From mboxrd@z Thu Jan 1 00:00:00 1970 From: Amir Noam Subject: [PATCH 2/10] [bonding 2.6] fix monitoring functions Date: Sun, 12 Oct 2003 16:42:26 +0200 Sender: netdev-bounce@oss.sgi.com Message-ID: <200310121642.26285.amir.noam@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 8bit Cc: bonding-devel@lists.sourceforge.net, netdev@oss.sgi.com Return-path: To: jgarzik@pobox.com, davem@redhat.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org Hi, This is a resend of the second patch of the propagations patch set sent on 2003/11/09. The rest of the set is already in 2.6 and this patch was left out only because it failed to reach Jeff the first time. (This patch is also in 2.4 since 2.4.23-pre3). Patch cleanly applies on 2.6.0-test7. Amir diff -Naurp a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c --- a/drivers/net/bonding/bond_main.c Sun Oct 12 15:19:27 2003 +++ b/drivers/net/bonding/bond_main.c Sun Oct 12 15:24:07 2003 @@ -2238,8 +2238,9 @@ out: static void bond_mii_monitor(struct net_device *master) { bonding_t *bond = (struct bonding *) master->priv; - slave_t *slave, *bestslave, *oldcurrent; + slave_t *slave, *oldcurrent; int slave_died = 0; + int do_failover = 0; read_lock(&bond->lock); @@ -2249,7 +2250,6 @@ static void bond_mii_monitor(struct net_ * program could monitor the link itself if needed. */ - bestslave = NULL; slave = (slave_t *)bond; read_lock(&bond->ptrlock); @@ -2257,8 +2257,6 @@ static void bond_mii_monitor(struct net_ read_unlock(&bond->ptrlock); while ((slave = slave->prev) != (slave_t *)bond) { - /* use updelay+1 to match an UP slave even when updelay is 0 */ - int mindelay = updelay + 1; struct net_device *dev = slave->dev; int link_state; u16 old_speed = slave->speed; @@ -2269,14 +2267,7 @@ static void bond_mii_monitor(struct net_ switch (slave->link) { case BOND_LINK_UP: /* the link was up */ if (link_state == BMSR_LSTATUS) { - /* link stays up, tell that this one - is immediately available */ - if (IS_UP(dev) && (mindelay > -2)) { - /* -2 is the best case : - this slave was already up */ - mindelay = -2; - bestslave = slave; - } + /* link stays up, nothing more to do */ break; } else { /* link going down */ @@ -2316,6 +2307,7 @@ static void bond_mii_monitor(struct net_ (bond_mode == BOND_MODE_8023AD)) { bond_set_slave_inactive_flags(slave); } + printk(KERN_INFO "%s: link status definitely down " "for interface %s, disabling it", @@ -2332,12 +2324,10 @@ static void bond_mii_monitor(struct net_ bond_alb_handle_link_change(bond, slave, BOND_LINK_DOWN); } - write_lock(&bond->ptrlock); - if (slave == bond->current_slave) { - /* find a new interface and be verbose */ - reselect_active_interface(bond); + if (slave == oldcurrent) { + do_failover = 1; } - write_unlock(&bond->ptrlock); + slave_died = 1; } else { slave->delay--; @@ -2352,13 +2342,6 @@ static void bond_mii_monitor(struct net_ master->name, (downdelay - slave->delay) * miimon, dev->name); - - if (IS_UP(dev) && (mindelay > -1)) { - /* -1 is a good case : this slave went - down only for a short time */ - mindelay = -1; - bestslave = slave; - } } break; case BOND_LINK_DOWN: /* the link was down */ @@ -2428,26 +2411,12 @@ static void bond_mii_monitor(struct net_ bond_alb_handle_link_change(bond, slave, BOND_LINK_UP); } - write_lock(&bond->ptrlock); - if ( (bond->primary_slave != NULL) - && (slave == bond->primary_slave) ) - reselect_active_interface(bond); - write_unlock(&bond->ptrlock); - } - else + if ((oldcurrent == NULL) || + (slave == bond->primary_slave)) { + do_failover = 1; + } + } else { slave->delay--; - - /* we'll also look for the mostly eligible slave */ - if (bond->primary_slave == NULL) { - if (IS_UP(dev) && (slave->delay < mindelay)) { - mindelay = slave->delay; - bestslave = slave; - } - } else if ( (IS_UP(bond->primary_slave->dev)) || - ( (!IS_UP(bond->primary_slave->dev)) && - (IS_UP(dev) && (slave->delay < mindelay)) ) ) { - mindelay = slave->delay; - bestslave = slave; } } break; @@ -2466,26 +2435,17 @@ static void bond_mii_monitor(struct net_ } /* end of while */ - /* - * if there's no active interface and we discovered that one - * of the slaves could be activated earlier, so we do it. - */ - read_lock(&bond->ptrlock); - oldcurrent = bond->current_slave; - read_unlock(&bond->ptrlock); + if (do_failover) { + write_lock(&bond->ptrlock); - /* no active interface at the moment or need to bring up the primary */ - if (oldcurrent == NULL) { /* no active interface at the moment */ - if (bestslave != NULL) { /* last chance to find one ? */ - write_lock(&bond->ptrlock); - change_active_interface(bond, bestslave); - write_unlock(&bond->ptrlock); - } else if (slave_died) { - /* print this message only once a slave has just died */ + reselect_active_interface(bond); + if (oldcurrent && !bond->current_slave) { printk(KERN_INFO "%s: now running without any active interface !\n", master->name); } + + write_unlock(&bond->ptrlock); } read_unlock(&bond->lock); @@ -2503,9 +2463,10 @@ static void bond_mii_monitor(struct net_ static void loadbalance_arp_monitor(struct net_device *master) { bonding_t *bond; - slave_t *slave; + slave_t *slave, *oldcurrent; int the_delta_in_ticks = arp_interval * HZ / 1000; int next_timer = jiffies + (arp_interval * HZ / 1000); + int do_failover = 0; bond = (struct bonding *) master->priv; if (master->priv == NULL) { @@ -2529,6 +2490,10 @@ static void loadbalance_arp_monitor(stru read_lock(&bond->lock); + read_lock(&bond->ptrlock); + oldcurrent = bond->current_slave; + read_unlock(&bond->ptrlock); + /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the current_slave does not come into * the picture unless it is null. also, slave->jiffies is not needed @@ -2555,21 +2520,19 @@ static void loadbalance_arp_monitor(stru * current_slave being null after enslaving * is closed. */ - write_lock(&bond->ptrlock); - if (bond->current_slave == NULL) { + if (oldcurrent == NULL) { printk(KERN_INFO "%s: link status definitely up " "for interface %s, ", master->name, slave->dev->name); - reselect_active_interface(bond); + do_failover = 1; } else { printk(KERN_INFO "%s: interface %s is now up\n", master->name, slave->dev->name); } - write_unlock(&bond->ptrlock); } } else { /* slave->link == BOND_LINK_UP */ @@ -2592,11 +2555,9 @@ static void loadbalance_arp_monitor(stru master->name, slave->dev->name); - write_lock(&bond->ptrlock); - if (slave == bond->current_slave) { - reselect_active_interface(bond); + if (slave == oldcurrent) { + do_failover = 1; } - write_unlock(&bond->ptrlock); } } @@ -2610,6 +2571,19 @@ static void loadbalance_arp_monitor(stru if (IS_UP(slave->dev)) { arp_send_all(slave); } + } + + if (do_failover) { + write_lock(&bond->ptrlock); + + reselect_active_interface(bond); + if (oldcurrent && !bond->current_slave) { + printk(KERN_INFO + "%s: now running without any active interface !\n", + master->name); + } + + write_unlock(&bond->ptrlock); } read_unlock(&bond->lock);