From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from foss.arm.com (usa-sjc-mx-foss1.foss.arm.com [217.140.101.70]) by dpdk.org (Postfix) with ESMTP id 4B4D1559A for ; Tue, 10 Jul 2018 06:01:21 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 6213F7A9; Mon, 9 Jul 2018 21:01:20 -0700 (PDT) Received: from ubuntu.localdomain (unknown [10.119.48.90]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id C37043F5A0; Mon, 9 Jul 2018 21:01:19 -0700 (PDT) From: Honnappa Nagarahalli To: honnappa.nagarahalli@arm.com, anatoly.burakov@intel.com, olivier.matz@6wind.com Cc: dev@dpdk.org, nd@arm.com Date: Mon, 9 Jul 2018 23:00:47 -0500 Message-Id: <1531195247-22612-1-git-send-email-honnappa.nagarahalli@arm.com> X-Mailer: git-send-email 2.7.4 Subject: [dpdk-dev] [PATCH v3] rte_ring: clarify preemptible nature of ring algorithm X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 10 Jul 2018 04:01:21 -0000 rte_ring implementation is not preemptible only under certain circumstances. This clarification is helpful for data plane and control plane communication using rte_ring. Signed-off-by: Honnappa Nagarahalli Reviewed-by: Gavin Hu Reviewed-by: Ola Liljedahl --- v3: * Corrected known issues for rte_ring * Referred to known issues in rte_ring.h (Burakov, Oliver) v2: * Fixed checkpatch warnings doc/guides/prog_guide/env_abstraction_layer.rst | 27 ++++++++++++++----------- lib/librte_ring/rte_ring.h | 5 +++-- 2 files changed, 18 insertions(+), 14 deletions(-) diff --git a/doc/guides/prog_guide/env_abstraction_layer.rst b/doc/guides/prog_guide/env_abstraction_layer.rst index a22640d..f47a4be 100644 --- a/doc/guides/prog_guide/env_abstraction_layer.rst +++ b/doc/guides/prog_guide/env_abstraction_layer.rst @@ -435,23 +435,26 @@ Known Issues The "non-preemptive" constraint means: - - a pthread doing multi-producers enqueues on a given ring must not - be preempted by another pthread doing a multi-producer enqueue on - the same ring. - - a pthread doing multi-consumers dequeues on a given ring must not - be preempted by another pthread doing a multi-consumer dequeue on - the same ring. + A preempted pthread can block other pthreads (operating on the same ring) + from completing their operations, only if those pthreads are performing + the same ring operation (enqueue/dequeue) as the preempted pthread. + In other words, a preempted consumer pthread will not block any producer + pthreads and vice versa. - Bypassing this constraint may cause the 2nd pthread to spin until the 1st one is scheduled again. - Moreover, if the 1st pthread is preempted by a context that has an higher priority, it may even cause a dead lock. + Bypassing this constraint may cause other pthreads to spin until the preempted pthread is scheduled again. + Moreover, if the pthread is preempted by a context that has a higher priority, it may even cause a dead lock. - This does not mean it cannot be used, simply, there is a need to narrow down the situation when it is used by multi-pthread on the same core. + This means, use cases involving preemptible pthreads should consider using rte_ring carefully. - 1. It CAN be used for any single-producer or single-consumer situation. + 1. It CAN be used for preemptible single-producer and single-consumer use case. - 2. It MAY be used by multi-producer/consumer pthread whose scheduling policy are all SCHED_OTHER(cfs). User SHOULD be aware of the performance penalty before using it. + 2. It CAN be used for non-preemptible multi-producer and preemptible single-consumer use case. - 3. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR. + 3. It CAN be used for preemptible single-producer and non-preemptible multi-consumer use case. + + 4. It MAY be used by preemptible multi-producer and/or preemptible multi-consumer pthreads whose scheduling policy are all SCHED_OTHER(cfs), SCHED_IDLE or SCHED_BATCH. User SHOULD be aware of the performance penalty before using it. + + 5. It MUST not be used by multi-producer/consumer pthreads, whose scheduling policies are SCHED_FIFO or SCHED_RR. + rte_timer diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h index 1245822..e680101 100644 --- a/lib/librte_ring/rte_ring.h +++ b/lib/librte_ring/rte_ring.h @@ -26,8 +26,9 @@ * - 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 is not preemptible. Refer to Programmer's + * guide/Environment Abstraction Layer/Multiple pthread/Known Issues/rte_ring + * for more information. * */ -- 2.7.4