From: Jay Vosburgh <fubar@us.ibm.com>
To: netdev@vger.kernel.org, jgarzik@pobox.com
Cc: andy@greyhouse.net, Jay Vosburgh <fubar@us.ibm.com>
Subject: [PATCH 2/6] Convert balance-rr transmit to new locking
Date: Wed, 17 Oct 2007 17:37:47 -0700 [thread overview]
Message-ID: <11926678762641-git-send-email-fubar@us.ibm.com> (raw)
In-Reply-To: <11926678763205-git-send-email-fubar@us.ibm.com>
Change locking in balance-rr transmit processing to use a free
running counter to determine which slave to transmit on. Instead, a
free-running counter is maintained, and modulo arithmetic used to select
a slave for transmit.
This removes lock operations from the TX path, and eliminates
a deadlock introduced by the conversion to work queues.
Signed-off-by: Andy Gospodarek <andy@greyhouse.net>
Signed-off-by: Jay Vosburgh <fubar@us.ibm.com>
---
drivers/net/bonding/bond_main.c | 25 ++++++++++++-------------
drivers/net/bonding/bonding.h | 1 +
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index ed361d6..862ed8e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4057,8 +4057,7 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
{
struct bonding *bond = bond_dev->priv;
struct slave *slave, *start_at;
- int i;
- int res = 1;
+ int i, slave_no, res = 1;
read_lock(&bond->lock);
@@ -4066,29 +4065,29 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev
goto out;
}
- read_lock(&bond->curr_slave_lock);
- slave = start_at = bond->curr_active_slave;
- read_unlock(&bond->curr_slave_lock);
+ /*
+ * Concurrent TX may collide on rr_tx_counter; we accept that
+ * as being rare enough not to justify using an atomic op here
+ */
+ slave_no = bond->rr_tx_counter++ % bond->slave_cnt;
- if (!slave) {
- goto out;
+ bond_for_each_slave(bond, slave, i) {
+ slave_no--;
+ if (slave_no < 0) {
+ break;
+ }
}
+ start_at = slave;
bond_for_each_slave_from(bond, slave, i, start_at) {
if (IS_UP(slave->dev) &&
(slave->link == BOND_LINK_UP) &&
(slave->state == BOND_STATE_ACTIVE)) {
res = bond_dev_queue_xmit(bond, skb, slave->dev);
-
- write_lock(&bond->curr_slave_lock);
- bond->curr_active_slave = slave->next;
- write_unlock(&bond->curr_slave_lock);
-
break;
}
}
-
out:
if (res) {
/* no suitable interface, frame not sent */
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index a8f2384..d1ed14b 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -197,6 +197,7 @@ struct bonding {
int (*xmit_hash_policy)(struct sk_buff *, struct net_device *, int);
__be32 master_ip;
u16 flags;
+ u16 rr_tx_counter;
struct ad_bond_info ad_info;
struct alb_bond_info alb_info;
struct bond_params params;
--
1.5.3.4.206.g58ba4-dirty
next prev parent reply other threads:[~2007-10-18 0:37 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-10-18 0:37 [PATCH 0/6] bonding workqueue and lock rework Jay Vosburgh
2007-10-18 0:37 ` [PATCH 1/6] Convert bonding timers to workqueues Jay Vosburgh
2007-10-18 0:37 ` [PATCH] Two small fixes to IPoIB support for bonding: Jay Vosburgh
2007-10-18 0:37 ` Jay Vosburgh [this message]
2007-10-18 0:37 ` [PATCH 3/6] Convert miimon to new locking Jay Vosburgh
2007-10-18 0:37 ` [PATCH 4/6] Convert locks to _bh, rework alb locking for " Jay Vosburgh
2007-10-18 0:37 ` [PATCH 5/6] Convert more locks to _bh, acquire rtnl, " Jay Vosburgh
2007-10-18 0:37 ` [PATCH 6/6] Acquire correct locks in alb for promisc change Jay Vosburgh
2007-10-18 1:15 ` [PATCH] Two small fixes to IPoIB support for bonding: Jay Vosburgh
2007-10-24 0:42 ` [PATCH 1/6] Convert bonding timers to workqueues Jeff Garzik
2007-10-24 1:00 ` Jay Vosburgh
2007-10-24 1:13 ` Andy Gospodarek
2007-10-24 1:19 ` Jeff Garzik
-- strict thread matches above, loose matches on Subject: below --
2007-10-11 4:14 [PATCH 0/6] bonding workqueue and lock rework Jay Vosburgh
2007-10-11 4:14 ` [PATCH 1/6] Convert bonding timers to workqueues Jay Vosburgh
2007-10-11 4:14 ` [PATCH 2/6] Convert balance-rr transmit to new locking Jay Vosburgh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=11926678762641-git-send-email-fubar@us.ibm.com \
--to=fubar@us.ibm.com \
--cc=andy@greyhouse.net \
--cc=jgarzik@pobox.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).