From f18f982abf183e91f435990d337164c7a43d1e6d Mon Sep 17 00:00:00 2001 From: Max Krasnyansky Date: Thu, 29 May 2008 11:17:01 -0700 Subject: sched: CPU hotplug events must not destroy scheduler domains created by the cpusets First issue is not related to the cpusets. We're simply leaking doms_cur. It's allocated in arch_init_sched_domains() which is called for every hotplug event. So we just keep reallocation doms_cur without freeing it. I introduced free_sched_domains() function that cleans things up. Second issue is that sched domains created by the cpusets are completely destroyed by the CPU hotplug events. For all CPU hotplug events scheduler attaches all CPUs to the NULL domain and then puts them all into the single domain thereby destroying domains created by the cpusets (partition_sched_domains). The solution is simple, when cpusets are enabled scheduler should not create default domain and instead let cpusets do that. Which is exactly what the patch does. Signed-off-by: Max Krasnyansky Cc: pj@sgi.com Cc: menage@google.com Cc: rostedt@goodmis.org Acked-by: Peter Zijlstra Signed-off-by: Thomas Gleixner --- kernel/cpuset.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 039baa4cd90c..bceb89557973 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1890,6 +1890,12 @@ static void common_cpu_mem_hotplug_unplug(void) top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; scan_for_empty_cpusets(&top_cpuset); + /* + * Scheduler destroys domains on hotplug events. + * Rebuild them based on the current settings. + */ + rebuild_sched_domains(); + cgroup_unlock(); } -- cgit v1.2.3 From 30e0e178193d4221abc9926b07a4c7661c7cc4a9 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Tue, 13 May 2008 10:27:17 +0800 Subject: cpuset: limit the input of cpuset.sched_relax_domain_level We allow the inputs to be [-1 ... SD_LV_MAX), and return -EINVAL for inputs outside this range. Signed-off-by: Li Zefan Acked-by: Paul Menage Acked-by: Paul Jackson Acked-by: Hidetoshi Seto Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- Documentation/cpusets.txt | 2 +- kernel/cpuset.c | 4 ++-- kernel/sched.c | 7 ++++++- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt index d803c5c68ab5..353504de3084 100644 --- a/Documentation/cpusets.txt +++ b/Documentation/cpusets.txt @@ -542,7 +542,7 @@ otherwise initial value -1 that indicates the cpuset has no request. 2 : search cores in a package. 3 : search cpus in a node [= system wide on non-NUMA system] ( 4 : search nodes in a chunk of node [on NUMA system] ) - ( 5~ : search system wide [on NUMA system]) + ( 5 : search system wide [on NUMA system] ) This file is per-cpuset and affect the sched domain where the cpuset belongs to. Therefore if the flag 'sched_load_balance' of a cpuset diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 039baa4cd90c..66103a119bfe 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1037,8 +1037,8 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { - if ((int)val < 0) - val = -1; + if (val < -1 || val >= SD_LV_MAX) + return -EINVAL; if (val != cs->relax_domain_level) { cs->relax_domain_level = val; diff --git a/kernel/sched.c b/kernel/sched.c index eaf6751e7612..bb2c699c9f5e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6877,7 +6877,12 @@ static int default_relax_domain_level = -1; static int __init setup_relax_domain_level(char *str) { - default_relax_domain_level = simple_strtoul(str, NULL, 0); + unsigned long val; + + val = simple_strtoul(str, NULL, 0); + if (val < SD_LV_MAX) + default_relax_domain_level = val; + return 1; } __setup("relax_domain_level=", setup_relax_domain_level); -- cgit v1.2.3