New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Prometeus VZ3 384MB 12GB 2TB OpenVZ Benchmark
ErawanArifNugroho
Member
First of all, let me apology for the forgoten promises of benchmark post and also thanks to @prometeus for giving me a vps for running the Benchmark
System: 1 Core 384mb/384mb vswap 12GB 1,95 TB BW Node pm22 Debian 6 32bit 1 IPv4 4 IPv6
Freevps.us
# wget freevps.us/downloads/bench.sh -O - -o /dev/null|bash Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz Number of cores : 1 CPU frequency : 2000.147 MHz Total amount of ram : 384 MB Total amount of swap : 384 MB System uptime : 6:31, Download speed from CacheFly: 54.2MB/s Download speed from Linode, Atlanta GA: 2.79MB/s Download speed from Linode, Dallas, TX: 3.82MB/s Download speed from Linode, Tokyo, JP: 4.24MB/s Download speed from Linode, London, UK: 34.0MB/s Download speed from Leaseweb, Haarlem, NL: 1.87MB/s Download speed from Softlayer, Singapore: 5.24MB/s Download speed from Softlayer, Seattle, WA: 5.37MB/s Download speed from Softlayer, San Jose, CA: 278KB/s Download speed from Softlayer, Washington, DC: 8.46MB/s I/O speed : 551 MB/s
CPU Info :
# cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 45 model name : Intel(R) Xeon(R) CPU E5-2620 0 @ 2.00GHz stepping : 7 cpu MHz : 2000.147 cache size : 15360 KB physical id : 0 siblings : 12 core id : 0 cpu cores : 6 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm dca sse 4_1 sse4_2 x2apic popcnt aes xsave avx lahf_lm ida arat epb xsaveopt pln pts dts tpr_shadow vnmi flexpriority ept vpid bogomips : 4000.29 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management:
Comments
Download test
IO Test :
IOPING :
UnixBench :
Well, I can say this is the best IO I ever meet
Thank you to Mr. Salvatore @prometeus
Thank you very much for your time :-)
This is the same hardware used for the KVM vps until now. :P
Salvatore rocks And has some very nice toys ;-)
Yep, atm the king of eu LEBs IMO. I think same specs would cost 10 times more at a "regular" provider. Add to this his will to help and nice personality...
M
~500MB/s that's insane.
But on KVM euro node is slightly lower, varies between ~100 ~270MB/s.
Probably that one was not in production. If it was...
M
Do you mean the OpenVZ?
Edit: Some souls live on pm22:
Do you mean the one I'm running the benchmark?
Aha But I see it is in production :P
Well, i am curious, how much was the storage ? In Eur.
M
Disks were less than €2K per server if I remember well, 6x600GB SAS2 10K, more or less half the cost of the server itself...
Thanks.
I am thinking that you are subsidizing LEB ppl. Am I right ?
M
No, as I already said somewhere it's more or less an old school business plan with a 2 years ROI as this is not our main income nor we depend on this to survive...
When I started again our online presence with our products (HA VM, Business vps) I had the impression that most people considered Italy like an exotic location, out of the Big Internet, so instead of insisting on selling our old product at a ever more discounted rate only to make people try our service, I asked my wife and my brothers to provide me 4 servers, our old SAN storages and a budget of €25K to start over the "Budget" (low end) line of service.
So the decision was: start from bottom, make people know we can play on par with other host providers and see what can be done in two years.... ;-)
BTW: subsidizing LEB in a place like this is more or less like for a narco trafficant giving away a dose or two in front of schools ;-)
That's so true.
Not really, it is more like giving those in places where addicted live Not all kids in school are addicted yet while we are over here.
M
I think he was refering especially to Prometeus VPSs, not VPSs in general.
well I'm started to be an addict because of him :-\
Yikes, 2 years at full capacity to make a dime of profit? Does that factor in bandwidth? Doesn't seem like that 'plan' can last too long.....
I'm not sure to understand what do you mean... Could you please elaborate?
Sorry for bumping up this thread
It's been the 2nd years of my active vps with Prometeus VZ3, and since the last reboot for patching OpenVZ, my uptime for this vps is 117 days.
Overall, I'm very satisfied with the performance and the stability
A simple system info can be viewed here :
If you need any benchmark or something, please make a comment to this thread
Seriously I was confused reading Mao and uncle Sal asking each other like that...
...until I looked at the date they are posted.
I have one on its KVM, the uptime now is:-
Current Server Time 2013-09-23 21:06:01
Server Uptime 465Day 10Hour 11Minute
Hehe, that's one of the reason I'm moving from OpenVZ to Xen and KVM, for a better uptime
Currently, I'm also having Prometeus Xen Biz and the iwStack, let's wait for another post / benchmark in the next year.
Hehe, I see 500+ MB/s was great speed, now I saw 1.9 GB in Dallas and not many people are so amazed.
Shortly after this I joined Uncle, I think a month or so
May I post another review like this for the Prometeus in Dallas, M?
It would use serverbear script, so I hope it not affecting other users
Go ahead, do you think you are the only one running benchmarks ? It only uses one thread of 8, so no problem, as for io, there is plenty...
This reminds of a joke:
One guy in a taxi:
Hey, may I smoke ?
Sorry sir, this is a no smoking car.
Then what's up with all these ashes from cigarettes ?
They are from the people that didnt ask for permission.