Thread (54 messages) flat view 54 messages, 8 authors, 2017-03-22

Re: [PATCH 07/17] net: convert sock.sk_refcnt from atomic_t to refcount_t

From: Peter Zijlstra <peterz@infradead.org>
Date: 2017-03-20 15:45:35
Also in: bridge, lkml

On Mon, Mar 20, 2017 at 07:51:01AM -0700, Eric Dumazet wrote:
PowerPC has no efficient atomic_inc() and this definitely shows on
network intensive workloads involving concurrent cores/threads.
Correct, PPC LL/SC are dreadfully expensive.
atomic_cmpxchg() on PowerPC is horribly more expensive because of the
added two SYNC instructions.
Note that refcount_t uses atomic_cmpxchg_release() and
atomic_cmpxchg_relaxed() which avoid most of the painful barriers.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help