June 2003
- Damage and Stuff (Math and Code) Ben Chambers
- MMO Launch issues ruining potential segments of the market. Derek Licciardi
- MMO Launch issues ruining potential segments of the market. Mike Shaver
- MMO Launch issues ruining potential segments of the market. Daniel Anderson
- MMO Launch issues ruining potential segments of the market. Chris Holko
- MMO Launch issues ruining potential segments of the market. Matt Mihaly
- MMO Launch issues ruining potential segments of the market. Daniel.Harman@barclayscapital.com
- MMO Launch issues ruining potential segments of the market. Justin Coleman
- MMO Launch issues ruining potential segments of th e market. Daniel.Harman@barclayscapital.com
- MMO Launch issues ruining potential segments of th e market. Jeff Fuller
- MMO Launch issues ruining potential segments of the market. Matt Mihaly
- MMO Launch issues ruining potential segments of the market. Luca Girardo
- New Column by Dave Rickey "Engines of Creation" Now at Skotos Christopher Allen
- Announcing Shadow Door: an NPC Control Interface for Neverwinter Nights Robert Zubek
- ADMIN: So, what has been happening? J C Lawrence
- [Meta] Forward of moderated message J C Lawrence
- New Here MIKE MacMartin
- Looking for a GUI Mud Development program Snicker Furfoot
- Looking for a GUI Mud Development program Ben Greear
- ADMIN: List archives are now restored. J C Lawrence
- The Price of Being Male Rayzam
- The Price of Being Male Sasha Hart
- The Price of Being Male Daniel.Harman@barclayscapital.com
- The Price of Being Male Rayzam
- The Price of Being Male Byron Ellacott
- The Price of Being Male Dr. Cat
- The Price of Being Male Castronova, Edward
- The Price of Being Male Boyle, Paul
- The Price of Being Male Mark 'Kamikaze' Hughes
- The Price of Being Male Rayzam
- The Price of Being Male Mark 'Kamikaze' Hughes
- The Price of Being Male Rayzam
- The Price of Being Male Mark 'Kamikaze' Hughes
- The Price of Being Male Marian Griffith
- The Price of Being Male Paul Schwanz
- The Price of Being Male Rayzam
- The Price of Being Male Paul Schwanz
- The Price of Being Male Vincent Archer
- The Price of Being Male Rayzam
- The Price of Being Male Castronova, Edward
- The Price of Being Male Sasha Hart
- The Price of Being Male Mark 'Kamikaze' Hughes
- The Price of Being Male Amanda Walker
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Castronova, Edward
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Tazzik
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Tazzik
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Marian Griffith
- The Price of Being Male Sasha Hart
- The Price of Being Male Tom
- The Price of Being Male Marian Griffith
- The Price of Being Male Sasha Hart
- The Price of Being Male Marian Griffith
- The Price of Being Male Sasha Hart
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Castronova, Edward
- The Price of Being Male Richard A. Bartle
- The Price of Being Male Daniel.Harman@barclayscapital.com
- The Price of Being Male Paul Schwanz
- The Price of Being Male Daniel Anderson
- The Price of Being Male Travis Casey
- The Price of Being Male Paul Schwanz
- The Price of Being Male Travis Casey
- The Price of Being Male Chris Holko
- The Price of Being Male Travis Casey
- The Price of Being Male Sanvean
- The Price of Being Male Sasha Hart
- The Price of Being Male Tom
- The Price of Being Male Sanvean
- The Price of Being Male Paul Schwanz
- The Price of Being Male Amanda Walker
- The Price of Being Male shop@isparkinson.co.uk
- The Price of Being Male Boyle, Paul
- The Price of Being Male Ola Fosheim Grøstad
- The Price of Being Male Sheela Caur'Lir
- The Price of Being Male Jeff Crane
- Are gold pieces taxable? Koster, Raph
- Are gold pieces taxable? Boyle, Paul
- Are gold pieces taxable? Amanda Walker
- Are gold pieces taxable? Thomas Leavitt
- Are gold pieces taxable? Daniel.Harman@barclayscapital.com
- Functors / Loki (was: New Here) Eli Stevens
- Architecture Peter "Pietro" Rossmann
- Architecture Peter "Pietro" Rossmann
- Architecture ceo
- Architecture Peter "Pietro" Rossmann
- SW:G this is so unfair Marian Griffith
- SW:G this is so unfair Marc Bowden
- SW:G this is so unfair Martin Bassie
- Players policing themselves (was: MMO Launch issues ruining potential segments of themarket.) Derek Licciardi
- Q&A with Ken Troop, Lead Designer at Turbine Michael Tresca
- Q&A with Ken Troop, Lead Designer at Turbine Threshold RPG
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) Zach Collins {Siege}
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) Daniel.Harman@barclayscapital.com
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) Rossmann Peter
- Architecture (Cell Rebalancing) ceo
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) J C Lawrence
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) J C Lawrence
- Architecture (Cell Rebalancing) Rossmann Peter
- Architecture (Cell Rebalancing) Rossmann Peter
- Architecture (Cell Rebalancing) J C Lawrence
On Thu, 3 Jul 2003 12:06:38 +0200
Rossmann Peter <peter.rossmann@siemens.com> wrote:
> On Wed, 02 Jul 2003 13:59:40 -0700 ceo <ceo@grexengine.com> wrote:
> I havent been thinking that deeply about your words, (because i was
> confused by why you mention working sets) until now:
> My idea of working sets is that i would never see any page paged...
Page swapping is not the only impact of working sets. The rate of
working set migration is a primary factor in the effectiveness of the
dcache. In the multi-processor cases the rate of working set collision
and the rate of working set migration are primary factors in memory bus
saturation and cache invalidation (this is one of the more common
reasons that shared memory based systems can run dramatically slower on
SMP systems).
All memory is not equal. Take a simple example:
1) Allocate a block of say 2Gig
2) Traverse the block writing one byte to every memory page in the
block (if you're unsure of the page alignment of your block, just
write a byte every N bytes where N is a bit smaller than your system's
memory page size. Note: Its better if your randomise the order of
pages touched while ensuring that all pages are touched, rather than
hitting proximal pages.
3) Time how long that takes.
4) Now allocate a block which is a little less (128 bytes?) than one
memory page long (due to random alignment it will likely cross two
pages). The slightly smaller than page size is to accommodate sbrk()
overhead which could stretch the block across three pages.
5) Write the same number of bytes as you wrote in #2 to this new
block, but to (random?) locations in this smaller block.
6) Time how long that takes.
Don't waste your TLB or CPU caches.
> Using shared memory, you need to optimize data layout so to minimize
> cache misses.
This is tough. In the SMP case the simple fact of tracking and
maintaining coherency for a SHM between the CPU caches is a non-trivial
overhead. (Intel systems do particularly badly in this space)
> Otherwise, your program, even though it is expressed in a concurrent
> fashion, could run very very slow.
Quite.
--
J C Lawrence
---------(*) Satan, oscillate my metallic sonatas.
claw@kanga.nu He lived as a devil, eh?
http://www.kanga.nu/~claw/ Evil is a name of a foeman, as I live. - Architecture (Cell Rebalancing) Peter "Pietro" Rossmann
- Architecture (Cell Rebalancing) J C Lawrence
- Architecture (Cell Rebalancing) Daniel.Harman@barclayscapital.com
- Architecture (Cell Rebalancing) Peter "Pietro" Rossmann