From: Stephen Hemminger <hidden> Date: 2012-11-26 06:04:26
On Fri, 23 Nov 2012 14:08:47 +0100
Jesper Dangaard Brouer [off-list ref] wrote:
Do NOT APPLY this patch.
After all the other patches, the rw_lock is now the contention point.
Reader-writer locks are significantly slower than a simple spinlock.
Unless the reader holds the lock for "significant" number of cycles,
a spin lock will be faster.
Did you try just changing it to a spinlock?