summaryrefslogtreecommitdiff
path: root/lib/mpi/mpi-bit.c
diff options
context:
space:
mode:
authorCalvin Owens <calvinowens@fb.com>2015-01-13 13:16:18 -0800
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2015-05-06 21:59:20 +0200
commit1f649f03683a908fb51ab40ab176c3902f14d335 (patch)
treee1d7957fbe2fc88c13bda617a0e5283ddf7770db /lib/mpi/mpi-bit.c
parent7507c7e11351c4dde218f1bc8bc9fce98329a5fa (diff)
ksoftirqd: Enable IRQs and call cond_resched() before poking RCU
commit 28423ad283d5348793b0c45cc9b1af058e776fd6 upstream. While debugging an issue with excessive softirq usage, I encountered the following note in commit 3e339b5dae24a706 ("softirq: Use hotplug thread infrastructure"): [ paulmck: Call rcu_note_context_switch() with interrupts enabled. ] ...but despite this note, the patch still calls RCU with IRQs disabled. This seemingly innocuous change caused a significant regression in softirq CPU usage on the sending side of a large TCP transfer (~1 GB/s): when introducing 0.01% packet loss, the softirq usage would jump to around 25%, spiking as high as 50%. Before the change, the usage would never exceed 5%. Moving the call to rcu_note_context_switch() after the cond_sched() call, as it was originally before the hotplug patch, completely eliminated this problem. Signed-off-by: Calvin Owens <calvinowens@fb.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Mike Galbraith <mgalbraith@suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'lib/mpi/mpi-bit.c')
0 files changed, 0 insertions, 0 deletions