Messages in this thread | | | Date | Mon, 30 Sep 2002 12:27:13 -0700 | From | Chris Wedgwood <> | Subject | Re: [patch] generic work queue handling, workqueue-2.5.39-D6 |
| |
On Mon, Sep 30, 2002 at 06:04:31PM +0200, Ingo Molnar wrote:
> the attached patch (against BK-curr) cleans up the impact of the > removal of task-queue support. It merges kernel/context.c (keventd) > and the old task-queue concept into a unified 'work queue' > concept. The basic primitives are:
> extern workqueue_t *create_workqueue(const char *name); > extern void destroy_workqueue(workqueue_t *wq); > extern int queue_work(work_t *work, workqueue_t *wq); > extern void flush_workqueue(workqueue_t *wq);
Is it possible to pin/stick a workqueue to a CPU (or group thereof)? I'm thinking about trying to intelligently spread the load on larger boxes exspecially perhaps NUMA machines where you may want the workqueue local to some specific node.
--cw
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |