Community discussions

 
rado3105
Member
Member
Topic Author
Posts: 480
Joined: Sat Jan 12, 2008 11:45 pm

rb3011 based on ARM CPU

Sun Mar 29, 2015 8:16 pm

This seems first time Mikrotik uses ARM cpu, will be packages for other boards based on ARM cpu? (like x86 package).
And other interesting thing is Power, it is written that it is 2x more powerfull than rb2011, but this is too little for that specs (dualcore cpu, 2 times higher frequency than rb2011). So why just only 2 times more powerfull?
 
InoX
Forum Guru
Forum Guru
Posts: 1962
Joined: Tue Jan 09, 2007 6:44 pm

Re: rb3011 based on ARM CPU

Sun Mar 29, 2015 8:59 pm

I really hope that is 4x more powerfull than rb2011 as the cpu speed sugest :D
 
nkourtzis
Member Candidate
Member Candidate
Posts: 204
Joined: Tue Dec 11, 2012 12:56 am
Location: Greece

Re: rb3011 based on ARM CPU

Mon Mar 30, 2015 1:24 pm

Performance is not only a matter of clock speed. Actually, it is much, much more than that! Until now, the processors used in MT devices were more like ASICs. ARM is a general-purpose platform, which may not be as efficient in networking-related jobs, but can still perform them adequately and it is much more flexible than highly-specialized chips.

I would guess that this turn (which was rejected by Normis a few months ago but is certainly welcome!) was dictated by cost factors, the vast availability of code for ARM and possibly the future Mikrotik wants for Metarouter.

Kudos to Mikrotik for the choice! Quad core ARM boards would be even nicer, now that RouterOS is largely multithreaded. But we are just in the beginning...
Passionate about networks
Enthusiastic about Mikrotik
MTCNA | MTCRE | MTCINE

No trees were killed to send this message,
but a large number of electrons were terribly inconvenienced.
 
User avatar
NathanA
Forum Veteran
Forum Veteran
Posts: 801
Joined: Tue Aug 03, 2004 9:01 am

Re: rb3011 based on ARM CPU

Tue Mar 31, 2015 11:32 am

[...] will be packages for other boards based on ARM cpu? (like x86 package).
I very much doubt that they will. MikroTik's modus operandi when it comes to different CPU architectures has always been that they license software for generic x86 hardware (probably, at this point, more for historical reasons than anything else; I would be sad but not shocked if, at some point in the future, MikroTik discontinues the practice of licensing RouterOS separately from a hardware sale), but for all other architectures, it only runs on hardware that they make that uses that instruction set. As cool as it would be if they did so, as far as I can tell, MikroTik has no real incentive to try to make RouterOS for ARM run on "generic ARM hardware" since, really, there is no such thing. This means that if they did try to support ARM-based systems that other companies build, they would have to pick and choose which specific boards to support, and they would be spending huge quantities of time and resources to ensure that RouterOS runs on somebody else's board flawlessly even though they have no assurance that they will sell a lot of copies to people who use those boards.
I would guess that this turn (which was rejected by Normis a few months ago but is certainly welcome!) was dictated by cost factors, the vast availability of code for ARM...
I would also guess that in conjunction with your guess about cost factors (and, perhaps more accurately, cost-to-performance ratio factors...I would not be shocked if, at this point, given the fact that ARM is very heavily used in mobile handsets, and that there has been something of an arms race when it comes to mobile CPU performance over the last few years as that market has developed, if an SoC based around ARM that cost about the same as a similarly-spec'd SoC based around MIPS outperforms the MIPS chip), part of this has to do with MikroTik's good (?) relationship with Atheros (which, at this point, is the only 802.11 chipset family that RouterOS supports; MikroTik is in trouble if Atheros ever goes bye-bye), which at this point, as we all know, is owned by Qualcomm. All of the MIPS CPUs that MikroTik has been using since the RB1xx and RB5xx series were discontinued have been built by Atheros, but Qualcomm already had the ARM-based Snapdragon CPU line before the Atheros acquisition. Since MikroTik already gets their wireless chips from Qualcomm, it would not surprise me to learn that there is a Snapdragon CPU under the hood of the RB3011. I think it is also possible (though I readily admit I am just spitballing here) that Qualcomm may be starting to question why they are bothering to build both MIPS and ARM based SoCs when they could be making life simpler for themselves by standardizing on a single architecture across-the-board. MIPS-based Qualcomm SoCs may not be long for this world.

-- Nathan
 
nkourtzis
Member Candidate
Member Candidate
Posts: 204
Joined: Tue Dec 11, 2012 12:56 am
Location: Greece

Re: rb3011 based on ARM CPU

Tue Mar 31, 2015 4:53 pm

This means that if they did try to support ARM-based systems that other companies build, they would have to pick and choose which specific boards to support...
Except if... they actually decide to do that. 8) I wonder, what if their ARM boards are not entirely custom-made, but based on some popular prototype with some additions?
Passionate about networks
Enthusiastic about Mikrotik
MTCNA | MTCRE | MTCINE

No trees were killed to send this message,
but a large number of electrons were terribly inconvenienced.
 
rado3105
Member
Member
Topic Author
Posts: 480
Joined: Sat Jan 12, 2008 11:45 pm

Re: rb3011 based on ARM CPU

Tue Mar 31, 2015 10:55 pm

ARM cpus are the future, have very fast development, power growth per year. They are made in quantities, so the price of made is low....
 
bds1904
Frequent Visitor
Frequent Visitor
Posts: 60
Joined: Tue Sep 10, 2013 2:52 am

Re: rb3011 based on ARM CPU

Wed Apr 01, 2015 1:49 am

Now if we could get a routerboard based on AppliedMicro X-Gene ARMv8-A architecture. 4x 10Gb SFP+, 2-4 1Gbe interfaces, large amount of memory and 8-16 2.4GHz cores.

That would be the stuff!
 
User avatar
NathanA
Forum Veteran
Forum Veteran
Posts: 801
Joined: Tue Aug 03, 2004 9:01 am

Re: rb3011 based on ARM CPU

Wed Apr 01, 2015 3:07 am

Except if... they actually decide to do that. 8) I wonder, what if their ARM boards are not entirely custom-made, but based on some popular prototype with some additions?
There is no way that this is the case. Why would MikroTik suddenly subcontract the hardware design to somebody else when they have been making their own custom boards now for years? They have the staff and the expertise, so there is almost no reason for them not to use it. (Also, just look at the case design of the RB3011. Clearly it is in the exact same shape and has the same port layouts as an RB2011. That is only possible if they designed the RB3011 board.)

An ARM-based RouterBoard is also going to be using a port of RouterBOOT, guaranteed, and RouterBOOT does things a little differently than most other widely-used embedded bootloaders out there. RouterOS on platforms other than x86 is pretty closely tied to RouterBOOT, and RouterBOOT probably wouldn't take kindly to being flashed to some random hardware that it was never designed to run on or recognize.

-- Nathan
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Fri Apr 03, 2015 6:36 pm

I for one would really like to see a 64-bit version of Router OS running on Intel CPUs (and VMware ESXi and AMD and on future Mikrotik products).

This is where the CPU market is rapidly expanding with low cost options and hi-end systems).

Wouldn't it be great to have a Mikrotik multi-threaded 64-bit operating system supporting 256 Gig running full BGP tables - and OSPF and sitting at 3 percent CPU load with many many 10-gig interfaces supported with hundreds of vlans.

Wouldn't it be great to see Mikrotik jump onto the virtual VMware bandwagon also and be known as the high-end router solution over a virtual or physical Cisco router solution.

I just don't think there would be much work to do to support this environment and come out as the best solution for everybody everywhere.
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Thu Apr 09, 2015 3:39 am

Now if we could get a routerboard based on AppliedMicro X-Gene ARMv8-A architecture. 4x 10Gb SFP+, 2-4 1Gbe interfaces, large amount of memory and 8-16 2.4GHz cores.

That would be the stuff!
unlikely thats suits for routers, yet, even with 14nm wafers produced SoC.
both A72(the only ARMv8A-based design, anounced, yet) and pervious A57 and A53 really hungry/hot.
but A53 cores was probably good start. relatively cold and relatively fast.
there was several multi-core and many-core(up to 64x in really mass-produced. all more ambitious ARM-devoted companies/design labs, shutdown, sadly) ARMv8 and ARMv8A -based chips, but they are REALLY hugry to use in networking.
as for smaller devices, with up to four cores - its could be decent entry for both SOHO and SMB market. bigger chips - bigger compelxity of design, especially in terms of heat dissipation and PSU/power circuitrty performance/reliability.
both Marvell and especially Qualcomm had quite Nice ARM-based SoC for networking(especially like Krait chips). more beefier are more suitable for dedicated IPS or storage/NAS, rather than generic router/CPE.


p.s.
for that price i was probably purchase one rb3011 "just from curiosity". seriously.
but maybe its fit my home or work too(permanently). like bunch 450g's, 751's, 951's 2011 did(&did good work) before.
thats would be long-awaited 2011 replacement. and 450g/850gx2 replacement of same platform/approach may get quad-core version of same chip. for extra $50-$80(with "extras" like 2x RAM and SD slot) in price or something alike in similar enclosure as 2011/3011 or 450/850 used before.


p.p.s.
about ROS over 64-bit x86 - more likely adoption of K12 chips from AMD(both full-scale APU's and ULV chips follow later). originally they use improved A57 cores, but follow-up WILL use A72 and promised to be very cold and quiet.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Thu Apr 09, 2015 5:55 pm

Now if we could get a routerboard based on AppliedMicro X-Gene ARMv8-A architecture. 4x 10Gb SFP+, 2-4 1Gbe interfaces, large amount of memory and 8-16 2.4GHz cores.

That would be the stuff!
unlikely thats suits for routers, yet, even with 14nm wafers produced SoC.
both A72(the only ARMv8A-based design, anounced, yet) and pervious A57 and A53 really hungry/hot.
but A53 cores was probably good start. relatively cold and relatively fast.
there was several multi-core and many-core(up to 64x in really mass-produced. all more ambitious ARM-devoted companies/design labs, shutdown, sadly) ARMv8 and ARMv8A -based chips, but they are REALLY hugry to use in networking.
as for smaller devices, with up to four cores - its could be decent entry for both SOHO and SMB market. bigger chips - bigger compelxity of design, especially in terms of heat dissipation and PSU/power circuitrty performance/reliability.
both Marvell and especially Qualcomm had quite Nice ARM-based SoC for networking(especially like Krait chips). more beefier are more suitable for dedicated IPS or storage/NAS, rather than generic router/CPE.


p.s.
for that price i was probably purchase one rb3011 "just from curiosity". seriously.
but maybe its fit my home or work too(permanently). like bunch 450g's, 751's, 951's 2011 did(&did good work) before.
thats would be long-awaited 2011 replacement. and 450g/850gx2 replacement of same platform/approach may get quad-core version of same chip. for extra $50-$80(with "extras" like 2x RAM and SD slot) in price or something alike in similar enclosure as 2011/3011 or 450/850 used before.


p.p.s.
about ROS over 64-bit x86 - more likely adoption of K12 chips from AMD(both full-scale APU's and ULV chips follow later). originally they use improved A57 cores, but follow-up WILL use A72 and promised to be very cold and quiet.

Re: about ROS over 64-bit x86
Here is a big reason I would like to see "ROS over 64-bit x86" with vmxnet3 support:
#1 - a virtual "ROS over 32-bit x86" running MvWare ESXi using "e1000e" network interfaces - performing a bandwidth speed test to 127.0.0.1 = 14.6 Gbps
#2 - a virtual "ROS over 32-bit x86" running MvWare ESXi using "e1000e" network interfaces - performing a bandwidth speed test to a second "ROS over 32-bit x86" on a second VMware ESXi server with a 10-Gig Cisco switch in the middle = 9.7 Gbps

I would assume these speeds would only just get faster with 64-Bit ROS with vmxnet3 network driver support - and larger memory support for full IPV4 and IPV6 BGP tables.

In a virtual router server world, things will only get faster at time goes by.

North Idaho Tom Jones
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Thu Apr 09, 2015 8:49 pm

no, you needs/purposes was clear, quite common among ROS x86 users, but there was conflict of interests and major purpose of ROS - sell it with hardware. so hardly we're see x86 improvements soon, if at all.
while x86-compatible ARM drop-in replacements(like announced by AMD) mayd had more interesting future, sharing same ROS images/package due to same arch both in devices and in standalone/custom installations.

p.s.
maybe im wrong. but my impressions thats x86 wasn't priority market for MikroTik team.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Thu Apr 09, 2015 9:01 pm

re: maybe im wrong. but my impressions thats x86 wasn't priority market for MikroTik team.

I totally think you are correct - however it is still a huge market where profits could be made by Mikrotik with a router solution for the VMware ESXi platform. Even Cisco is already on the band-wagon - but Cisco is way expensive for any decent x86 32-bit or 64-bit virtual environment.

Also - I would kinda like to see Intel/AMD 64 bit multi-core CPUs with large amounts of ram/cache be considered for new high-end Mikrotik CCR products. There is a lot of cool new developments as newer very high-end CPUs come out every year from both AMD and Intel. - And there is a huge source of existing GPL code and compilers and programmers already available. Also - I think that for flat-out processing the Intel/AMD world is far faster than the ARM processing world - however you pay a price in Watts.
 
User avatar
docmarius
Forum Guru
Forum Guru
Posts: 1219
Joined: Sat Nov 06, 2010 12:04 pm
Location: Timisoara, Romania
Contact:

Re: rb3011 based on ARM CPU

Fri Apr 10, 2015 1:21 pm

Let's not forget the low power processors, e.g. Intel Xeon E3-1220L v2 - TDP 17W, 2 cores, 2.3 GHz up to 3.5 GHz, and others up to 35W, including eight core Atoms like the C2758 (4 integrated 2.5Gbps Ethernet, 20W, 2.4 Ghz), which all support 64-bit and could make a decent router with a decent power consumption.

http://ark.intel.com/products/family/71 ... unications
Torturing CCR1009-7G-1C-1S+, RB450G, RB750GL, RB951G-2HnD, RB960PGS, RB260GSP, OmniTIK 5HnD and NetMetal 922UAGS-5HPacD + R11e-5HnD in my home network.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Fri Apr 10, 2015 7:35 pm

Let's not forget the low power processors, e.g. Intel Xeon E3-1220L v2 - TDP 17W, 2 cores, 2.3 GHz up to 3.5 GHz, and others up to 35W, including eight core Atoms like the C2758 (4 integrated 2.5Gbps Ethernet, 20W, 2.4 Ghz), which all support 64-bit and could make a decent router with a decent power consumption.

http://ark.intel.com/products/family/71 ... unications
Agree
What I am also thinking is, if we want high-throughput performance then power consumption is second. If we want energy conservation, then performance is second. Where CCRs are used, I would think that performance/throughput is the highest priority to achieve first.

North Idaho Tom Jones
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Fri Apr 10, 2015 9:53 pm

maybe.
when SDN and OpenFlow become mature(about 1.5-2 years or so ? :)MikroTik move portions/all feats of ROS over it, instead of "bare metall", kernel-based version and drop deprecated implementation of feats, w/o affecting b/w compatibility.
as for x86 "in general" - future ULV chips(esp Skylake and Carrizo) with 6W-18W TDP will obliterate MIPS/ARM/PPC chips with same termal package about 5x times and being multicore(and generally SMT too. while AMD rumored to had 4x threads/per core instead of 2x as intel does), but generally SDH boxes(universal/open or proprietary, OpenFlow/alikes-incompatible)presently VERY pricy/expensive. major concern was - relable SoC/CPU supply, cuz only two vendors mean you VERY vulnerable(VIA IP future still unclear), while MIPS/ARM/PPC chips available from nearly hungred of suppliers, many of which had own factories, even small/outdated/archaic.
second was price. and presently major, cuz x86 CPU's remain very expensive.
so some consumers may build x86 gear for ROS, but MikroTik itself unlikely enter such market soon, or contribute much to x86 fork/branch of ROS polishing/fixing/improving.
thats why we're lack 64-bit version of ROS and etc.
Last edited by Zorro on Fri Apr 10, 2015 11:19 pm, edited 2 times in total.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Fri Apr 10, 2015 10:06 pm

maybe.
when SDH and OpenFlow become mature(about 1.5-2 years or so ? :)MikroTik move portions/all feats of ROS over it, and drop deprecated implementation of feats, w/o affecting b/w compatibility.
as for x86 "in general" - future ULV chips(esp Skylake and Carrizo) with 6W-18W TDP will obliterate MIPS/ARM/PPC chips with same termal package about 5x times and being multicore(and generally SMT too. while AMD rumored to had 4x threads/per core instead of 2x as intel does), but generally SDH boxes(universal/open or proprietary, OpenFlow/alikes-incompatible)presently VERY pricy/expensive. major concern was - relable SoC/CPU supply, cuz only two vendors mean you VERY vulnerable(VIA IP future still unclear), while MIPS/ARM/PPC chips available from nearly hungred of suppliers, many of which had own factories, even small/outdated/archaic.
second was price. and presently major, cuz x86 CPU's remain very expensive.
so some consumers may build x86 gear for ROS, but MikroTik itself unlikely enter such market soon, or contribute much to x86 fork/branch of ROS polishing/fixing/improving.
thats why we're lack 64-bit version of ROS and etc.
A question - I am not a programmer however I will ask: With x86 source code, are there re-writes of code to compile into a 64-bit ROS (so that more RAM memory could be allocated or gain additional CPU throughput) ?

Another question - is it difficult to compile for a different type of CPU. Lets say somebody comes out with a new super-fast 20 GHz 128-core 128-bit CPU but the instruction set is different. I would assume that first a compiler would be needed for the new CPU.

Just wondering ...
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Fri Apr 10, 2015 10:41 pm

its ain't that simple, sadly.
and arch-specific things differ between x86 and 64-bit(AMD64/IMT64 arch) Seriously.
and properly-done kernels/firmware imply Many time spend in both testing, debugging, profiling.
its not "difficult"/impossible, but @#% of work if you do it Right.
some linux distros made/tuned/designed Especially toward this, mastering "consistency by design", especially Gentoo and forks by rolling/devloping clean toolchain-based systems..
few config changes(global and local(in rare cases) ones), then you just re-build AnyThing for different arch(chrot or in VM) or with Different optimisation/priorities. generally, aside access to bigger RAM amounts there was fast IO and integer and FP computing speed beenfits, potentially on properly-profiled 64-bit x86 code(benefits on intel chips slihtly smaller, yet).
 
rzirzi
Member
Member
Posts: 378
Joined: Mon Oct 09, 2006 2:33 pm

Re: rb3011 based on ARM CPU

Mon Jun 22, 2015 11:07 pm

When it will be available?
RB3011 - when?
 
kiler129
Member Candidate
Member Candidate
Posts: 227
Joined: Tue Mar 31, 2015 4:32 pm
Contact:

Re: rb3011 based on ARM CPU

Sun Jun 28, 2015 9:39 pm

@normis: Any news about 3011 availability date? Q2 is ending in a few days and there's still silent about release :(
 
User avatar
BartoszP
Forum Guru
Forum Guru
Posts: 1715
Joined: Mon Jun 16, 2014 1:13 pm
Location: Poland

Re: rb3011 based on ARM CPU

Sun Jun 28, 2015 11:04 pm

its ain't that simple, sadly.
and arch-specific things differ between x86 and 64-bit(AMD64/IMT64 arch) Seriously.
You are right but conversion's dark time is far far away behind us....64-bit is quite common and Linux kernel is more than ready to forget 32-bit times.
Conversion from 64 to 128 bits is not easy as it was for 32 to 64 bit process but conversion between different ARM/X32/x64 and big and little endian is not a problem...it is already done.
ARM is already Linux's Tier 1 architecture and we should do not expect problems in recompiling to new architecture if only MT code is properly written.
Real admins use real keyboards.
 
rzirzi
Member
Member
Posts: 378
Joined: Mon Oct 09, 2006 2:33 pm

Re: rb3011 based on ARM CPU

Mon Jul 13, 2015 6:09 pm

MikroTik Team - could You answer - WHEN? When will be available RB3011 ???
 
User avatar
normis
MikroTik Support
MikroTik Support
Posts: 24215
Joined: Fri May 28, 2004 11:04 am
Location: Riga, Latvia

Re: rb3011 based on ARM CPU

Tue Jul 14, 2015 9:18 am

We encountered a setback during final testing, so there was a delay, we have solved the issue, and device is moving to manufacturing.

The process of developing a device is long, it involves lots of prototypes, samples, etc. Sometimes there is a small issue and the whole chain of events is affected.

When we announce a product, we only give a rough estimate when it will become available. Sometimes there is a shift in the development process and the date moves. I can't say exactly when it will be available, because there are many variables that can still change.
No answer to your question? How to write posts
 
rzirzi
Member
Member
Posts: 378
Joined: Mon Oct 09, 2006 2:33 pm

Re: rb3011 based on ARM CPU

Thu Aug 13, 2015 12:33 pm

Normis, month after Your answer - I'm asking again - WHEN ?
When will be available RB3011 ?
 
Siona
Frequent Visitor
Frequent Visitor
Posts: 83
Joined: Thu Jan 29, 2015 11:56 am

Thu Aug 13, 2015 3:07 pm

I've lost my patience. I've bought new 850gx2H.
 
pimmie
just joined
Posts: 13
Joined: Fri Mar 27, 2015 4:51 pm

Re: rb3011 based on ARM CPU

Mon Aug 17, 2015 11:46 am

As I also have some projects coming up, I wonder if Mikrotik/Normis could give some rough estimate when the 3011 and hAP ac will become available?

Allthough I understand that you can't give us an exact date, it should be possible to give us a 'within 1, 2 or 3 months' date range. E.g. if you already know now that it will not be within 2 months I can move on with my projects and look for other devices, it would be very much appreciated!
 
wiresharky
just joined
Posts: 4
Joined: Sat Aug 22, 2015 3:04 pm

Re: rb3011 based on ARM CPU

Sat Aug 22, 2015 4:29 pm

which is or will be faster? the new rb850gx2 or the rb3011 ?
 
pimmie
just joined
Posts: 13
Joined: Fri Mar 27, 2015 4:51 pm

Re: rb3011 based on ARM CPU

Tue Sep 01, 2015 11:53 pm

As I also have some projects coming up, I wonder if Mikrotik/Normis could give some rough estimate when the 3011 and hAP ac will become available?
A small follow up for fellow anxious waiters; we gave Mikrotik a call and on the phone they said both devices should be available end of Q3 / last week of September.
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 12:25 am

resellers withdraw/cancelled preorders in both companies i preorder. perhaps there was probles with production or availability of RB3011. they said "had no idea when/if it will b available" :(
which is or will be faster? the new rb850gx2 or the rb3011 ?
go figure - dualcore 1.2Ghz ARM even in crippled A9(?) core with tiny caches/bus/IMC/FPU seriously outperform low-power 32-bit E550(?) PPC SoC from FreeScale.
Qualcomm/Atheros also had better SDK than Freescale and Broadcom, IMO.
if RB850gx was based on 64-bit PPC cores From freescale it would be more fun. have it 2x 1.2 E5500 or E6500 cores(these usually start from 8x ;P)it may be really challenging for RB3011.


p.s.
personally i would like something more like 951 version on this chip for home.
no LCD screen. no 8 ports(5x more than enough). no USB port, no SFP cage, no external antenna. more compact case(951 and 750/751 form-factor was okay)
and similar version without WiFi whatsoever to replace/Augment hEX.

and RB850Gx2 and RB2011 will be replaced by slighly OC'ed to 1.6Ghz(?)version of chip with HUGE heatsink. or quad-core version of it.
Last edited by Zorro on Wed Sep 02, 2015 1:00 am, edited 1 time in total.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 12:48 am

Myself - I would love to see a a new bread of screaming high-throughput Mikrotiks using the latest/fastest/lots-of-CPU-cache Intel 64-bit processors available.

Even using ROS x86 (32-bit) in a VMware environment, I am able to get Mikrotik UDP speed tests using 127.0.0.1 over 17 gig. And between two different VMware boxes with 10-Gig links with each hosting a ROS x86 (32-bit) in a VMware environment, I am still able to get a Mikrotik speedtest of of almost 10 gig (ROS to ROS through the network).

I also suspect that running the same tests without using Hypervisors (VMware), the results would only be faster.

I would like to ask, what is the fastest any RB has achieved with a Mikrotik speedtest to 127.0.0.1 ?

I would very much like to see a high-end Mikrotik with the power to take on a full-sized Cisco router and possibly out-perform a Cisco.

my 2 cents
North Idaho Tom Jones
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 1:06 am

Myself - I would love to see a a new bread of screaming high-throughput Mikrotiks using the latest/fastest/lots-of-CPU-cache Intel 64-bit processors available.

Even using ROS x86 (32-bit) in a VMware environment, I am able to get Mikrotik UDP speed tests using 127.0.0.1 over 17 gig. And between two different VMware boxes with 10-Gig links with each hosting a ROS x86 (32-bit) in a VMware environment, I am still able to get a Mikrotik speedtest of of almost 10 gig (ROS to ROS through the network).

I also suspect that running the same tests without using Hypervisors (VMware), the results would only be faster.

I would like to ask, what is the fastest any RB has achieved with a Mikrotik speedtest to 127.0.0.1 ?

I would very much like to see a high-end Mikrotik with the power to take on a full-sized Cisco router and possibly out-perform a Cisco.

my 2 cents
North Idaho Tom Jones
these SDN boxes already made in last 3years. still Very expensive, quirky and lot of prorietary stuff, despite being based on FOSS SDN solutions.
both x86-based and Arm/MIPS/PPC-based.
personally i would prefer new AMD low-power x86 SoC for that purpose, than intel things.
cuz low-power chips from AMD seriously faster and colder, yet.
as for high-performance setups, its will be b-necked by chipsets and CPU interface with it. and already do even in desktop applications.
well you may notice(including links in my post above)new tilera chip(ARM based 100-core many-core SoC ;), which eventually would be used in top-dog CCR devices.
as for future version - it would be based on A72-based(instead of A53)cores, maybe and had faster(optical)fabric/interconnect(essential for both many-core and multicore(starting from ~3x cores or so)chips).
so far in "networking" applications - ARM beat intel. so many-core and multi-core A57, A53 and A72-based SoC will had OUTSTANDING power/speed/footprint/price ration compared to such. and if you go for "monster-load" applications/use - stick to Tilera. software/ROS not scale enough(no ZOL things/approach used from Tilera, yet and nothing was Erlang-rewritten, yet too), but its about time.
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 1:27 am

re: personally i would prefer new AMD low-power x86 SoC for that purpose, than intel things.

Sometimes and often, there is a trade-off in speed to achieve a lower power consumption.

I would rather see a build it to run the absolute fastest, then have an optional ROS package that can be enabled to support Advanced-Power-Management.

Also - AMD vs Intel 64-bit processors. I would suggest going with the fastest CPU & highest throughput CPU (for ROS) no matter which company makes it (AMD or Intel).

Also, with a (very bad ass) 64-Bit ROS (Intel/AMD) environment, Mikrotik could also capture a huge growing Virtual Hypervisor market share at the same time. Has anybody looked at the price of a Cisco router/firewall platform that runs in a HyperVisor environment? This is way to big of a market to simply ignore. When ever possible, I use HyperVisor environments for my routers and firewalls. All of my Mikrotiks are only doing WDS or AP or customer NAT functions, and I only use my Cisco routers/switches because they support lots of 10-gig interfaces.

North Idaho Tom Jones
 
User avatar
janisk
MikroTik Support
MikroTik Support
Posts: 6283
Joined: Tue Feb 14, 2006 9:46 am
Location: Riga, Latvia

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 11:31 am

it seems that you have not seen CHR yet
 
User avatar
TomjNorthIdaho
Forum Veteran
Forum Veteran
Posts: 990
Joined: Mon Oct 04, 2010 11:25 pm
Location: North Idaho
Contact:

Re: rb3011 based on ARM CPU

Wed Sep 02, 2015 6:42 pm

it seems that you have not seen CHR yet
I know almost nothing about the CHR. What is the difference between CHR and x-86 ROS?
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Thu Sep 03, 2015 1:58 pm

as for "fastest and baddest" any kind of x86 sucks compared to things like Power8 or Sparc T5 and alikes.
including E5, E7 and EP chips.
 
User avatar
normis
MikroTik Support
MikroTik Support
Posts: 24215
Joined: Fri May 28, 2004 11:04 am
Location: Riga, Latvia

Re: rb3011 based on ARM CPU

Thu Sep 03, 2015 3:22 pm

it seems that you have not seen CHR yet
I know almost nothing about the CHR. What is the difference between CHR and x-86 ROS?
CHR is Cloud Hosted Router, a special IMG file for virtual machines. Improvements over regular x86 from ISO file:

- free (no license) with all features
- supports hyper-v and all the drivers for various environments
- 64bit

Currently runs at 1Mbit per interface, because we will have a subscription service for around 1-2$ per month to remove this limit. There are no other limits for now (like a Level6 license).

More info:
http://forum.mikrotik.com/viewtopic.php?f=21&t=98981
http://forum.mikrotik.com/viewtopic.php?f=2&t=99658
No answer to your question? How to write posts
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Thu Sep 03, 2015 4:17 pm

wow !
sounds like cool offer/product :=)
there isn't plans to port appliance to EMC/VMWare, VirtualBox/HyperBox, Parallels contaniers/format and community-made/support FOSS platforms ?
qemu atleast ? kvm-based products ?
 
vortex
Forum Veteran
Forum Veteran
Posts: 713
Joined: Sat Feb 16, 2013 6:10 pm

Re: rb3011 based on ARM CPU

Thu Sep 03, 2015 5:19 pm

Will we be able to buy a 5GHz version already assembled?
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Fri Sep 04, 2015 12:35 pm

personally i was more curious by "-ln" low-end version and "-rm" rack-mount versions of device :)
but all resellers refuse to take pre-orders. some even to my surprise - unaware about such device existence/announcement :((
(send them brochure and newsletter. they seems really interested)
 
User avatar
normis
MikroTik Support
MikroTik Support
Posts: 24215
Joined: Fri May 28, 2004 11:04 am
Location: Riga, Latvia

Re: rb3011 based on ARM CPU

Fri Sep 04, 2015 12:35 pm

wow !
sounds like cool offer/product :=)
there isn't plans to port appliance to EMC/VMWare, VirtualBox/HyperBox, Parallels contaniers/format and community-made/support FOSS platforms ?
qemu atleast ? kvm-based products ?
CHR is already available for all of the above. It is an image that you can convert to any of the mentioned formats, and run CHR in KVM, Quemy etc. See the forum links I posted, there are instructions
No answer to your question? How to write posts
 
vortex
Forum Veteran
Forum Veteran
Posts: 713
Joined: Sat Feb 16, 2013 6:10 pm

Re: rb3011 based on ARM CPU

Sat Sep 05, 2015 7:46 pm

Now that I got rid of the bridge on my RB2011 I think I will pass and remain ac-less.

Upgrade triggers:

- gigabit WAN next year
- 10GBaseT wirespeed ports
- triple band wireless plus HFS+ plus AFP
- PoE out plus built-in power supply
 
kiler129
Member Candidate
Member Candidate
Posts: 227
Joined: Tue Mar 31, 2015 4:32 pm
Contact:

Re: rb3011 based on ARM CPU

Sat Sep 05, 2015 9:00 pm

- triple band wireless plus HFS+ plus AFP
Forget about it. HFS+ and AFP are proprietary technologies made by Apple and not licensed to anyone.
Also keep in mind it's a ROUTER - performance for file sharing will be horrible anyway.
 
vortex
Forum Veteran
Forum Veteran
Posts: 713
Joined: Sat Feb 16, 2013 6:10 pm

Re: rb3011 based on ARM CPU

Sat Sep 05, 2015 9:43 pm

- triple band wireless plus HFS+ plus AFP
Forget about it. HFS+ and AFP are proprietary technologies made by Apple and not licensed to anyone.
Also keep in mind it's a ROUTER - performance for file sharing will be horrible anyway.
There are commercial HFS+ drivers for Windows since many years ago, for example.

There are many third-party products supporting AFP.

Performance would still be much better than the horrible Airport Extreme.
 
kiler129
Member Candidate
Member Candidate
Posts: 227
Joined: Tue Mar 31, 2015 4:32 pm
Contact:

Re: rb3011 based on ARM CPU

Sun Sep 06, 2015 1:59 am

HFS+ support in all Windows (and Linux) products came from reverse engineering. The best one from Paragon added journal replay which works only sometimes.
Speaking in terms of AFP all Linux products out there uses Netatalk implementation which is not as perfect as you may think. I'm running it for 3 years now, updated from sources every time it's get updated - it works but it's stability is discussable.
Speaking in terms of performance transferring at ~120Mb/s uses around 80% of one of two cpu cores on my home NAS which is x86 and have drives connected via SATA. Using USB drives will require more power.

Network storage is rather complicated area. If you don't believe me look at commercial NAS solutions (keep in mind I'm not talking about pro-grade SANs) - every unit with decent speeds will run x86. I replaced my NAS with custom one because of two reasons: I had few ARM storages and they just sucks plus custom x86 was cheaper.


So yeah, I think router CPU is not going to handle network storage well - I did seen many with such functionality, none of them were near good. If you're complaining about AEx speeds look how beefy ARM it's holding - it's 1Ghz + 512MB ram :)
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Mon Sep 07, 2015 8:13 am

Now that I got rid of the bridge on my RB2011 I think I will pass and remain ac-less.

Upgrade triggers:

- gigabit WAN next year
- 10GBaseT wirespeed ports
- triple band wireless plus HFS+ plus AFP
- PoE out plus built-in power supply
for 10Gb ports im afraid even top CCR aren't powerful enough, mostly because ROS didn't scale much between many-cores, yet.
(unless you willing to sacrifice/"dumbify" config for speed, making its essentially "smart switch" for lan ports,which isn't good idea for ANY router)
HFS+ and AFP not matter.
its like GOPHER in 2015 year. or http 0.9.
but 802.11ax would be cool, but such wireless chipsets isn't come out yet and generally 60GHz support was quite rare at all :(
 
vortex
Forum Veteran
Forum Veteran
Posts: 713
Joined: Sat Feb 16, 2013 6:10 pm

Re: rb3011 based on ARM CPU

Mon Sep 07, 2015 9:29 am

CCR does not have a 10GbE switch, everything goes through the CPU.

It is possible to have something cheaper which is not suboptimal in this regard.
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Tue Sep 08, 2015 2:01 am

CCR does not have a 10GbE switch, everything goes through the CPU.

It is possible to have something cheaper which is not suboptimal in this regard.
its meant "USE/configure as smart switch" ie with sacrificed/crippled/reduced config.
and no, CCR1009 do use switch chip. (and its ironically aged 8327 chip. even my hEX had 8337 as interface/PHY. which way, WAY better)
http://i.mt.lv/routerboard/files/CCR100 ... 151432.pdf
"something" is always possible. question only if/who/when will do that.
 
Xsaron
just joined
Posts: 16
Joined: Tue Oct 27, 2015 10:11 am

Re: rb3011 based on ARM CPU

Tue Oct 27, 2015 10:13 am

And so, distracted by technicalities, everyone seems to have forgotten that RB3011 should have been available for a month already, which isn't. So I'm wondering, is there something really wrong with the new to be product and should I go and buy something else?
 
jarda
Forum Guru
Forum Guru
Posts: 7603
Joined: Mon Oct 22, 2012 4:46 pm

Tue Oct 27, 2015 1:32 pm

I have learnt that it is normal when mikrotik doesn't fulfill it's timing given in announcements. Nothing special. Just take it as it is. The official answer was once to me: "It will be when it will be."
 
josu
Member Candidate
Member Candidate
Posts: 152
Joined: Wed May 27, 2015 6:20 pm

Re: rb3011 based on ARM CPU

Wed Jun 15, 2016 10:41 pm

Has the RB3011 IPSec hardware acceleration?

I am looking for a cheap device that could handle 500mbps IPSec.

Regards.
 
User avatar
ZeroByte
Forum Guru
Forum Guru
Posts: 4051
Joined: Wed May 11, 2011 6:08 pm

Re: rb3011 based on ARM CPU

Wed Jun 15, 2016 11:03 pm

Has the RB3011 IPSec hardware acceleration?

I am looking for a cheap device that could handle 500mbps IPSec.

Regards.
Yes, it has the hardware, but no it's not yet working - they haven't gotten the drivers for it integrated into RouterOS yet. I presume that will be something that happens in ROSv7.... whenever that might be. (It's like sasquatch - there have been a few blurry pictures of it, but nothing concrete).
When given a spoon,
you should not cling to your fork.
The soup will get cold.
 
josu
Member Candidate
Member Candidate
Posts: 152
Joined: Wed May 27, 2015 6:20 pm

Re: rb3011 based on ARM CPU

Thu Jun 16, 2016 9:27 am

Yes, it has the hardware, but no it's not yet working - they haven't gotten the drivers for it integrated into RouterOS yet. I presume that will be something that happens in ROSv7.... whenever that might be. (It's like sasquatch - there have been a few blurry pictures of it, but nothing concrete).
Thanks ZeroByte!
Any developer could tell something about it? I hope IPSec acceletarion could work soon.
Kind regards.
 
andriys
Forum Guru
Forum Guru
Posts: 1180
Joined: Thu Nov 24, 2011 1:59 pm
Location: Kharkiv, Ukraine

Re: rb3011 based on ARM CPU

Thu Jun 16, 2016 10:03 pm

I hope IPSec acceletarion could work soon.
I wouldn't rely on that. It was promised, but I don't believe it'll happen soon.
 
cb22
just joined
Posts: 1
Joined: Thu Jul 14, 2016 10:29 am

Re: rb3011 based on ARM CPU

Thu Jul 14, 2016 10:33 am

I hope IPSec acceletarion could work soon.
I wouldn't rely on that. It was promised, but I don't believe it'll happen soon.
Does anyone perhaps have any numbers (or could run a quick benchmark) on what it can handle in terms of unaccelerated IPsec/AES? If the RB2011 could hit around ~40mbps, it shouldn't be a stretch for the significantly faster processor in the RB3011 to get close to 100mbps at least?
 
User avatar
mrz
MikroTik Support
MikroTik Support
Posts: 5934
Joined: Wed Feb 07, 2007 12:45 pm
Location: Latvia
Contact:

Re: rb3011 based on ARM CPU

Thu Jul 14, 2016 11:07 am

RB3011 without acceleration can get around 150Mbps UDP traffic with 1400 byte packets.
 
User avatar
nz_monkey
Forum Guru
Forum Guru
Posts: 1819
Joined: Mon Jan 14, 2008 1:53 pm
Location: Straya
Contact:

Re: rb3011 based on ARM CPU

Thu Jul 14, 2016 12:02 pm

RB3011 without acceleration can get around 150Mbps UDP traffic with 1400 byte packets.
Thank you for the informative reply mrz.
That is quite impressive for software crypto.
Hopefully we one day see hardware crypto on ARM.
http://thebrotherswisp.com/ | Mikrotik MTCNA, MTCRE, MTCINE | Fortinet FTCNA, FCNSP, FCT | Extreme Networks ENA
 
Zorro
Long time Member
Long time Member
Posts: 676
Joined: Wed Apr 16, 2014 2:43 pm

Re: rb3011 based on ARM CPU

Fri Jul 15, 2016 8:57 pm

RB3011 without acceleration can get around 150Mbps UDP traffic with 1400 byte packets.
Thank you for the informative reply mrz.
That is quite impressive for software crypto.
Hopefully we one day see hardware crypto on ARM.
i think hardware - advance faster than sofware implmentation for "advertised as hardware implementation" offloading of some portions of it.
A35, A32 cores, and even proposed mid tier A53 replacement (A72 Already get A73 to switch to and A32/A35 replace weaker ones)
and 1004k and his new, improved successor - make even MIPS-BE look not so bleak, perhaps.
in any/each case - cost and time of design/development was anyway remain significant to be problem. thats one of major reasons why ARM - outperform MIPS, PPC and x86 - they had notably quicker "time to market" performance, despite sometimes idential launch time for similar ideas in.
 
vortex
Forum Veteran
Forum Veteran
Posts: 713
Joined: Sat Feb 16, 2013 6:10 pm

Re: rb3011 based on ARM CPU

Thu Oct 11, 2018 10:32 pm

I think it is time for a line in this routing class but cheaper.

Many people still don't get 1000/100 and it would be enough if the router would be able to support a 2000/200 upgrade later.

Who is online

Users browsing this forum: No registered users and 13 guests