the hardware.
Fix this by always ring the doorbell in sequence and avoid unnecessary
rings.
Trivial problem^_^
s/ring/ringing ?
Zhu Yanjun
Cc: sta...@vger.kernel.org
Fixes: e1b5683ff62e ("net: mana: Move NAPI from EQ to CQ")
Signed-off-by: Long Li
---
drivers/net/ethernet/micr
IGNED(txq_size));
+ txq_size = apc->tx_queue_size * 32;
Not sure if the following is needed or not.
"
WARN_ON(!MANA_PAGE_ALIGNED(txq_size));
"
Zhu Yanjun
- cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE;
+ cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE;
if (ring->rx_mini_pending) {
+ netdev_err(ndev, "%s: rx_mini_pending not supported\n",
__func__);
ditto. " rx_mini_pending not supported"
Thanks,
Zhu Yanjun
+ return -EINVAL;
+ }
+
+ if (!apc)
+ return -EINVAL;
+
+
t
should be used for printing
Not sure if this file drivers/infiniband/hw/usnic/usnic_ib_sysfs.c is a
good example or not.
Zhu Yanjun
Jason
d the difference on latency and
throughput on RoCEv2 devices.
Anyone also made tests with these patches on IB? Any difference on
Latency and throughput?
Thanks,
Zhu Yanjun
Signed-off-by: Allen Pais
---
drivers/infiniband/hw/bnxt_re/bnxt_re.h| 3 +-
drivers/infiniband/hw/bnxt_re/qplib
and 3.
https://static.lwn.net/images/pdf/LDD3/ch10.pdf
Zhu Yanjun
6) If all CPUs in all NUMA nodes are used, but still there are IRQs
then wrap over from first local NUMA node and continue
doing 2, 3 4 till all IRQs are assigned.
