Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > comp.programming.threads > #2196 > unrolled thread

And about starvation...

Started byaminer <aminer@toto.net>
First post2014-04-19 21:56 -0700
Last post2014-04-19 21:57 -0700
Articles 2 — 1 participant

Back to article view | Back to comp.programming.threads


Contents

  And about starvation... aminer <aminer@toto.net> - 2014-04-19 21:56 -0700
    Re: And about starvation... aminer <aminer@toto.net> - 2014-04-19 21:57 -0700

#2196 — And about starvation...

Fromaminer <aminer@toto.net>
Date2014-04-19 21:56 -0700
SubjectAnd about starvation...
Message-ID<liv9g7$d0p$1@news.albasani.net>
Hello,

I think i will now change the fair lock unfair lock inside my 
SemaCondvar.pas that will be used by my concurrent FIFO queue,it has 
given a throughput of 7.4 millions millions of transactions per second 
for my concurrent FIFO queue , and what about the starvation problem ?

Please read this:

"The change to unfair locks clearly has the risk of leading to 
starvation.  But, statistically speaking, timing in concurrent systems 
tends to be so volatile that each thread will eventually get its turn to 
run, probabilistically speaking.  Many more programs would suffer from 
the convoy problems resulting from fair locks than would notice 
starvation happening in production systems as a result of unfair locks."


Please read the following:



http://joeduffyblog.com/2006/12/14/anticonvoy-locks-in-windows-server-2003-sp1-and-windows-vista/



Thank you,
Amine Moulay Ramdane.

[toc] | [next] | [standalone]


#2197

Fromaminer <aminer@toto.net>
Date2014-04-19 21:57 -0700
Message-ID<liv9im$d0p$5@news.albasani.net>
In reply to#2196
Hello...

I think i will now change the fair lock to unfair lock inside my 
SemaCondvar.pas that will be used by my concurrent FIFO queue,it has 
given a throughput of 7.4 millions millions of transactions per second 
for my concurrent FIFO queue , and what about the starvation problem ?

Please read this:

"The change to unfair locks clearly has the risk of leading to 
starvation.  But, statistically speaking, timing in concurrent systems 
tends to be so volatile that each thread will eventually get its turn to 
run, probabilistically speaking.  Many more programs would suffer from 
the convoy problems resulting from fair locks than would notice 
starvation happening in production systems as a result of unfair locks."


Please read the following:



http://joeduffyblog.com/2006/12/14/anticonvoy-locks-in-windows-server-2003-sp1-and-windows-vista/



Thank you,
Amine Moulay Ramdane.

[toc] | [prev] | [standalone]


Back to top | Article view | comp.programming.threads


csiph-web