summaryrefslogtreecommitdiffstats
path: root/include/linux/skbuff.h
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2010-05-05 01:07:37 -0700
committerDavid S. Miller <davem@davemloft.net>2010-05-05 01:07:37 -0700
commitec7d2f2cf3a1b76202986519ec4f8ec75b2de232 (patch)
tree177c324eb0cf7e687d1bbd10a6add3a7d5979002 /include/linux/skbuff.h
parent8753d29fd5daf890004a38c80835e1eb3acda394 (diff)
net: __alloc_skb() speedup
With following patch I can reach maximum rate of my pktgen+udpsink simulator : - 'old' machine : dual quad core E5450 @3.00GHz - 64 UDP rx flows (only differ by destination port) - RPS enabled, NIC interrupts serviced on cpu0 - rps dispatched on 7 other cores. (~130.000 IPI per second) - SLAB allocator (faster than SLUB in this workload) - tg3 NIC - 1.080.000 pps without a single drop at NIC level. Idea is to add two prefetchw() calls in __alloc_skb(), one to prefetch first sk_buff cache line, the second to prefetch the shinfo part. Also using one memset() to initialize all skb_shared_info fields instead of one by one to reduce number of instructions, using long word moves. All skb_shared_info fields before 'dataref' are cleared in __alloc_skb(). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/linux/skbuff.h')
-rw-r--r--include/linux/skbuff.h7
1 files changed, 6 insertions, 1 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 746a652b9f6..88d55395a27 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -187,7 +187,6 @@ union skb_shared_tx {
* the end of the header data, ie. at skb->end.
*/
struct skb_shared_info {
- atomic_t dataref;
unsigned short nr_frags;
unsigned short gso_size;
/* Warning: this field is not always filled in (UFO)! */
@@ -197,6 +196,12 @@ struct skb_shared_info {
union skb_shared_tx tx_flags;
struct sk_buff *frag_list;
struct skb_shared_hwtstamps hwtstamps;
+
+ /*
+ * Warning : all fields before dataref are cleared in __alloc_skb()
+ */
+ atomic_t dataref;
+
skb_frag_t frags[MAX_SKB_FRAGS];
/* Intermediate layers must ensure that destructor_arg
* remains valid until skb destructor */