From: Eric Dumazet <eric.dumazet@gmail.com>
To: "David S . Miller" <davem@davemloft.net>,
Jakub Kicinski <kuba@kernel.org>
Cc: netdev <netdev@vger.kernel.org>,
Eric Dumazet <edumazet@google.com>,
Eric Dumazet <eric.dumazet@gmail.com>
Subject: [PATCH net-next 0/4] net: make dev_watchdog() less intrusive
Date: Tue, 16 Nov 2021 19:29:20 -0800 [thread overview]
Message-ID: <20211117032924.1740327-1-eric.dumazet@gmail.com> (raw)
From: Eric Dumazet <edumazet@google.com>
dev_watchdog() is used on many NIC to periodically monitor TX queues
to detect hangs.
Problem is : It stops all queues, then check them, then 'unfreeze' them.
Not only this stops feeding the NIC, it also migrates all qdiscs
to be serviced on the cpu calling netif_tx_unlock(), causing
a potential latency artifact.
With many TX queues, this is becoming more visible.
Eric Dumazet (4):
net: use an atomic_long_t for queue->trans_timeout
net: annotate accesses to queue->trans_start
net: do not inline netif_tx_lock()/netif_tx_unlock()
net: no longer stop all TX queues in dev_watchdog()
.../net/ethernet/apm/xgene/xgene_enet_main.c | 2 +-
drivers/net/ethernet/atheros/ag71xx.c | 2 +-
.../net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +-
.../net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
drivers/net/ethernet/ibm/ibmvnic.c | 2 +-
drivers/net/ethernet/intel/igb/igb_main.c | 4 +-
.../mellanox/mlx5/core/en/reporter_tx.c | 2 +-
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +-
drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +-
drivers/net/virtio_net.c | 2 +-
drivers/net/wireless/marvell/mwifiex/init.c | 2 +-
drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
include/linux/netdevice.h | 57 +++++----------
net/core/net-sysfs.c | 6 +-
net/sched/sch_generic.c | 69 ++++++++++++++++---
15 files changed, 94 insertions(+), 70 deletions(-)
--
2.34.0.rc1.387.gb447b232ab-goog
next reply other threads:[~2021-11-17 3:29 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-17 3:29 Eric Dumazet [this message]
2021-11-17 3:29 ` [PATCH net-next 1/4] net: use an atomic_long_t for queue->trans_timeout Eric Dumazet
2021-11-17 3:29 ` [PATCH net-next 2/4] net: annotate accesses to queue->trans_start Eric Dumazet
2021-11-18 18:27 ` kernel test robot
2021-11-17 3:29 ` [PATCH net-next 3/4] net: do not inline netif_tx_lock()/netif_tx_unlock() Eric Dumazet
2021-11-17 3:29 ` [PATCH net-next 4/4] net: no longer stop all TX queues in dev_watchdog() Eric Dumazet
2021-11-17 15:00 ` [PATCH net-next 0/4] net: make dev_watchdog() less intrusive patchwork-bot+netdevbpf
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=20211117032924.1740327-1-eric.dumazet@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=kuba@kernel.org \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.