4 files changed, 203 insertions, 9 deletions

diff --git a/Documentation/cpusets.txt b/Documentation/cpusets.txt
index 30c41459953c..159e2a0c3e80 100644
--- a/Documentation/cpusets.txt
+++ b/Documentation/cpusets.txt
@@ -18,7 +18,8 @@ CONTENTS:
   1.4 What are exclusive cpusets ?
   1.5 What does notify_on_release do ?
   1.6 What is memory_pressure ?
-  1.7 How do I use cpusets ?
+  1.7 What is memory spread ?
+  1.8 How do I use cpusets ?
 2. Usage Examples and Syntax
   2.1 Basic Usage
   2.2 Adding/removing cpus
@@ -317,7 +318,78 @@ the tasks in the cpuset, in units of reclaims attempted per second,
 times 1000.
 
 
-1.7 How do I use cpusets ?
+1.7 What is memory spread ?
+---------------------------
+There are two boolean flag files per cpuset that control where the
+kernel allocates pages for the file system buffers and related in
+kernel data structures.  They are called 'memory_spread_page' and
+'memory_spread_slab'.
+
+If the per-cpuset boolean flag file 'memory_spread_page' is set, then
+the kernel will spread the file system buffers (page cache) evenly
+over all the nodes that the faulting task is allowed to use, instead
+of preferring to put those pages on the node where the task is running.
+
+If the per-cpuset boolean flag file 'memory_spread_slab' is set,
+then the kernel will spread some file system related slab caches,
+such as for inodes and dentries evenly over all the nodes that the
+faulting task is allowed to use, instead of preferring to put those
+pages on the node where the task is running.
+
+The setting of these flags does not affect anonymous data segment or
+stack segment pages of a task.
+
+By default, both kinds of memory spreading are off, and memory
+pages are allocated on the node local to where the task is running,
+except perhaps as modified by the tasks NUMA mempolicy or cpuset
+configuration, so long as sufficient free memory pages are available.
+
+When new cpusets are created, they inherit the memory spread settings
+of their parent.
+
+Setting memory spreading causes allocations for the affected page
+or slab caches to ignore the tasks NUMA mempolicy and be spread
+instead.    Tasks using mbind() or set_mempolicy() calls to set NUMA
+mempolicies will not notice any change in these calls as a result of
+their containing tasks memory spread settings.  If memory spreading
+is turned off, then the currently specified NUMA mempolicy once again
+applies to memory page allocations.
+
+Both 'memory_spread_page' and 'memory_spread_slab' are boolean flag
+files.  By default they contain "0", meaning that the feature is off
+for that cpuset.  If a "1" is written to that file, then that turns
+the named feature on.
+
+The implementation is simple.
+
+Setting the flag 'memory_spread_page' turns on a per-process flag
+PF_SPREAD_PAGE for each task that is in that cpuset or subsequently
+joins that cpuset.  The page allocation calls for the page cache
+is modified to perform an inline check for this PF_SPREAD_PAGE task
+flag, and if set, a call to a new routine cpuset_mem_spread_node()
+returns the node to prefer for the allocation.
+
+Similarly, setting 'memory_spread_cache' turns on the flag
+PF_SPREAD_SLAB, and appropriately marked slab caches will allocate
+pages from the node returned by cpuset_mem_spread_node().
+
+The cpuset_mem_spread_node() routine is also simple.  It uses the
+value of a per-task rotor cpuset_mem_spread_rotor to select the next
+node in the current tasks mems_allowed to prefer for the allocation.
+
+This memory placement policy is also known (in other contexts) as
+round-robin or interleave.
+
+This policy can provide substantial improvements for jobs that need
+to place thread local data on the corresponding node, but that need
+to access large file system data sets that need to be spread across
+the several nodes in the jobs cpuset in order to fit.  Without this
+policy, especially for jobs that might have one thread reading in the
+data set, the memory allocation across the nodes in the jobs cpuset
+can become very uneven.
+
+
+1.8 How do I use cpusets ?
 --------------------------
 
 In order to minimize the impact of cpusets on critical kernel
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 3bc606927116..9354722a9217 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -4,7 +4,7 @@
  *  cpuset interface
  *
  *  Copyright (C) 2003 BULL SA
- *  Copyright (C) 2004 Silicon Graphics, Inc.
+ *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
  *
  */
 
@@ -51,6 +51,18 @@ extern char *cpuset_task_status_allowed(struct task_struct *task, char *buffer);
 extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
 
+extern int cpuset_mem_spread_node(void);
+
+static inline int cpuset_do_page_mem_spread(void)
+{
+        return current->flags & PF_SPREAD_PAGE;
+}
+
+static inline int cpuset_do_slab_mem_spread(void)
+{
+        return current->flags & PF_SPREAD_SLAB;
+}
+
 #else /* !CONFIG_CPUSETS */
 
 static inline int cpuset_init_early(void) { return 0; }
@@ -99,6 +111,21 @@ static inline char *cpuset_task_status_allowed(struct task_struct *task,
 static inline void cpuset_lock(void) {}
 static inline void cpuset_unlock(void) {}
 
+static inline int cpuset_mem_spread_node(void)
+{
+        return 0;
+}
+
+static inline int cpuset_do_page_mem_spread(void)
+{
+        return 0;
+}
+
+static inline int cpuset_do_slab_mem_spread(void)
+{
+        return 0;
+}
+
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e60a91d5b369..b0e37cfa09f5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -869,6 +869,7 @@ struct task_struct {
         struct cpuset *cpuset;
         nodemask_t mems_allowed;
         int cpuset_mems_generation;
+        int cpuset_mem_spread_rotor;
 #endif
         atomic_t fs_excl;       /* holding fs exclusive resources */
         struct rcu_head rcu;
@@ -929,6 +930,8 @@ static inline void put_task_struct(struct task_struct *t)
 #define PF_BORROWED_MM  0x00400000      /* I am a kthread doing use_mm */
 #define PF_RANDOMIZE    0x00800000      /* randomize virtual address space */
 #define PF_SWAPWRITE    0x01000000      /* Allowed to write to swap */
+#define PF_SPREAD_PAGE  0x04000000      /* Spread page cache over cpuset */
+#define PF_SPREAD_SLAB  0x08000000      /* Spread some slab caches over cpuset */
 
 /*
  * Only the _current_ task can read/write to tsk->flags, but other
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 44d13c246e5c..38f18b33de6c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -4,15 +4,14 @@
  *  Processor and Memory placement constraints for sets of tasks.
  *
  *  Copyright (C) 2003 BULL SA.
- *  Copyright (C) 2004 Silicon Graphics, Inc.
+ *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
  *
  *  Portions derived from Patrick Mochel's sysfs code.
  *  sysfs is Copyright (c) 2001-3 Patrick Mochel
- *  Portions Copyright (c) 2004 Silicon Graphics, Inc.
  *
- *  2003-10-10 Written by Simon Derr <simon.derr@bull.net>
+ *  2003-10-10 Written by Simon Derr.
  *  2003-10-22 Updates by Stephen Hemminger.
- *  2004 May-July Rework by Paul Jackson <pj@sgi.com>
+ *  2004 May-July Rework by Paul Jackson.
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License.  See the file COPYING in the main directory of the Linux
@@ -108,7 +107,9 @@ typedef enum {
         CS_MEM_EXCLUSIVE,
         CS_MEMORY_MIGRATE,
         CS_REMOVED,
-        CS_NOTIFY_ON_RELEASE
+        CS_NOTIFY_ON_RELEASE,
+        CS_SPREAD_PAGE,
+        CS_SPREAD_SLAB,
 } cpuset_flagbits_t;
 
 /* convenient tests for these bits */
@@ -137,6 +138,16 @@ static inline int is_memory_migrate(const struct cpuset *cs)
         return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
 }
 
+static inline int is_spread_page(const struct cpuset *cs)
+{
+        return test_bit(CS_SPREAD_PAGE, &cs->flags);
+}
+
+static inline int is_spread_slab(const struct cpuset *cs)
+{
+        return test_bit(CS_SPREAD_SLAB, &cs->flags);
+}
+
 /*
  * Increment this atomic integer everytime any cpuset changes its
  * mems_allowed value.  Users of cpusets can track this generation
@@ -657,6 +668,14 @@ void cpuset_update_task_memory_state(void)
                 cs = tsk->cpuset;       /* Maybe changed when task not locked */
                 guarantee_online_mems(cs, &tsk->mems_allowed);
                 tsk->cpuset_mems_generation = cs->mems_generation;
+                if (is_spread_page(cs))
+                        tsk->flags |= PF_SPREAD_PAGE;
+                else
+                        tsk->flags &= ~PF_SPREAD_PAGE;
+                if (is_spread_slab(cs))
+                        tsk->flags |= PF_SPREAD_SLAB;
+                else
+                        tsk->flags &= ~PF_SPREAD_SLAB;
                 task_unlock(tsk);
                 mutex_unlock(&callback_mutex);
                 mpol_rebind_task(tsk, &tsk->mems_allowed);
@@ -956,7 +975,8 @@ static int update_memory_pressure_enabled(struct cpuset *cs, char *buf)
 /*
  * update_flag - read a 0 or a 1 in a file and update associated flag
  * bit: the bit to update (CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE,
- *                              CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE)
+ *                              CS_NOTIFY_ON_RELEASE, CS_MEMORY_MIGRATE,
+ *                              CS_SPREAD_PAGE, CS_SPREAD_SLAB)
  * cs:  the cpuset to update
  * buf: the buffer where we read the 0 or 1
  *
@@ -1187,6 +1207,8 @@ typedef enum {
         FILE_NOTIFY_ON_RELEASE,
         FILE_MEMORY_PRESSURE_ENABLED,
         FILE_MEMORY_PRESSURE,
+        FILE_SPREAD_PAGE,
+        FILE_SPREAD_SLAB,
         FILE_TASKLIST,
 } cpuset_filetype_t;
 
@@ -1246,6 +1268,14 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us
         case FILE_MEMORY_PRESSURE:
                 retval = -EACCES;
                 break;
+        case FILE_SPREAD_PAGE:
+                retval = update_flag(CS_SPREAD_PAGE, cs, buffer);
+                cs->mems_generation = atomic_inc_return(&cpuset_mems_generation);
+                break;
+        case FILE_SPREAD_SLAB:
+                retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
+                cs->mems_generation = atomic_inc_return(&cpuset_mems_generation);
+                break;
         case FILE_TASKLIST:
                 retval = attach_task(cs, buffer, &pathbuf);
                 break;
@@ -1355,6 +1385,12 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
         case FILE_MEMORY_PRESSURE:
                 s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
                 break;
+        case FILE_SPREAD_PAGE:
+                *s++ = is_spread_page(cs) ? '1' : '0';
+                break;
+        case FILE_SPREAD_SLAB:
+                *s++ = is_spread_slab(cs) ? '1' : '0';
+                break;
         default:
                 retval = -EINVAL;
                 goto out;
@@ -1718,6 +1754,16 @@ static struct cftype cft_memory_pressure = {
         .private = FILE_MEMORY_PRESSURE,
 };
 
+static struct cftype cft_spread_page = {
+        .name = "memory_spread_page",
+        .private = FILE_SPREAD_PAGE,
+};
+
+static struct cftype cft_spread_slab = {
+        .name = "memory_spread_slab",
+        .private = FILE_SPREAD_SLAB,
+};
+
 static int cpuset_populate_dir(struct dentry *cs_dentry)
 {
         int err;
@@ -1736,6 +1782,10 @@ static int cpuset_populate_dir(struct dentry *cs_dentry)
                 return err;
         if ((err = cpuset_add_file(cs_dentry, &cft_memory_pressure)) < 0)
                 return err;
+        if ((err = cpuset_add_file(cs_dentry, &cft_spread_page)) < 0)
+                return err;
+        if ((err = cpuset_add_file(cs_dentry, &cft_spread_slab)) < 0)
+                return err;
         if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
                 return err;
         return 0;
@@ -1764,6 +1814,10 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode)
         cs->flags = 0;
         if (notify_on_release(parent))
                 set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
+        if (is_spread_page(parent))
+                set_bit(CS_SPREAD_PAGE, &cs->flags);
+        if (is_spread_slab(parent))
+                set_bit(CS_SPREAD_SLAB, &cs->flags);
         cs->cpus_allowed = CPU_MASK_NONE;
         cs->mems_allowed = NODE_MASK_NONE;
         atomic_set(&cs->count, 0);
@@ -2201,6 +2255,44 @@ void cpuset_unlock(void)
 }
 
 /**
+ * cpuset_mem_spread_node() - On which node to begin search for a page
+ *
+ * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for
+ * tasks in a cpuset with is_spread_page or is_spread_slab set),
+ * and if the memory allocation used cpuset_mem_spread_node()
+ * to determine on which node to start looking, as it will for
+ * certain page cache or slab cache pages such as used for file
+ * system buffers and inode caches, then instead of starting on the
+ * local node to look for a free page, rather spread the starting
+ * node around the tasks mems_allowed nodes.
+ *
+ * We don't have to worry about the returned node being offline
+ * because "it can't happen", and even if it did, it would be ok.
+ *
+ * The routines calling guarantee_online_mems() are careful to
+ * only set nodes in task->mems_allowed that are online.  So it
+ * should not be possible for the following code to return an
+ * offline node.  But if it did, that would be ok, as this routine
+ * is not returning the node where the allocation must be, only
+ * the node where the search should start.  The zonelist passed to
+ * __alloc_pages() will include all nodes.  If the slab allocator
+ * is passed an offline node, it will fall back to the local node.
+ * See kmem_cache_alloc_node().
+ */
+
+int cpuset_mem_spread_node(void)
+{
+        int node;
+
+        node = next_node(current->cpuset_mem_spread_rotor, current->mems_allowed);
+        if (node == MAX_NUMNODES)
+                node = first_node(current->mems_allowed);
+        current->cpuset_mem_spread_rotor = node;
+        return node;
+}
+EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
+
+/**
  * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors?
  * @p: pointer to task_struct of some other task.
  *