search for: 1700ms

...istribution for my linux router and I tried to use wondershaper. On start up of wshaper, there are no errors or any other problems but I''m not sure if it''s running correctly. Only one qdisc / one class is used and when I start an uplink ftp transfer, my ping time is growing up to 1700ms - I don''t think that there is anything shaped oder scheduled. In the wshaper file I set the up- and downlink values and for the p2p I set this: # low priority source ports NOPRIOPORTSRC=4662 # low priority destination ports NOPRIOPORTDST=4662 Then i start it: [root@Astoria bin]# wshape...

...xchg. No extra ops needed. And at that point you don't need a whole > byte, you can use a single bit. > > that removes the whole NR_CPUS dependent logic. After modifying it to do a deterministic cmpxchg, the test run time of 2 contending tasks jumps up from 600ms (best case) to about 1700ms which was worse than the original qspinlock's 1300-1500ms. It is the opportunistic nature of the xchg() code that can potentially combine multiple steps in the deterministic atomic sequence which can saves time. Without that, I would rather prefer going back to the basic qspinlock queuing...

On Thu, Feb 27, 2014 at 03:42:19PM -0500, Waiman Long wrote: > >>+ old = xchg(&qlock->lock_wait, _QSPINLOCK_WAITING|_QSPINLOCK_LOCKED); > >>+ > >>+ if (old == 0) { > >>+ /* > >>+ * Got the lock, can clear the waiting bit now > >>+ */ > >>+ smp_u8_store_release(&qlock->wait, 0); > > > >So we just did an

On Thu, Feb 27, 2014 at 03:42:19PM -0500, Waiman Long wrote: > >>+ old = xchg(&qlock->lock_wait, _QSPINLOCK_WAITING|_QSPINLOCK_LOCKED); > >>+ > >>+ if (old == 0) { > >>+ /* > >>+ * Got the lock, can clear the waiting bit now > >>+ */ > >>+ smp_u8_store_release(&qlock->wait, 0); > > > >So we just did an