Ofer Levi 2c925db0a7 net/mlx5e: Support enhanced CQE compression ... CQE compression feature improves performance by reducing PCI bandwidth bottleneck on CQEs write. Enhanced CQE compression introduced in ConnectX-6 and it aims to reduce CPU utilization of SW side packets decompression by eliminating the need to rewrite ownership bit, which is likely to cost a cache-miss, is replaced by validity byte handled solely by HW. Another advantage of the enhanced feature is that session packets are available to SW as soon as a single CQE slot is filled, instead of waiting for session to close, this improves packet latency from NIC to host. Performance: Following are tested scenarios and reults comparing basic and enahnced CQE compression. setup: IXIA 100GbE connected directly to port 0 and port 1 of ConnectX-6 Dx 100GbE dual port. Case #1 RX only, single flow goes to single queue: IRQ rate reduced by ~ 30%, CPU utilization improved by 2%. Case #2 IP forwarding from port 1 to port 0 single flow goes to single queue: Avg latency improved from 60us to 21us, frame loss improved from 0.5% to 0.0%. Case #3 IP forwarding from port 1 to port 0 Max Throughput IXIA sends 100%, 8192 UDP flows, goes to 24 queues: Enhanced is equal or slightly better than basic. Testing the basic compression feature with this patch shows there is no perfrormance degradation of the basic compression feature. Signed-off-by: Ofer Levi <oferle@nvidia.com> Reviewed-by: Tariq Toukan <tariqt@nvidia.com> Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>		2022-11-12 02:20:19 -08:00
..
cq.h	net/mlx5: Use mlx5_cmd_do() in core create_{cq,dct}	2022-02-23 15:21:59 -08:00
device.h	net/mlx5e: Support enhanced CQE compression	2022-11-12 02:20:19 -08:00
doorbell.h
driver.h	net/mlx5: Fix possible use-after-free in async command interface	2022-10-27 11:06:56 -07:00
eq.h
eswitch.h	net/mlx5: E-switch, Remove dependency between sriov and eswitch mode	2022-07-02 11:58:26 -07:00
fs_helpers.h	net/mlx5: Remove unused functions	2022-09-27 12:50:27 -07:00
fs.h	net/mlx5: Add MACsec Rx tables support to fs_core	2022-09-07 14:02:08 +01:00
mlx5_ifc_fpga.h	net/mlx5: Remove from FPGA IFC file not-needed definitions	2022-09-27 12:50:27 -07:00
mlx5_ifc_vdpa.h	vdpa/mlx5: Implement susupend virtqueue callback	2022-08-11 04:26:08 -04:00
mlx5_ifc.h	v6.1 merge window pull request	2022-10-07 12:05:29 -07:00
mpfs.h
port.h	IB/mlx5: Fix undefined behavior due to shift overflowing the constant	2022-04-06 10:15:03 +03:00
qp.h	net/mlx5e: xsk: Use KSM for unaligned XSK	2022-09-30 07:55:46 -07:00
rsc_dump.h
transobj.h
vport.h