Good question. As I don't know what you want to do exactly, you have a link somewhere explaining it ?Can you try to run vmware type 1 hypervisor and CHR in it virtually?
processor : 3
vendor_id : GenuineIntel
cpu family : 6
model : 55
model name : Intel(R) Celeron(R) CPU J1900 @ 1.99GHz
stepping : 8
microcode : 0x829
cpu MHz : 1332.357
cache size : 1024 KB
physical id : 0
siblings : 4
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 sep 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 nopl xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 movbe popcnt tsc_deadline_timer rdrand lahf_lm 3dnowprefetch ida arat epb dtherm tpr_shadow vnmi flexpriority ept vpid tsc_adjust smep erms
bogomips : 3993.60
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
I don't like to mix things up. The Microserver is our NAS. No Internet access, internal cloud etc.When you have that HP server with VMware, why don't you run RouterOS under VMware on that same server?
Then you don't need the small box at all.
smurphy 2613 0.0 0.2 22996 4896 pts/1 Ss 11:08 0:00 -bash
smurphy 2681 0.0 0.5 116176 10864 ? S 11:11 0:00 /usr/lib/virtualbox/VBoxXPCOMIPCD
smurphy 2686 0.1 0.9 538468 18108 ? Sl 11:11 0:00 /usr/lib/virtualbox/VBoxSVC --auto-shutdown
smurphy 2706 3.6 4.1 1621944 82184 pts/0 Sl+ 11:11 0:20 /usr/lib/virtualbox/VBoxHeadless --startvm Router OS
smurphy 2751 0.0 0.1 19100 2528 pts/1 R+ 11:21 0:00 ps aux
In my opinion the advantage of VMware is that you can draw and construct such a network without limitationsI don't like to mix things up. The Microserver is our NAS. No Internet access, internal cloud etc.When you have that HP server with VMware, why don't you run RouterOS under VMware on that same server?
Then you don't need the small box at all.
Web/Mail Server is again one other dedicated machine, in the Service network.
I then have one device which handles the firewall and separates networks etc.
That's how I think
I can do the same thing with the right hardware too ...In my opinion the advantage of VMware is that you can draw and construct such a network without limitations
on things like network cards, cables, etc. You can define serveral virtual switches for all your
internal networks, connect all your services to it as separate virtual machines having access to one
or more of those networks, and run the router on it as well (having access to the external world and the networks).
For me, it is the ideal solution. For you, apparently not.
I tried. It won't install. As I said before - I suspect not having enough memory in my device (2GB). It loads all modules then tells it will relocate the kernel and everything stops there. Won't continue.smurphy, nice report. Thank you.
Do you think it could be possible you try to install the hypervisor directly on the hardware and test chr in it? It could be better option for you too, even you do not like virtualization for production, you might change your mind...
celeron j1900 is a new generation of atom processor architecture called Silvermont, supports intel VT-x hardware virtualization, another improvement is the evolution form in order execution to out of order improving performance a lot in contrast to anemic previous atomI don't think you will be able to run any modern hypervisor on such boxes that have Intel Atom processor,
but maybe there are ways I don't know about.
its ideal but not optimal,virtualization puts big latency overhead, because that telecom applications still not migrate completely to virtualizationIn my opinion the advantage of VMware is that you can draw and construct such a network without limitationsI don't like to mix things up. The Microserver is our NAS. No Internet access, internal cloud etc.When you have that HP server with VMware, why don't you run RouterOS under VMware on that same server?
Then you don't need the small box at all.
Web/Mail Server is again one other dedicated machine, in the Service network.
I then have one device which handles the firewall and separates networks etc.
That's how I think
on things like network cards, cables, etc. You can define serveral virtual switches for all your
internal networks, connect all your services to it as separate virtual machines having access to one
or more of those networks, and run the router on it as well (having access to the external world and the networks).
For me, it is the ideal solution. For you, apparently not.
If you guys explain me how to test this, I'll let you know.i thik celeron j1900 and the new j3160 and n3160 are very interesting to use it with routeros because the low power consumption and relative good cpu performance vs mipsbe,powerpc e500v2, an tilera cpus
will be interesting to see what performance can be achieved with this silvermont 4 core CPU on routerOS
That's the point. I don't have a general config. I only have my specialized config... I can compare it, but I don't know if you will be able to make something out of it.well, just use the same config that you can compare with something that is generally known.
thats an issue plaguing the industry, on one side are the marketing folks who love to publish pretty numbers about equipment performance, far from real scenario performance, on the other side we have us, the people who has to deal with surprises about performance in real scenarios.If you guys explain me how to test this, I'll let you know.i thik celeron j1900 and the new j3160 and n3160 are very interesting to use it with routeros because the low power consumption and relative good cpu performance vs mipsbe,powerpc e500v2, an tilera cpus
will be interesting to see what performance can be achieved with this silvermont 4 core CPU on routerOS
Does a regular Test-scheme exist, or a regular configuration for routerOS to use for the speed-tests? Reason I ask - is that on my RB493G's I have around 190 active firewall rules, NAT, Mangle, ~200 Blacklist entries (can go up to 2000 in periods of high script kiddy activities) and some other configurations active. With that they achieve, tested with iperf from one i7 system to one other i7 system 192Mbps max speed if no other activity happens on the network.
I could send you the comparative to my setup, but not to the regular setup's Mikrotik uses.
mikrotik published this page with infoThat's the point. I don't have a general config. I only have my specialized config... I can compare it, but I don't know if you will be able to make something out of it.well, just use the same config that you can compare with something that is generally known.
IMHO, Mikrotik should have some default test router configurations they could provide.
Anyone from Mikrotik reading who could confirm???
Just use the same config you use now and you told that rb493g does 192Mbits. I wonder what will do the J1900 with the same config (maybe will be capped by interfaces, so then what the cpu utilisation will be under the test...That's the point. I don't have a general config. I only have my specialized config... I can compare it, but I don't know if you will be able to make something out of it.well, just use the same config that you can compare with something that is generally known.
IMHO, Mikrotik should have some default test router configurations they could provide.
Anyone from Mikrotik reading who could confirm???
Thx, and to all of you others for the advice (and also the link published by Mikrotik).can be useful to known your config to test it on another equipment
Device 64Bytes CPU Load 512Bytes CPU Load 1518Bytes CPU Load Comment
RB493G 35.3MBits/s 4.00% 283Mbits/s 3.00% 555MBits/s 3.00% Lan 2 Lan / FastPath active
RB493G 35.4MBits/s 34.00% 216Mbits/s 100.00% 233Mbits/s 100.00% Lan 2 Service / FastPath active
Device 64Bytes CPU Load 512Bytes CPU Load 1518Bytes CPU Load Comment
HS-NJ1900FW 35.4MBits/s 0.00% 284Mbits/s 3.00% 302Mbits/s 10.00% Lan 2 Service
HS-NJ1900FW 35.4MBits/s 0.00% 284Mbits/s 0.00% 302Mbits/s 10.00% Lan 2 Service / No filters
20150304_MIN-CentOS6u5-cd_b133_GA-x86_64.iso 100% 699MB 116.6MB/s 00:06
20150304_MIN-CentOS6u5-cd_b133_GA-x86_64.iso 100% 699MB 22.6MB/s 00:31
I admit that you are right, but that is also the reason I have added data on the RB493G, because I don't have the same test environment you have, nor do I know how you perform the measurements, and because you won't test this setup...little note on how to use rfc2544 published results from routerboard.com:
when you want to know how the router will perform, you can compare these numbers between the routers. As RFC is quite strict on what numbers can be reported relative performance should be as stated.
next, when you make test setup - you have reference value that you should get with your own test system. When you have that - add your configuration on the router and with the same method test for the performance. It should scale with the original test result.
Such loging for "general router test" is completely wrong, as there is no defined term to what that "general performance" is and everyone can just paint whatever numbers they wish.