bond: tx performance enhancement part deux

- Reduce per packet cost by buffering the output packet buffer indexes in the queue and
process the queue outside the packet processing loop.
- Move unnecessary variable initialization outside of the while loop.
- There is no need to save the old interface if tracing is not enabled.

Test result for 256 bytes packet comparison. Other packet size shows similar improvement.

With the patch
--------------
BondEthernet0-output             active              52836        13526016               0          1.71e1          256.00
BondEthernet0-tx                 active              52836        13526016               0          2.68e1          256.00
TenGigabitEthernet6/0/0-output   active              52836         6762896               0          9.17e0          127.99
TenGigabitEthernet6/0/0-tx       active              52836         6762896               0          6.97e1          127.99
TenGigabitEthernet6/0/1-output   active              52836         6763120               0          9.40e0          128.00
TenGigabitEthernet6/0/1-tx       active              52836         6763120               0          7.00e1          128.00
bond-input                       active              52836        13526016               0          1.76e1          256.00

Without the patch
-----------------
BondEthernet0-output             active              60858        15579648               0          1.73e1          256.00
BondEthernet0-tx                 active              60858        15579648               0          2.94e1          256.00
TenGigabitEthernet6/0/0-output   active              60858         7789626               0          9.29e0          127.99
TenGigabitEthernet6/0/0-tx       active              60858         7789626               0          7.01e1          127.99
TenGigabitEthernet6/0/1-output   active              60858         7790022               0          9.31e0          128.00
TenGigabitEthernet6/0/1-tx       active              60858         7790022               0          7.10e1          128.00
bond-input                       active              60858        15579648               0          1.77e1          256.00

Change-Id: Ib6d73a63ceeaa2f1397ceaf4c5391c57fd865b04
Signed-off-by: Steven <sluong@cisco.com>

1 files changed, 11 insertions, 4 deletions

diff --git a/src/vnet/bonding/node.h b/src/vnet/bonding/node.h
index 104b7b15700..6b13a46a355 100644
--- a/src/vnet/bonding/node.h
+++ b/src/vnet/bonding/node.h
@@ -139,9 +139,15 @@ typedef CLIB_PACKED (struct
 
 typedef struct
 {
-  vlib_frame_t **frame;
+  CLIB_CACHE_LINE_ALIGN_MARK (cacheline0);
+  u32 buffers[VLIB_FRAME_SIZE];
+  u32 n_buffers;
+} bond_per_port_queue_t;
 
-} bond_if_per_thread_t;
+typedef struct
+{
+  bond_per_port_queue_t *per_port_queue;
+} bond_per_thread_data_t;
 
 typedef struct
 {
@@ -175,7 +181,6 @@ typedef struct
   u8 hw_address[6];
 
   clib_spinlock_t lockp;
-  bond_if_per_thread_t *per_thread_info;
 } bond_if_t;
 
 typedef struct
@@ -292,7 +297,7 @@ typedef struct
   /* pool of bonding interfaces */
   bond_if_t *interfaces;
 
-  /* pool of lacp neighbors */
+  /* pool of slave interfaces */
   slave_if_t *neighbors;
 
   /* rapidly find a bond by vlib software interface index */
@@ -308,6 +313,8 @@ typedef struct
   lacp_enable_disable_func lacp_enable_disable;
 
   uword *slave_by_sw_if_index;
+
+  bond_per_thread_data_t *per_thread_data;
 } bond_main_t;
 
 /* bond packet trace capture */