open All Channels
seplocked EVE Information Portal
blankseplocked New Dev Blog: TQ Level Up
 
This thread is older than 90 days and has been locked due to inactivity.


 
Pages: first : previous : 1 2 3 4 [5] 6 7 8 9 ... : last (11)

Author Topic

Jaime Wulfe
Amarr
Space Marine Academy
Posted - 2010.06.16 22:25:00 - [121]
 

Damn I love upgrade time!

Envy Envy Envy!!!

Good Luck CCP!!

Musical Fist
Gallente
NAP Coalition
Posted - 2010.06.16 22:27:00 - [122]
 

Im confused still

How exactly will this affect players, I understand the technical side keeps getting spoke about but what exactly will it change for new players if anything?

What changes can we see after the 23rd?

Will this kill the lagg monster?

etc etc etc

Rikki Sals
Caldari
Posted - 2010.06.16 22:51:00 - [123]
 

10 ml epinephrine straight to the jugular should do it!! Very Happy

Doctor Ungabungas
Caldari
GoonWaffe
Goonswarm Federation
Posted - 2010.06.16 22:53:00 - [124]
 

Originally by: Barakkus
This is what I've been beating into my boss' head for the last 2 years. He found out about virtualization and he wanted to virtualize EVERYTHING in the office...I fought tooth and nail to keep some things on dedicated servers. Had to do the same thing when he found out about iSCSI...he figured a heavily loaded Exchange server and PostgreSQL server would be great on iSCSI Rolling Eyes


I used to run a fifty thousand user exchange 2k3 cluster on iSCSI, it works like a dream. [Compared to the alternative.]

Olleybear
Minmatar
I R' Carebear
Posted - 2010.06.16 23:00:00 - [125]
 

Originally by: Musical Fist
Im confused still...

How exactly will this affect players...

Will this kill the lagg monster?




1) CCP is increasing the size of the datacenter housing TQ.

2) At the same time they are increasing their server to server network capacity by 800%. They are expecting the increased network capacity to reduce lag.

3) They then go on to show the current TQ servers.

4) ** My Speculation ** By increasing both the size of the datacenter and the server to server network capacity, it sounds like our beloved TQ is about to get more/more powerfull servers. This will also reduce lag.

StuffYouFear
Posted - 2010.06.16 23:06:00 - [126]
 

Nice to hear what runs this crazy game, and love the shiny pic's :D looking forward to the next devblog

Musical Fist
Gallente
NAP Coalition
Posted - 2010.06.16 23:12:00 - [127]
 

Originally by: Olleybear
Originally by: Musical Fist
Im confused still...

How exactly will this affect players...

Will this kill the lagg monster?




1) CCP is increasing the size of the datacenter housing TQ.

2) At the same time they are increasing their server to server network capacity by 800%. They are expecting the increased network capacity to reduce lag.

3) They then go on to show the current TQ servers.

4) ** My Speculation ** By increasing both the size of the datacenter and the server to server network capacity, it sounds like our beloved TQ is about to get more/more powerfull servers. This will also reduce lag.


Cool thanks, now that I see it my comment may have came across a little *****y which wasnt my intention I was just confused on how we (players) benefitted from this :)

ihcn
Posted - 2010.06.16 23:24:00 - [128]
 

Not "no lag ever" though. Just an improvement.

smaster
BLOOM.
HYDRA RELOADED
Posted - 2010.06.17 00:14:00 - [129]
 

Originally by: CCP Yokai
Edited by: CCP Yokai on 16/06/2010 14:26:51Do some research and see how many servers someone like a game about secondary life needs to operate at that level.


The last time I was doing second life, there was no lag and no users yelling at their computers, hammering their keyboards in rage.

Louis deGuerre
Gallente
Malevolence.
Posted - 2010.06.17 00:18:00 - [130]
 

I'm a little turned on right now Embarassed

Also :

OMG, THE EVE APOCALYPSE IS NIGH ! Shocked

Cinori Aluben
Minmatar
Gladiators of Rage
Intrepid Crossing
Posted - 2010.06.17 00:22:00 - [131]
 

CCP Yokai, you have imbued me with much confidence in your capabilities, it looks as though CCP has done a very good thing in promoting you.
Great job responding to comments in this thread, and I eagerly look forward to your next blog!

You'll find there's quite a few EVE players who are specialists in just about any area (I'm only an amateur IT fan, Structural Engineering is my main focus), and CCP gains much by listening to their free consultations (though some may come across as rants).

Now don't let us down! Very Happy

Dacil Arandur
Habitual Euthanasia
Pandemic Legion
Posted - 2010.06.17 00:22:00 - [132]
 

Originally by: smaster
The last time I was doing second life, there was no lag and no users yelling at their computers, hammering their keyboards in rage.


That's because the hands of people who play Second Life are busy doing other things...

lceman
Gallente
FinFleet
Raiden.
Posted - 2010.06.17 00:28:00 - [133]
 

Is ccp gonna or currently testing out using GPU's to run server code with.
Both ati and nvidia offers this on their newer cards such as nvidia cuda, ati stream.

I belive they of better way of scaling and loadbalancing, and in many ways better processing power.

Confirm/deny please with pictures of tests results :)

next stop 5x sli/crossfire for the server room.
imo this interesting, cause it gives more ways to choose to upgrade hardware.

Chiralos
Merchant Princes
Posted - 2010.06.17 00:41:00 - [134]
 

Edited by: Chiralos on 17/06/2010 00:42:42
Originally by: A3A3EJ1b
I propose to place a server EVE in space .. geostationary orbit .. :)
Pluses:
1. cosmic cold.
2. solar energy.
3. lack of earthly disasters.


Minuses:
1. adding 250ms to everyone's ping
2. service call-out fee
3. danger of mutant space-hamsters

Inara Brey
Posted - 2010.06.17 01:03:00 - [135]
 

Originally by: Hawk TT
Edited by: Hawk TT on 16/06/2010 19:51:53

Ok, have you tested HS22 w/ Intel Xeon 5667 3.06/3.43GHz? It's a 4 core Westmere 32nm CPU (one generation ahead of Nehalem)?
The fastest CPU bin IBM would fit in a blade (95W TDP limit) is Xeon X5667 @ 3.06GHz, but it has turbo-boost, so one of the cores could go up to 3.43GHz.
If you combine this with the QPI benefits and other microarchitecture enhancements, you would have much better performance.
Let's see Intel X5600 vs X5200/X5400 series & HS22 vs HS21 blades:
- 200-300% memory bandwidth improvement (QPI vs. FSB)
- 40% memory latency reduction (QPI vs. FSB)
- 200% cache memory size w/ completely different cache hierarchy and much lower latency
- 50% more RAM capacity w/ the fastest cheap 4GB DDR3 1333MHz modules (12 x 4GB vs 4 x 8GB)



Listening to my IBM Tech Rep *last year*, CCP has seen the HS22. The Blade reps use CCP in presentations ... a lot.

So consider this another vote for an HS22 upgrade. Take it from a "big bank" SA, it is worth the extra heat. Just hot-swap one HS22 blade for Jita (please).

Lolion Reglo
Caldari Provisions
Posted - 2010.06.17 02:35:00 - [136]
 

Edited by: Lolion Reglo on 17/06/2010 03:18:03
I can see it now... The hamsters who were tired of working in cubicles running in their wheels all day with the over head AC only cooling them off a little bit as they constantly turn their wheels, your upgrading their cubicles to nice offices. each with their own AC vent in the office too.

Better yet your letting them be more social by putting all the offices next to each other which will only increase their productivity cause they're next to their friends. so what is next? a spa treatment package to relax those aching muscles from running the wheels all day to keep them in tip top performance?

hell if it keeps the lag down and keeps the game running more smooth i say break out the tiki torches, pour them a margarita and start to fan them with palm leaves to treat them like gods...rofl.Laughing

Originally by: Aisley Tyrion
All I can say is...

Prepare for unforeseen consequences. Twisted Evil


so long as they aren't experimenting with radioactive isotopes from deep in the earth and using portal technology to try and increase the TQ abilities then i don't foresee consequences...lol. nice reference... brought back good memories. hope they release ep 3 soon enough.

CommanderShepard1
Gallente
Kaleidascopic Military Association
Posted - 2010.06.17 02:50:00 - [137]
 

Very Happy The new gear looks sexxxxxxyLaughing

Kern Hotha
Posted - 2010.06.17 02:50:00 - [138]
 

Extra cold hamsters.

EdwardNardella
Capital Construction Research
Posted - 2010.06.17 03:10:00 - [139]
 

Have you looked into over clocking on all or some machines?

Digital Solaris
Posted - 2010.06.17 03:20:00 - [140]
 

But will it run Crysis? Surprised

TheShadow001
Posted - 2010.06.17 04:28:00 - [141]
 

Awesome! I love hearing about the technology behind EVE. It makes me all tingly inside.

<rant>
It's good to hear that code is being optimized. All to often IT is asked to throw hardware at problems that can be fixed with smarter coding (pet peeve of mine).
</rant>

Anikadir
JC Ferguson and Son Ltd
Ferguson Alliance
Posted - 2010.06.17 04:53:00 - [142]
 

Nice little space you have there. I manage a few caged cabinets in AU & HK, but haven't seen a covered cool aisle like that before. Do they make much difference? And 79kW, is that allocated or generated for the space?

Xearal
Minmatar
SOL Industries
Black Thorne Alliance
Posted - 2010.06.17 04:57:00 - [143]
 

Whoohoo! Nice new toys for TQ.. when are you going to install the pool of liquid nitrogen?

G'Kar5
Gallente
Intaki Research and Manufacturing
Distorted Percepts
Posted - 2010.06.17 05:09:00 - [144]
 

Edited by: G''Kar5 on 17/06/2010 05:10:26
Originally by: Lord XSiV

Your ignorance is obvious.

Cisco isn't used for anything important, just low end enterprise class. People think it is a good choice mainly because they don't know any better. When you get into moving massive amounts of traffic across large areas (or need very low latency, high bandwidth locally) then you go with some real hardware from Juniper.

I can let you in on a little secret in the tele/datacom space - Cisco isn't a hardware manufacturer, they create software. They make their money off IOS support contracts. The hardware is only a fraction of the cost (less than 5%) of purchase price leaving 95% for the services end. Essentially they outsource all of their production to the lowest cost bidders and use 'jit' production/distribution. This is why Cisco has one of the highest rate for port failures on their switching equipment; it is easier (and cheaper) for them to replace the gear under service contract as it ensures the client continues to pay for that contract.

Real companies that are part of critical infrastructure can't risk the downtime and poor performance offered by the Cisco line which is why you only see Juniper, Alcatel, Eriksson and even some old Nortel stuff used for major backbones by any of the 3 IECs. The smaller guys compromise and go with the Cisco junk and more often than not have a higher rate of occurrence for outages which at the end of the day costs them high end customers.




Sigh... http://www.lightreading.com/ Spend some time on that site.

See for edge router market share:
http://www.networkworld.com/community/node/48649

And the Internet core is mostly CRS-1/T1600 btw.

Yes, I know that Cisco doesn't make their own hardware. They just design the ASICs and IBM builds them; they OEM optics, etc. Cisco just assembles the pieces. But nobody really builds their own silicon in house nowadays.

In reality, no router/switch vendor really knows how to spell IP except for Juniper and Cisco. Yes, some companies bought good startups to give them an IP portfolio (Alcatel bought Timetra, Brocade bought Foundary, Ericsson bought Redback). I guess you should consider Huawei too, but I don't trust them at all.

If you want to argue about why CCP should use and MX over a 7600, then there are reasons. Both platforms have their pros and cons. Anyway, this argument is stupid as it pertains to Eve because network latency is not a problem. CCP is still using GE server connections anyway and almost any platform they picked can handle that just fine. If they need huge 10GE density, then I think Force10 is still the best density.

Lord XSiV
Amarr
Kodar Innovations
Posted - 2010.06.17 05:45:00 - [145]
 

Originally by: G'Kar5
Edited by: G''Kar5 on 17/06/2010 05:10:26


Sigh... http://www.lightreading.com/ Spend some time on that site.

See for edge router market share:
http://www.networkworld.com/community/node/48649

And the Internet core is mostly CRS-1/T1600 btw.

Yes, I know that Cisco doesn't make their own hardware. They just design the ASICs and IBM builds them; they OEM optics, etc. Cisco just assembles the pieces. But nobody really builds their own silicon in house nowadays.

In reality, no router/switch vendor really knows how to spell IP except for Juniper and Cisco. Yes, some companies bought good startups to give them an IP portfolio (Alcatel bought Timetra, Brocade bought Foundary, Ericsson bought Redback). I guess you should consider Huawei too, but I don't trust them at all.

If you want to argue about why CCP should use and MX over a 7600, then there are reasons. Both platforms have their pros and cons. Anyway, this argument is stupid as it pertains to Eve because network latency is not a problem. CCP is still using GE server connections anyway and almost any platform they picked can handle that just fine. If they need huge 10GE density, then I think Force10 is still the best density.



Well I guess you are validating what I stated to a certain extent but are still way off base if you think Cisco produces good product.

Then again you probably aren't or have been, nor will be for matter, in a position to architect a solution of critical significance. This is obvious due to your linkage to lightreading, the basic 'tabloid' equivalent in the tele/datacom space....

Furthermore, Cisco doesn't build their gear, its all outsourced including assembly. They don't even design their ASICs either, that is outsourced as well. As I said earlier they are a software company and that's it. You can drink their 'kool aid' all you want it still doesn't make a difference. Just like their definition of a 'A' class IP address is wrong, but don't tell a CCIE that or he might cry.... So in reality, strike Cisco off your list of vendors knowing 'IP'

I would ramble on more but it would probably be pressing the limits of some NDA points but regardless, it is still considered junk by top tier professionals. The simple and steady rule is you go big iron when important stuff is on the line. These days with the pricing being so low it might be advantageous to go with it anyhow once you factor in TCO. Cisco generally has the highest TCO because you are required to have an expensive support contract in comparison to a less costly support arrangement with Juniper. Plus you have the added knowledge knowing you don't have to worry about hardware failures due to quality issues Cisco is notorious for.


jaelle Nox
Posted - 2010.06.17 05:56:00 - [146]
 

Well, at last you change server, is that a sign that you anticipate the futur arrival and release of DUST 514 on that node ?

In your architecture, how EVE and DUST will be interract ?

Xeron Rich
Posted - 2010.06.17 06:26:00 - [147]
 

Edited by: Xeron Rich on 17/06/2010 06:26:13
ccp, you should make a timeline that shows each server improvement made since eve has began. i think it would be interesting to see. we all know how the game evolved, but not how the server evolved behind the game.

PS: let the lag fixing begin (i hope) :)

Rowbin Hod
InterSun Freelance
The Forsaken.
Posted - 2010.06.17 06:40:00 - [148]
 

I'm not sure why you went with cold aisle containment, the ba***rd stepchild of hot aisle containment. Creating a stable environment for the equipment is about the removal of the hot air as opposed to just blowing a load of cold ai at it.

Having said that, if you're still in Soevereign House, the ambient temperature is stupid as Telecity have no concept of an efficeint datacentre layout, so you can never be sure what you're getting.

Maybe you were right with cold aisle. Which is why you did it, I expect.

Artenac
Posted - 2010.06.17 07:58:00 - [149]
 

Originally by: Trick Novalight
Edited by: Trick Novalight on 16/06/2010 13:13:59
As someone who works in a data center and sees moves like this all the time, getting this done in 4 hours will be a HUGE task....that is if they haven't been prepping for this for the past few weeks and the 4 hours of downtime is actually due to copying files

(1x72GB hd? No raid 5? Seems like setting up 15k rpm HDs in raid 5 or raid 10 would help increase the read/write of the SQL database...)

If I Remember right a while back ( 06-07 ) CCP upgraded their disks to TI RanSam 4000's. All glorious top knotch solid state goodness.

HeliosGal
Caldari
Posted - 2010.06.17 09:07:00 - [150]
 

well seems like if it works its a good idea


Pages: first : previous : 1 2 3 4 [5] 6 7 8 9 ... : last (11)

This thread is older than 90 days and has been locked due to inactivity.


 


The new forums are live

Please adjust your bookmarks to https://forums.eveonline.com

These forums are archived and read-only