From 141b6b2ad75d92770240de3af98d55c41ce7cd18 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Wed, 1 May 2019 19:56:59 -0700 Subject: net: add a generic tracepoint for TX queue timeout Although devlink health report does a nice job on reporting TX timeout and other NIC errors, unfortunately it requires drivers to support it but currently only mlx5 has implemented it. Before other drivers could catch up, it is useful to have a generic tracepoint to monitor this kind of TX timeout. We have been suffering TX timeout with different drivers, we plan to start to monitor it with rasdaemon which just needs a new tracepoint. Sample output: ksoftirqd/1-16 [001] ..s2 144.043173: net_dev_xmit_timeout: dev=ens3 driver=e1000 queue=0 Cc: Eran Ben Elisha Cc: Jiri Pirko Signed-off-by: Cong Wang Acked-by: Jiri Pirko Reviewed-by: Eran Ben Elisha Signed-off-by: David S. Miller --- net/sched/sch_generic.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 848aab3693bd..cce1e9ee85af 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -32,6 +32,7 @@ #include #include #include +#include #include /* Qdisc to use by default */ @@ -441,6 +442,7 @@ static void dev_watchdog(struct timer_list *t) } if (some_queue_timedout) { + trace_net_dev_xmit_timeout(dev, i); WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", dev->name, netdev_drivername(dev), i); dev->netdev_ops->ndo_tx_timeout(dev); -- cgit