event/octeontx2: reduce chunk pool memory usage

Reduce amount of memory used by chunk pool when the mempool used
is OCTEONTX2 NPA.
Previously, the number of chunks configured when NPA is used is
equal to the number of timers requested plus the number of buckets
and if the max timeout is long enough w.r.t. resolution requested
there will a large number of buckets which would cause high memory
usage.
Reduce the number of chunks when NPA is used to the number of timers
requested as buckets that are processed chunk lists are automatically
freed.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>

diff --git a/drivers/event/octeontx2/otx2_tim_evdev.c b/drivers/event/octeontx2/otx2_tim_evdev.c
index 0bbba48b41a0592388ccc828760d97881e58d625..688f6b84f7cd86b334c3c5d9a83a0bee4af13781 100644 (file)
--- a/drivers/event/octeontx2/otx2_tim_evdev.c
+++ b/drivers/event/octeontx2/otx2_tim_evdev.c
@@ -92,6 +92,8 @@ tim_chnk_pool_create(struct otx2_tim_ring *tim_ring,
        if (cache_sz > RTE_MEMPOOL_CACHE_MAX_SIZE)
                cache_sz = RTE_MEMPOOL_CACHE_MAX_SIZE;
 
+       cache_sz = cache_sz != 0 ? cache_sz : 2;
+       tim_ring->nb_chunks += (cache_sz * rte_lcore_count());
        if (!tim_ring->disable_npa) {
                tim_ring->chunk_pool = rte_mempool_create_empty(pool_name,
                                tim_ring->nb_chunks, tim_ring->chunk_sz,
@@ -286,16 +288,15 @@ otx2_tim_ring_create(struct rte_event_timer_adapter *adptr)
                }
        }
 
-       tim_ring->nb_chunks = tim_ring->nb_timers / OTX2_TIM_NB_CHUNK_SLOTS(
-                                                       tim_ring->chunk_sz);
-       tim_ring->nb_chunk_slots = OTX2_TIM_NB_CHUNK_SLOTS(tim_ring->chunk_sz);
-
-       if (tim_ring->disable_npa)
+       if (tim_ring->disable_npa) {
+               tim_ring->nb_chunks =
+                       tim_ring->nb_timers /
+                       OTX2_TIM_NB_CHUNK_SLOTS(tim_ring->chunk_sz);
                tim_ring->nb_chunks = tim_ring->nb_chunks * tim_ring->nb_bkts;
-       else
-               tim_ring->nb_chunks = tim_ring->nb_chunks + tim_ring->nb_bkts;
-
-       /* Create buckets. */
+       } else {
+               tim_ring->nb_chunks = tim_ring->nb_timers;
+       }
+       tim_ring->nb_chunk_slots = OTX2_TIM_NB_CHUNK_SLOTS(tim_ring->chunk_sz);
        tim_ring->bkt = rte_zmalloc("otx2_tim_bucket", (tim_ring->nb_bkts) *
                                    sizeof(struct otx2_tim_bkt),
                                    RTE_CACHE_LINE_SIZE);

diff --git a/drivers/event/octeontx2/otx2_tim_evdev.h b/drivers/event/octeontx2/otx2_tim_evdev.h
index e9cefea9fc7213c617efec107be947d5dab66a80..2492252dc7ec7dcfaebe0130a099a29d26b88716 100644 (file)
--- a/drivers/event/octeontx2/otx2_tim_evdev.h
+++ b/drivers/event/octeontx2/otx2_tim_evdev.h
@@ -70,7 +70,7 @@
 #define OTX2_TIM_MAX_BURST             (RTE_CACHE_LINE_SIZE / \
                                                OTX2_TIM_CHUNK_ALIGNMENT)
 #define OTX2_TIM_NB_CHUNK_SLOTS(sz)    (((sz) / OTX2_TIM_CHUNK_ALIGNMENT) - 1)
-#define OTX2_TIM_MIN_CHUNK_SLOTS       (0x1)
+#define OTX2_TIM_MIN_CHUNK_SLOTS       (0x8)
 #define OTX2_TIM_MAX_CHUNK_SLOTS       (0x1FFE)
 #define OTX2_TIM_MIN_TMO_TKS           (256)