Pages: [1] 2 3 :: one page |
|
Author |
Thread Statistics | Show CCP posts - 0 post(s) |
Amarr Citizen 1312151005
Royal Amarr Institute Amarr Empire
0
|
Posted - 2013.12.26 10:37:00 -
[1] - Quote
Just wondering would a more powerful server fix tidi? Or is it more of a coding issue? Just wondering this because I got bored and started looking up super computer's. The two fastest in the world run at about 20 and 40 petaflops.
And I thought I had read somewhere that tranquility runs at like 300-400 teraflops. Could one of these super computers handle large eve battles without tidi? This is of course hypothetical.
But just curious if it would ever be possible to see the end of tidi. I am thinking hardware wise the tech is out there while not realistic for a small company like ccp to obtain and maintain.
I would think if one if those super computers where designed with the purpose of running eve they could more than handle the processing needs. And in time I think we could see an end to tidi.
However if tidi is related to some deeply coded issue I think we may never see its end..
TL:DR. Could tidi be fixed with pure power or is it a coding issue that may never be fixed? |
Xercodo
Xovoni Astronautical Manufacturing and Engineering
3176
|
Posted - 2013.12.26 10:39:00 -
[2] - Quote
Nope, CCP's pretty much already using the most advanced stuff they can afford. It's really a coding problem that will simply take time to work out.
They gave TiDi as a band aid to the problem until such a time as they have the ultimate solution. The Drake is a Lie |
Amarr Citizen 1312151005
Royal Amarr Institute Amarr Empire
0
|
Posted - 2013.12.26 10:40:00 -
[3] - Quote
Xercodo wrote:Nope, CCP's pretty much already using the most advanced stuff they can afford. It's really a coding problem that will simply take time to work out.
They gave TiDi as a band aid to the problem until such a time as they have the ultimate solution. I know they are using the most advanced stuff they can afford but could of of the top 2 super computers run it? |
Ibrahim Vaughn Holtzman
Center for Advanced Studies Gallente Federation
31
|
Posted - 2013.12.26 10:47:00 -
[4] - Quote
Supercomputers only work great if they can compute massively parallel.
Eve's backend, however, is mostly single-threaded and scales terribly with number of cores and/or threads. It is basically from a time when Intel kept promising us that 10GHz-CPU's (single core) are right around the corner. Which didn't happen due to exponential thermal output. |
Lors Dornick
Kallisti Industries Solar Assault Fleet
895
|
Posted - 2013.12.26 10:49:00 -
[5] - Quote
Amarr Citizen 1312151005 wrote:Just wondering would a more powerful server fix tidi? Or is it more of a coding issue? Just wondering this because I got bored and started looking up super computer's. The two fastest in the world run at about 20 and 40 petaflops.
And I thought I had read somewhere that tranquility runs at like 300-400 teraflops. Could one of these super computers handle large eve battles without tidi? This is of course hypothetical.
Those 20-40 petaflops aren't getting that performance from a single core.
The current 'mega nodes' are amongst the most powerful single core rigs that money can buy (actually, there's been some hardware in use that money couldn't buy at that time).
So, it's mostly down to code.
Amarr Citizen 1312151005 wrote: But just curious if it would ever be possible to see the end of tidi.
It's unlikely that any solution will ever see the end of TiDi.
Like nature abhors vacuum, gamers tend to fill every free gap of processing power, and then grab some more.
Recoding of vital parts of the server code in combination with clever use of hardware will push the limit for when TiDi kicks in, but it'll will never removing it totally. CCP Eterne: Silly player, ALL devs are evil. CCP Fozzie: When Veritas describes a programming challenge as "very hard" I tend to believe him.
|
Dante Chusuk
eHarmony Inc.
18
|
Posted - 2013.12.26 10:50:00 -
[6] - Quote
Amarr Citizen 1312151005 wrote:Xercodo wrote:Nope, CCP's pretty much already using the most advanced stuff they can afford. It's really a coding problem that will simply take time to work out.
They gave TiDi as a band aid to the problem until such a time as they have the ultimate solution. I know they are using the most advanced stuff they can afford but could of of the top 2 super computers run it?
From memory no, if I remember correctly the underlying Python aspects are not multi-threaded in a way that allows you to split a solar system across more than one CPU so the "best" granularity you can have is one solar system per core on a CPU. So you'd need a super computer with in excess of 5000 cores for the galaxy alone plus the login and DB computers which sit as separate blades.
It's possible with one of the top super computers I guess but given the number of systems that likely sit empty or low load you would have a lot of spare processing power that you couldn't resource elsewhere due to the one solar system per core "best" limit |
Amarr Citizen 1312151005
Royal Amarr Institute Amarr Empire
0
|
Posted - 2013.12.26 10:50:00 -
[7] - Quote
Ibrahim Vaughn Holtzman wrote:Supercomputers only work great if they can compute massively parallel.
Eve's backend, however, is mostly single-threaded and scales terribly with number of cores and/or threads. It is basically from a time when Intel kept insisting that 10GHz-CPU's are right around the corner. Which didn't happen due to exponential thermal output. So a coding issue in other words? Same reason my I7 is worthless for eve client side. |
Amarr Citizen 1312151005
Royal Amarr Institute Amarr Empire
0
|
Posted - 2013.12.26 10:56:00 -
[8] - Quote
Dante Chusuk wrote:Amarr Citizen 1312151005 wrote:Xercodo wrote:Nope, CCP's pretty much already using the most advanced stuff they can afford. It's really a coding problem that will simply take time to work out.
They gave TiDi as a band aid to the problem until such a time as they have the ultimate solution. I know they are using the most advanced stuff they can afford but could of of the top 2 super computers run it? From memory no, if I remember correctly the underlying Python aspects are not multi-threaded in a way that allows you to split a solar system across more than one CPU so the "best" granularity you can have is one solar system per core on a CPU. So you'd need a super computer with in excess of 5000 cores for the galaxy alone plus the login and DB computers which sit as separate blades. It's possible with one of the top super computers I guess but given the number of systems that likely sit empty or low load you would have a lot of spare processing power that you couldn't resource elsewhere due to the one solar system per core "best" limit The titan super computer has over 516000 cores. So it seems they can make one with enough cores. And I understand that tidings is leaps and bounds better than years ago I started in 2009. But I just can't personally stand it..
While I am grateful for it as is allows my alliance to be active in past big wars. I just can't bring myself to participate in tidi.. |
crononyx
Running with Knives Nexus Fleet
1
|
Posted - 2013.12.26 10:57:00 -
[9] - Quote
Amarr Citizen 1312151005 wrote:Ibrahim Vaughn Holtzman wrote:Supercomputers only work great if they can compute massively parallel.
Eve's backend, however, is mostly single-threaded and scales terribly with number of cores and/or threads. It is basically from a time when Intel kept insisting that 10GHz-CPU's are right around the corner. Which didn't happen due to exponential thermal output. So a coding issue in other words? Same reason my I7 is worthless for eve client side. Well, it allows you to run multiple clients smoothly. And other software as well. |
flakeys
Antwerpse Kerels Fidelas Constans
1697
|
Posted - 2013.12.26 11:03:00 -
[10] - Quote
Short answer : No because any barrier that is being set will be the new norm for engagements.
If they cap it at X pilots or as seen lately X drones+pilots then the new cap will be the new norm within a few months.It's been like that since i joined eve allmost 10 years back.
Blob > servers
We are all born ignorant, but one must work hard to remain stupid.
|
|
Dante Chusuk
eHarmony Inc.
18
|
Posted - 2013.12.26 11:03:00 -
[11] - Quote
crononyx wrote:Amarr Citizen 1312151005 wrote: So a coding issue in other words? Same reason my I7 is worthless for eve client side.
Well, it allows you to run multiple clients smoothly. And other software as well.
This, I remember getting one of the first AMD X-2s when they came out (rather than an Intel "virtual" core), made a fair amount of difference to three accounts running ... but this was back in deepest, darkest 2004/05 ... |
Amhra Rho
Accujac Elimination
268
|
Posted - 2013.12.26 12:34:00 -
[12] - Quote
A big part of the genius of the game is that its back-end is run on a single monster server. No other gamer really does it this way, and while it's ingenious in many ways, that single server is also Eve's biggest constraint.
From what I've read (extensively, btw), I'm pretty satisfied that CCP has thought of just about everything at this point with regards to maximizing that single server's potential. Prognosticators are saying that 2014 will be a huge year for server technology, though, (here and here for instance), so maybe we'll soon see some changes and upgrades. There's real reasons why your Eve character doesn't do /dance. |
ElQuirko
Black Dragon Fighting Society The Devil's Tattoo
2924
|
Posted - 2013.12.26 12:37:00 -
[13] - Quote
Amarr Citizen 1312151005 wrote:Xercodo wrote:Nope, CCP's pretty much already using the most advanced stuff they can afford. It's really a coding problem that will simply take time to work out.
They gave TiDi as a band aid to the problem until such a time as they have the ultimate solution. I know they are using the most advanced stuff they can afford but could of of the top 2 super computers run it? IIRC they're already using at least one supercomputer combined with the node system. Their tech is seriously advanced. Dodixie > Hek |
Sentient Blade
Crisis Atmosphere
1088
|
Posted - 2013.12.26 12:44:00 -
[14] - Quote
As far as I know, they're not using a "supercomputer" to run specific nodes, at least under any accepted terminology I have seen. Instead, their super-RF nodes are extreme-level chip with most of their cores turned off, to act as heat sinks for the individual cores which run at very-high overclocks to get ultra-high speeds, but still put through less computations a second than your high-end home PC running off all its cores at once.
The problem is in the coding architecture and its single threaded nature. Although CCP has said they have made some steps towards parallel offloading it seems the nature of the beast remains that it's single-threaded. Until this changes CCP is hamstrung - although they're doing a damn fine job of working with what they've got.
It's going to take a massive amount of work... but the other question is, is it worth it? Do we necessary want 3,000 people on a node, or should the game mechanics be altered so it's not beneficial / required to do so. |
Azami Nevinyrall
Red Federation RvB - RED Federation
1458
|
Posted - 2013.12.26 12:51:00 -
[15] - Quote
Optimized coding would fix TiDi, but that's too hard. Here's a bandaid.... ... |
Tippia
Sunshine and Lollipops
18045
|
Posted - 2013.12.26 12:52:00 -
[16] - Quote
Aside from the answer of GĒ£noGĒ„ that people have already given, you don't really want to fix tidi anyway. Tidi itself is a fix for a problem; you don't want that fix removed because then the problem comes back. GĒ£If you're not willing to fight for what you have in GėķvGėķ you don't deserve it, and you will lose it.GĒ„
Get a good start: newbie skill plan 2.0. |
Robert Caldera
Caldera Trading and Investment
658
|
Posted - 2013.12.26 12:56:00 -
[17] - Quote
you guys are just looking at CPU load which grows linear but ignore network load completely, which however increases quadratically with the number of clients on grid. Assuming server architecture scales perfectly (it doesnt) and you can stuff more and more CPUs into the cluster, you cant extend your netzwork bone infinitely, things have physical limits. |
Logan Revelore
Minimal Solutions Aurora Irae
16
|
Posted - 2013.12.26 13:03:00 -
[18] - Quote
It could also be a bandwidth limitation. |
James Amril-Kesh
4S Corporation Goonswarm Federation
7242
|
Posted - 2013.12.26 13:09:00 -
[19] - Quote
Logan Revelore wrote:It could also be a bandwidth limitation. No. The amount of bandwidth used by EVE is really, really small. Latest video - Pandemic Legion titan and supers killed |
Jonah Gravenstein
Machiavellian Space Bastards
14994
|
Posted - 2013.12.26 13:13:00 -
[20] - Quote
James Amril-Kesh wrote:Logan Revelore wrote:It could also be a bandwidth limitation. No. The amount of bandwidth used by EVE is really, really small. As in playable over 56k Dialup IIRC, I've played over a 3G connection with no problems. |
|
Robert Caldera
Caldera Trading and Investment
658
|
Posted - 2013.12.26 13:13:00 -
[21] - Quote
James Amril-Kesh wrote:Logan Revelore wrote:It could also be a bandwidth limitation. No. The amount of bandwidth used by EVE is really, really small.
yes, for you maybe, for the server side its multiplied by the total number of interacting nerds.
In a simplified model lets assume one particular grid would result in network traffic volume of 1 bytes per player and there would be 1 guy on grid -> ensueing server load of 1 bytes per tick for 1 player. As soon as another player enters the grid would mean 2 bytes of grid data communicating to 2 these players = 4 bytes total load. With 3rd player on scenery, its 3x3=9 bytes to be communicated over all participants. 4 player = 16 bytes, 5 players = 25 bytes. you see the network requirement grows quadratically with the number of players in a room sharing same universe. There is surely some optimization implemented to flatten the load curve a bit but you got the basic idea. |
Lors Dornick
Kallisti Industries Solar Assault Fleet
895
|
Posted - 2013.12.26 13:14:00 -
[22] - Quote
Amhra Rho wrote:A big part of the genius of the game is that its back-end is run on a single monster server. No other gamer really does it this way, and while it's ingenious in many ways, that single server is also Eve's biggest constraint. Well no.
TQ is a cluster of several servers with several blades with load and functions shared over the cluster.
The issue is that a the in space calculations for a single system can't be split over multiple servers. CCP Eterne: Silly player, ALL devs are evil. CCP Fozzie: When Veritas describes a programming challenge as "very hard" I tend to believe him.
|
Sarah McKnobbo
Griffin Capsuleers Ad-Astra
29
|
Posted - 2013.12.26 13:23:00 -
[23] - Quote
There was a post by a dev after the last node crash during a big sov battle, where they said the last 3 crashes were down to coding/program errors, not actual server overload. I can't find it at the minute, forum searching is horrid on a smartphone with a cracked screen! |
Amhra Rho
Accujac Elimination
268
|
Posted - 2013.12.26 13:28:00 -
[24] - Quote
Robert Caldera wrote:you guys are just looking at CPU load which grows linear but ignore network load completely, which however increases quadratically with the number of clients on grid. Assuming server architecture scales perfectly (it doesnt) and you can stuff more and more CPUs into the cluster, you cant extend your network bone infinitely, things have physical limits. Not necessarily the case. You'll find I've provided links that speak to not only the CPU, but the RAM base - as well as how Intel will soon address DDR4 server RAM in the next fiscal quarter - the aggregate bandwidth, load balancing (that's been more than optimized), WAN links (also optimal), multi-threading (largely constrained by the code, as mentioned above), use of fiber infrastructure, advanced leveraged VLAN bandwidth switching, real time system monitoring and response, judicious use of virtualization, strategies for managing huge numbers of multiple connections that's been borrowed from recent advanced cloud computing technology, and SSD drive implementation.
I just can't see where you can take a conservative stance with the intention of ensuring stability, predictability and reliability, while at the same time performing a wholesale systems upgrade to something that would function markedly better at this point. In other words, I really think they've thought of everything for now. There's real reasons why your Eve character doesn't do /dance. |
Kagura Nikon
Mentally Assured Destruction The Pursuit of Happiness
976
|
Posted - 2013.12.26 13:33:00 -
[25] - Quote
Amarr Citizen 1312151005 wrote:Just wondering would a more powerful server fix tidi? Or is it more of a coding issue? Just wondering this because I got bored and started looking up super computer's. The two fastest in the world run at about 20 and 40 petaflops.
And I thought I had read somewhere that tranquility runs at like 300-400 teraflops. Could one of these super computers handle large eve battles without tidi? This is of course hypothetical.
But just curious if it would ever be possible to see the end of tidi. I am thinking hardware wise the tech is out there while not realistic for a small company like ccp to obtain and maintain.
I would think if one if those super computers where designed with the purpose of running eve they could more than handle the processing needs. And in time I think we could see an end to tidi.
However if tidi is related to some deeply coded issue I think we may never see its end..
TL:DR. Could tidi be fixed with pure power or is it a coding issue that may never be fixed?
Do not try to find solutions whn that is not your expertise area. Super computers are massively parallel systems. That measurement is throughput not local speed on a defined thread, therefore irrelevant for the issue. "If brute force does not solve your problem..... -įthen you are -įsurely not using enough!" |
Amhra Rho
Accujac Elimination
268
|
Posted - 2013.12.26 13:35:00 -
[26] - Quote
Lors Dornick wrote:Amhra Rho wrote:A big part of the genius of the game is that its back-end is run on a single monster server. No other gamer really does it this way, and while it's ingenious in many ways, that single server is also Eve's biggest constraint. Well no. TQ is a cluster of several servers with several blades with load and functions shared over the cluster. The issue is that a the in space calculations for a single system can't be split over multiple servers. By definition, a clusteris a single virtual server. Clustering indeed leverages multiple identical physical "boxes" for the purposes of either load balancing or failover, or both, but the cluster will always "read" as a singular server. There's real reasons why your Eve character doesn't do /dance. |
Kagura Nikon
Mentally Assured Destruction The Pursuit of Happiness
976
|
Posted - 2013.12.26 13:36:00 -
[27] - Quote
Amarr Citizen 1312151005 wrote:Ibrahim Vaughn Holtzman wrote:Supercomputers only work great if they can compute massively parallel.
Eve's backend, however, is mostly single-threaded and scales terribly with number of cores and/or threads. It is basically from a time when Intel kept insisting that 10GHz-CPU's are right around the corner. Which didn't happen due to exponential thermal output. So a coding issue in other words? Same reason my I7 is worthless for eve client side.
Nope, its a fundamental problem of what is being tryied to acomplish. If you tried to make eve massively paralel on each noce you would face a lot of OTHER issue.
If this was somethign easy to solve by a random internet guy, software engineers would not have such high pay grades. "If brute force does not solve your problem..... -įthen you are -įsurely not using enough!" |
Kagura Nikon
Mentally Assured Destruction The Pursuit of Happiness
976
|
Posted - 2013.12.26 13:37:00 -
[28] - Quote
Amhra Rho wrote:Lors Dornick wrote:Amhra Rho wrote:A big part of the genius of the game is that its back-end is run on a single monster server. No other gamer really does it this way, and while it's ingenious in many ways, that single server is also Eve's biggest constraint. Well no. TQ is a cluster of several servers with several blades with load and functions shared over the cluster. The issue is that a the in space calculations for a single system can't be split over multiple servers. By definition, a clusteris a single virtual server. Clustering indeed leverages multiple identical physical "boxes" for the purposes of either load balancing or failover, or both, but the cluster will always "read" as a singular server.
Externally yes, but internal to the proccess beign executed not necessarily. YOu can code it manually to distribute the load or use APIs like MPI to offload foryou between nodes, but its never completely transparent for the software. "If brute force does not solve your problem..... -įthen you are -įsurely not using enough!" |
Themanfromdalmontee
EVE RADIO ARMY
1
|
Posted - 2013.12.26 13:46:00 -
[29] - Quote
Not sure why people complain about a bit of tidi, its fun :)
|
Amhra Rho
Accujac Elimination
268
|
Posted - 2013.12.26 13:48:00 -
[30] - Quote
Kagura Nikon wrote:Amhra Rho wrote:Lors Dornick wrote:Amhra Rho wrote:A big part of the genius of the game is that its back-end is run on a single monster server. No other gamer really does it this way, and while it's ingenious in many ways, that single server is also Eve's biggest constraint. Well no. TQ is a cluster of several servers with several blades with load and functions shared over the cluster. The issue is that a the in space calculations for a single system can't be split over multiple servers. By definition, a clusteris a single virtual server. Clustering indeed leverages multiple identical physical "boxes" for the purposes of either load balancing or failover, or both, but the cluster will always "read" as a singular server. Externally yes, but internal to the proccess beign executed not necessarily. YOu can code it manually to distribute the load or use APIs like MPI to offload foryou between nodes, but its never completely transparent for the software. I'm running the risk that we might be saying the exact same thing, but just to be clear, yes, what you describe is cluster-level load balancing. It works like this - you have, say, nine physical boxes in the cluster. It shows up on your management screens as a single computer with, say, a singular (virtual) drive C:. You can indeed leverage that cluster-level load balancing feature as follows: give a little bit of the processing to box number 3 until it starts to be taxed, then switch the processing to a languishing box number 8 for a while, etc. In other words, you can't view all the multiple cores which are in turn each hyperthreaded as a single CPU - you literally have to parcel out tasks to one physical CPU in the cluster, followed by the next, etc.
Again, it's possible we are saying the same thing. There's real reasons why your Eve character doesn't do /dance. |
|
|
|
|
Pages: [1] 2 3 :: one page |
First page | Previous page | Next page | Last page |