Jump to content

Recommended Posts

Posted
Should/will multithreaded maps increase performance on a single core cpu?

I doubt it, this patch was mainly ment to get the load off the main thread to have more room till 1 cpu core is used with 100% by that thread.

Posted
I am somewhat befuzzled as to how this works exactly, but I do have a question:

Should/will multithreaded maps increase performance on a single core cpu?

on a single core cpu there would be no advantage to a multiple threads as in the end all threads are executed on the same core. the multi threaded maps is, like stated above, to allow the OS to distribute the load to the additional cores on a multicore system.

on a single core system the OS alots time slices to each thread so you would see no advantage to it.

  • 4 weeks later...
Posted

Any progress here?

I test now for about 1 month the branch from the beginning of November which was created by Scamp and it is STABLE and FAST and it use all CPUs fine, I don't get why nobody care about it anymore cause it make Mangos a lot better.

Posted

I hope so too because without this patch mangos lags like h*ll....at least the last time I tried. That's why I am sticking with an old revision..

Or is the big-lag-spike-thing solved in the latest Git-revisions because of maybe more async queries? Can someone confirm or disprove?

Posted
I hope so too because without this patch mangos lags like h*ll....at least the last time I tried. That's why I am sticking with an old revision..

Or is the big-lag-spike-thing solved in the latest Git-revisions because of maybe more async queries? Can someone confirm or disprove?

with ~600-800 players it lag's often, from time to time it's like hell (like you said)... hope someone fixes this

Posted

I currently running ~1250 people without any bigger problems, althought the main thread of mangos is draining 100% on core most of the time and you can already notice it's getting unsmooth ingame.

I also think the mtmaps patch could really help with that. There is free room on the other cpu core that could easily take 1 or 2 map threads.

Posted

Thanks for the answers guys. Yeah, I hope derex can find some of his valuable time to look at this!

--Derex if you are reading this...yes, this is a scream for help -- haha ;)

  • 3 weeks later...
Posted

how do u do the test. is there really 1250 guys in the server? or u have developed a self client that can play automatically with script?

I want to test it by myself, but large ammount of connection with game activity is difficult to get.

leak, Can u help?

Posted

That's no test, those a really 1250 people. I think you can't really meassure performance by spawning bots with lets say Pseuwow. The interaction as in combat, movement, etc. are the real performance drainers.

Posted
The interaction as in combat, movement, etc. are the real performance drainers.
Interesting claim .. one would figure that handling creatures should take more time than players since there may be a thousand players but tens of thousands of creatures ..
Posted

sad mtmaps dont work anymore, and without them mangos lags really lot, if u have LOS=1

anyone got working mtmaps for latest rev? :(

or give me some test patch, i can really test performance with real testers (1***many)

  • 1 month later...
Posted

compile error unter linux:

../game/libmangosgame.a(MapUpdater.o): In function `MapUpdater::activated()':

/../../src/game/MapUpdater.cpp:135: undefined reference to `DelayExecutor::activated()'

../game/libmangosgame.a(MapUpdater.o): In function `MapUpdater::activate(unsigned int)':

../../../src/game/MapUpdater.cpp:90: undefined reference to `DelayExecutor::activate(int, ACE_Method_Request*, ACE_Method_Request*)'

with actually revsiion from multithreading,a nd newest mangos git

Guest
This topic is now closed to further replies.
×
×
  • Create New...

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue. Privacy Policy Terms of Use