96MB Low End VPS Review Part 50 – BlueVM
How time flies! It seems 96MB was just opened yesterday but in fact the blog is a year old now. In the highly competitive VPS industry, one year is a long time and many providers has started during this time, some of them become highly successful and grew, while others simply vanished into the thin air (we have plenty of examples here which I am not going to mention). BlueVM has celebrated its first birthday earlier last month and I have decided to buy a VPS from them and take a look at.
Basic Information and Set Up
As per their advertisement on LowEndTalk, here is what you can get for 1.99USD per month:
Unfortunately when I signed up with them, they are already out of stock for this special for all four locations they offer, and I ended up have to sign up for the BlueVM2 Plan which has the following specifications (Yes, I took the last available stock in California):
Although this is not the ideal situation, however this would make this review more useful since the Blue2 plan is considered as a “standard” plan and the Blue3 Special is really a one of special which may or may not come back again.
Note that one of their important selling points is they offer a 99.9997% uptime guarantee as stated on this page. Compare to many providers who only guarantee 99% to 99.9% of uptime, this is definitely quite a good guarantee. However, as you can see, there are quite a few exclusions and I am not sure how their track record is in keeping the promise:
Their sign up system is using WHMCS with HTTPS protocol. One you have the stock chosen and if it is available (since most of their stock are not at the moment, may be they are learning from BuyVM?), you will be presented with a page like this:
Everything is pretty standard, and there are a few more configurations down the bottom:
I would say these addons are relatively cheap, such as 3 cents per month for 1GB of additional space and 15 cents per month for additional 100GB of bandwidth, even the IP is relatively cheap at 1USD each, when most of the VPs providers are charging 1.50 – 2.00 USD per month for one and most shared hosting providers charging even more for that. (Interestingly if I remembered correctly, that’s how I got started with the VPS world, I was originally with Stablehost for some tiny little blogs that I have that attracted probably 10 visitors a month, however due to some specific requirements that I had, I need to set up SSL and had to purchase additional IPs since CPanel does not allow SSL on the shared IP, turned out Stablehost was charging 3USD per month on the IP, which comes to 6USD per month for me since I needed 2, more than enough for me to get a decent VPS with 1 IP and configuring my own SSL on the same IP. Yes, I know it is not best practice to configuring 2 SSLs on the same IP, but I did not really care. 
)
Anyways, without drifting this topic away even further, something pretty interesting happened when I placed my order and was about to check out. As it turned out, BlueVM has its website placed behind Cloudflare, and I am not sure about the servers they used to house their WHMCS, but it was taking a while for the order to be generated and apparently that caused Cloudflare to believe the website was offline and sent me to the ugly website offline page.
The problem was fixed, however, when I refreshed the webpage. Interesting enough, when I had a few seconds to choose between making a subscription or making a one time payment while I was being redirected to the payment gateway, I still ended up landing on the subscription page:
It is not exactly a big deal as I can always cancel the subscription as soon as I made my first payment, however it is definitely a hassle that way.
Activation was instant and I had received the welcome email the minute my payment to paypal was made. However, instead of VPS Welcome Information, this email actually has the subject title of New Dedicated Server Information, I guess they just don’t like to change the subject title in the WHMCS template?
Scrolling down the page, something more amusing happened: they actually masked out the main IP address in the SSH access information although it was clearly written in plain text a few lines above. Similar, the root password was masked but in the server details, the root password was in plain text.
I am not sure if they were just being careless and have no clients informing them about it or it was just a little joke they have, either way it does not really matter but was definitely offered me a good 30 seconds of laughter.
Once logged into their WHMCS system, you can see your VPS under My Services:
Note that there is no bar charts or graphs indicating the resources usage of the VPS and there is only one control button here: Restart VPS Server (yes, it is actually called VPS Server now, not dedicated). Granted this restart is probably the most frequently used function on the control panel (although shutdown –r normally just does the job nicely for me), however you will still need to log back into HyperVM control panel if you need access to the emergency recovery console or change the root password without log into the box.
Clicking down the row and it is interesting to note the number of support departments they have, it seems that they have really detailed classification of support request, including a TUN/TAP department for VPN, a transfer department. Strange enough, they do not seems to have a rDNS department, I guess that falls into support.
And did I just mentioned about HyperVM? Yes, instead of using SolusVM, BlueVM actually uses HyperVM on a non-standard http port and with a randomly assigned user name that is pretty difficult to remember.
I am not a fan of HyperVM since it reminded me the now-bankrupt HostRail, which I had their VPS with HyperVM after seeing their crazy deal, only to cancel it a day or two later since the disk I/O was impossible to do anything serious. However, it is just me and it is not fair to criticize a solid control panel platform just because someone with a bad reputation on the low end VPS community used it to make some quick money. In fact, there are quite a few advantages in HyperVM, such as everything is on one screen (which was a nice feature in SolusVM until they have updated their platform, now I have to remember rDNS is under the Network tab, which sometimes may not be that intuitive), and the fact that install Kloxo could be done within a click, which, unless the provider has a Kloxo template, is not possible within SolusVM. Finally, there is also File Manager which allows you to look at the files in the VPS even without log into the VPS.
I am not going to dig into the details of the functionalities of each one of those icons since they are pretty self-explanatory, however I was not able to find any backup functionalities and there does not seem to be instant rDNS available as well.
In the rebuild section, we can see all the OS templates that are available for reinstallation, including what I would presume to be a highly optimized Kloxo on CentOS template that uses 16MB of RAM as well as a few other major Linux distributions:
While most of the template name make sense, some template names are just beyond my comprehension. For example, does anyone know what is CentOS-5-i386-afull? How about gentoo-openvz-stage3-amd64? And then we also have ubuntu-11.04-x86-backupofswhttnij as the template that used the largest amount of hard drive space? I was not in the adventurous mode so I did not restore any of the template names mentioned above. However, I definitely hope I was been assigned to a production machine rather than a QA/test environment, which seems to be the case here. Furthermore, I definitely hope whttnij is just a generic name and that backup does not contain any client data.
Test on the VPS
As mentioned above, the VPS that I have obtained has 128MB of guaranteed RAM, 1 CPU core, 20GB of storage and 400GB of bandwidth per month. The VPS is located in California simply because it was the last location that still have one stock left on the plan when I signed up and a simple traceroute shows that they are located in Quadranet in Los Angeles in California, US and I have installed Debian 6 32 bit for testing purposes.
When the VPS was first loaded with the OS template, 16MB of RAM was used, which seems to be the standard on the Debian 6 templates these days:
free -m
total used free shared buffers cached
Mem: 256 16 239 0 0 0
-/+ buffers/cache: 16 239
Swap: 0 0 0
The htop output showing the processes running:
Slightly more than 400MB of hard drive space was used:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 20G 413M 20G 3% / tmpfs 128M 0 128M 0% /lib/init/rw tmpfs 128M 0 128M 0% /dev/shm
And the inodes are set to pretty standard values as well:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 10485760 26118 10459642 1% / tmpfs 32768 4 32764 1% /lib/init/rw tmpfs 32768 1 32767 1% /dev/shm
When the full LNMP stack is loaded, 63MB of RAM was used:
free -m
total used free shared buffers cached
Mem: 256 63 192 0 0 0
-/+ buffers/cache: 63 192
Swap: 0 0 0
Top output showing the processes running:
top - 09:29:32 up 48 min, 1 user, load average: 0.00, 0.06, 0.32
Tasks: 21 total, 2 running, 19 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.3%us, 0.0%sy, 0.0%ni, 99.7%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 262144k total, 65948k used, 196196k free, 0k buffers
Swap: 0k total, 0k used, 0k free, 0k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
7816 www 19 0 14992 10m 428 S 0.0 4.2 0:00.00 nginx
7797 mysql 19 0 33944 4640 2040 S 0.0 1.8 0:00.00 mysqld
7807 root 18 0 22620 4544 1404 S 0.0 1.7 0:00.00 php-cgi
7808 www 18 0 22620 4144 1004 S 0.0 1.6 0:00.00 php-cgi
7809 www 18 0 22620 4144 1004 S 0.0 1.6 0:00.00 php-cgi
7810 www 18 0 22620 4144 1004 S 0.0 1.6 0:00.00 php-cgi
7811 www 18 0 22620 4144 1004 S 0.0 1.6 0:00.00 php-cgi
7812 www 25 0 22620 4144 1004 S 0.0 1.6 0:00.00 php-cgi
1619 root 16 1 9488 3884 2468 R 0.0 1.5 0:01.84 sshd
1621 root 15 0 2956 1652 1328 S 0.0 0.6 0:00.01 bash
1588 root 15 0 9984 1588 544 S 0.0 0.6 0:00.00 sendmail-mta
7694 root 25 0 2676 1216 1008 S 0.0 0.5 0:00.00 mysqld_safe
7864 root 15 0 2324 1100 896 R 0.0 0.4 0:00.00 top
1603 root 18 0 5484 992 604 S 0.0 0.4 0:00.00 sshd
1562 root 25 0 2388 860 692 S 0.0 0.3 0:00.00 xinetd
1413 root 15 0 2284 848 664 S 0.0 0.3 0:00.00 cron
1364 root 18 0 8664 820 484 S 0.0 0.3 0:00.00 saslauthd
7815 root 19 0 4780 720 276 S 0.0 0.3 0:00.00 nginx
1 root 15 0 2024 668 580 S 0.0 0.3 0:00.19 init
1380 root 15 0 1732 632 528 S 0.0 0.2 0:00.00 syslogd
1366 root 18 0 8664 500 164 S 0.0 0.2 0:00.00 saslauthd
And the htop output:
When the full LNMP stack was installed, the total amount of disk space used is about 1.6GB:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 20G 1.6G 19G 8% / tmpfs 128M 0 128M 0% /lib/init/rw tmpfs 128M 0 128M 0% /dev/shm
And the inodes values:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 10485760 69270 10416490 1% / tmpfs 32768 4 32764 1% /lib/init/rw tmpfs 32768 1 32767 1% /dev/shm
vmstat shows the VPS is idle:
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 195940 0 0 0 0 0 0 0 390 0 0 100 0
Which is shown in the output of uptime as well:
uptime 09:45:24 up 1 day, 5:50, 1 user, load average: 0.00, 0.00, 0.00
CPUinfo shows there one CPU core and it is not throttled:
cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 23 model name : Intel(R) Xeon(R) CPU L5420 @ 2.50GHz stepping : 10 cpu MHz : 2500.036 cache size : 6144 KB physical id : 0 siblings : 4 core id : 0 cpu cores : 4 apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 lahf_lm bogomips : 5000.07 clflush size : 64 cache_alignment : 64 address sizes : 38 bits physical, 48 bits virtual power management:
Beancounters shows barrier and limit values:
cat /proc/user_beancounters
Version: 2.5
uid resource held maxheld barrier limit failcnt
11540: kmemsize 2417716 3388920 2147483646 2147483646 0
lockedpages 0 0 999999 999999 0
privvmpages 16304 34079 65536 65536 0
shmpages 642 672 32768 32768 0
dummy 0 0 0 0 0
numproc 22 30 999999 999999 0
physpages 7427 31394 0 2147483647 0
vmguarpages 0 0 32768 2147483647 0
oomguarpages 7427 31394 32768 2147483647 0
numtcpsock 6 9 7999992 7999992 0
numflock 4 10 999999 999999 0
numpty 1 2 500000 500000 0
numsiginfo 0 3 999999 999999 0
tcpsndbuf 199248 199248 26843136 208869376 0
tcprcvbuf 98304 876112 26843136 208869376 0
othersockbuf 11640 22112 26843136 208869376 0
dgramrcvbuf 0 8472 26843136 208869376 0
numothersock 14 18 7999992 7999992 0
dcachesize 0 0 2147483646 2147483646 0
numfile 514 594 23999976 23999976 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
numiptent 21 21 999999 999999 0
Meminfo does not show anything too interesting:
cat /proc/meminfo MemTotal: 262144 kB MemFree: 196472 kB Buffers: 0 kB Cached: 0 kB SwapCached: 0 kB Active: 0 kB Inactive: 0 kB HighTotal: 0 kB HighFree: 0 kB LowTotal: 262144 kB LowFree: 196472 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 97760 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
And VZfree shows no sign of oversell:
vzfree
Total Used Free
Kernel: 2048.00M 2.32M 2045.68M
Allocate: 256.00M 63.68M 192.32M (128M Guaranteed)
Commit: 128.00M 31.32M 96.68M (45.5% of Allocated)
Swap: 0.00M (0.0% of Committed)
Time sync values did not show anything interesting as well:
time sync real 0m0.157s user 0m0.000s sys 0m0.038s
Disk I/O are OK, but far from anything impressive:
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, 21.4961 s, 50.0 MB/s
Testing again showed similar 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, 21.7939 s, 49.3 MB/s
IOPings are pretty sluggish as well:
ioping -c 10 . 4096 bytes from . ( ): request=1 time=6.8 ms 4096 bytes from . ( ): request=2 time=12.1 ms 4096 bytes from . ( ): request=3 time=9.9 ms 4096 bytes from . ( ): request=4 time=8.1 ms 4096 bytes from . ( ): request=5 time=23.3 ms 4096 bytes from . ( ): request=6 time=13.6 ms 4096 bytes from . ( ): request=7 time=7.1 ms 4096 bytes from . ( ): request=8 time=5.6 ms 4096 bytes from . ( ): request=9 time=11.2 ms 4096 bytes from . ( ): request=10 time=11.0 ms --- . ( ) ioping statistics --- 10 requests completed in 9118.3 ms, 92 iops, 0.4 mb/s min/avg/max/mdev = 5.6/10.9/23.3/4.8 ms
Testing again showed even worse results:
ioping -c 10 . 4096 bytes from . ( ): request=1 time=0.2 ms 4096 bytes from . ( ): request=2 time=97.6 ms 4096 bytes from . ( ): request=3 time=10.4 ms 4096 bytes from . ( ): request=4 time=8.0 ms 4096 bytes from . ( ): request=5 time=11.6 ms 4096 bytes from . ( ): request=6 time=10.3 ms 4096 bytes from . ( ): request=7 time=172.0 ms 4096 bytes from . ( ): request=8 time=111.4 ms 4096 bytes from . ( ): request=9 time=109.0 ms 4096 bytes from . ( ): request=10 time=105.0 ms --- . ( ) ioping statistics --- 10 requests completed in 9642.3 ms, 16 iops, 0.1 mb/s min/avg/max/mdev = 0.2/63.6/172.0/58.7 ms
I am not sure what the port speed is, but the download speed seems to tell me it is hardly even getting close to the port speed:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2012-06-02 11:05:49-- 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 6.89M/s in 14s 2012-06-02 11:06:04 (6.92 MB/s) - `/dev/null' saved [104857600/104857600]
Testing again gave me similar results:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2012-06-02 11:07:29-- 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 5.45M/s in 18s 2012-06-02 11:07:47 (5.71 MB/s) - `/dev/null' saved [104857600/104857600]
Upload speed is by no means impressive as well, the best upload speed I got was obviously on the west coast, with my Quickweb VPS in Los Angeles, CA:
wget 173.254.xxx.xxx/100mb.test -O /dev/null --2012-06-01 23:01:29-- http://173.254.xxx.xxx/100mb.test Connecting to 173.254.xxx.xxx:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 6.92M/s in 13s 2012-06-01 23:01:42 (7.58 MB/s) - `/dev/null' saved [104857600/104857600]
My Quickweb VPS in Chicago, IL, gave me the second best results:
wget 173.254.xxx.xxx/100mb.test -O /dev/null --2012-06-02 10:59:49-- http://173.254.xxx.xxx/100mb.test Connecting to 173.254.xxx.xxx:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 1.65M/s in 46s 2012-06-02 11:00:35 (2.18 MB/s) - `/dev/null' saved [104857600/104857600]
And the XenVZ VPS in MaidenHead, UK, offered the slowest upload speed since it is physically the furthest:
wget 173.254.xxx.xxx/100mb.test -O /dev/null --2012-06-02 11:01:04-- http://173.254.xxx.xxx/100mb.test Connecting to 173.254.xxx.xxx:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 1.37M/s in 65s 2012-06-02 11:02:09 (1.55 MB/s) - `/dev/null' saved [104857600/104857600]
Finally, benchmark time, since this is just another low end VPS box, I was not expecting too much out of it, however I was still a little disappointed when the box did not even score 1000 points, ended up at slightly above 800 points:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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: xxxxxxx: GNU/Linux
OS: GNU/Linux -- 2.6.32-308.el5.028stab099.3 -- #1 SMP Wed Mar 7 15:56:00 MSK 2012
Machine: i686 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
12:14:14 up 3:33, 1 user, load average: 0.00, 0.00, 0.00; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Sat Jun 02 2012 12:14:14 - 12:42:27
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 12508275.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2567.8 MWIPS (10.1 s, 7 samples)
Execl Throughput 3845.3 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 433938.6 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 121730.5 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 724384.2 KBps (30.0 s, 2 samples)
Pipe Throughput 809069.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 241553.4 lps (10.0 s, 7 samples)
Process Creation 11318.8 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4503.7 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 599.0 lpm (60.1 s, 2 samples)
System Call Overhead 661766.8 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 12508275.0 1071.8
Double-Precision Whetstone 55.0 2567.8 466.9
Execl Throughput 43.0 3845.3 894.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 433938.6 1095.8
File Copy 256 bufsize 500 maxblocks 1655.0 121730.5 735.5
File Copy 4096 bufsize 8000 maxblocks 5800.0 724384.2 1248.9
Pipe Throughput 12440.0 809069.1 650.4
Pipe-based Context Switching 4000.0 241553.4 603.9
Process Creation 126.0 11318.8 898.3
Shell Scripts (1 concurrent) 42.4 4503.7 1062.2
Shell Scripts (8 concurrent) 6.0 599.0 998.3
System Call Overhead 15000.0 661766.8 441.2
========
System Benchmarks Index Score 805.3
Testing again showed slightly lower 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
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: xxxxxx: GNU/Linux
OS: GNU/Linux -- 2.6.32-308.el5.028stab099.3 -- #1 SMP Wed Mar 7 15:56:00 MSK 2012
Machine: i686 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Intel(R) Xeon(R) CPU L5420 @ 2.50GHz (5000.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
10:08:32 up 1:27, 1 user, load average: 0.62, 0.43, 0.18; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Sat Jun 02 2012 10:08:32 - 10:36:35
1 CPU in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 12604383.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2300.5 MWIPS (10.1 s, 7 samples)
Execl Throughput 3832.2 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 423183.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 122272.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 722499.1 KBps (30.0 s, 2 samples)
Pipe Throughput 827695.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 247221.0 lps (10.0 s, 7 samples)
Process Creation 11184.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4512.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 601.9 lpm (60.1 s, 2 samples)
System Call Overhead 661948.6 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 12604383.8 1080.1
Double-Precision Whetstone 55.0 2300.5 418.3
Execl Throughput 43.0 3832.2 891.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 423183.0 1068.6
File Copy 256 bufsize 500 maxblocks 1655.0 122272.1 738.8
File Copy 4096 bufsize 8000 maxblocks 5800.0 722499.1 1245.7
Pipe Throughput 12440.0 827695.0 665.3
Pipe-based Context Switching 4000.0 247221.0 618.1
Process Creation 126.0 11184.3 887.6
Shell Scripts (1 concurrent) 42.4 4512.1 1064.2
Shell Scripts (8 concurrent) 6.0 601.9 1003.2
System Call Overhead 15000.0 661948.6 441.3
========
System Benchmarks Index Score 799.4
Similar situation happened to the Geekbench tests, I was not impressed to be honest:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Linux 2.6.32-308.el5.028stab099.3 i686
Model: Linux PC (Intel Xeon L5420)
Motherboard: Unknown Motherboard
Processor: Intel Xeon L5420
Processor ID: GenuineIntel Family 6 Model 23 Stepping 10
Logical Processors: 1
Physical Processors: 1
Processor Frequency: 2.50 GHz
L1 Instruction Cache: 0.00 B
L1 Data Cache: 0.00 B
L2 Cache: 6.00 MB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 7.79 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: Intel Xeon L5420
Processor Cores: 1
Integer
Blowfish
single-threaded scalar 1792 |||||||
multi-threaded scalar 1920 |||||||
Text Compress
single-threaded scalar 2019 ||||||||
multi-threaded scalar 1963 |||||||
Text Decompress
single-threaded scalar 1824 |||||||
multi-threaded scalar 1864 |||||||
Image Compress
single-threaded scalar 1727 ||||||
multi-threaded scalar 1698 ||||||
Image Decompress
single-threaded scalar 1517 ||||||
multi-threaded scalar 1559 ||||||
Lua
single-threaded scalar 3420 |||||||||||||
multi-threaded scalar 3388 |||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 1870 |||||||
multi-threaded scalar 1901 |||||||
Dot Product
single-threaded scalar 3422 |||||||||||||
multi-threaded scalar 3628 ||||||||||||||
single-threaded vector 2572 ||||||||||
multi-threaded vector 2957 |||||||||||
LU Decomposition
single-threaded scalar 2206 ||||||||
multi-threaded scalar 2232 ||||||||
Primality Test
single-threaded scalar 2929 |||||||||||
multi-threaded scalar 2359 |||||||||
Sharpen Image
single-threaded scalar 6101 ||||||||||||||||||||||||
multi-threaded scalar 6174 ||||||||||||||||||||||||
Blur Image
single-threaded scalar 4429 |||||||||||||||||
multi-threaded scalar 4455 |||||||||||||||||
Memory
Read Sequential
single-threaded scalar 2493 |||||||||
Write Sequential
single-threaded scalar 3230 ||||||||||||
Stdlib Allocate
single-threaded scalar 2280 |||||||||
Stdlib Write
single-threaded scalar 1261 |||||
Stdlib Copy
single-threaded scalar 2578 ||||||||||
Stream
Stream Copy
single-threaded scalar 1885 |||||||
single-threaded vector 2061 ||||||||
Stream Scale
single-threaded scalar 1972 |||||||
single-threaded vector 1970 |||||||
Stream Add
single-threaded scalar 1742 ||||||
single-threaded vector 2023 ||||||||
Stream Triad
single-threaded scalar 1902 |||||||
single-threaded vector 1500 ||||||
Integer Score: 2057 ||||||||
Floating Point Score: 3373 |||||||||||||
Memory Score: 2368 |||||||||
Stream Score: 1881 |||||||
Overall Geekbench Score: 2562 ||||||||||
Testing again:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Linux 2.6.32-308.el5.028stab099.3 i686
Model: Linux PC (Intel Xeon L5420)
Motherboard: Unknown Motherboard
Processor: Intel Xeon L5420
Processor ID: GenuineIntel Family 6 Model 23 Stepping 10
Logical Processors: 1
Physical Processors: 1
Processor Frequency: 2.50 GHz
L1 Instruction Cache: 0.00 B
L1 Data Cache: 0.00 B
L2 Cache: 6.00 MB
L3 Cache: 0.00 B
Bus Frequency: 0.00 Hz
Memory: 7.79 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: Intel Xeon L5420
Processor Cores: 1
Integer
Blowfish
single-threaded scalar 1799 |||||||
multi-threaded scalar 1921 |||||||
Text Compress
single-threaded scalar 2020 ||||||||
multi-threaded scalar 1964 |||||||
Text Decompress
single-threaded scalar 1827 |||||||
multi-threaded scalar 1873 |||||||
Image Compress
single-threaded scalar 1698 ||||||
multi-threaded scalar 1661 ||||||
Image Decompress
single-threaded scalar 1470 |||||
multi-threaded scalar 1520 ||||||
Lua
single-threaded scalar 3409 |||||||||||||
multi-threaded scalar 3379 |||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 1870 |||||||
multi-threaded scalar 1901 |||||||
Dot Product
single-threaded scalar 3422 |||||||||||||
multi-threaded scalar 3628 ||||||||||||||
single-threaded vector 2571 ||||||||||
multi-threaded vector 2957 |||||||||||
LU Decomposition
single-threaded scalar 2179 ||||||||
multi-threaded scalar 2235 ||||||||
Primality Test
single-threaded scalar 2932 |||||||||||
multi-threaded scalar 2360 |||||||||
Sharpen Image
single-threaded scalar 6030 ||||||||||||||||||||||||
multi-threaded scalar 6158 ||||||||||||||||||||||||
Blur Image
single-threaded scalar 4423 |||||||||||||||||
multi-threaded scalar 4438 |||||||||||||||||
Memory
Read Sequential
single-threaded scalar 2471 |||||||||
Write Sequential
single-threaded scalar 3244 ||||||||||||
Stdlib Allocate
single-threaded scalar 2250 |||||||||
Stdlib Write
single-threaded scalar 1220 ||||
Stdlib Copy
single-threaded scalar 2481 |||||||||
Stream
Stream Copy
single-threaded scalar 1876 |||||||
single-threaded vector 2034 ||||||||
Stream Scale
single-threaded scalar 1972 |||||||
single-threaded vector 1951 |||||||
Stream Add
single-threaded scalar 1738 ||||||
single-threaded vector 2012 ||||||||
Stream Triad
single-threaded scalar 1942 |||||||
single-threaded vector 1490 |||||
Integer Score: 2045 ||||||||
Floating Point Score: 3364 |||||||||||||
Memory Score: 2333 |||||||||
Stream Score: 1876 |||||||
Overall Geekbench Score: 2547 ||||||||||
Overall, I have to say that may be because I was having quite a lot of expectation from them, but what the performance of the VPS is far from the performance from someone who “sold out” on the stock.
Customer Service and Support
As my quest for the the popularity of Bluehost (EDIT: it is BlueVM, apologies for the typo) continued, I decided to make use of the numerous number of support departments they have and send in three tickets to three different support departments, one each for support, TUN/TAP and VPS Transfer, since I understand some of the departments may not be working over the weekend.
However, it seems none of their support department is working on the weekend, and in fact, they even decided to take Monday off (EDIT: was told by the owner of BlueVM that weekend happened to be a long weekend in US). My support tickets sent out on June 2 at 04:41, 04:53 and 04:54 was not responded until June 5 at 03:24, 03:25 and 03:27 respectively, even though there does not seems to be any emergencies happened during that weekend. Granted none of those issues were level 1 priority, however, they were very simple issues (such as enable TUN/TAP) and it is pretty disappointing for them to take that long to respond.
Conclusion
Overall, I have to say my experience with BlueVM is less than perfect, granted the price they were offering their VPS for was pretty nice (however not the lowest), but may be the fact that they were out of stock almost everywhere has made me having a pretty high expectation of them, but given that the slow upload/download speed, low benchmark score, together with very slow customer support, unfortunately I have found it is pretty difficult, based on my own experience, to recommend them for any purposes. However, I have to say that 40GB of hard drive space was a very generous amount, which, again, if you are just looking for something that works to house your backup of backup, might be a pretty decent choice.
I must say, your review was very odd. You seemed to expect a lot from BlueVM, even though they are not a high quality provider, nor do they claim so. Why did you assume the data speed would be the full port speed? 60% of a 100mbit port is more than adequate for a lower end VPS. Overall I’d have to say you seemed to look at this company with a negative predisposition once realizing they weren’t the greatest thing since sliced bread.
@Quentin: Thanks for your input, and as I have mentioned several times before, all my reviews are based solely on my interaction with the company and testing out the VPS that I was provisioned, perhaps I just happened to be in a full node, perhaps it happened to be a bad timing, perhaps something else happened.
However, those are my experience with the provider. And I am not here to judge if anything is “adequate” or not (it is for the user to judge), but I am reporting this because this is what I saw and it is relatively low compare to providers who offer VPS at similar price points.
And finally, just to let you know, here is what I see in the About Us section of BlueVM:
So do you mind let me know if they claim to be high quality provider or not?
I can’t believe you missed their specials, it ran for more than a month!!!
i experienced sending a ticket too on a weekend, and I understand your point. But when sending tickets during weekdays, it only took only 40mins on the average. I even asked my node to be relocated to another state, and everything was done after 40 mins, and gave me my new IP, and all my data intact.
I guess what I like about BlueVM is generous bandwidth (1TB for $1.99) and lots of disk space. I hope through time they can improve on their disk/io and network speed. And also support during weekends.
@jcaleb: Actually I had one of those, then for some reason one day my brain just went crazy and I decided to cancel all the VPS that I had no use of (actually ended up cancelling only 2 before I got lazy), and BlueVM happened to be one of them. Then I realized that BlueVM is on my review list and I had to sign up for another box later on, LOL.
Avoid this provider at all costs.
1) Support is horrible; typical response time to tickets: 3 – 8 DAYS
2) Support doesn’t appear to be knowledgeable about some basic configuration requirements or setups
3) It seems like this is not their “day job” and may be a hobby based on their lack of support responsiveness
I have had at least 10 VPS’s with various providers and these guys are by far the worst on support.
Not worth it at any price
@VPS Evaluator: Looks like you have had much worse experience than me…I think they had no problem enable TUN/TAP for me at least, but I have not really asked them anything too deep…Thanks for your input though.
because its cheap and lots of resources, i use it for experiments.
16iops is pretty scary, I think my old floppy drive averages that
A bit off topic, but maybe it’s time to remove the “part xx” part from the post title haha
i second. it sounds like UFC series
I would like to share my experience again. I submitted 2 tickets, one last night, and one this morning. And their replies are very prompt and professional.
@jcaleb, consider yourself very, very lucky!
Since i know you post on LEB, check the last 4 or so posts in the BlueVM thread starting here:
http://www.lowendbox.com/blog/bluevm-special-leb-deal-in-california/#comment-69036
None of those posts were made by me.
I seem to have plenty of company in experiencing horrible support from them!
I can’t even use the vps for “experiments” since they can’t get some basic stuff working for me.
will cancel after end of what i paid already
@jcaleb: Care to share why? You seems to be pretty happy with the service before
sorry for the late reply. no support on weekends. and you find your vps is down almost once a week, could be more frequent. good for just learning
Yes, their prices are cheap. Support is pretty poor for tickets. Weekdays doesn’t seem too bad, but wekends are very poor. The owners/staff have day jobs and do this on the side from what they told me, so that explains it. I’ve put in a ticket and its been more than 12 hours, no response (weekend). Wish I’d spent a few extra $ and went with someone else.
PS: The staff appear to spend a lot of time on IRC, and if you complain on there, they are quick to respond to your criticism and kick you off IRC. Wish they just spent it answering the tickets rather than pissing about on the IRC channel.