summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/cpusets.txt17
-rw-r--r--include/linux/sched.h3
-rw-r--r--kernel/cpuset.c84
-rw-r--r--kernel/sched.c29
4 files changed, 2 insertions, 131 deletions
diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index b875d231ac74..ec9de6917f01 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -87,9 +87,6 @@ This can be especially valuable on:
and a database), or
* NUMA systems running large HPC applications with demanding
performance characteristics.
- * Also cpu_exclusive cpusets are useful for servers running orthogonal
- workloads such as RT applications requiring low latency and HPC
- applications that are throughput sensitive
These subsets, or "soft partitions" must be able to be dynamically
adjusted, as the job mix changes, without impacting other concurrently
@@ -132,8 +129,6 @@ Cpusets extends these two mechanisms as follows:
- A cpuset may be marked exclusive, which ensures that no other
cpuset (except direct ancestors and descendents) may contain
any overlapping CPUs or Memory Nodes.
- Also a cpu_exclusive cpuset would be associated with a sched
- domain.
- You can list all the tasks (by pid) attached to any cpuset.
The implementation of cpusets requires a few, simple hooks
@@ -145,9 +140,6 @@ into the rest of the kernel, none in performance critical paths:
allowed in that tasks cpuset.
- in sched.c migrate_all_tasks(), to keep migrating tasks within
the CPUs allowed by their cpuset, if possible.
- - in sched.c, a new API partition_sched_domains for handling
- sched domain changes associated with cpu_exclusive cpusets
- and related changes in both sched.c and arch/ia64/kernel/domain.c
- in the mbind and set_mempolicy system calls, to mask the requested
Memory Nodes by what's allowed in that tasks cpuset.
- in page_alloc.c, to restrict memory to allowed nodes.
@@ -232,15 +224,6 @@ If a cpuset is cpu or mem exclusive, no other cpuset, other than
a direct ancestor or descendent, may share any of the same CPUs or
Memory Nodes.
-A cpuset that is cpu_exclusive has a scheduler (sched) domain
-associated with it. The sched domain consists of all CPUs in the
-current cpuset that are not part of any exclusive child cpusets.
-This ensures that the scheduler load balancing code only balances
-against the CPUs that are in the sched domain as defined above and
-not all of the CPUs in the system. This removes any overhead due to
-load balancing code trying to pull tasks outside of the cpu_exclusive
-cpuset only to be prevented by the tasks' cpus_allowed mask.
-
A cpuset that is mem_exclusive restricts kernel allocations for
page, buffer and other data commonly shared by the kernel across
multiple users. All cpusets, whether mem_exclusive or not, restrict
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 285ee4827a3c..592e3a55f818 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -729,9 +729,6 @@ struct sched_domain {
#endif
};
-extern int partition_sched_domains(cpumask_t *partition1,
- cpumask_t *partition2);
-
#endif /* CONFIG_SMP */
/*
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e196510aa40f..0864f4097930 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -755,68 +755,13 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
}
/*
- * For a given cpuset cur, partition the system as follows
- * a. All cpus in the parent cpuset's cpus_allowed that are not part of any
- * exclusive child cpusets
- * b. All cpus in the current cpuset's cpus_allowed that are not part of any
- * exclusive child cpusets
- * Build these two partitions by calling partition_sched_domains
- *
- * Call with manage_mutex held. May nest a call to the
- * lock_cpu_hotplug()/unlock_cpu_hotplug() pair.
- * Must not be called holding callback_mutex, because we must
- * not call lock_cpu_hotplug() while holding callback_mutex.
- */
-
-static void update_cpu_domains(struct cpuset *cur)
-{
- struct cpuset *c, *par = cur->parent;
- cpumask_t pspan, cspan;
-
- if (par == NULL || cpus_empty(cur->cpus_allowed))
- return;
-
- /*
- * Get all cpus from parent's cpus_allowed not part of exclusive
- * children
- */
- pspan = par->cpus_allowed;
- list_for_each_entry(c, &par->children, sibling) {
- if (is_cpu_exclusive(c))
- cpus_andnot(pspan, pspan, c->cpus_allowed);
- }
- if (!is_cpu_exclusive(cur)) {
- cpus_or(pspan, pspan, cur->cpus_allowed);
- if (cpus_equal(pspan, cur->cpus_allowed))
- return;
- cspan = CPU_MASK_NONE;
- } else {
- if (cpus_empty(pspan))
- return;
- cspan = cur->cpus_allowed;
- /*
- * Get all cpus from current cpuset's cpus_allowed not part
- * of exclusive children
- */
- list_for_each_entry(c, &cur->children, sibling) {
- if (is_cpu_exclusive(c))
- cpus_andnot(cspan, cspan, c->cpus_allowed);
- }
- }
-
- lock_cpu_hotplug();
- partition_sched_domains(&pspan, &cspan);
- unlock_cpu_hotplug();
-}
-
-/*
* Call with manage_mutex held. May take callback_mutex during call.
*/
static int update_cpumask(struct cpuset *cs, char *buf)
{
struct cpuset trialcs;
- int retval, cpus_unchanged;
+ int retval;
/* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
if (cs == &top_cpuset)
@@ -843,12 +788,9 @@ static int update_cpumask(struct cpuset *cs, char *buf)
retval = validate_change(cs, &trialcs);
if (retval < 0)
return retval;
- cpus_unchanged = cpus_equal(cs->cpus_allowed, trialcs.cpus_allowed);
mutex_lock(&callback_mutex);
cs->cpus_allowed = trialcs.cpus_allowed;
mutex_unlock(&callback_mutex);
- if (is_cpu_exclusive(cs) && !cpus_unchanged)
- update_cpu_domains(cs);
return 0;
}
@@ -1085,7 +1027,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
{
int turning_on;
struct cpuset trialcs;
- int err, cpu_exclusive_changed;
+ int err;
turning_on = (simple_strtoul(buf, NULL, 10) != 0);
@@ -1098,14 +1040,10 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, char *buf)
err = validate_change(cs, &trialcs);
if (err < 0)
return err;
- cpu_exclusive_changed =
- (is_cpu_exclusive(cs) != is_cpu_exclusive(&trialcs));
mutex_lock(&callback_mutex);
cs->flags = trialcs.flags;
mutex_unlock(&callback_mutex);
- if (cpu_exclusive_changed)
- update_cpu_domains(cs);
return 0;
}
@@ -1965,17 +1903,6 @@ static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode)
return cpuset_create(c_parent, dentry->d_name.name, mode | S_IFDIR);
}
-/*
- * Locking note on the strange update_flag() call below:
- *
- * If the cpuset being removed is marked cpu_exclusive, then simulate
- * turning cpu_exclusive off, which will call update_cpu_domains().
- * The lock_cpu_hotplug() call in update_cpu_domains() must not be
- * made while holding callback_mutex. Elsewhere the kernel nests
- * callback_mutex inside lock_cpu_hotplug() calls. So the reverse
- * nesting would risk an ABBA deadlock.
- */
-
static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
struct cpuset *cs = dentry->d_fsdata;
@@ -1995,13 +1922,6 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
mutex_unlock(&manage_mutex);
return -EBUSY;
}
- if (is_cpu_exclusive(cs)) {
- int retval = update_flag(CS_CPU_EXCLUSIVE, cs, "0");
- if (retval < 0) {
- mutex_unlock(&manage_mutex);
- return retval;
- }
- }
parent = cs->parent;
mutex_lock(&callback_mutex);
set_bit(CS_REMOVED, &cs->flags);
diff --git a/kernel/sched.c b/kernel/sched.c
index 78c8fbd373a3..0da2b2635c54 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6348,35 +6348,6 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
arch_destroy_sched_domains(cpu_map);
}
-/*
- * Partition sched domains as specified by the cpumasks below.
- * This attaches all cpus from the cpumasks to the NULL domain,
- * waits for a RCU quiescent period, recalculates sched
- * domain information and then attaches them back to the
- * correct sched domains
- * Call with hotplug lock held
- */
-int partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
-{
- cpumask_t change_map;
- int err = 0;
-
- cpus_and(*partition1, *partition1, cpu_online_map);
- cpus_and(*partition2, *partition2, cpu_online_map);
- cpus_or(change_map, *partition1, *partition2);
-
- /* Detach sched domains from all of the affected cpus */
- detach_destroy_domains(&change_map);
- if (!cpus_empty(*partition1))
- err = build_sched_domains(partition1);
- if (!err && !cpus_empty(*partition2))
- err = build_sched_domains(partition2);
-
- register_sched_domain_sysctl();
-
- return err;
-}
-
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
static int arch_reinit_sched_domains(void)
{