 2.6.38-8-virtual i686
Model: Linux PC (QEMU Virtual CPU version (cpu64-rhel6))
Motherboard: Unknown Motherboard
Processor: QEMU Virtual CPU version (cpu64-rhel6)
Processor ID: GenuineIntel Family 6 Model 13 Stepping 3
Logical Processors: 4
Physical Processors: 1
Processor Frequency: 2.27 GHz
L1 Instruction Cache: 64.0 KB
L1 Data Cache: 64.0 KB
L2 Cache: 512 KB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 1.96 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: QEMU Virtual CPU version (cpu64-rhel6)
Processor Cores: 4
Integer
Blowfish
single-threaded scalar 1058 ||||
multi-threaded scalar 4560 ||||||||||||||||||
Text Compress
single-threaded scalar 1964 |||||||
multi-threaded scalar 5600 ||||||||||||||||||||||
Text Decompress
single-threaded scalar 1985 |||||||
multi-threaded scalar 5425 |||||||||||||||||||||
Image Compress
single-threaded scalar 1018 ||||
multi-threaded scalar 3770 |||||||||||||||
Image Decompress
single-threaded scalar 932 |||
multi-threaded scalar 3617 ||||||||||||||
Lua
single-threaded scalar 3093 ||||||||||||
multi-threaded scalar 7674 ||||||||||||||||||||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 2089 ||||||||
multi-threaded scalar 5321 |||||||||||||||||||||
Dot Product
single-threaded scalar 2130 ||||||||
multi-threaded scalar 8687 ||||||||||||||||||||||||||||||||||
single-threaded vector 2748 ||||||||||
multi-threaded vector 10854 |||||||||||||||||||||||||||||||||||||||||||
LU Decomposition
single-threaded scalar 1386 |||||
multi-threaded scalar 5259 |||||||||||||||||||||
Primality Test
single-threaded scalar 3442 |||||||||||||
multi-threaded scalar 9982 |||||||||||||||||||||||||||||||||||||||
Sharpen Image
single-threaded scalar 3877 |||||||||||||||
multi-threaded scalar 14012 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 5235 ||||||||||||||||||||
multi-threaded scalar 12740 ||||||||||||||||||||||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 3046 ||||||||||||
Write Sequential
single-threaded scalar 4916 |||||||||||||||||||
Stdlib Allocate
single-threaded scalar 2318 |||||||||
Stdlib Write
single-threaded scalar 1233 ||||
Stdlib Copy
single-threaded scalar 5098 ||||||||||||||||||||
Stream
Stream Copy
single-threaded scalar 3537 ||||||||||||||
single-threaded vector 3500 ||||||||||||||
Stream Scale
single-threaded scalar 2148 ||||||||
single-threaded vector 3640 ||||||||||||||
Stream Add
single-threaded scalar 2503 ||||||||||
single-threaded vector 3349 |||||||||||||
Stream Triad
single-threaded scalar 2446 |||||||||
single-threaded vector 2556 ||||||||||
Integer Score: 3391 |||||||||||||
Floating Point Score: 6268 |||||||||||||||||||||||||
Memory Score: 3322 |||||||||||||
Stream Score: 2959 |||||||||||
Overall Geekbench Score: 4340 |||||||||||||||||
And second time gave even better results:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Ubuntu Natty (development branch) 2.6.38-8-virtual i686
Model: Linux PC (QEMU Virtual CPU version (cpu64-rhel6))
Motherboard: Unknown Motherboard
Processor: QEMU Virtual CPU version (cpu64-rhel6)
Processor ID: GenuineIntel Family 6 Model 13 Stepping 3
Logical Processors: 4
Physical Processors: 1
Processor Frequency: 2.27 GHz
L1 Instruction Cache: 64.0 KB
L1 Data Cache: 64.0 KB
L2 Cache: 512 KB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 1.96 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: QEMU Virtual CPU version (cpu64-rhel6)
Processor Cores: 4
Integer
Blowfish
single-threaded scalar 1689 ||||||
multi-threaded scalar 4687 ||||||||||||||||||
Text Compress
single-threaded scalar 1966 |||||||
multi-threaded scalar 7449 |||||||||||||||||||||||||||||
Text Decompress
single-threaded scalar 1980 |||||||
multi-threaded scalar 7336 |||||||||||||||||||||||||||||
Image Compress
single-threaded scalar 1614 ||||||
multi-threaded scalar 5941 |||||||||||||||||||||||
Image Decompress
single-threaded scalar 988 |||
multi-threaded scalar 3550 ||||||||||||||
Lua
single-threaded scalar 3092 ||||||||||||
multi-threaded scalar 5835 |||||||||||||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 2096 ||||||||
multi-threaded scalar 5286 |||||||||||||||||||||
Dot Product
single-threaded scalar 2115 ||||||||
multi-threaded scalar 11434 |||||||||||||||||||||||||||||||||||||||||||||
single-threaded vector 3388 |||||||||||||
multi-threaded vector 16693 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LU Decomposition
single-threaded scalar 2030 ||||||||
multi-threaded scalar 7812 |||||||||||||||||||||||||||||||
Primality Test
single-threaded scalar 3389 |||||||||||||
multi-threaded scalar 8104 ||||||||||||||||||||||||||||||||
Sharpen Image
single-threaded scalar 3499 |||||||||||||
multi-threaded scalar 13360 |||||||||||||||||||||||||||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 3241 ||||||||||||
multi-threaded scalar 13235 ||||||||||||||||||||||||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 3284 |||||||||||||
Write Sequential
single-threaded scalar 5120 ||||||||||||||||||||
Stdlib Allocate
single-threaded scalar 2180 ||||||||
Stdlib Write
single-threaded scalar 1410 |||||
Stdlib Copy
single-threaded scalar 5783 |||||||||||||||||||||||
Stream
Stream Copy
single-threaded scalar 4566 ||||||||||||||||||
single-threaded vector 4424 |||||||||||||||||
Stream Scale
single-threaded scalar 3201 ||||||||||||
single-threaded vector 4768 |||||||||||||||||||
Stream Add
single-threaded scalar 2964 |||||||||||
single-threaded vector 4367 |||||||||||||||||
Stream Triad
single-threaded scalar 3015 ||||||||||||
single-threaded vector 3256 |||||||||||||
Integer Score: 3843 |||||||||||||||
Floating Point Score: 6834 |||||||||||||||||||||||||||
Memory Score: 3555 ||||||||||||||
Stream Score: 3820 |||||||||||||||
Overall Geekbench Score: 4829 |||||||||||||||||||
Customer Service and Support
Since the product is still in beta stage, I assume there is no “production” level of support as well. Indeed, the only way you could contact Brightbox regarding the beta services is to send an email to their email account and most of the time it takes at least a day to get a reply, although the replies are really helpful and not something like “we’ll look into it” kind. John seems to be the only one responding to all help requests (or at least the only one I have been in contact with), but he was able to solve the problem within the first few interactions.
Conclusion
By no means Brightbox is in the low end range, both in terms of price and performance. The VPS is definitely very solid, with zero downtime and amazingly high disk I/O and network speed. It was still in beta stage while I was testing it and there were definitely a few issues here and there and although the support was a little slow, they are definitely knowledgeable and are able to tackle and resolve all of the issue that I have had. If they could bring support to the “production” level, I think Brightbox will definitely be an great option for business or serious hobby sites (with a deep pocket obviously!).
I was looking at the website for these guys and they seem to be more orientated towards cloud technology and higher end hardware them most budget providers.
They use real SAN’s for storage and it looks like if one node goes down it will automatically move your VPS to another node and things like that which is closer to what Amazon would do then a typical budget vps.
That would explain the price though still a ton of money!
Just checked, the VPS is still up and running, definitely one of the best uptime I have ever had: