Hi Kelvin.
On 30 April 2014 10:52, wrote:
> In arch/arm64/include/asm/barrier.h, there is the definition of
> smp_mb()/smp_rmb()/smp_wmb() for arm64. I noticed that all the 3 macors are
> using “dmb ishxx”, which is only affect the cluster of the CPU executing the
> instruction.
This is incorre
Hi All,
In arch/arm64/include/asm/barrier.h, there is the definition of
smp_mb()/smp_rmb()/smp_wmb() for arm64. I noticed that all the 3 macors
are using "dmb ishxx", which is only affect the cluster of the CPU
executing the instruction. But in the big.LITTLE system, there will be 2
cluster.
Hello Sanjay,
As far I know, if option argument is 0, the parent will wait for
specified child pid to terminate, its not for immediate return as in case
of WNOHANG. This is probably the intended use of the code (author will be
able to confirm). Changing 0 to WNOHANG macro will change the meaning o
On Wednesday 30 April 2014 12:14 PM, Mohammad Merajul Islam Molla wrote:
Hello,
I would like to share two observations -
1. Is it necessary to initialize nrcpus = 2 anymore?
thanks, ack
2. Another problem may happen in the code below where waitpid is called -
for (i = 0; i < nrcpus; i++)
