96MB Low End VPS Review Part XXXXI – VPSDeploy SSD
As I am pondering slowly over the long-overdue list of review request, VPSDeploy seems to be the next one on the list. Their VPS offerings got me really excited as it was one of the very few low end VPS that is actually offered on SSD! We are know the advantages of SSD: fast disk I/O, however, the current cost of SSD is a lot higher than the standard HDD and therefore kept the low cost VPS providers away from offering it. In fact, there is only one other VPS provider that I have reviewed so far that offered this service. So how is this particular offering from VPS Deploy performs.
Basic Information and Set Up
As per this post on LowEndBox, here is what you get for 4.99USD:
Although LEA has supplied a discount code for 50% off the first month payment, I did not actually get to use it when I signed up, since the only payment option that was available to me when I signed up was prepaying for 3 months:
One really nice feature of VPSDeploy is the slider they have. I know many offers slider when selecting products, however most of them just simply have a levels and not the specifics. On the other hand, VPSDeploy actually shows the exact configuration of the product at each level, which is something I personally like:
The sign up page is actually on a unsecured HTTP page, however I have to mention that they have customized the WHMCS so that it won’t ask you for domain names.
Also, it is interesting to note that as per this comment, they do not offer RAID on these VPS, which means that if the SSD fails, the VPS is destroyed. Obviously you always have the option to back up and restore data and as per this comment, two Central Backup slots were provided to prevent failure.
The sign up process is quite standard, however, it is really the process that happened after the sign up was quite a pain. A few hours after I have made my payment, I received an email from them asking me the purpose of the VPS and also what I plan to set up on the VPS.
The email was a bit confusing (I hope it is not the work of Google Translate), because it actually said “this validation is not necessary anymore” and yet asked me to reply with the “detailed description”. So am I really supposed to reply the email or am I supposed to ignore it?
After informing them that I would be setting up a LNMP stack on the VPS, I finally got the Welcome email, which is pretty short and sweet:
I received yet another email a few hours later instructing me to make sure VPS is in the A record of a domain name, for which they could ping to make sure I did exactly what I claim. Luckily I have a few spare domains that I can use and I chose one of them, change the A record to point to the IP of the VPS.
I have zero knowledge in Spanish, but could someone please let me know how I can configure a domain that could respond to ping from the Internet and yet the domain name does not have to be valid since “that is valid” is crossed out? I am not really upset by any means, and actually found it pretty amusing. However, I do really wish they would have got someone to read through the emails before sending them out to their new clients.
Finally, after all these are done, I am officially a verified VPSDeploy customer.
I guess you can view things in both ways, on the positive side, this does show VPSDeploy has gone an extra mile to make sure they are not taking some random abusers. However, for a legitimate customer (or someone like me, who would like to test their services), it is quite a bit of hassle, particularly when a lot of times I actually prefer just to leave the box there without installing anything on it just to make sure the VPS is at least more or less stable to start with.
The client area for VPS Deploy is on non-secured HTTP as well, however they do have full control of the VPS available in WHMCS:
Note that although the percentage bar of resources usage are available, the actual graph is not.
Once logged into the SolusVM control panel via either secured or unsecured page, a standard SolusVM control panel page is shown:
As you can see, the hostname has been updated to the domain name which I have pointed the A record to this VPS.
One nice features about VPSDeploy is that they do have 2 Central Backup slots for the VPS server, and it appears to work well:
However, instant rDNS, like most of the other providers, is not available here:
There are quite a few OS templates available from VPSDeploy, and one really good feature about the OS template list is that they have listed very clearly whether the OS template is 32 or 64 bit, which some providers failed to do. Interestingly, there is no CentOS + CPanel (or CPanel DNS Only) template, which is common among the providers. Instead, there is a Direct Admin template with CentOS (64 bit version) and it has also stated clearly that the license cost 10 USD per month extra. Finally, there seems to be a Debian based WordPress template available, although I really wish they have a bit more detail on the Debian version it is based on.
Test on the VPS
As mentioned above, the test VPS comes with 384MB of dedicated RAM, 128MB of Swap and 5GB of hard drive space. As usual, I have installed Debian 6 32 bit for testing purposes. The VPS seems to be based in OVH in France from this reverse IP lookup report:
When the OS template is freshly loaded, about 15MB of RAM was used:
free -m total used free shared buffers cached Mem: 384 31 352 0 0 15 -/+ buffers/cache: 15 368 Swap: 128 0 128
Top output showing the processes running:
top - 18:44:15 up 11 min, 1 user, load average: 0.00, 0.00, 0.00 Tasks: 15 total, 1 running, 14 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 393216k total, 31500k used, 361716k free, 0k buffers Swap: 131072k total, 0k used, 131072k free, 16128k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 627 root 20 0 8544 3028 2472 S 0 0.8 0:00.06 sshd 381 root 20 0 5140 2428 1176 S 0 0.6 0:00.00 apache2 384 www-data 20 0 5140 1848 588 S 0 0.5 0:00.00 apache2 653 root 20 0 2960 1612 1292 S 0 0.4 0:00.00 bash 578 root 20 0 9992 1552 504 S 0 0.4 0:00.00 sendmail-mta 662 root 20 0 2328 1068 876 R 0 0.3 0:00.00 top 593 root 20 0 5488 968 576 S 0 0.2 0:00.00 sshd 403 root 20 0 2288 848 668 S 0 0.2 0:00.00 cron 555 root 20 0 2392 840 672 S 0 0.2 0:00.00 xinetd 355 root 20 0 8668 784 448 S 0 0.2 0:00.00 saslauthd 1 root 20 0 2028 684 588 S 0 0.2 0:00.00 init 370 root 20 0 1736 620 508 S 0 0.2 0:00.00 syslogd 356 root 20 0 8668 384 48 S 0 0.1 0:00.00 saslauthd 2 root 20 0 0 0 0 S 0 0.0 0:00.00 kthreadd/828 3 root 20 0 0 0 0 S 0 0.0 0:00.00 khelper/828
One interesting observation is that in there are two process named kthreadd and khelper running on the VPS, although they consume essentially no resources, I do not think I have actually seen such processes running on a VPS before (or may be I just did not notice them in the previous reviews). Does anyone know what these processes are for?
And as per usual, the htop output for the htop fans:
Slightly more than 400MB of hard drive space were used, which is pretty standard:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 5.0G 409M 4.7G 8% / tmpfs 192M 0 192M 0% /lib/init/rw tmpfs 192M 0 192M 0% /dev/shm
And the inodes are set to pretty standard values:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 2621440 26104 2595336 1% / tmpfs 49152 4 49148 1% /lib/init/rw tmpfs 49152 1 49151 1% /dev/shm
When the full LNMP stack loaded, about 44MB of RAM is used:
free -m total used free shared buffers cached Mem: 384 54 329 0 0 9 -/+ buffers/cache: 44 339 Swap: 128 11 116
And top output showing the processes running:
top - 10:49:45 up 7 days, 11:18, 2 users, load average: 0.00, 0.00, 0.00 Tasks: 25 total, 1 running, 24 sleeping, 0 stopped, 0 zombie Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,100.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 393216k total, 57168k used, 336048k free, 0k buffers Swap: 131072k total, 11868k used, 119204k free, 10768k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 29342 www 20 0 15424 9876 96 S 0 2.5 0:00.14 nginx 29252 www 20 0 24496 3972 4 S 0 1.0 0:00.12 php-cgi 29257 www 20 0 24260 3784 8 S 0 1.0 0:00.22 php-cgi 29255 www 20 0 23960 3704 48 S 0 0.9 0:00.30 php-cgi 29254 www 20 0 23960 3404 8 S 0 0.9 0:00.25 php-cgi 21931 root 20 0 8544 3016 2472 S 0 0.8 0:00.07 sshd 29253 www 20 0 22932 2020 8 S 0 0.5 0:00.12 php-cgi 21933 root 20 0 2960 1620 1296 S 0 0.4 0:00.00 bash 21940 root 20 0 2328 1072 880 R 0 0.3 0:00.00 top 29249 root 20 0 22616 816 48 S 0 0.2 1:46.30 php-cgi 16315 root 20 0 8676 708 136 S 0 0.2 0:10.41 sshd 578 root 20 0 9992 428 280 S 0 0.1 0:12.75 sendmail-mta 370 root 20 0 1736 340 236 S 0 0.1 0:00.81 syslogd 593 root 20 0 5488 312 204 S 0 0.1 0:00.12 sshd 16317 root 20 0 2960 304 4 S 0 0.1 0:00.01 bash 403 root 20 0 2288 212 148 S 0 0.1 0:00.60 cron 3302 mysql 20 0 34136 208 0 S 0 0.1 0:00.01 mysqld
And htop output:
About 1.6GB of hard drive space were used:
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 5.0G 1.6G 3.5G 32% / tmpfs 192M 0 192M 0% /lib/init/rw tmpfs 192M 0 192M 0% /dev/shm
Uptime shows the VPS is really stable since I have received them, and is basically idle:
uptime 10:48:37 up 7 days, 11:16, 2 users, load average: 0.00, 0.00, 0.00
VMStat shows pretty big idle percentage as well:
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 11868 336940 0 10476 0 0 5 9 0 10 2 1 97 1
It is also interesting to note that the beancounters values have reasonable held and maxheld values, however the barrier is really high:
cat /proc/user_beancounters Version: 2.5 uid resource held maxheld barrier limit failcnt 828: kmemsize 7136012 114257920 9223372036854775807 9223372036854775807 0 lockedpages 0 0 9223372036854775807 9223372036854775807 0 privvmpages 19850 102819 9223372036854775807 9223372036854775807 0 shmpages 1282 1298 9223372036854775807 9223372036854775807 0 dummy 0 0 0 0 0 numproc 26 141 9223372036854775807 9223372036854775807 0 physpages 11425 98304 0 98304 0 vmguarpages 0 0 9223372036854775807 9223372036854775807 0 oomguarpages 9629 33435 9223372036854775807 9223372036854775807 0 numtcpsock 8 13 9223372036854775807 9223372036854775807 0 numflock 4 9 9223372036854775807 9223372036854775807 0 numpty 2 3 9223372036854775807 9223372036854775807 0 numsiginfo 0 30 9223372036854775807 9223372036854775807 0 tcpsndbuf 157224 351112 9223372036854775807 9223372036854775807 0 tcprcvbuf 131072 3807608 9223372036854775807 9223372036854775807 0 othersockbuf 9248 68952 9223372036854775807 9223372036854775807 0 dgramrcvbuf 0 2576 9223372036854775807 9223372036854775807 0 numothersock 57 62 9223372036854775807 9223372036854775807 0 dcachesize 4038951 106039559 9223372036854775807 9223372036854775807 0 numfile 400 865 9223372036854775807 9223372036854775807 0 dummy 0 0 0 0 0 dummy 0 0 0 0 0 dummy 0 0 0 0 0 numiptent 24 24 9223372036854775807 9223372036854775807 0
This really cause the vzfree value to go beyond reasonable limit:
vzfree Total Used Free Kernel: 8796093022208.00M 6.86M 8796093022201.14M Allocate: 36028797018963968.00M 77.55M 36028797018963892.00M (36028797018963967M Guaranteed) Commit: 36028797018963968.00M 43.33M 36028797018963924.00M (47.0% of Allocated) Swap: -340.01M (-932.4% of Committed)
CPUInfo shows there are 4 cores assigned to the VPS, however the clock speed is limited to 333MHz:
cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 26 model name : Intel(R) Xeon(R) CPU W3520 @ 2.67GHz stepping : 5 cpu MHz : 333.312 cache size : 8192 KB physical id : 0 siblings : 8 core id : 0 cpu cores : 4 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 popcnt lahf_lm ida tpr_shadow vnmi flexpriority ept vpid bogomips : 5333.12 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 26 model name : Intel(R) Xeon(R) CPU W3520 @ 2.67GHz stepping : 5 cpu MHz : 333.312 cache size : 8192 KB physical id : 0 siblings : 8 core id : 1 cpu cores : 4 apicid : 2 initial apicid : 2 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 popcnt lahf_lm ida tpr_shadow vnmi flexpriority ept vpid bogomips : 5332.51 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 6 model : 26 model name : Intel(R) Xeon(R) CPU W3520 @ 2.67GHz stepping : 5 cpu MHz : 333.312 cache size : 8192 KB physical id : 0 siblings : 8 core id : 2 cpu cores : 4 apicid : 4 initial apicid : 4 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 popcnt lahf_lm ida tpr_shadow vnmi flexpriority ept vpid bogomips : 5332.51 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 26 model name : Intel(R) Xeon(R) CPU W3520 @ 2.67GHz stepping : 5 cpu MHz : 333.312 cache size : 8192 KB physical id : 0 siblings : 8 core id : 3 cpu cores : 4 apicid : 6 initial apicid : 6 fpu : yes fpu_exception : yes cpuid level : 11 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm dca sse4_1 sse4_2 popcnt lahf_lm ida tpr_shadow vnmi flexpriority ept vpid bogomips : 5332.51 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management:
Although I was happy with the 4 cores, I certainly do not see too much benefit of offering 4 cores at such a low clock speed than one single core at 1.33GHz. This actually reminded me of a VPS provider in UK (I shall not name the company), which, recently offered his customers a “cloud” platform that has four cores at…100MHz, what a joke!
However, I have to give VPSDeploy the credit for being so honest even with the CPU priority. Most of the time, providers just mentioned “shared” CPU cores. However, for most of the proiders (if not all of them), the “share” is not necessarily equal, and the customers paying more cash every month gets priority with the CPU over customers who are paying less, which is set by the CPU Units. Therefore, even though some providers promises things like eight CPU cores, eseentially what you can get is perhaps way less than a single core if the CPU Units (i.e., relative weighting) of your VPS is set to really low, or if you are sharing the CPU with many customers who are paying the big bucks. From that perspective, I definitely think VPSDeploy deserves some appreciation for its honesty.
Interestingly, the output of meminfo is actually pretty “normal”, I thought the meminfo is partially derived from beancounters as well, but I guess it is definitely not true in this case.
cat /proc/meminfo MemTotal: 393216 kB MemFree: 1080 kB Cached: 379056 kB Active: 4012 kB Inactive: 376156 kB Active(anon): 336 kB Inactive(anon): 776 kB Active(file): 3676 kB Inactive(file): 375380 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 131072 kB SwapFree: 92372 kB Dirty: 0 kB AnonPages: 1112 kB Shmem: 5128 kB Slab: 6904 kB SReclaimable: 3880 kB SUnreclaim: 3024 kB
Time sync value is pretty good:
time sync real 0m0.109s user 0m0.001s sys 0m0.089s
For this particular SSD VPS offers, the part that interested me the most is the disk I/O, and indeed VPSDeploy did not disappoint me on this. The dd test went well above 100MB/s:
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, 6.68217 s, 161 MB/s
Testing again showed even close to 200MB/s:
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, 5.40167 s, 199 MB/s
The first ioping values is a little unstable initially, however it quickly becomes very stable:
ioping -c 10 . 4096 bytes from . (simfs /vz/private/828): request=1 time=1.8 ms 4096 bytes from . (simfs /vz/private/828): request=2 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=3 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=4 time=0.2 ms 4096 bytes from . (simfs /vz/private/828): request=5 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=6 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=7 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=8 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=9 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=10 time=0.3 ms --- . (simfs /vz/private/828) ioping statistics --- 10 requests completed in 9005.8 ms, 2333 iops, 9.1 mb/s min/avg/max/mdev = 0.2/0.4/1.8/0.5 ms
Testing again shows stable ioping:
ioping -c 10 . 4096 bytes from . (simfs /vz/private/828): request=1 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=2 time=0.2 ms 4096 bytes from . (simfs /vz/private/828): request=3 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=4 time=0.2 ms 4096 bytes from . (simfs /vz/private/828): request=5 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=6 time=0.2 ms 4096 bytes from . (simfs /vz/private/828): request=7 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=8 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=9 time=0.3 ms 4096 bytes from . (simfs /vz/private/828): request=10 time=0.3 ms --- . (simfs /vz/private/828) ioping statistics --- 10 requests completed in 9004.3 ms, 3715 iops, 14.5 mb/s min/avg/max/mdev = 0.2/0.3/0.3/0.0 ms
Network speed is something else that actually impressed me:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2012-01-14 10:52:04-- http://cachefly.cachefly.net/100mb.test Resolving cachefly.cachefly.net... 205.234.175.175 Connecting to cachefly.cachefly.net|205.234.175.175|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[=============================================================================>] 104,857,600 23.0M/s in 5.8s 2012-01-14 10:52:10 (17.2 MB/s) - `/dev/null' saved [104857600/104857600]
Not impressive enough? Testing again showed even better results:
wget cachefly.cachefly.net/100mb.test -O /dev/null --2012-01-14 10:52:35-- 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 28.4M/s in 4.0s 2012-01-14 10:52:39 (24.9 MB/s) - `/dev/null' saved [104857600/104857600]
There was actually a little hiccup when I tested the upload speed of this VPS, when I first downloaded the 100mb test file from this VPS to my test VPS at BuffaloVPS in Chicago, IL, I actually received a pretty disappointing speed:
wget 176.31.80.198/100mb.test -O /dev/null --2012-01-13 22:35:48-- http://176.31.80.198/100mb.test Connecting to 176.31.80.198:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 120K/s in 14m 51s 2012-01-13 22:50:39 (115 KB/s) - `/dev/null' saved [104857600/104857600]
This was pretty slow and I decided to give it another shot:
wget 176.31.80.198/100mb.test -O /dev/null --2012-01-13 22:57:11-- http://176.31.80.198/100mb.test Connecting to 176.31.80.198:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 10.2M/s in 19s 2012-01-13 22:57:31 (5.29 MB/s) - `/dev/null' saved [104857600/104857600]
Although not fast, but 5.3MB/s is definitely acceptable for the VPS, way better than 115KB/s.
Next is from a BuyVM VPS in San Jose, CA:
wget 176.31.80.198/100mb.test -O /dev/null --2012-01-13 22:34:24-- http://176.31.80.198/100mb.test Connecting to 176.31.80.198:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 2.43M/s in 44s 2012-01-13 22:35:08 (2.26 MB/s) - `/dev/null' saved [104857600/104857600]
And finally, my Quickweb VPS in London, UK:
wget 176.31.80.198/100mb.test -O /dev/null --2012-01-13 22:56:43-- http://176.31.80.198/100mb.test Connecting to 176.31.80.198:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `/dev/null' 100%[======================================>] 104,857,600 18.0M/s in 6.3s 2012-01-13 22:56:49 (15.8 MB/s) - `/dev/null' saved [104857600/104857600]
Note how fast the download speed is with my London VPS!
For benchmarking, I guess most of you probably have guessed that the results won’t be too impressive due to the limited VPU resources. Indeed that is the case. Actually Unixbench is somewhat penalizing servers with multiple CPU cores but limited resources for each core. Therefore, I do think this VPS would have got a much better score if it was a single-core CPU with 1.33GHz of clock speed:
# # # # # # # ##### ###### # # #### # # # # ## # # # # # # # ## # # # # # # # # # # # ## ##### ##### # # # # ###### # # # # # # ## # # # # # # # # # # # # ## # # # # # # # ## # # # # #### # # # # # ##### ###### # # #### # # 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: ***************: GNU/Linux OS: GNU/Linux -- 2.6.32-042stab044.11 -- #1 SMP Wed Dec 14 16:02:00 MSK 2011 Machine: i686 (unknown) Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968") CPU 0: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5333.1 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 1: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 2: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 3: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization 23:36:30 up 1 day, 4 min, 1 user, load average: 0.45, 0.70, 0.50; runlevel 2 ------------------------------------------------------------------------ Benchmark Run: Sat Jan 07 2012 23:36:30 - 00:09:11 4 CPUs in system; running 1 parallel copy of tests Dhrystone 2 using register variables 6607277.5 lps (10.0 s, 7 samples) Double-Precision Whetstone 2598.3 MWIPS (10.1 s, 7 samples) Execl Throughput 1945.6 lps (29.5 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 242888.9 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 71378.6 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 640171.6 KBps (30.0 s, 2 samples) Pipe Throughput 409098.1 lps (10.0 s, 7 samples) Pipe-based Context Switching 102182.8 lps (10.0 s, 7 samples) Process Creation 5096.6 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2138.8 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 314.9 lpm (60.1 s, 2 samples) System Call Overhead 335608.0 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 6607277.5 566.2 Double-Precision Whetstone 55.0 2598.3 472.4 Execl Throughput 43.0 1945.6 452.5 File Copy 1024 bufsize 2000 maxblocks 3960.0 242888.9 613.4 File Copy 256 bufsize 500 maxblocks 1655.0 71378.6 431.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 640171.6 1103.7 Pipe Throughput 12440.0 409098.1 328.9 Pipe-based Context Switching 4000.0 102182.8 255.5 Process Creation 126.0 5096.6 404.5 Shell Scripts (1 concurrent) 42.4 2138.8 504.4 Shell Scripts (8 concurrent) 6.0 314.9 524.8 System Call Overhead 15000.0 335608.0 223.7 ======== System Benchmarks Index Score 451.2 ------------------------------------------------------------------------ Benchmark Run: Sun Jan 08 2012 00:09:11 - 00:52:34 4 CPUs in system; running 4 parallel copies of tests Dhrystone 2 using register variables 6666695.4 lps (10.0 s, 7 samples) Double-Precision Whetstone 10311.3 MWIPS (10.1 s, 7 samples) Execl Throughput 1994.4 lps (29.5 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 231596.1 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 61783.3 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 637929.5 KBps (30.0 s, 2 samples) Pipe Throughput 442765.3 lps (10.2 s, 7 samples) Pipe-based Context Switching 96496.9 lps (10.0 s, 7 samples) Process Creation 5088.7 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2282.0 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 309.9 lpm (60.5 s, 2 samples) System Call Overhead 322973.5 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 6666695.4 571.3 Double-Precision Whetstone 55.0 10311.3 1874.8 Execl Throughput 43.0 1994.4 463.8 File Copy 1024 bufsize 2000 maxblocks 3960.0 231596.1 584.8 File Copy 256 bufsize 500 maxblocks 1655.0 61783.3 373.3 File Copy 4096 bufsize 8000 maxblocks 5800.0 637929.5 1099.9 Pipe Throughput 12440.0 442765.3 355.9 Pipe-based Context Switching 4000.0 96496.9 241.2 Process Creation 126.0 5088.7 403.9 Shell Scripts (1 concurrent) 42.4 2282.0 538.2 Shell Scripts (8 concurrent) 6.0 309.9 516.6 System Call Overhead 15000.0 322973.5 215.3 ======== System Benchmarks Index Score 500.6
Testing again pretty much showed the same:
# # # # # # # ##### ###### # # #### # # # # ## # # # # # # # ## # # # # # # # # # # # ## ##### ##### # # # # ###### # # # # # # ## # # # # # # # # # # # # ## # # # # # # # ## # # # # #### # # # # # ##### ###### # # #### # # 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: ***************: GNU/Linux OS: GNU/Linux -- 2.6.32-042stab044.11 -- #1 SMP Wed Dec 14 16:02:00 MSK 2011 Machine: i686 (unknown) Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968") CPU 0: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5333.1 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 1: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 2: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization CPU 3: Intel(R) Xeon(R) CPU W3520 @ 2.67GHz (5332.5 bogomips) Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSCALL/SYSRET, Intel virtualization 01:11:39 up 1 day, 1:39, 2 users, load average: 0.00, 0.29, 2.20; runlevel 2 ------------------------------------------------------------------------ Benchmark Run: Sun Jan 08 2012 01:11:39 - 01:44:07 4 CPUs in system; running 1 parallel copy of tests Dhrystone 2 using register variables 6710685.9 lps (10.0 s, 7 samples) Double-Precision Whetstone 2508.1 MWIPS (10.0 s, 7 samples) Execl Throughput 2115.7 lps (29.8 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 240347.3 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 71531.1 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 636483.9 KBps (30.0 s, 2 samples) Pipe Throughput 443150.7 lps (10.0 s, 7 samples) Pipe-based Context Switching 103007.2 lps (10.0 s, 7 samples) Process Creation 5074.6 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2288.5 lpm (60.0 s, 2 samples) Shell Scripts (8 concurrent) 314.0 lpm (60.1 s, 2 samples) System Call Overhead 337702.0 lps (10.0 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 6710685.9 575.0 Double-Precision Whetstone 55.0 2508.1 456.0 Execl Throughput 43.0 2115.7 492.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 240347.3 606.9 File Copy 256 bufsize 500 maxblocks 1655.0 71531.1 432.2 File Copy 4096 bufsize 8000 maxblocks 5800.0 636483.9 1097.4 Pipe Throughput 12440.0 443150.7 356.2 Pipe-based Context Switching 4000.0 103007.2 257.5 Process Creation 126.0 5074.6 402.7 Shell Scripts (1 concurrent) 42.4 2288.5 539.7 Shell Scripts (8 concurrent) 6.0 314.0 523.4 System Call Overhead 15000.0 337702.0 225.1 ======== System Benchmarks Index Score 458.9 ------------------------------------------------------------------------ Benchmark Run: Sun Jan 08 2012 01:44:07 - 02:28:17 4 CPUs in system; running 4 parallel copies of tests Dhrystone 2 using register variables 6875484.8 lps (10.1 s, 7 samples) Double-Precision Whetstone 10366.3 MWIPS (10.2 s, 7 samples) Execl Throughput 1840.6 lps (29.7 s, 2 samples) File Copy 1024 bufsize 2000 maxblocks 232548.2 KBps (30.0 s, 2 samples) File Copy 256 bufsize 500 maxblocks 65234.3 KBps (30.0 s, 2 samples) File Copy 4096 bufsize 8000 maxblocks 639607.3 KBps (30.0 s, 2 samples) Pipe Throughput 443098.3 lps (10.2 s, 7 samples) Pipe-based Context Switching 96136.5 lps (10.0 s, 7 samples) Process Creation 5150.7 lps (30.0 s, 2 samples) Shell Scripts (1 concurrent) 2219.4 lpm (60.1 s, 2 samples) Shell Scripts (8 concurrent) 296.7 lpm (60.4 s, 2 samples) System Call Overhead 328248.9 lps (10.2 s, 7 samples) System Benchmarks Index Values BASELINE RESULT INDEX Dhrystone 2 using register variables 116700.0 6875484.8 589.2 Double-Precision Whetstone 55.0 10366.3 1884.8 Execl Throughput 43.0 1840.6 428.0 File Copy 1024 bufsize 2000 maxblocks 3960.0 232548.2 587.2 File Copy 256 bufsize 500 maxblocks 1655.0 65234.3 394.2 File Copy 4096 bufsize 8000 maxblocks 5800.0 639607.3 1102.8 Pipe Throughput 12440.0 443098.3 356.2 Pipe-based Context Switching 4000.0 96136.5 240.3 Process Creation 126.0 5150.7 408.8 Shell Scripts (1 concurrent) 42.4 2219.4 523.5 Shell Scripts (8 concurrent) 6.0 296.7 494.5 System Call Overhead 15000.0 328248.9 218.8 ======== System Benchmarks Index Score 499.4
Geekbench tests is actually more reasonable:
System Information Platform: Linux x86 (32-bit) Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33) Operating System: Linux 2.6.32-042stab044.11 i686 Model: Linux PC (Intel Xeon W3520) Motherboard: Unknown Motherboard Processor: Intel Xeon W3520 Processor ID: GenuineIntel Family 6 Model 26 Stepping 5 Logical Processors: 4 Physical Processors: 1 Processor Frequency: 333 MHz L1 Instruction Cache: 0.00 B L1 Data Cache: 0.00 B L2 Cache: 256 KB L3 Cache: 0.00 B Bus Frequency: 0.00 Hz Memory: 384 MB Memory Type: N/A SIMD: 1 BIOS: N/A Processor Model: Intel Xeon W3520 Processor Cores: 4 Integer Blowfish single-threaded scalar 1534 |||||| multi-threaded scalar 999 ||| Text Compress single-threaded scalar 1026 |||| multi-threaded scalar 972 ||| Text Decompress single-threaded scalar 941 ||| multi-threaded scalar 1040 |||| Image Compress single-threaded scalar 862 ||| multi-threaded scalar 813 ||| Image Decompress single-threaded scalar 945 ||| multi-threaded scalar 797 ||| Lua single-threaded scalar 1565 |||||| multi-threaded scalar 1553 |||||| Floating Point Mandelbrot single-threaded scalar 1148 |||| multi-threaded scalar 1136 |||| Dot Product single-threaded scalar 1726 |||||| multi-threaded scalar 1857 ||||||| single-threaded vector 2728 |||||||||| multi-threaded vector 2418 ||||||||| LU Decomposition single-threaded scalar 2288 ||||||||| multi-threaded scalar 2446 ||||||||| Primality Test single-threaded scalar 1743 |||||| multi-threaded scalar 1432 ||||| Sharpen Image single-threaded scalar 3027 |||||||||||| multi-threaded scalar 2999 ||||||||||| Blur Image single-threaded scalar 2739 |||||||||| multi-threaded scalar 2715 |||||||||| Memory Read Sequential single-threaded scalar 2465 ||||||||| Write Sequential single-threaded scalar 4224 |||||||||||||||| Stdlib Allocate single-threaded scalar 2431 ||||||||| Stdlib Write single-threaded scalar 3675 |||||||||||||| Stdlib Copy single-threaded scalar 6564 |||||||||||||||||||||||||| Stream Stream Copy single-threaded scalar 3606 |||||||||||||| single-threaded vector 4414 ||||||||||||||||| Stream Scale single-threaded scalar 3167 |||||||||||| single-threaded vector 3801 ||||||||||||||| Stream Add single-threaded scalar 3285 ||||||||||||| single-threaded vector 4066 |||||||||||||||| Stream Triad single-threaded scalar 3094 |||||||||||| single-threaded vector 2669 |||||||||| Integer Score: 1087 |||| Floating Point Score: 2171 |||||||| Memory Score: 3871 ||||||||||||||| Stream Score: 3512 |||||||||||||| Overall Geekbench Score: 2265 |||||||||
And test again:
System Information Platform: Linux x86 (32-bit) Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33) Operating System: Linux 2.6.32-042stab044.11 i686 Model: Linux PC (Intel Xeon W3520) Motherboard: Unknown Motherboard Processor: Intel Xeon W3520 Processor ID: GenuineIntel Family 6 Model 26 Stepping 5 Logical Processors: 4 Physical Processors: 1 Processor Frequency: 333 MHz L1 Instruction Cache: 0.00 B L1 Data Cache: 0.00 B L2 Cache: 256 KB L3 Cache: 0.00 B Bus Frequency: 0.00 Hz Memory: 384 MB Memory Type: N/A SIMD: 1 BIOS: N/A Processor Model: Intel Xeon W3520 Processor Cores: 4 Integer Blowfish single-threaded scalar 1571 |||||| multi-threaded scalar 981 ||| Text Compress single-threaded scalar 1031 |||| multi-threaded scalar 1003 |||| Text Decompress single-threaded scalar 1070 |||| multi-threaded scalar 1048 |||| Image Compress single-threaded scalar 903 ||| multi-threaded scalar 772 ||| Image Decompress single-threaded scalar 785 ||| multi-threaded scalar 771 ||| Lua single-threaded scalar 1508 |||||| multi-threaded scalar 1353 ||||| Floating Point Mandelbrot single-threaded scalar 1117 |||| multi-threaded scalar 1126 |||| Dot Product single-threaded scalar 1378 ||||| multi-threaded scalar 1472 ||||| single-threaded vector 1540 |||||| multi-threaded vector 1545 |||||| LU Decomposition single-threaded scalar 1472 ||||| multi-threaded scalar 1621 |||||| Primality Test single-threaded scalar 1690 |||||| multi-threaded scalar 1346 ||||| Sharpen Image single-threaded scalar 3080 |||||||||||| multi-threaded scalar 2810 ||||||||||| Blur Image single-threaded scalar 2404 ||||||||| multi-threaded scalar 2382 ||||||||| Memory Read Sequential single-threaded scalar 2172 |||||||| Write Sequential single-threaded scalar 4127 |||||||||||||||| Stdlib Allocate single-threaded scalar 1731 |||||| Stdlib Write single-threaded scalar 4042 |||||||||||||||| Stdlib Copy single-threaded scalar 7572 |||||||||||||||||||||||||||||| Stream Stream Copy single-threaded scalar 3748 |||||||||||||| single-threaded vector 4417 ||||||||||||||||| Stream Scale single-threaded scalar 2952 ||||||||||| single-threaded vector 4612 |||||||||||||||||| Stream Add single-threaded scalar 3574 |||||||||||||| single-threaded vector 4616 |||||||||||||||||| Stream Triad single-threaded scalar 3607 |||||||||||||| single-threaded vector 3328 ||||||||||||| Integer Score: 1066 |||| Floating Point Score: 1784 ||||||| Memory Score: 3928 ||||||||||||||| Stream Score: 3856 ||||||||||||||| Overall Geekbench Score: 2168 ||||||||
Overall, the VPS shows good disk I/O and good network speed, however, the limited resources in terms of CPU clock speed definitely hindered the overall performance of this VPS.
Customer Service and Support
My first encounter with their customer service is actually over the validation process. After I replied the email asking me for the domain name pointing to the VPS server at 10:21AM on a Saturday morning (EST), a ticket was created in 4 minutes and they have completed the verification at 10:31AM, which is pretty impressive. However, this is provided it is day time in Europe. I tried to ask them if they could remove the restriction on the CPU resources on a Friday evening and that reply did not come in until the next morning.
Conclusion
One thing I like about writing VPS reviews is that I get to talk (electronically) to people all around the world, and sometimes you get a sneak peek of the business culture through the limited interaction you have with them, which I otherwise would not have a chance to. VPSDeploy is the first Spanish company I have ever reviewed and although the sign up process is a little bit cumbersome and I really wished the initial correspondence from them could be more professional and less confusing (however I do understand the process is to protect regular customers from abusers), the VPS itself, nonetheless, is pretty good. The disk I/O is high (although no RAID set up somehow sounds pretty risky these days) and so is the network. The only drawback is the clock speed of the CPU, which, to me, I would rather have one single core at its full clock speed than 4 cores at 333Mhz. Overall, I am happy with the performance of the VPS and I think VPSDeploy, among other things, are very honest about what they do, which definitely deserves some credit.
I checked out their website and it says the cpu speed is 1333mhz. I find that VERY misleading as they also say 4cores.
4 cores at 333 does not equal 4 cores at 1333 nor does it even equal 1 core at 1333. If you use many single threaded applications on that machine they will be very slow.
What a shame, had so much potential.
@Luma: Completely agree, I am really not sure what is the rationale of doing it, it is otherwise a really good VPS…
@admin i think you should consider dropping the roman numbers and use normal numbers for the titles of your threads 🙂
Otherwise nice reviews, keep up the good work.
@rds100: Totally agreed 🙂 Even I started to hate myself for using all the Xs and Is and Vs 🙂 Thanks for the comments and I will start changing things soon 🙂
Enjoyed the read on that one, quite a ‘unique’ signup process.
I have to say I am a little surprised at the write times though, expected higher.
Anthony.
Hi all, now we dont provide more 4x 333Mhz.
The new CPU specs that we provide are full CPU-cores. Minium 1x 2667 Mhz.
Best regards.