[dpdk-dev,v2] event/sw: code refractor to reduce the fetch stall
Checks
Commit Message
With rearranging the code to prefetch the contents before
loop check increases performance from single and multistage
atomic pipeline.
Signed-off-by: Vipin Varghese <vipin.varghese@intel.com>
Acked-by: Harry van Haaren <harry.van.haaren@intel.com>
---
Changes in V2:
- compilation fix for const flowid - Harry
- Removal of sw_refill_pp_buf logic - Harry
---
drivers/event/sw/sw_evdev_scheduler.c | 19 ++++++++++++++-----
1 file changed, 14 insertions(+), 5 deletions(-)
@@ -44,12 +44,13 @@
uint32_t qid_id = qid->id;
iq_dequeue_burst(sw, &qid->iq[iq_num], qes, count);
- for (i = 0; i < count; i++) {
- const struct rte_event *qe = &qes[i];
- const uint16_t flow_id = SW_HASH_FLOWID(qes[i].flow_id);
- struct sw_fid_t *fid = &qid->fids[flow_id];
- int cq = fid->cq;
+ const struct rte_event *qe = &qes[i];
+ uint16_t flow_id = SW_HASH_FLOWID(qes[i].flow_id);
+ struct sw_fid_t *fid = &qid->fids[flow_id];
+ int cq = fid->cq;
+
+ for (i = 0; i < count; i++) {
if (cq < 0) {
uint32_t cq_idx = qid->cq_next_tx++;
if (qid->cq_next_tx == qid->cq_num_mapped_cqs)
@@ -101,6 +102,14 @@
&sw->cq_ring_space[cq]);
p->cq_buf_count = 0;
}
+
+ if (likely(i+1 < count)) {
+ qe = (qes + i + 1);
+ flow_id = SW_HASH_FLOWID(qes[i + 1].flow_id);
+ fid = &qid->fids[flow_id];
+ cq = fid->cq;
+ }
+
}
iq_put_back(sw, &qid->iq[iq_num], blocked_qes, nb_blocked);