From 1bd53a7efdc988163ec4c25f656df38dbe500632 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Thu, 12 Dec 2013 15:23:23 +0800 Subject: sched/numa: Drop sysctl_numa_balancing_settle_count sysctl commit 887c290e (sched/numa: Decide whether to favour task or group weights based on swap candidate relationships) drop the check against sysctl_numa_balancing_settle_count, this patch remove the sysctl. Signed-off-by: Wanpeng Li Acked-by: Mel Gorman Reviewed-by: Rik van Riel Acked-by: David Rientjes Signed-off-by: Peter Zijlstra Cc: Andrew Morton Cc: Naoya Horiguchi Link: http://lkml.kernel.org/r/1386833006-6600-1-git-send-email-liwanp@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 34a604726d0b..c8da99f905cf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -384,13 +384,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "numa_balancing_settle_count", - .data = &sysctl_numa_balancing_settle_count, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "numa_balancing_migrate_deferred", .data = &sysctl_numa_balancing_migrate_deferred, -- cgit v1.2.2 From 332ac17ef5bfcff4766dfdfd3b4cdf10b8f8f155 Mon Sep 17 00:00:00 2001 From: Dario Faggioli Date: Thu, 7 Nov 2013 14:43:45 +0100 Subject: sched/deadline: Add bandwidth management for SCHED_DEADLINE tasks In order of deadline scheduling to be effective and useful, it is important that some method of having the allocation of the available CPU bandwidth to tasks and task groups under control. This is usually called "admission control" and if it is not performed at all, no guarantee can be given on the actual scheduling of the -deadline tasks. Since when RT-throttling has been introduced each task group have a bandwidth associated to itself, calculated as a certain amount of runtime over a period. Moreover, to make it possible to manipulate such bandwidth, readable/writable controls have been added to both procfs (for system wide settings) and cgroupfs (for per-group settings). Therefore, the same interface is being used for controlling the bandwidth distrubution to -deadline tasks and task groups, i.e., new controls but with similar names, equivalent meaning and with the same usage paradigm are added. However, more discussion is needed in order to figure out how we want to manage SCHED_DEADLINE bandwidth at the task group level. Therefore, this patch adds a less sophisticated, but actually very sensible, mechanism to ensure that a certain utilization cap is not overcome per each root_domain (the single rq for !SMP configurations). Another main difference between deadline bandwidth management and RT-throttling is that -deadline tasks have bandwidth on their own (while -rt ones doesn't!), and thus we don't need an higher level throttling mechanism to enforce the desired bandwidth. This patch, therefore: - adds system wide deadline bandwidth management by means of: * /proc/sys/kernel/sched_dl_runtime_us, * /proc/sys/kernel/sched_dl_period_us, that determine (i.e., runtime / period) the total bandwidth available on each CPU of each root_domain for -deadline tasks; - couples the RT and deadline bandwidth management, i.e., enforces that the sum of how much bandwidth is being devoted to -rt -deadline tasks to stay below 100%. This means that, for a root_domain comprising M CPUs, -deadline tasks can be created until the sum of their bandwidths stay below: M * (sched_dl_runtime_us / sched_dl_period_us) It is also possible to disable this bandwidth management logic, and be thus free of oversubscribing the system up to any arbitrary level. Signed-off-by: Dario Faggioli Signed-off-by: Juri Lelli Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1383831828-15501-12-git-send-email-juri.lelli@gmail.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c8da99f905cf..c7fb0790ac63 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -414,6 +414,20 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sched_rr_handler, }, + { + .procname = "sched_dl_period_us", + .data = &sysctl_sched_dl_period, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_dl_handler, + }, + { + .procname = "sched_dl_runtime_us", + .data = &sysctl_sched_dl_runtime, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_dl_handler, + }, #ifdef CONFIG_SCHED_AUTOGROUP { .procname = "sched_autogroup_enabled", -- cgit v1.2.2 From 1724813d9f2c7ff702b46d3e4a4f6d9b10a8f8c2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 17 Dec 2013 12:44:49 +0100 Subject: sched/deadline: Remove the sysctl_sched_dl knobs Remove the deadline specific sysctls for now. The problem with them is that the interaction with the exisiting rt knobs is nearly impossible to get right. The current (as per before this patch) situation is that the rt and dl bandwidth is completely separate and we enforce rt+dl < 100%. This is undesirable because this means that the rt default of 95% leaves us hardly any room, even though dl tasks are saver than rt tasks. Another proposed solution was (a discarted patch) to have the dl bandwidth be a fraction of the rt bandwidth. This is highly confusing imo. Furthermore neither proposal is consistent with the situation we actually want; which is rt tasks ran from a dl server. In which case the rt bandwidth is a direct subset of dl. So whichever way we go, the introduction of dl controls at this point is painful. Therefore remove them and instead share the rt budget. This means that for now the rt knobs are used for dl admission control and the dl runtime is accounted against the rt runtime. I realise that this isn't entirely desirable either; but whatever we do we appear to need to change the interface later, so better have a small interface for now. Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-zpyqbqds1r0vyxtxza1e7rdc@git.kernel.org Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c7fb0790ac63..c8da99f905cf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -414,20 +414,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sched_rr_handler, }, - { - .procname = "sched_dl_period_us", - .data = &sysctl_sched_dl_period, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_dl_handler, - }, - { - .procname = "sched_dl_runtime_us", - .data = &sysctl_sched_dl_runtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_dl_handler, - }, #ifdef CONFIG_SCHED_AUTOGROUP { .procname = "sched_autogroup_enabled", -- cgit v1.2.2