From bbf393b0d5350d68dbcf1f231b8af07b1b31121d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 12 Feb 2014 11:12:37 -0800 Subject: Documentation/kernel-per-CPU-kthreads.txt: Workqueue affinity This commit documents the ability to apply CPU affinity to WQ_SYSFS workqueues, thus offloading them from the desired worker CPUs. Signed-off-by: Paul E. McKenney Reviewed-by: Tejun Heo Acked-by: Frederic Weisbecker Reviewed-by: Lai Jiangshan Reviewed-by: Josh Triplett --- Documentation/kernel-per-CPU-kthreads.txt | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt index 827104fb9364..f3cd299fcc41 100644 --- a/Documentation/kernel-per-CPU-kthreads.txt +++ b/Documentation/kernel-per-CPU-kthreads.txt @@ -162,7 +162,18 @@ Purpose: Execute workqueue requests To reduce its OS jitter, do any of the following: 1. Run your workload at a real-time priority, which will allow preempting the kworker daemons. -2. Do any of the following needed to avoid jitter that your +2. A given workqueue can be made visible in the sysfs filesystem + by passing the WQ_SYSFS to that workqueue's alloc_workqueue(). + Such a workqueue can be confined to a given subset of the + CPUs using the /sys/devices/virtual/workqueue/*/cpumask sysfs + files. The set of WQ_SYSFS workqueues can be displayed using + "ls sys/devices/virtual/workqueue". That said, the workqueues + maintainer would like to caution people against indiscriminately + sprinkling WQ_SYSFS across all the workqueues. The reason for + caution is that it is easy to add WQ_SYSFS, but because sysfs is + part of the formal user/kernel API, it can be nearly impossible + to remove it, even if its addition was a mistake. +3. Do any of the following needed to avoid jitter that your application cannot tolerate: a. Build your kernel with CONFIG_SLUB=y rather than CONFIG_SLAB=y, thus avoiding the slab allocator's periodic -- cgit