Linked by Eugenia Loli on Thu 7th Apr 2005 02:04 UTC, submitted by David Rhodus
Permalink for comment
To read all comments associated with this story, please click here.
To read all comments associated with this story, please click here.
News
Linked by Thom Holwerda on 05/21/13 22:06 UTC
Linked by Thom Holwerda on 05/21/13 21:45 UTC
Linked by Thom Holwerda on 05/21/13 15:53 UTC
Linked by Thom Holwerda on 05/20/13 22:43 UTC
Linked by Thom Holwerda on 05/20/13 21:50 UTC
Linked by Thom Holwerda on 05/19/13 23:15 UTC
Linked by Thom Holwerda on 05/19/13 23:11 UTC, submitted by Drumhellar
Linked by Thom Holwerda on 05/18/13 21:06 UTC
Linked by Thom Holwerda on 05/18/13 7:37 UTC
Linked by fran on 05/18/13 1:38 UTC
More News »
Sponsored Links



How do you have a lockless path in an SMP environment and still share resources?
There are a lot of lockless algorithms and data structures.
The schemes preferred the Linux kernel where scalability is important are firstly per-CPU data structures where possible, then things like RCU and seqence/generation counting with read retry, atomic modification of data, etc.
Do you mean they focus on minimizing lock operations by increasing the ammount of code covered by a single locked segment?
No. In Linux, you lock data, not code. And where locks are used, the focus is on having as narrow a hold width as possible.
In this case, you inhibit the option for preemption which incurs latency. There is always a trade off. Lunix has been working on SMP a lot longer than FreeBSD. Give it a chance.
Actually FreeBSD developers used to brag about having a working SMP implementation before Linux, which I think may have been true - if not then it would have been very close, definitely not "a lot longer".
And it's not about giving it a chance or not. It simply currently does not have a good SMP implementation.