@@ -4186,20 +4186,17 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
struct ibmvnic_sub_crq_queue *scrq)
{
struct device *dev = &adapter->vdev->dev;
+ int num_packets = 0, total_bytes = 0;
struct ibmvnic_tx_pool *tx_pool;
struct ibmvnic_tx_buff *txbuff;
struct netdev_queue *txq;
union sub_crq *next;
- int index;
- int i;
+ int index, i;
restart_loop:
while (pending_scrq(adapter, scrq)) {
unsigned int pool = scrq->pool_index;
int num_entries = 0;
- int total_bytes = 0;
- int num_packets = 0;
-
next = ibmvnic_next_scrq(adapter, scrq);
for (i = 0; i < next->tx_comp.num_comps; i++) {
index = be32_to_cpu(next->tx_comp.correlators[i]);
@@ -4235,8 +4232,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
/* remove tx_comp scrq*/
next->tx_comp.first = 0;
- txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index);
- netdev_tx_completed_queue(txq, num_packets, total_bytes);
if (atomic_sub_return(num_entries, &scrq->used) <=
(adapter->req_tx_entries_per_subcrq / 2) &&
@@ -4261,6 +4256,9 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,
goto restart_loop;
}
+ txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index);
+ netdev_tx_completed_queue(txq, num_packets, total_bytes);
+
return 0;
}
Byte Queue Limits depends on dql_completed being called once per tx completion round in order to adjust its algorithm appropriately. The dql->limit value is an approximation of the amount of bytes that the NIC can consume per irq interval. If this approximation is too high then the NIC will become over-saturated. Too low and the NIC will starve. The dql->limit depends on dql->prev-* stats to calculate an optimal value. If dql_completed() is called more than once per irq handler then those prev-* values become unreliable (because they are not an accurate representation of the previous state of the NIC) resulting in a sub-optimal limit value. Therefore, move the call to netdev_tx_completed_queue() to the end of ibmvnic_complete_tx(). When performing 150 sessions of TCP rr (request-response 1 byte packets) workloads, one could observe: PREVIOUSLY: - limit and inflight values hovering around 130 - transaction rate of around 750k pps. NOW: - limit rises and falls in response to inflight (130-900) - transaction rate of around 1M pps (33% improvement) Signed-off-by: Nick Child <nnac123@linux.ibm.com> --- drivers/net/ethernet/ibm/ibmvnic.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)