On 02/13/2014 12:26 PM, Peter Zijlstra wrote:
On Thu, Feb 13, 2014 at 05:35:46PM +0100, Peter Zijlstra wrote:
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their
On 02/13/2014 11:35 AM, Peter Zijlstra wrote:
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket
On 02/13/2014 11:35 AM, Peter Zijlstra wrote:
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket
On 02/13/2014 12:26 PM, Peter Zijlstra wrote:
On Thu, Feb 13, 2014 at 05:35:46PM +0100, Peter Zijlstra wrote:
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their
On Thu, Feb 13, 2014 at 05:35:46PM +0100, Peter Zijlstra wrote:
> On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
> > Using the same locktest program to repetitively take a single rwlock with
> > programmable number of threads and count their execution times. Each
> > thread takes the
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
> Using the same locktest program to repetitively take a single rwlock with
> programmable number of threads and count their execution times. Each
> thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
> system. I bound all
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
system. I bound all the
On Thu, Feb 13, 2014 at 05:35:46PM +0100, Peter Zijlstra wrote:
On Tue, Feb 11, 2014 at 03:12:59PM -0500, Waiman Long wrote:
Using the same locktest program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock
On 02/11/2014 01:17 PM, Waiman Long wrote:
Peter,
I had written a test program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
system. I bound all the threads to
Peter,
I had written a test program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
system. I bound all the threads to different CPUs with the following
3
Peter,
I had written a test program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
system. I bound all the threads to different CPUs with the following
3
On 02/11/2014 01:17 PM, Waiman Long wrote:
Peter,
I had written a test program to repetitively take a single rwlock with
programmable number of threads and count their execution times. Each
thread takes the lock 5M times on a 4-socket 40-core Westmere-EX
system. I bound all the threads to
This rwlock uses the arch_spin_lock_t as a waitqueue, and assuming the
arch_spin_lock_t is a fair lock (ticket,mcs etc..) the resulting
rwlock is a fair lock.
It fits in the same 8 bytes as the regular rwlock_t by folding the
reader and writer count into a single integer, using the remaining 4
This rwlock uses the arch_spin_lock_t as a waitqueue, and assuming the
arch_spin_lock_t is a fair lock (ticket,mcs etc..) the resulting
rwlock is a fair lock.
It fits in the same 8 bytes as the regular rwlock_t by folding the
reader and writer count into a single integer, using the remaining 4
14 matches
Mail list logo