提交 2a1af5d7 编写于 作者: J Jeff Kirsher 提交者: root

e1000: Add performance enahancement by balancing TX and RX

Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: NJesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: NJohn Ronciak <john.ronciak@intel.com>
上级 85b22eb6
......@@ -3349,6 +3349,9 @@ e1000_clean_tx_irq(struct e1000_adapter *adapter,
struct e1000_tx_desc *tx_desc, *eop_desc;
struct e1000_buffer *buffer_info;
unsigned int i, eop;
#ifdef CONFIG_E1000_NAPI
unsigned int count = 0;
#endif
boolean_t cleaned = FALSE;
i = tx_ring->next_to_clean;
......@@ -3370,6 +3373,11 @@ e1000_clean_tx_irq(struct e1000_adapter *adapter,
eop = tx_ring->buffer_info[i].next_to_watch;
eop_desc = E1000_TX_DESC(*tx_ring, eop);
#ifdef CONFIG_E1000_NAPI
#define E1000_TX_WEIGHT 64
/* weight of a sort for tx, to avoid endless transmit cleanup */
if (count++ == E1000_TX_WEIGHT) break;
#endif
}
tx_ring->next_to_clean = i;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册