bonding: Add tlb_dynamic_lb parameter for tlb mode

The aggresive load balancing causes packet re-ordering as active
flows are moved from a slave to another within the group. Sometime
this aggresive lb is not necessary if the preference is for less
re-ordering. This parameter if used with value "0" disables
this dynamic flow shuffling minimizing packet re-ordering. Of course
the side effect is that it has to live with the static load balancing
that the hashing distribution provides. This impact is less severe if
the correct xmit-hashing-policy is used for the tlb setup.

The default value of the parameter is set to "1" mimicing the earlier
behavior.

Ran the netperf test with 200 stream for 1 min between two hosts with
4x1G trunk (xmit-lb mode with xmit-policy L3+4) before and after these
changes. Following was the command used for those 200 instances -

    netperf -t TCP_RR -l 60 -s 5 -H <host> -- -r81920,81920

Transactions per second:
    Before change: 1,367.11
    After  change: 1,470.65

Change-Id: Ie3f75c77282cf602e83a6e833c6eb164e72a0990
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 111 insertions, 12 deletions

diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index a97c567f24e8..9c723ecd0025 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -585,13 +585,19 @@ mode
         balance-tlb or 5
 
                 Adaptive transmit load balancing: channel bonding that
-                does not require any special switch support.  The
-                outgoing traffic is distributed according to the
-                current load (computed relative to the speed) on each
-                slave.  Incoming traffic is received by the current
-                slave.  If the receiving slave fails, another slave
-                takes over the MAC address of the failed receiving
-                slave.
+                does not require any special switch support.
+
+                In tlb_dynamic_lb=1 mode; the outgoing traffic is
+                distributed according to the current load (computed
+                relative to the speed) on each slave.
+
+                In tlb_dynamic_lb=0 mode; the load balancing based on
+                current load is disabled and the load is distributed
+                only using the hash distribution.
+
+                Incoming traffic is received by the current slave.
+                If the receiving slave fails, another slave takes over
+                the MAC address of the failed receiving slave.
 
                 Prerequisite:
 
@@ -736,6 +742,28 @@ primary_reselect
 
         This option was added for bonding version 3.6.0.
 
+tlb_dynamic_lb
+
+        Specifies if dynamic shuffling of flows is enabled in tlb
+        mode. The value has no effect on any other modes.
+
+        The default behavior of tlb mode is to shuffle active flows across
+        slaves based on the load in that interval. This gives nice lb
+        characteristics but can cause packet reordering. If re-ordering is
+        a concern use this variable to disable flow shuffling and rely on
+        load balancing provided solely by the hash distribution.
+        xmit-hash-policy can be used to select the appropriate hashing for
+        the setup.
+
+        The sysfs entry can be used to change the setting per bond device
+        and the initial value is derived from the module parameter. The
+        sysfs entry is allowed to be changed only if the bond device is
+        down.
+
+        The default value is "1" that enables flow shuffling while value "0"
+        disables it. This option was added in bonding driver 3.7.1
+
+
 updelay
 
         Specifies the time, in milliseconds, to wait before enabling a
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 153232ed4b3f..70de039dad2e 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1356,7 +1356,8 @@ static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
         if (!tx_slave) {
                 /* unbalanced or unassigned, send through primary */
                 tx_slave = rcu_dereference(bond->curr_active_slave);
-                bond_info->unbalanced_load += skb->len;
+                if (bond->params.tlb_dynamic_lb)
+                        bond_info->unbalanced_load += skb->len;
         }
 
         if (tx_slave && SLAVE_IS_OK(tx_slave)) {
@@ -1369,7 +1370,7 @@ static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond,
                 goto out;
         }
 
-        if (tx_slave) {
+        if (tx_slave && bond->params.tlb_dynamic_lb) {
                 _lock_tx_hashtbl(bond);
                 __tlb_clear_slave(bond, tx_slave, 0);
                 _unlock_tx_hashtbl(bond);
@@ -1399,11 +1400,21 @@ int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev)
                     /* In case of IPX, it will falback to L2 hash */
                 case htons(ETH_P_IPV6):
                         hash_index = bond_xmit_hash(bond, skb);
-                        tx_slave = tlb_choose_channel(bond, hash_index & 0xFF, skb->len);
+                        if (bond->params.tlb_dynamic_lb) {
+                                tx_slave = tlb_choose_channel(bond,
+                                                              hash_index & 0xFF,
+                                                              skb->len);
+                        } else {
+                                struct list_head *iter;
+                                int idx = hash_index % bond->slave_cnt;
+
+                                bond_for_each_slave_rcu(bond, tx_slave, iter)
+                                        if (--idx < 0)
+                                                break;
+                        }
                         break;
                 }
         }
-
         return bond_do_alb_xmit(skb, bond, tx_slave);
 }
 
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1fd32a16cbc5..9d08e007d853 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3096,7 +3096,8 @@ static int bond_open(struct net_device *bond_dev)
                  */
                 if (bond_alb_initialize(bond, (bond->params.mode == BOND_MODE_ALB)))
                         return -ENOMEM;
-                queue_delayed_work(bond->wq, &bond->alb_work, 0);
+                if (bond->params.tlb_dynamic_lb)
+                        queue_delayed_work(bond->wq, &bond->alb_work, 0);
         }
 
         if (bond->params.miimon)  /* link check interval, in milliseconds. */
@@ -4304,6 +4305,7 @@ static int bond_check_params(struct bond_params *params)
         params->min_links = min_links;
         params->lp_interval = lp_interval;
         params->packets_per_slave = packets_per_slave;
+        params->tlb_dynamic_lb = 1; /* Default value */
         if (packets_per_slave > 0) {
                 params->reciprocal_packets_per_slave =
                         reciprocal_value(packets_per_slave);
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index dc3893841752..9fba7a1e6d51 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -70,6 +70,8 @@ static int bond_option_mode_set(struct bonding *bond,
                                 const struct bond_opt_value *newval);
 static int bond_option_slaves_set(struct bonding *bond,
                                   const struct bond_opt_value *newval);
+static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
+                                  const struct bond_opt_value *newval);
 
 
 static const struct bond_opt_value bond_mode_tbl[] = {
@@ -179,6 +181,12 @@ static const struct bond_opt_value bond_lp_interval_tbl[] = {
         { NULL,      -1,      0},
 };
 
+static const struct bond_opt_value bond_tlb_dynamic_lb_tbl[] = {
+        { "off", 0,  0},
+        { "on",  1,  BOND_VALFLAG_DEFAULT},
+        { NULL,  -1, 0}
+};
+
 static const struct bond_option bond_opts[] = {
         [BOND_OPT_MODE] = {
                 .id = BOND_OPT_MODE,
@@ -364,6 +372,15 @@ static const struct bond_option bond_opts[] = {
                 .flags = BOND_OPTFLAG_RAWVAL,
                 .set = bond_option_slaves_set
         },
+        [BOND_OPT_TLB_DYNAMIC_LB] = {
+                .id = BOND_OPT_TLB_DYNAMIC_LB,
+                .name = "dynamic_lb",
+                .desc = "Enable dynamic flow shuffling",
+                .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_TLB)),
+                .values = bond_tlb_dynamic_lb_tbl,
+                .flags = BOND_OPTFLAG_IFDOWN,
+                .set = bond_option_tlb_dynamic_lb_set,
+        },
         { }
 };
 
@@ -1337,3 +1354,13 @@ err_no_cmd:
         ret = -EPERM;
         goto out;
 }
+
+static int bond_option_tlb_dynamic_lb_set(struct bonding *bond,
+                                          const struct bond_opt_value *newval)
+{
+        pr_info("%s: Setting dynamic-lb to %s (%llu)\n",
+                bond->dev->name, newval->string, newval->value);
+        bond->params.tlb_dynamic_lb = newval->value;
+
+        return 0;
+}
diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h
index 12be9e1bfb0c..c1860f06145a 100644
--- a/drivers/net/bonding/bond_options.h
+++ b/drivers/net/bonding/bond_options.h
@@ -62,6 +62,7 @@ enum {
         BOND_OPT_RESEND_IGMP,
         BOND_OPT_LP_INTERVAL,
         BOND_OPT_SLAVES,
+        BOND_OPT_TLB_DYNAMIC_LB,
         BOND_OPT_LAST
 };
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 0e8b268da0a0..431892f1a4ce 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1039,6 +1039,34 @@ static ssize_t bonding_store_lp_interval(struct device *d,
 static DEVICE_ATTR(lp_interval, S_IRUGO | S_IWUSR,
                    bonding_show_lp_interval, bonding_store_lp_interval);
 
+static ssize_t bonding_show_tlb_dynamic_lb(struct device *d,
+                                           struct device_attribute *attr,
+                                           char *buf)
+{
+        struct bonding *bond = to_bond(d);
+        return sprintf(buf, "%d\n", bond->params.tlb_dynamic_lb);
+}
+
+static ssize_t bonding_store_tlb_dynamic_lb(struct device *d,
+                                            struct device_attribute *attr,
+                                            const char *buf,
+                                            size_t count)
+{
+        struct bonding *bond = to_bond(d);
+        int ret;
+
+        ret = bond_opt_tryset_rtnl(bond, BOND_OPT_TLB_DYNAMIC_LB,
+                                   (char *)buf);
+        if (!ret)
+                ret = count;
+
+        return ret;
+}
+
+static DEVICE_ATTR(tlb_dynamic_lb, S_IRUGO | S_IWUSR,
+                   bonding_show_tlb_dynamic_lb,
+                   bonding_store_tlb_dynamic_lb);
+
 static ssize_t bonding_show_packets_per_slave(struct device *d,
                                               struct device_attribute *attr,
                                               char *buf)
@@ -1099,6 +1127,7 @@ static struct attribute *per_bond_attrs[] = {
         &dev_attr_min_links.attr,
         &dev_attr_lp_interval.attr,
         &dev_attr_packets_per_slave.attr,
+        &dev_attr_tlb_dynamic_lb.attr,
         NULL,
 };
 
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index c0948ca26389..c1c7c2f12ac4 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -174,6 +174,7 @@ struct bond_params {
         int resend_igmp;
         int lp_interval;
         int packets_per_slave;
+        int tlb_dynamic_lb;
         struct reciprocal_value reciprocal_packets_per_slave;
 };