Pages: 1 [2] 3 4 :: one page |
|
Author |
Thread Statistics | Show CCP posts - 7 post(s) |
Typhena
Blueprint Haus Intrepid Crossing
|
Posted - 2008.10.06 21:30:00 -
[31]
Originally by: CCP Mindstar
To clarify the fleet fight notifications. It should be clarified that this is not a way to simply "ask and ye shall receive a dedicated node". It is a way of telling the people that make the decisions that you are planning something. In short - we are listening if you wish to tell us there will be a big fight. If we can, we will make sure it is running on the best hardware it can.
I'm not used to reply or comment this kinda news, but .. For the first time I can see CCP doing something feasible to improve our game play. I hope you guys keep the good work and effort before any other expansion.
Just a clarification to avoid misunderstanding : what would be a "Fleet Fight" (ballpark number of course!) based on your current experience? 100 in the same system? 200? 500? over 1000?
I guess over 250 would be a reasonable number, but I prefer to read your opinion --- Sig Under Construction |
Arous Drephius
Perkone
|
Posted - 2008.10.06 21:44:00 -
[32]
Yay more tech blogs, way to go CCP!
|
|
ISD Serathu Ashk
ISD Interstellar Correspondents
|
Posted - 2008.10.06 22:04:00 -
[33]
I came across some news the other day that CCP is implementing the Cisco ACE blade in its London datacenter in order to increase the performance of applications at the network layer.
Having been involved in an ACE blade implementation before, I'm interested to know what this was used for and if it has anything to do with all of these lovely performance benefits.
Can anyone shed any light on this please?
*smiles sweetly*
|
|
Haradgrim
Tyrell Corp INTERDICTION
|
Posted - 2008.10.06 22:17:00 -
[34]
Originally by: Danny Centurai
Originally by: DogTyred
Originally by: Danny Centurai
What could also be put in place is a region/constellation standby report, something like ok we know BOB are going to invade Tribute but we donÆt know where they will hit next. This would mean DevÆs monitoring Tribute and doing their wizardry if necessary, this is open to some omg dev intervention comments but its then at the alliances discretion do we want things monitoring or do we want it to remain 100% secret.
Damm caod said we're going to Fountain
I honestly can't believe you managed to read my whole post and get far enough to quote this bit. Thanks for sticking with me dude.
You had me at hello? --
Originally by: CCP Oveur ...every forum whine feels like a baby pony is getting killed
|
Wired
Caldari Provisions
|
Posted - 2008.10.06 22:25:00 -
[35]
Quote: Our 3.0Ghz Intel Woodcrest blades are nice, but that processor architecture has been replaced by Wolfdale, which is even more powerful. So we have put a fast-track order in for some Intel Xeon 3.3Ghz Wolfdale blades.
So if you've got some spare 3Ghz Woodcrest, can i have your stuff please?
I love reading about techie stuff, more please. =============================================
My sig got edited, and all i got was a lousy e-mail |
Mashie Saldana
Sharks With Frickin' Laser Beams
|
Posted - 2008.10.06 22:39:00 -
[36]
I'm curious how your Wolfdale blades will be configured as I have yet to see 4GB non ECC memory modules. The P45 and similar chipsets do support 16GB RAM however they only have 4 memory slots. So, do IBM offer socket 775 motherboards with 8 memory slots or have they developed 4GB sticks? I guess the other option is to run on only 8GB.
|
Aprudena Gist
GoonFleet GoonSwarm
|
Posted - 2008.10.06 22:52:00 -
[37]
Originally by: Mashie Saldana I'm curious how your Wolfdale blades will be configured as I have yet to see 4GB non ECC memory modules. The P45 and similar chipsets do support 16GB RAM however they only have 4 memory slots. So, do IBM offer socket 775 motherboards with 8 memory slots or have they developed 4GB sticks? I guess the other option is to run on only 8GB.
Well they are moving to 64 bit version of eve server to help with scalability so yes they would most likely do 8 or 16gb setups. They Intel Setup they have for jita currently is a 16gb one.
|
Fastercart
Gallente Ihatalo Heavy Industries Ihatalo Cartel
|
Posted - 2008.10.06 23:22:00 -
[38]
Originally by: Wired
Quote: Our 3.0Ghz Intel Woodcrest blades are nice, but that processor architecture has been replaced by Wolfdale, which is even more powerful. So we have put a fast-track order in for some Intel Xeon 3.3Ghz Wolfdale blades.
So if you've got some spare 3Ghz Woodcrest, can i have your stuff please?
I love reading about techie stuff, more please.
Dang, you beat me to it. And, I agree, more tech blogs. __ Rorqual AKA Mega Maid
Oh, my God. It's Mega Maid. She's gone from suck to blow. |
Mashie Saldana
Sharks With Frickin' Laser Beams
|
Posted - 2008.10.06 23:30:00 -
[39]
Originally by: Aprudena Gist
Originally by: Mashie Saldana I'm curious how your Wolfdale blades will be configured as I have yet to see 4GB non ECC memory modules. The P45 and similar chipsets do support 16GB RAM however they only have 4 memory slots. So, do IBM offer socket 775 motherboards with 8 memory slots or have they developed 4GB sticks? I guess the other option is to run on only 8GB.
Well they are moving to 64 bit version of eve server to help with scalability so yes they would most likely do 8 or 16gb setups. They Intel Setup they have for jita currently is a 16gb one.
It's a hardware limitation with the Wolfdale as they use socket 775 and hence limited to unbuffered (non ECC) DDR2/DDR3 memory. The Woodcrest systems (running Jita) are Xeon based and uses ECC. The thing is ECC based systems are designed to handle a lot more memory, after all some Xeon motherboards can handle up to 192GB.
|
Dr Slaughter
Minmatar Rabies Inc.
|
Posted - 2008.10.06 23:55:00 -
[40]
Awesome news.. awesome information and awesome to get an update on what's happening with the infrastructure too!
Now all I need is to convince the wife I need to go to Iceland to learn about HPC.... ~~~~ There is no parody in this thread. Honest. |
|
Maren Maen
|
Posted - 2008.10.07 01:10:00 -
[41]
SOL Blades, huh? As in "$#!& out of Luck" I'm guessing...
|
Koyama Ise
Caldari Equestrian Knight Order of Lolicon
|
Posted - 2008.10.07 01:39:00 -
[42]
Just wondering is this a precursor to Dynamic Load Distribution? Which I fairly sure you haven't implemented yet (In Refrence to Dynamic Load Distribution) due to the huge implications involved with reworking the system like that so it takes a while. ----- Cause it can't be quoted enough.
Originally by: Damned Force Something like: Nanoships need a nerf but only the 10km/s+ ships. Nano HACs to slowboating Battleships wil be ****ed by this nerf.
|
Raist Varis
Sensus Numinis
|
Posted - 2008.10.07 02:18:00 -
[43]
Very nice! More! Now!
|
Nick Faulkner
|
Posted - 2008.10.07 04:50:00 -
[44]
Edited by: Nick Faulkner on 07/10/2008 04:51:14 Hi, Thanks for the informative post. Good to see that you guys are upgrading the hardware to the latest and greatest.
In your post you made it clear that AMD Opteron with 4GB is no match for Intel Xeon 3.0Ghz Woodcrest with 16GB ram. I was wondering if you performance tested the Opteron with 16GB in 64 bit.
What percentage of the performance increase is attributed to memory? And, what percentage of the performance increase is attributed to cpu?
Thanks, Nick.
|
Garia666
Amarr T.H.U.G L.I.F.E White Core
|
Posted - 2008.10.07 05:40:00 -
[45]
Edited by: Garia666 on 07/10/2008 05:43:00 Best news since long time. excellent work ccp.. keep it up.
Great btw for the MAX pain campaign.. lets hope bob kicks some more ass. the failswarm will be a nice target.. www.garia.net |
Gnulpie
Minmatar Miner Tech
|
Posted - 2008.10.07 05:54:00 -
[46]
Lots of improvements and lots of plans!
Keep up the good and exciting work :)
The fleet/battle/hots-pot notification is something which needs to be done with care though. Perception is everything and if one side feels being cheated (if true or not doesn't matter!!) then more harm than good is done.
|
|
Chribba
Otherworld Enterprises Otherworld Empire
|
Posted - 2008.10.07 06:19:00 -
[47]
Can I buy your old hamsters for Veldspar to beef up my services a bit? EVE-Search would like a new database server or two hehe
Keep up the good work!
Secure 3rd party service ■ Veldspar |
|
Nova Fox
Gallente Novafox Shipyards
|
Posted - 2008.10.07 07:37:00 -
[48]
For those of you crying about automation as a more advanced solution to areas needing dedication I ask why not upgrade the entire sol cluster to the machine the dedicated servers run off of?
Pre Order your Sisters of Eve ship today!!! |
ju4n1ta
Gallente The Scope
|
Posted - 2008.10.07 07:52:00 -
[49]
Edited by: ju4n1ta on 07/10/2008 07:53:06 I just want to say you made me a very happy panda today!!! Interacting with players to help improve game experience in suck a direct and constructive manner has been unheard of (by me at least). Keep up the good work with the hamsters running TQ, keep up the good work with people behind the scenes and again job well done on improving this game!!
|
Kerfira
|
Posted - 2008.10.07 07:54:00 -
[50]
Yet ANOTHER tech blog... Are you guys trying to charm us into insensibility?
Oh, what the heck... it's working.... MORE TECH BLOGS!!!!
Originally by: CCP Wrangler EVE isn't designed to just look like a cold, dark and harsh world, it's designed to be a cold, dark and harsh world.
|
|
Myrhial Arkenath
Ghost Festival
|
Posted - 2008.10.07 08:29:00 -
[51]
Considering lots of players in one area is something that makes most mmo's crash if you only get a few hundred people in one spot I am pretty impressed by the way this game deals with that.
Diary of a pod pilot |
Lucas Avignon
Avignon Associates Inc.
|
Posted - 2008.10.07 08:37:00 -
[52]
Originally by: CCP Mindstar
Originally by: mechtech Shouldn't you wait for Nehalem to come out?
Those processors are about 50% faster in server based applications.
This is an interesting question, and one we have talked with our suppliers at length about. Essentially, it comes down to the fact that the Nehalem will not be running at speeds that will be useful for EVE until late next year. It is true that Nehalem makes some good advances in for server applications, however the nature of the current EVE process being mostly single threaded means that going with higher clock speeds and less cores gives us a much greater performance gain.
In the future we may be able to better utilise the Nehalem (or some subsequent technology), however for what EVE needs at this point, we really can't find something that tops the Wolfdale.
So basically your going to use the new E8600 or repackaged server version, I believe that is the last in the line of dual core solutions from intel and will be the highest clocked core for quite a while.
My only question is, do you plan to overclock these new cpus, taking advantage or their incredible overclocking head room.
It seems these cpu's overclock to over 4.5ghz and can overclock to 3.9ghz without voltage manipulation.
Oh and make sure to check with your supplier that the cpus are using the newer E0 stepping as opposed to the older C0 stepping
Originally by: CCP Prism X Yeah, and while we're at it we can create a controlled environment around account hacking and credit card fraud and all the other EULA breaches..
|
Mioelnir
Minmatar Meltd0wn iPOD Alliance
|
Posted - 2008.10.07 08:40:00 -
[53]
Edited by: Mioelnir on 07/10/2008 08:44:46
Originally by: Nova Fox For those of you crying about automation as a more advanced solution to areas needing dedication I ask why not upgrade the entire sol cluster to the machine the dedicated servers run off of?
I think you missed the part about gradually upgrading the cluster, but they obviously can't swap the whole thing in one go.
Meanwhile they put their (originally) test hardware live and use it, instead of telling us it will all be cool in a few months when all the new hardware is in place.
And to the tinfoil experts, one may or may not be paranoid enough to not report the start of a secret invasion plan. But there is hardly anything even remotely secret about the end of an important POS's RF timer for example. Oh, and you don't have to use it obviously.
[Edit] @ Lucas: you've never run a service that had 'reliability' in its description, have you?
|
Necronomicon
Caldari KIA Corp KIA Alliance
|
Posted - 2008.10.07 08:42:00 -
[54]
Originally by: CCP Mindstar To clarify the fleet fight notifications.
When we receive a petition indicating that there is likely to be a fleet fight in a certain place, at a certain time - this will be escalated to the Virtual World Administration team (we are the guys that run the EVE Cluster itself). During the next day at downtime, we will look at all available information and decide based on that as to which systems we will allocate onto this hardware. Things such as current conflicts - what areas have been "hot" in the last few days and weeks.
It should be clarified that this is not a way to simply "ask and ye shall receive a dedicated node". It is a way of telling the people that make the decisions that you are planning something. In short - we are listening if you wish to tell us there will be a big fight. If we can, we will make sure it is running on the best hardware it can.
If you are worried about people abusing this system of notification, please understand that we have ensured both the lead Game Masters and Internal Affairs have been involved in every step of this process. Every petition and any action (such as putting a certain system on a dedicated sol server) is under their watchful eye.
None of this is going to stop CCP employee xyz contacting Alliance Leader abc on MSN/IRC and telling them though, is it?
KIA - Don't ask me, I was off grid.
|
Mioelnir
Minmatar Meltd0wn iPOD Alliance
|
Posted - 2008.10.07 09:04:00 -
[55]
Originally by: Necronomicon None of this is going to stop CCP employee xyz contacting Alliance Leader abc on MSN/IRC and telling them though, is it?
And nothing is going to stop Alliance Leader abc from replying: "Yeah, yeah, I know already."
There is no secrecy in eve.
|
Niraco79
Gallente Black Nova Corp Band of Brothers
|
Posted - 2008.10.07 09:33:00 -
[56]
Are there any investigation on the inability to log in in a reinforced node after the battle started?
Is this client/server side related or I/O related?
Thank you
|
Niccolado Starwalker
Shadow Templars
|
Posted - 2008.10.07 10:42:00 -
[57]
Stupid question.. but is EVE64/StacklessIO the same as the reputed infiniband?
Good work anyway CCP!
Originally by: Dianabolic Your tears are absolutely divine, like a fine fine wine, rolling down your cheeks until they flow down the river of LOL |
The Beekeeper
|
Posted - 2008.10.07 10:42:00 -
[58]
Nice blog, gotta love the techie stuff
Quote: At peak hours, our database is processing over 2,000 transactions per second, which generates around 38,000 IOPS (input output operations per second)
This seems really quite low, those ramsans must be sitting around bored half the time, and I would have thought an enviroment such as eve's would generate way more transactions.
|
Franga
NQX Innovations
|
Posted - 2008.10.07 10:49:00 -
[59]
Oh, this is sexah. You finally got the idea that we like frequent, useful dev-blogs.
<3 you guys. ----------
|
Deva Blackfire
D00M.
|
Posted - 2008.10.07 11:14:00 -
[60]
Im quite happy with results but i have one thingy: why most clients blackscreen on system load while jumping in/logging on? Which part of server architecture is responsible for it? And finally - is it possible to see fix in forseable future? ;p
|
|
|
|
|
Pages: 1 [2] 3 4 :: one page |
First page | Previous page | Next page | Last page |