Per cpuset dirty ratios This implements dirty ratios per cpuset. Two new files are added to the cpuset directories: background_dirty_ratio Percentage at which background writeback starts throttle_dirty_ratio Percentage at which the application is throttled and we start synchrononous writeout. Both variables are set to -1 by default which means that the global limits (/proc/sys/vm/vm_dirty_ratio and /proc/sys/vm/dirty_background_ratio) are used for a cpuset. Signed-off-by: Christoph Lameter Index: linux-2.6.20-rc5/include/linux/cpuset.h =================================================================== --- linux-2.6.20-rc5.orig/include/linux/cpuset.h 2007-01-22 13:06:51.691390590 -0600 +++ linux-2.6.20-rc5/include/linux/cpuset.h 2007-01-22 13:08:29.670773834 -0600 @@ -75,6 +75,7 @@ static inline int cpuset_do_slab_mem_spr extern void cpuset_track_online_nodes(void); +extern void cpuset_get_current_ratios(int *background, int *ratio); /* * We need macros since struct address_space is not defined yet */ Index: linux-2.6.20-rc5/mm/page-writeback.c =================================================================== --- linux-2.6.20-rc5.orig/mm/page-writeback.c 2007-01-22 13:04:31.288784522 -0600 +++ linux-2.6.20-rc5/mm/page-writeback.c 2007-01-22 13:08:29.688353343 -0600 @@ -173,6 +173,7 @@ get_dirty_limits(struct dirty_limits *dl nr_mapped += node_page_state(node, NR_FILE_MAPPED) + node_page_state(node, NR_ANON_PAGES); } + cpuset_get_current_ratios(&background_ratio, &dirty_ratio); } else #endif { @@ -184,6 +185,8 @@ get_dirty_limits(struct dirty_limits *dl high_memory = totalhigh_pages; nr_mapped = global_page_state(NR_FILE_MAPPED) + global_page_state(NR_ANON_PAGES); + dirty_ratio = vm_dirty_ratio; + background_ratio = dirty_background_ratio; } #ifdef CONFIG_HIGHMEM /* @@ -197,14 +200,12 @@ get_dirty_limits(struct dirty_limits *dl unmapped_ratio = 100 - (nr_mapped * 100) / available_memory; - dirty_ratio = vm_dirty_ratio; if (dirty_ratio > unmapped_ratio / 2) dirty_ratio = unmapped_ratio / 2; if (dirty_ratio < 5) dirty_ratio = 5; - background_ratio = dirty_background_ratio; if (background_ratio >= dirty_ratio) background_ratio = dirty_ratio / 2; Index: linux-2.6.20-rc5/kernel/cpuset.c =================================================================== --- linux-2.6.20-rc5.orig/kernel/cpuset.c 2007-01-22 13:07:58.943746472 -0600 +++ linux-2.6.20-rc5/kernel/cpuset.c 2007-01-22 13:08:29.720582443 -0600 @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -100,6 +101,9 @@ struct cpuset { int mems_generation; struct fmeter fmeter; /* memory_pressure filter */ + + int background_dirty_ratio; + int throttle_dirty_ratio; }; /* bits in struct cpuset flags field */ @@ -177,6 +181,8 @@ static struct cpuset top_cpuset = { .count = ATOMIC_INIT(0), .sibling = LIST_HEAD_INIT(top_cpuset.sibling), .children = LIST_HEAD_INIT(top_cpuset.children), + .background_dirty_ratio = -1, + .throttle_dirty_ratio = -1, }; static struct vfsmount *cpuset_mount; @@ -1071,6 +1077,21 @@ static int update_flag(cpuset_flagbits_t return 0; } +static int update_int(int *cs_int, char *buf, int min, int max) +{ + char *endp; + int val; + + val = simple_strtol(buf, &endp, 10); + if (val < min || val > max) + return -EINVAL; + + mutex_lock(&callback_mutex); + *cs_int = val; + mutex_unlock(&callback_mutex); + return 0; +} + /* * Frequency meter - How fast is some event occurring? * @@ -1279,6 +1300,8 @@ typedef enum { FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, FILE_TASKLIST, + FILE_THROTTLE_DIRTY_RATIO, + FILE_BACKGROUND_DIRTY_RATIO, } cpuset_filetype_t; static ssize_t cpuset_common_file_write(struct file *file, @@ -1349,6 +1372,12 @@ static ssize_t cpuset_common_file_write( case FILE_TASKLIST: retval = attach_task(cs, buffer, &pathbuf); break; + case FILE_BACKGROUND_DIRTY_RATIO: + retval = update_int(&cs->background_dirty_ratio, buffer, -1, 100); + break; + case FILE_THROTTLE_DIRTY_RATIO: + retval = update_int(&cs->throttle_dirty_ratio, buffer, -1, 100); + break; default: retval = -EINVAL; goto out2; @@ -1461,6 +1490,12 @@ static ssize_t cpuset_common_file_read(s case FILE_SPREAD_SLAB: *s++ = is_spread_slab(cs) ? '1' : '0'; break; + case FILE_BACKGROUND_DIRTY_RATIO: + s += sprintf(s, "%d", cs->background_dirty_ratio); + break; + case FILE_THROTTLE_DIRTY_RATIO: + s += sprintf(s, "%d", cs->throttle_dirty_ratio); + break; default: retval = -EINVAL; goto out; @@ -1834,6 +1869,16 @@ static struct cftype cft_spread_slab = { .private = FILE_SPREAD_SLAB, }; +static struct cftype cft_background_dirty_ratio = { + .name = "background_dirty_ratio", + .private = FILE_BACKGROUND_DIRTY_RATIO, +}; + +static struct cftype cft_throttle_dirty_ratio = { + .name = "throttle_dirty_ratio", + .private = FILE_THROTTLE_DIRTY_RATIO, +}; + static int cpuset_populate_dir(struct dentry *cs_dentry) { int err; @@ -1856,6 +1901,10 @@ static int cpuset_populate_dir(struct de return err; if ((err = cpuset_add_file(cs_dentry, &cft_spread_slab)) < 0) return err; + if ((err = cpuset_add_file(cs_dentry, &cft_background_dirty_ratio)) < 0) + return err; + if ((err = cpuset_add_file(cs_dentry, &cft_throttle_dirty_ratio)) < 0) + return err; if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0) return err; return 0; @@ -1895,6 +1944,8 @@ static long cpuset_create(struct cpuset INIT_LIST_HEAD(&cs->children); cs->mems_generation = cpuset_mems_generation++; fmeter_init(&cs->fmeter); + cs->background_dirty_ratio = parent->background_dirty_ratio; + cs->throttle_dirty_ratio = parent->throttle_dirty_ratio; cs->parent = parent; @@ -2531,8 +2582,30 @@ int cpuset_mem_spread_node(void) } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); -#if MAX_NUMNODES > BITS_PER_LONG +/* + * Determine the dirty ratios for the currently active cpuset + */ +void cpuset_get_current_ratios(int *background_ratio, int *throttle_ratio) +{ + int background = -1; + int throttle = -1; + struct task_struct *tsk = current; + + task_lock(tsk); + background = tsk->cpuset->background_dirty_ratio; + throttle = tsk->cpuset->throttle_dirty_ratio; + task_unlock(tsk); + if (background == -1) + background = dirty_background_ratio; + if (throttle == -1) + throttle = vm_dirty_ratio; + + *background_ratio = background; + *throttle_ratio = throttle; +} + +#if MAX_NUMNODES > BITS_PER_LONG /* * Special functions for NUMA systems with a large number of nodes. * The nodemask is pointed to from the address space. Modifications