[dpdk-dev] rte_ring: clarify preemptable nature of ring algorithm
Checks
Commit Message
Agree Stephen.
But rte_ring is not as basic as spinlock. IMO, existing note results in more questions than answers.
From: Stephen Hemminger <stephen@networkplumber.org>
Sent: Tuesday, May 29, 2018 9:39 PM
To: Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>
Cc: Olivier Matz <olivier.matz@6wind.com>; dev@dpdk.org
Subject: Re: [dpdk-dev] [PATCH] rte_ring: clarify preemptable nature of ring algorithm
Spinlock has same problem
On Tue, May 29, 2018, 1:06 AM Honnappa Nagarahalli <honnappa.nagarahalli@arm.com<mailto:honnappa.nagarahalli@arm.com>> wrote:
rte_ring implementation is not preemptable only under certain circumstances.
This clarification is helpful for data plane and control plane communication
using rte_ring.
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com<mailto:honnappa.nagarahalli@arm.com>>
Reviewed-by: Gavin Hu <gavin.hu@arm.com<mailto:gavin.hu@arm.com>>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com<mailto:ola.liljedahl@arm.com>>
---
lib/librte_ring/rte_ring.h | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
--
2.7.4
IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.
@@ -26,8 +26,13 @@
* - Bulk dequeue.
* - Bulk enqueue.
*
- * Note: the ring implementation is not preemptable. A lcore must not
- * be interrupted by another task that uses the same ring.
+ * Note: the ring implementation can block threads from completing their
+ * operation under the following circumstances.
+ * A preempted thread can block other threads (operating on the same ring)
+ * from completing their operations, only if those threads are performing
+ * the same ring operation (enqueue/dequeue) as the preempted thread.
+ * In other words, a preempted consumer thread will not block any producer
+ * threads and vice versa.
*
*/