96MB Low End VPS Review Part XI – IPAP.CO
There is perhaps no VPS providers recently (other than the ones almost in the dead-pool, such as Hostrail or W2 Servers) has caused as much controversy as IPAP.Co. Their previous offer on LowEndBox has gathered close to 500 replies. However, they are definitely not satisfied with the amount publicity (positive or negative) that they have received, and this time, they came up with a even more surprising offer on LowEndBox, and for 6.99 USD per month, here is what you expect to receive:
I have to say I really doubt how they could possibly offer this crazy amount of resources at this price. After all, 6.99 would perhaps cover the cost of 2IP + 2GB memory and nothing else. So, I decided to give it a shot myself to see how such a insane plan works.
General and Set Up
The origin of IPAP.CO is truly a mystery, besides a hidden WhoIs, the stuff only identify themselves by “IPAP CO. admin” and there were even, at one point, some speculations that the company is Iran-based, stir even further debates, until one of the “IPAP.CO admin” replied to say that all they have is an exchange office there.
Iranians or not, there is no politics on 96MB.com, just great and not-so-great VPS providers. From this aspect, I have to say IPAP.CO has improved somewhat since their first not-so-successful debut on the low end VPS world. The original design of their website was a free template, probably one of the most common ones you will see among low-end VPS providers, however I think they have learnt to invest a little bit more on their company and switched a template that is not very commonly seen. Although for other offers that they have put up before, it literally took them days, if not weeks, to set up the VPS, the provision for the SuperVPS was instant. My Paypal confirmation was sent at 10:47AM and the VPS was provisioned the very next minute, with root password masked by ***** for security reasons.
After getting some negative feedback for using Blesta initially, they have managed to switch to WHMCS for their billing management/customer support platform. It was pretty much standard set up with no SSL login, however IPAP has enabled controlling VPS in WHMCS platform.
Although I have observed more and more hosts are using this feature, it still pleases me whenever I see something like this. Having SolusVM is obviously nice and powerful, however since most of the providers do not run SolusVM on port 80 and sometimes I can only access Internet via that port, it is a bit pain in the butt for me if I need to do some maintenance on the VPS during the day.
Interestingly, the SolusVM link on their VPS welcome email pointed to http://xxxx:2086, so you can not just click on the link and expect to get to your control panel. However, if you copy and paste the link, which is a non-secured IP address running on port 5353, you will see the SolusVM login.
Other than seeing a crazy amount of resources, there is really no surprise factor, everything is standard SolusVM set up with manual rDNS and non-working Backups.
They have really few varieties of OS template available, just the major CentOS, Ubuntu and Debian templates:
Even for Ubuntu templates, my favourite version, the 10.04 LTS is not available. Instead, I had to use 10.10, which seems to work perfectly.
Tests on the VPS
With an almost insane specifications, and a decent datacenter (although Hetzner one of the cheapest in Europe, if not the world, they provide pretty good services with good connections), I was hoping that this monster could put in some good performance. Needless to say, initially there were a lot of problems at the beginning when the offer first came. In fact, one of the IPAP.CO Admin (assuming they have multiple admins) has even posted an urgent help request after their VePortal was not working and they did not have too much luck getting help from VePortal.
So how are they doing right now?
The test VPS, as mentioned at the beginning of this post, has 2048MB of guaranteed memory and 4096MB of burstable memory, with 12 virtual cores of i7 980 CPU, the CPU list is so long that the screen was half-truncated, however for all 12 cores, the information is pretty much the same:
fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.26 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 2 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 2 cpu cores : 6 apicid : 4 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.43 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 8 cpu cores : 6 apicid : 16 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.09 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 4 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 9 cpu cores : 6 apicid : 18 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.15 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 5 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 10 cpu cores : 6 apicid : 20 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.08 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 6 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 0 cpu cores : 6 apicid : 1 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.14 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 7 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 1 cpu cores : 6 apicid : 3 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.21 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 8 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 2 cpu cores : 6 apicid : 5 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.46 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 9 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 8 cpu cores : 6 apicid : 17 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.19 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 10 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 9 cpu cores : 6 apicid : 19 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.19 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8] processor : 11 vendor_id : GenuineIntel cpu family : 6 model : 44 model name : Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz stepping : 2 cpu MHz : 1112.797 cache size : 12288 KB physical id : 0 siblings : 12 core id : 10 cpu cores : 6 apicid : 21 fpu : yes fpu_exception : yes cpuid level : 11 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 pdpe1gb rdtscp lm constant_tsc ida nonstop_tsc arat pni monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr sse4_1 sse4_2 popcnt lahf_lm bogomips : 6683.19 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual power management: [8]
VZFree, surprisingly, did not show too much sign of heavy overselling:
vzfree
Total Used Free
Kernel: 2048.00M 6.90M 2041.10M
Allocate: 4096.00M 567.36M 3528.64M (2048M Guaranteed)
Commit: 2048.00M 126.13M 1921.87M (21.0% of Allocated)
Swap: 0.00M (0.0% of Committed)
Even with a full LAMP installed from apt with no optimization at all, the box still showed a pretty good RAM usage:
free -m
total used free shared buffers cached
Mem: 4096 566 3529 0 0 0
-/+ buffers/cache: 566 3529
Swap: 0 0 0
And the full top output from when the LAMP stack is installed:
top - 00:39:28 up 2 days, 5:50, 1 user, load average: 0.38, 0.18, 0.07 Tasks: 19 total, 2 running, 17 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: 4194304k total, 580020k used, 3614284k free, 0k buffers Swap: 0k total, 0k used, 0k free, 0k cached PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 9901 www-data 19 0 415m 40m 4044 S 0 1.0 0:02.49 apache2 7500 mysql 23 6 249m 25m 7272 S 0 0.6 0:00.57 mysqld 5351 bind 23 0 216m 24m 2076 S 0 0.6 0:00.00 named 9925 www-data 16 0 187m 17m 4556 S 0 0.4 0:00.08 apache2 9897 root 18 0 178m 9680 4452 S 0 0.2 0:00.16 apache2 9930 www-data 18 0 180m 9484 2312 S 0 0.2 0:00.00 apache2 9934 www-data 18 0 180m 9472 2308 S 0 0.2 0:00.00 apache2 9935 www-data 16 0 180m 9472 2308 S 0 0.2 0:00.00 apache2 9936 www-data 15 0 180m 9472 2308 S 0 0.2 0:00.00 apache2 22383 root 18 0 70628 3380 2632 R 0 0.1 0:00.02 sshd 5435 root 15 0 49268 2684 2124 S 0 0.1 0:00.09 sshd 1655 root 24 8 72080 2092 532 S 0 0.0 0:01.20 sendmail-mta 22394 root 15 0 17856 1928 1444 S 0 0.0 0:00.00 bash 1 root 15 0 23324 1608 1296 S 0 0.0 0:00.10 init 22414 root 15 0 19096 1316 1064 R 0 0.0 0:00.00 top 1141 root 15 0 21084 1020 784 S 0 0.0 0:00.01 cron 5737 root 25 0 19528 976 768 S 0 0.0 0:00.00 xinetd
VMStat indicated tat the VPS was relatively lightly used when the tests are done:
vmstat procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu---- r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 3609300 0 0 0 0 0 0 0 17 0 0 100 0
This was the uptime output when I originally did the data collection process, which showed the node was pretty heavily used:
uptime 00:40:54 up 2 days, 5:52, 1 user, load average: 0.17, 0.16, 0.07
As I was typing this post, however, I decided to give it another shot just for curiosity sake:
uptime 04:48:31 up 13 days, 9:59, 1 user, load average: 0.08, 0.02, 0.01
As you can see, the usage is still pretty high, however has come down quite a bit, presumably due to less users doing heavy lifting to test the servers than initially.
Results of time sync did not sounds too promising:
time sync real 0m7.347s user 0m0.000s sys 0m0.002s
Beancounters shows little restrictions:
cat /proc/user_beancounters
Version: 2.5
uid resource held maxheld barrier limit failcnt
2439: kmemsize 7566234 9166875 2147483646 2147483646 0
lockedpages 0 4 999999 999999 0
privvmpages 152095 168013 1048576 1048576 0
shmpages 658 1362 524288 524288 0
dummy 0 0 0 0 0
numproc 67 74 999999 999999 0
physpages 35998 40637 0 2147483647 0
vmguarpages 0 0 524288 2147483647 0
oomguarpages 35998 40637 524288 2147483647 0
numtcpsock 14 25 7999992 7999992 0
numflock 6 12 999999 999999 0
numpty 1 2 500000 500000 0
numsiginfo 0 3 999999 999999 0
tcpsndbuf 245056 550168 214748160 396774400 0
tcprcvbuf 229376 10335608 214748160 396774400 0
othersockbuf 23280 78024 214748160 396774400 0
dgramrcvbuf 0 16944 214748160 396774400 0
numothersock 16 51 7999992 7999992 0
dcachesize 0 0 2147483646 2147483646 0
numfile 1475 2300 23999976 23999976 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
dummy 0 0 0 0 0
numiptent 18 18 999999 999999 0
And both df -i and df -h output seems to show that at least the disk is not that heavily oversold:
df -i Filesystem Inodes IUsed IFree IUse% Mounted on /dev/simfs 131072000 39060 131032940 1% /
df -h Filesystem Size Used Avail Use% Mounted on /dev/simfs 250G 899M 250G 1% /
Disk I/O was another interesting test, however, it was particularly weird (And if you have any reasons behind it, feel free to comment on), because dd actually gets better and better every time I run it, the first three are running one after another and the last two ran as I typed:
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, 72.5646 s, 14.8 MB/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, 44.078 s, 24.4 MB/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, 41.7715 s, 25.7 MB/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, 26.8778 s, 39.9 MB/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, 13.7178 s, 78.3 MB/s
Although it is still low compare to many of the VPS providers, it has at least go from unusable to somewhat usable.
Download tests showed some pretty decent results:
wget http://cachefly.cachefly.net/100mb.test --2011-06-25 00:38:10-- http://cachefly.cachefly.net/100mb.test Resolving cachefly.cachefly.net... 140.99.93.175, 140.99.93.175 Connecting to cachefly.cachefly.net|140.99.93.175|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `100mb.test' 100%[======================================>] 104,857,600 29.8M/s in 3.4s 2011-06-25 00:38:14 (29.8 MB/s) - `100mb.test' saved [104857600/104857600]
And running it again while typing this article showed the download speed did not slow down a lot after a while, which seems to contradict a popular belief that the download speed will be capped if the entire hardware node hit 10TB every month:
wget http://cachefly.cachefly.net/100mb.test --2011-07-06 05:49:36-- http://cachefly.cachefly.net/100mb.test Resolving cachefly.cachefly.net... 205.234.175.175 Connecting to cachefly.cachefly.net|205.234.175.175|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [application/octet-stream] Saving to: `100mb.test' 100%[======================================>] 104,857,600 43.1M/s in 2.3s 2011-07-06 05:49:39 (43.1 MB/s) - `100mb.test' saved [104857600/104857600]
The download speed are equally impressive. In fact, download results to BuyVM’s VPS in Fremont, CA, is probably one of the best I have observed on the BuyVM box:
wget 46.4.127.16/upfiles/100mb.test --2011-07-06 05:53:26-- http://46.4.127.16/upfiles/100mb.test Connecting to 46.4.127.16:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [text/plain] Saving to: `100mb.test' 100%[======================================>] 104,857,600 11.4M/s in 13s 2011-07-06 05:53:40 (7.73 MB/s) - `100mb.test' saved [104857600/104857600]
On Nix Communication’s VPS in Montreal, Canada, the results are similar:
wget http://46.4.127.16/upfiles/100mb.test --2011-07-05 21:58:27-- http://46.4.127.16/upfiles/100mb.test Connecting to 46.4.127.16:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [text/plain] Saving to: `100mb.test' 100%[======================================>] 104,857,600 10.3M/s in 12s 2011-07-05 21:58:40 (8.19 MB/s) - `100mb.test' saved [104857600/104857600]
Similar results showed from a QualityServers from Tempa, Florida
wget http://46.4.127.16/upfiles/100mb.test --2011-07-06 05:59:55-- http://46.4.127.16/upfiles/100mb.test Connecting to 46.4.127.16:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [text/plain] Saving to: `100mb.test' 100%[======================================>] 104,857,600 8.42M/s in 14s 2011-07-06 06:00:10 (7.06 MB/s) - `100mb.test' saved [104857600/104857600]
I was sort of expecting my Quickweb VPS in London, UK would give a pretty good speed since both are in Europe, and it looks like it is definitely the case!
wget http://46.4.127.16/upfiles/100mb.test --2011-07-05 22:34:53-- http://46.4.127.16/upfiles/100mb.test Connecting to 46.4.127.16:80... connected. HTTP request sent, awaiting response... 200 OK Length: 104857600 (100M) [text/plain] Saving to: `100mb.test' 100%[======================================>] 104,857,600 57.7M/s in 1.7s 2011-07-05 22:34:55 (57.7 MB/s) - `100mb.test' saved [104857600/104857600]
This is indeed a truly impressive upload speed!
Finally the UnixBench results, which, given the fact that it has 12 cores running, offers little surprise factor:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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
12 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
12 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
12 x Execl Throughput 1 2 3
12 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
12 x File Copy 256 bufsize 500 maxblocks 1 2 3
12 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
12 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
12 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
12 x Process Creation 1 2 3
12 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
12 x Shell Scripts (1 concurrent) 1 2 3
12 x Shell Scripts (8 concurrent) 1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: : GNU/Linux
OS: GNU/Linux -- 2.6.18-238.9.1.el5.028stab089.1 -- #1 SMP Thu Apr 14 14:06:0 1 MSD 2011
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.4 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 4: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 5: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 6: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 7: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 8: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.5 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 9: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 10: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 11: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
07:14:21 up 5 days, 12:25, 1 user, load average: 0.15, 0.09, 0.03; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Tue Jun 28 2011 07:14:21 - 07:43:39
12 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 27841016.3 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3875.9 MWIPS (10.0 s, 7 samples)
Execl Throughput 3609.4 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 532745.6 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 166474.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1104785.9 KBps (30.0 s, 2 samples)
Pipe Throughput 1222951.8 lps (10.0 s, 7 samples)
Pipe-based Context Switching 143402.2 lps (10.0 s, 7 samples)
Process Creation 9387.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 5545.4 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2246.4 lpm (60.0 s, 2 samples)
System Call Overhead 1100102.3 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 27841016.3 2385.7
Double-Precision Whetstone 55.0 3875.9 704.7
Execl Throughput 43.0 3609.4 839.4
File Copy 1024 bufsize 2000 maxblocks 3960.0 532745.6 1345.3
File Copy 256 bufsize 500 maxblocks 1655.0 166474.7 1005.9
File Copy 4096 bufsize 8000 maxblocks 5800.0 1104785.9 1904.8
Pipe Throughput 12440.0 1222951.8 983.1
Pipe-based Context Switching 4000.0 143402.2 358.5
Process Creation 126.0 9387.3 745.0
Shell Scripts (1 concurrent) 42.4 5545.4 1307.9
Shell Scripts (8 concurrent) 6.0 2246.4 3744.1
System Call Overhead 15000.0 1100102.3 733.4
========
System Benchmarks Index Score 1108.2
------------------------------------------------------------------------
Benchmark Run: Tue Jun 28 2011 07:43:39 - 08:19:24
12 CPUs in system; running 12 parallel copies of tests
Dhrystone 2 using register variables 93015044.6 lps (10.0 s, 7 samples)
Double-Precision Whetstone 44007.1 MWIPS (10.0 s, 7 samples)
Execl Throughput 12641.0 lps (29.3 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 570411.2 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 153741.7 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1160426.7 KBps (30.0 s, 2 samples)
Pipe Throughput 4175135.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 1207130.2 lps (10.0 s, 7 samples)
Process Creation 35322.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 16586.8 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 2730.7 lpm (60.1 s, 2 samples)
System Call Overhead 3709574.4 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 93015044.6 7970.4
Double-Precision Whetstone 55.0 44007.1 8001.3
Execl Throughput 43.0 12641.0 2939.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 570411.2 1440.4
File Copy 256 bufsize 500 maxblocks 1655.0 153741.7 929.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 1160426.7 2000.7
Pipe Throughput 12440.0 4175135.9 3356.2
Pipe-based Context Switching 4000.0 1207130.2 3017.8
Process Creation 126.0 35322.7 2803.4
Shell Scripts (1 concurrent) 42.4 16586.8 3912.0
Shell Scripts (8 concurrent) 6.0 2730.7 4551.2
System Call Overhead 15000.0 3709574.4 2473.0
========
System Benchmarks Index Score 3041.8
As you may have guessed, I decided to run the test one more time as I am typing, again, just for curiosity sake:
# # # # # # # ##### ###### # # #### # #
# # ## # # # # # # # ## # # # # #
# # # # # # ## ##### ##### # # # # ######
# # # # # # ## # # # # # # # # #
# # # ## # # # # # # # ## # # # #
#### # # # # # ##### ###### # # #### # #
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
12 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10
12 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10
12 x Execl Throughput 1 2 3
12 x File Copy 1024 bufsize 2000 maxblocks 1 2 3
12 x File Copy 256 bufsize 500 maxblocks 1 2 3
12 x File Copy 4096 bufsize 8000 maxblocks 1 2 3
12 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10
12 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10
12 x Process Creation 1 2 3
12 x System Call Overhead 1 2 3 4 5 6 7 8 9 10
12 x Shell Scripts (1 concurrent) 1 2 3
12 x Shell Scripts (8 concurrent) 1 2 3
========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)
System: : GNU/Linux
OS: GNU/Linux -- 2.6.18-238.9.1.el5.028stab089.1 -- #1 SMP Thu Apr 14 14:06:01 MSD 2011
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.4 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 4: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 5: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 6: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.1 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 7: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 8: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.5 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 9: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 10: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 11: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz (6683.2 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
05:45:24 up 13 days, 10:56, 1 user, load average: 0.08, 0.02, 0.01; runlevel 2
------------------------------------------------------------------------
Benchmark Run: Wed Jul 06 2011 05:45:25 - 06:15:39
12 CPUs in system; running 1 parallel copy of tests
Dhrystone 2 using register variables 27566964.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3896.0 MWIPS (9.9 s, 7 samples)
Execl Throughput 3796.0 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 466694.4 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 156305.3 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 902497.0 KBps (30.0 s, 2 samples)
Pipe Throughput 1244689.6 lps (10.0 s, 7 samples)
Pipe-based Context Switching 156284.6 lps (10.0 s, 7 samples)
Process Creation 9635.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 4789.3 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1821.1 lpm (60.0 s, 2 samples)
System Call Overhead 1104575.5 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 27566964.1 2362.2
Double-Precision Whetstone 55.0 3896.0 708.4
Execl Throughput 43.0 3796.0 882.8
File Copy 1024 bufsize 2000 maxblocks 3960.0 466694.4 1178.5
File Copy 256 bufsize 500 maxblocks 1655.0 156305.3 944.4
File Copy 4096 bufsize 8000 maxblocks 5800.0 902497.0 1556.0
Pipe Throughput 12440.0 1244689.6 1000.6
Pipe-based Context Switching 4000.0 156284.6 390.7
Process Creation 126.0 9635.0 764.7
Shell Scripts (1 concurrent) 42.4 4789.3 1129.5
Shell Scripts (8 concurrent) 6.0 1821.1 3035.2
System Call Overhead 15000.0 1104575.5 736.4
========
System Benchmarks Index Score 1056.4
------------------------------------------------------------------------
Benchmark Run: Wed Jul 06 2011 06:15:39 - 06:53:00
12 CPUs in system; running 12 parallel copies of tests
Dhrystone 2 using register variables 93314480.5 lps (10.0 s, 7 samples)
Double-Precision Whetstone 44268.2 MWIPS (10.0 s, 7 samples)
Execl Throughput 12835.4 lps (29.7 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 477837.8 KBps (30.1 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 225744.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1235396.5 KBps (30.3 s, 2 samples)
Pipe Throughput 4305587.0 lps (10.0 s, 7 samples)
Pipe-based Context Switching 1263281.2 lps (10.0 s, 7 samples)
Process Creation 38401.1 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 17314.9 lpm (60.3 s, 2 samples)
Shell Scripts (8 concurrent) 2407.4 lpm (60.1 s, 2 samples)
System Call Overhead 3846332.1 lps (10.0 s, 7 samples)
System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 93314480.5 7996.1
Double-Precision Whetstone 55.0 44268.2 8048.8
Execl Throughput 43.0 12835.4 2985.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 477837.8 1206.7
File Copy 256 bufsize 500 maxblocks 1655.0 225744.1 1364.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 1235396.5 2130.0
Pipe Throughput 12440.0 4305587.0 3461.1
Pipe-based Context Switching 4000.0 1263281.2 3158.2
Process Creation 126.0 38401.1 3047.7
Shell Scripts (1 concurrent) 42.4 17314.9 4083.7
Shell Scripts (8 concurrent) 6.0 2407.4 4012.4
System Call Overhead 15000.0 3846332.1 2564.2
========
System Benchmarks Index Score 3146.8
Finally, in order to satisfy all the GeekBench fans, I actually reloaded the OS template to run the GeekBench tests.
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Ubuntu 10.10 2.6.18-238.9.1.el5.028stab089.1 i686
Model: Linux PC (Intel(R) Core(TM) i7 CPU X 980 @ 3 .33GHz)
Motherboard: Unknown Motherboard
Processor: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz
Processor ID: GenuineIntel Family 6 Model 44 Stepping 2
Logical Processors: 12
Physical Processors: 1
Processor Frequency: 1.11 GHz
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: 23.5 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz
Processor Cores: 12
Integer
Blowfish
single-threaded scalar 2344 |||||||||
multi-threaded scalar 11781 ||||||||||||||||||||||||||||||||||||||||||||| ||
Text Compress
single-threaded scalar 2415 |||||||||
multi-threaded scalar 8102 ||||||||||||||||||||||||||||||||
Text Decompress
single-threaded scalar 2128 ||||||||
multi-threaded scalar 9027 ||||||||||||||||||||||||||||||||||||
Image Compress
single-threaded scalar 2138 ||||||||
multi-threaded scalar 8099 ||||||||||||||||||||||||||||||||
Image Decompress
single-threaded scalar 1459 |||||
multi-threaded scalar 6834 |||||||||||||||||||||||||||
Lua
single-threaded scalar 3777 |||||||||||||||
multi-threaded scalar 12273 |||||||||||||||||||||||||||||||||||||||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 2881 |||||||||||
multi-threaded scalar 13851 |||||||||||||||||||||||||||||||||||||||||||||||||||||||
Dot Product
single-threaded scalar 4454 |||||||||||||||||
multi-threaded scalar 13956 |||||||||||||||||||||||||||||||||||||||||||||||||||||||
single-threaded vector 5459 |||||||||||||||||||||
multi-threaded vector 17730 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LU Decomposition
single-threaded scalar 3266 |||||||||||||
multi-threaded scalar 7147 ||||||||||||||||||||||||||||
Primality Test
single-threaded scalar 3955 |||||||||||||||
multi-threaded scalar 11945 |||||||||||||||||||||||||||||||||||||||||||||||
Sharpen Image
single-threaded scalar 4593 ||||||||||||||||||
multi-threaded scalar 22167 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 6568 ||||||||||||||||||||||||||
multi-threaded scalar 21209 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 5198 ||||||||||||||||||||
Write Sequential
single-threaded scalar 8681 ||||||||||||||||||||||||||||||||||
Stdlib Allocate
single-threaded scalar 4960 |||||||||||||||||||
Stdlib Write
single-threaded scalar 4220 ||||||||||||||||
Stdlib Copy
single-threaded scalar 8227 ||||||||||||||||||||||||||||||||
Stream
Stream Copy
single-threaded scalar 5983 |||||||||||||||||||||||
single-threaded vector 5876 |||||||||||||||||||||||
Stream Scale
single-threaded scalar 5503 ||||||||||||||||||||||
single-threaded vector 5900 |||||||||||||||||||||||
Stream Add
single-threaded scalar 4804 |||||||||||||||||||
single-threaded vector 4212 ||||||||||||||||
Stream Triad
single-threaded scalar 4392 |||||||||||||||||
single-threaded vector 5098 ||||||||||||||||||||
Integer Score: 5864 |||||||||||||||||||||||
Floating Point Score: 9941 |||||||||||||||||||||||||||||||||||||||
Memory Score: 6257 |||||||||||||||||||||||||
Stream Score: 5221 ||||||||||||||||||||
Overall Geekbench Score: 7305 |||||||||||||||||||||||||||||
And the second time, the results are almost equally good:
System Information
Platform: Linux x86 (32-bit)
Compiler: GCC 4.1.2 20070925 (Red Hat 4.1.2-33)
Operating System: Ubuntu 10.10 2.6.18-238.9.1.el5.028stab089.1 i686
Model: Linux PC (Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz)
Motherboard: Unknown Motherboard
Processor: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz
Processor ID: GenuineIntel Family 6 Model 44 Stepping 2
Logical Processors: 12
Physical Processors: 1
Processor Frequency: 1.11 GHz
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: 23.5 GB
Memory Type: N/A
SIMD: 1
BIOS: N/A
Processor Model: Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz
Processor Cores: 12
Integer
Blowfish
single-threaded scalar 2366 |||||||||
multi-threaded scalar 10298 |||||||||||||||||||||||||||||||||||||||||
Text Compress
single-threaded scalar 2488 |||||||||
multi-threaded scalar 8124 ||||||||||||||||||||||||||||||||
Text Decompress
single-threaded scalar 2613 ||||||||||
multi-threaded scalar 8971 |||||||||||||||||||||||||||||||||||
Image Compress
single-threaded scalar 2231 ||||||||
multi-threaded scalar 8208 ||||||||||||||||||||||||||||||||
Image Decompress
single-threaded scalar 1521 ||||||
multi-threaded scalar 6122 ||||||||||||||||||||||||
Lua
single-threaded scalar 3331 |||||||||||||
multi-threaded scalar 11956 |||||||||||||||||||||||||||||||||||||||||||||||
Floating Point
Mandelbrot
single-threaded scalar 2893 |||||||||||
multi-threaded scalar 13105 ||||||||||||||||||||||||||||||||||||||||||||||||||||
Dot Product
single-threaded scalar 4415 |||||||||||||||||
multi-threaded scalar 14030 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||
single-threaded vector 5601 ||||||||||||||||||||||
multi-threaded vector 16546 ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LU Decomposition
single-threaded scalar 1845 |||||||
multi-threaded scalar 8356 |||||||||||||||||||||||||||||||||
Primality Test
single-threaded scalar 4353 |||||||||||||||||
multi-threaded scalar 11911 |||||||||||||||||||||||||||||||||||||||||||||||
Sharpen Image
single-threaded scalar 7079 ||||||||||||||||||||||||||||
multi-threaded scalar 23827 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Blur Image
single-threaded scalar 6600 ||||||||||||||||||||||||||
multi-threaded scalar 20781 |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Memory
Read Sequential
single-threaded scalar 5204 ||||||||||||||||||||
Write Sequential
single-threaded scalar 8021 ||||||||||||||||||||||||||||||||
Stdlib Allocate
single-threaded scalar 3349 |||||||||||||
Stdlib Write
single-threaded scalar 3523 ||||||||||||||
Stdlib Copy
single-threaded scalar 7344 |||||||||||||||||||||||||||||
Stream
Stream Copy
single-threaded scalar 4891 |||||||||||||||||||
single-threaded vector 9253 |||||||||||||||||||||||||||||||||||||
Stream Scale
single-threaded scalar 3678 ||||||||||||||
single-threaded vector 5681 ||||||||||||||||||||||
Stream Add
single-threaded scalar 4082 ||||||||||||||||
single-threaded vector 5369 |||||||||||||||||||||
Stream Triad
single-threaded scalar 3327 |||||||||||||
single-threaded vector 3547 ||||||||||||||
Integer Score: 5685 ||||||||||||||||||||||
Floating Point Score: 10095 ||||||||||||||||||||||||||||||||||||||||
Memory Score: 5488 |||||||||||||||||||||
Stream Score: 4978 |||||||||||||||||||
Overall Geekbench Score: 7118 ||||||||||||||||||||||||||||
In conclusion, the biggest advantage of this box is its fast download speed, although disk I/O is not that great, which is sort of a waste considering the processing power of the box can be quite useful as it is sitting on 12 virtual cores of CPU.
Service and Support
I have to give IPAP.Co some credits in terms of improving service standard. Although tickets have, in general, have been responded within a relatively short period of time, mostly within a few hours, the response are generally along the line of "we will do it!", which is essentially meaningless. It is particularly strange that they seems to really love closing tickets, and Blesta does not have the ability to re-open a ticket after it was closed, so my best record was opening three tickets for the same issue. However, since they are using WHMCS, closed tickets can always be re-opened easily by replying the ticket.
Furthermore, if you need to set up an add-on service, instead of putting in a ticket on WHMCS, you will need to email info AT ipap.co and after emailing them on June 19, I have yet to receive the free backup space as promised.
Conclusion
In the VPS service industry, there is always a saying that “if something is too good to be true, then it perhaps is.” IPAP.CO, unfortunately, could not escape from this. Although the VPS by itself is pretty steady and has good download speed and really strong processing power, it can only be used as-is and do not need any customer service. Hence, I would only recommend it if you need a download box due to the huge hard drive size. However, do note that torrent is prohibited for this service, so make sure you are just downloading from non-torrent places.
dd increases since the data gets cached in the RAID card (assuming there is one). Granted, they would have at least a 512MB cache if they do have an actual raid card so that performance is still very much sub par.
I can attest that from our 8 disk array boxes, even fully loaded, I can blow out 150 – 200MB/sec to the disk.
They recently passed a TOS change to ban all minecraft users, which makes no sense since users pay for 2GB so they should be able to use it.
Francisco
Francisco: Ahh…the caching, although I thought with fdatasync parameters, it should write directly to the disk, I guess that is not the case here huh?
@Francisco: And for Minecraft, I am not sure if you are able to run it anyways with such slow dd, but I did remember reading something about users are not able to control the CPU/memory usage in Java and hence trashing their boxes 🙂
The RAID card still has a cache that the OS isn’t aware of 🙂 fsyncdata expects to be told when the data is actually written and the raid card goes ‘yep its written (to my cache)’.
As for the java thing, you can control RAM by passing it -Xmin -Xmax or something along those lines for the RAM. By default java on OVZ isn’t great, but it just takes a few changes to get past that. For CPU the customers could use ‘cpulimit’, but, if they are bursting in CPU they’ll feel lag.
Francisco
@Francisco: Oh, so this make sense, the fsyncdata only ensure the data are written to the hard drive but not the memory but what happens in the hard drives (i.e., if they are in the RAID card or in the disc) is another story.
I have not exactly played around with Minecraft a lot, but I guess it is definitely controllable via parameters, after all, if a smart phone could run Java (although a slimmed down version for sure), I do not see why a VPS could not. However, I guess given IPAP.co’s technology know-how level, it is hard for them to control so that is perhaps why Minecraft was banned…Sigh, wondering when people will start to offer “unlimited” VPS resources that does not allow you to run anything 🙂
Just wondering,
Is there a problem with it being an iranian company?
It irritates me when people say that, I have gone too iraq twice and the people there are fine. Its not always like they are out to get you…
Thinks like this are what cause wars.
Sorry if I sound harsh, but this intolerance deal pisses me off. I even saw a company that refused a guy due to his name, even though he lived in the US.
Crazy days…