bianbu-repo-mirror/bianbu-linux-6.6
1
0
Fork 0
mirror of https://gitee.com/bianbu-linux/linux-6.6 synced 2025-04-24 14:07:52 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

net/sched: adjust device watchdog timer to detect stopped queue at right time

Browse source 
[ Upstream commit 33fb988b67050d9bb512f77f08453fa00088943c ]

Applications are sensitive to long network latency, particularly
heartbeat monitoring ones. Longer the tx timeout recovery higher the
risk with such applications on a production machines. This patch
remedies, yet honoring device set tx timeout.

Modify watchdog next timeout to be shorter than the device specified.
Compute the next timeout be equal to device watchdog timeout less the
how long ago queue stop had been done. At next watchdog timeout tx
timeout handler is called into if still in stopped state. Either called
or not called, restore the watchdog timeout back to device specified.

Signed-off-by: Praveen Kumar Kannoju <praveen.kannoju@oracle.com>
Link: https://lore.kernel.org/r/20240508133617.4424-1-praveen.kannoju@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 95ecba62e2fd ("net: fix races in netdev_tx_sent_queue()/dev_watchdog()")
Signed-off-by: Sasha Levin <sashal@kernel.org>
This commit is contained in:
Praveen Kumar Kannoju 2024-05-08 19:06:17 +05:30 • committed by Greg Kroah-Hartman
parent 69076f8435
commit 10cb940429
1 changed files with 7 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

11
net/sched/sch_generic.c
View file

@ -505,19 +505,22 @@ static void dev_watchdog(struct timer_list *t)
unsigned int timedout_ms = 0; unsigned int timedout_ms = 0;
unsigned int i; unsigned int i;
unsigned long trans_start; unsigned long trans_start;
unsigned long oldest_start = jiffies;
for (i = 0; i < dev->num_tx_queues; i++) { for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq; struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i); txq = netdev_get_tx_queue(dev, i);
trans_start = READ_ONCE(txq->trans_start); trans_start = READ_ONCE(txq->trans_start);
if (netif_xmit_stopped(txq) && if (!netif_xmit_stopped(txq))
time_after(jiffies, (trans_start + continue;
dev->watchdog_timeo))) { if (time_after(jiffies, trans_start + dev->watchdog_timeo)) {
timedout_ms = jiffies_to_msecs(jiffies - trans_start); timedout_ms = jiffies_to_msecs(jiffies - trans_start);
atomic_long_inc(&txq->trans_timeout); atomic_long_inc(&txq->trans_timeout);
break; break;
} }
if (time_after(oldest_start, trans_start))
oldest_start = trans_start;
} }
if (unlikely(timedout_ms)) { if (unlikely(timedout_ms)) {
@ -530,7 +533,7 @@ static void dev_watchdog(struct timer_list *t)
netif_unfreeze_queues(dev); netif_unfreeze_queues(dev);
} }
if (!mod_timer(&dev->watchdog_timer, if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies + round_jiffies(oldest_start +
dev->watchdog_timeo))) dev->watchdog_timeo)))
release = false; release = false;
} }