I posted this 2 weeks ago on the bonding-devel list, but didn't
receive any feedback so thought I would bring it up to a larger
audience.
Included is a patch for a new xmit_hash_policy for the bonding driver
that selects slaves based on MAC and IP information. This is a middle
ground between what currently exists in the layer2 only policy and the
layer3+4 policy. This policy strives to be fully 802.3ad compliant by
transmitting every packet of any particular flow over the same link.
As documented the layer3+4 policy is not fully compliant for extreme
cases such as ip fragmentation, so this policy is a nice compromise
for environments that require full compliance but desire more than the
layer2 only policy. Comments?
---
Documentation/networking/bonding.txt | 23 +++++++++++++++++++++++
drivers/net/bonding/bond_main.c | 26 ++++++++++++++++++++++++--
include/linux/if_bonding.h | 3 ++-
3 files changed, 49 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/bonding.txt
b/Documentation/networking/bonding.txt
index 1134062..5ac84c0 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -587,6 +587,29 @@ xmit_hash_policy
most UDP traffic is not involved in extended
conversations. Other implementations of 802.3ad may
or may not tolerate this noncompliance.
+
+ layer2+3
+
+ This policy uses a combination of layer2 and layer3
+ protocol information to generate the hash.
+
+ Uses XOR of hardware MAC addresses and IP addresses to
+ generate the hash. The formula is
+
+ (((source IP XOR dest IP) AND 0xffff) XOR
+ ( source MAC XOR destination MAC ))
+ modulo slave count
+
+ This algorithm will place all traffic to a particular
+ network peer on the same slave. For non-IP traffic,
+ the formula is the same as for the layer2 transmit
+ hash policy.
+
+ This policy is intended to provide a more balanced
+ distribution of traffic than layer2 alone, especially
+ in environments where a layer3 gateway device is
+ required to reach most destinations. This algorithm is
+ fully 802.3ad complient.
The default value is layer2. This option was added in bonding
version 2.6.3. In earlier versions of bonding, this parameter does
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 423298c..a731812 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -174,6 +174,7 @@ struct bond_parm_tbl bond_mode_tbl[] = {
struct bond_parm_tbl xmit_hashtype_tbl[] = {
{ "layer2", BOND_XMIT_POLICY_LAYER2},
{ "layer3+4", BOND_XMIT_POLICY_LAYER34},
+{ "layer2+3", BOND_XMIT_POLICY_LAYER23},
{ NULL, -1},
};
@@ -3604,6 +3605,24 @@ void bond_unregister_arp(struct bonding *bond)
/*---------------------------- Hashing Policies -----------------------------*/
/*
+ * Hash for the output device based upon layer 2 and layer 3 data. If
+ * the packet is not IP mimic bond_xmit_hash_policy_l2()
+ */
+static int bond_xmit_hash_policy_l23(struct sk_buff *skb,
+ struct net_device *bond_dev, int count)
+{
+ struct ethhdr *data = (struct ethhdr *)skb->data;
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (skb->protocol == __constant_htons(ETH_P_IP)) {
+ return ((ntohl(iph->saddr ^ iph->daddr) & 0xffff) ^
+ (data->h_dest[5] ^ bond_dev->dev_addr[5])) % count;
+ }
+
+ return (data->h_dest[5] ^ bond_dev->dev_addr[5]) % count;
+}
+
+/*
* Hash for the output device based upon layer 3 and layer 4 data. If
* the packet is a frag or not TCP or UDP, just use layer 3 data. If it is
* altogether not IP, mimic bond_xmit_hash_policy_l2()
@@ -4323,6 +4342,8 @@ void bond_set_mode_ops(struct bonding *bond, int mode)
bond_dev->hard_start_xmit = bond_xmit_xor;
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
+ else if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23)
+ bond->xmit_hash_policy = bond_xmit_hash_policy_l23;
else
bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
break;
@@ -4334,6 +4355,8 @@ void bond_set_mode_ops(struct bonding *bond, int mode)
bond_dev->hard_start_xmit = bond_3ad_xmit_xor;
if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34)
bond->xmit_hash_policy = bond_xmit_hash_policy_l34;
+ else if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23)
+ bond->xmit_hash_policy = bond_xmit_hash_policy_l23;
else
bond->xmit_hash_policy = bond_xmit_hash_policy_l2;
break;
@@ -4497,8 +4520,7 @@ int bond_parse_parm(char *mode_arg, struct
bond_parm_tbl *tbl)
for (i = 0; tbl[i].modename; i++) {
if ((isdigit(*mode_arg) &&
tbl[i].mode == simple_strtol(mode_arg, NULL, 0)) ||
- (strncmp(mode_arg, tbl[i].modename,
- strlen(tbl[i].modename)) == 0)) {
+ (strcmp(mode_arg, tbl[i].modename) == 0)) {
return tbl[i].mode;
}
}
diff --git a/include/linux/if_bonding.h b/include/linux/if_bonding.h
index 84598fa..65c2d24 100644
--- a/include/linux/if_bonding.h
+++ b/include/linux/if_bonding.h
@@ -85,7 +85,8 @@
/* hashing types */
#define BOND_XMIT_POLICY_LAYER2 0 /* layer 2 (MAC only),
default */
-#define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ MAC) */
+#define BOND_XMIT_POLICY_LAYER34 1 /* layer 3+4 (IP ^ (TCP || UDP)) */
+#define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */
typedef struct ifbond {
__s32 bond_mode;
--
1.5.2.5
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
