mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![]() Note: Tom Herbert posted almost same patch 3 months back, but for different reasons. The reasons we want to get rid of this spin_trylock() are : 1) Under high qdisc pressure, the spin_trylock() has almost no chance to succeed. 2) We loop multiple times in softirq handler, eventually reaching the max retry count (10), and we schedule ksoftirqd. Since we want to adhere more strictly to ksoftirqd being waked up in the future (https://lwn.net/Articles/687617/), better avoid spurious wakeups. 3) calls to __netif_reschedule() dirty the cache line containing q->next_sched, slowing down the owner of qdisc. 4) RT kernels can not use the spin_trylock() here. With help of busylock, we get the qdisc spinlock fast enough, and the trylock trick brings only performance penalty. Depending on qdisc setup, I observed a gain of up to 19 % in qdisc performance (1016600 pps instead of 853400 pps, using prio+tbf+fq_codel) ("mpstat -I SCPU 1" is much happier now) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Tom Herbert <tom@herbertland.com> Acked-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
---|---|---|
.. | ||
datagram.c | ||
dev.c | ||
dev_addr_lists.c | ||
dev_ioctl.c | ||
devlink.c | ||
drop_monitor.c | ||
dst.c | ||
dst_cache.c | ||
ethtool.c | ||
fib_rules.c | ||
filter.c | ||
flow.c | ||
flow_dissector.c | ||
gen_estimator.c | ||
gen_stats.c | ||
hwbm.c | ||
link_watch.c | ||
lwtunnel.c | ||
Makefile | ||
neighbour.c | ||
net-procfs.c | ||
net-sysfs.c | ||
net-sysfs.h | ||
net-traces.c | ||
net_namespace.c | ||
netclassid_cgroup.c | ||
netevent.c | ||
netpoll.c | ||
netprio_cgroup.c | ||
pktgen.c | ||
ptp_classifier.c | ||
request_sock.c | ||
rtnetlink.c | ||
scm.c | ||
secure_seq.c | ||
skbuff.c | ||
sock.c | ||
sock_diag.c | ||
sock_reuseport.c | ||
stream.c | ||
sysctl_net_core.c | ||
timestamping.c | ||
tso.c | ||
utils.c |