From f0c0b2b808f232741eadac272bd4bc51f18df0f4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Sun, 15 Jul 2007 23:38:01 -0700 Subject: change zonelist order: zonelist order selection logic Make zonelist creation policy selectable from sysctl/boot option v6. This patch makes NUMA's zonelist (of pgdat) order selectable. Available order are Default(automatic)/ Node-based / Zone-based. [Default Order] The kernel selects Node-based or Zone-based order automatically. [Node-based Order] This policy treats the locality of memory as the most important parameter. Zonelist order is created by each zone's locality. This means lower zones (ex. ZONE_DMA) can be used before higher zone (ex. ZONE_NORMAL) exhausion. IOW. ZONE_DMA will be in the middle of zonelist. current 2.6.21 kernel uses this. Pros. * A user can expect local memory as much as possible. Cons. * lower zone will be exhansted before higher zone. This may cause OOM_KILL. Maybe suitable if ZONE_DMA is relatively big and you never see OOM_KILL because of ZONE_DMA exhaution and you need the best locality. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(0)'s DMA -> node(1)'s NORMAL. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. [Zone-based order] This policy treats the zone type as the most important parameter. Zonelist order is created by zone-type order. This means lower zone never be used bofere higher zone exhaustion. IOW. ZONE_DMA will be always at the tail of zonelist. Pros. * OOM_KILL(bacause of lower zone) occurs only if the whole zones are exhausted. Cons. * memory locality may not be best. (example) assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL. *node(0)'s memory allocation order: node(0)'s NORMAL -> node(1)'s NORMAL -> node(0)'s DMA. *node(1)'s memory allocation order: node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA. bootoption "numa_zonelist_order=" and proc/sysctl is supporetd. command: %echo N > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Node-based order. command: %echo Z > /proc/sys/vm/numa_zonelist_order Will rebuild zonelist in Zone-based order. Thanks to Lee Schermerhorn, he gives me much help and codes. [Lee.Schermerhorn@hp.com: add check_highest_zone to build_zonelists_in_zone_order] [akpm@linux-foundation.org: build fix] Signed-off-by: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Christoph Lameter Cc: Andi Kleen Cc: "jesse.barnes@intel.com" Signed-off-by: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 5 + Documentation/sysctl/vm.txt | 45 ++++++ include/linux/mmzone.h | 5 + kernel/sysctl.c | 11 ++ mm/page_alloc.c | 273 +++++++++++++++++++++++++++++++++--- 5 files changed, 317 insertions(+), 22 deletions(-) diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 62aab585d9d..4344f69ae24 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1196,6 +1196,11 @@ and is between 256 and 4096 characters. It is defined in the file nowb [ARM] + numa_zonelist_order= [KNL, BOOT] Select zonelist order for NUMA. + one of ['zone', 'node', 'default'] can be specified + This can be set from sysctl after boot. + See Documentation/sysctl/vm.txt for details. + nr_uarts= [SERIAL] maximum number of UARTs to be registered. opl3= [HW,OSS] diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 8cfca173d4b..df3ff2095f9 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -32,6 +32,7 @@ Currently, these files are in /proc/sys/vm: - min_slab_ratio - panic_on_oom - mmap_min_address +- numa_zonelist_order ============================================================== @@ -231,3 +232,47 @@ security module. Setting this value to something like 64k will allow the vast majority of applications to work correctly and provide defense in depth against future potential kernel bugs. +============================================================== + +numa_zonelist_order + +This sysctl is only for NUMA. +'where the memory is allocated from' is controlled by zonelists. +(This documentation ignores ZONE_HIGHMEM/ZONE_DMA32 for simple explanation. + you may be able to read ZONE_DMA as ZONE_DMA32...) + +In non-NUMA case, a zonelist for GFP_KERNEL is ordered as following. +ZONE_NORMAL -> ZONE_DMA +This means that a memory allocation request for GFP_KERNEL will +get memory from ZONE_DMA only when ZONE_NORMAL is not available. + +In NUMA case, you can think of following 2 types of order. +Assume 2 node NUMA and below is zonelist of Node(0)'s GFP_KERNEL + +(A) Node(0) ZONE_NORMAL -> Node(0) ZONE_DMA -> Node(1) ZONE_NORMAL +(B) Node(0) ZONE_NORMAL -> Node(1) ZONE_NORMAL -> Node(0) ZONE_DMA. + +Type(A) offers the best locality for processes on Node(0), but ZONE_DMA +will be used before ZONE_NORMAL exhaustion. This increases possibility of +out-of-memory(OOM) of ZONE_DMA because ZONE_DMA is tend to be small. + +Type(B) cannot offer the best locality but is more robust against OOM of +the DMA zone. + +Type(A) is called as "Node" order. Type (B) is "Zone" order. + +"Node order" orders the zonelists by node, then by zone within each node. +Specify "[Nn]ode" for zone order + +"Zone Order" orders the zonelists by zone type, then by node within each +zone. Specify "[Zz]one"for zode order. + +Specify "[Dd]efault" to request automatic configuration. Autoconfiguration +will select "node" order in following case. +(1) if the DMA zone does not exist or +(2) if the DMA zone comprises greater than 50% of the available memory or +(3) if any node's DMA zone comprises greater than 60% of its local memory and + the amount of local memory is big enough. + +Otherwise, "zone" order will be selected. Default order is recommended unless +this is causing problems for your system/application. diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d09b1345a3a..04b1636a970 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -566,6 +566,11 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +extern int numa_zonelist_order_handler(struct ctl_table *, int, + struct file *, void __user *, size_t *, loff_t *); +extern char numa_zonelist_order[]; +#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ + #include /* Returns the number of the current Node. */ #ifndef numa_node_id diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d93e13d93f2..ccaebbbd75a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -958,6 +958,17 @@ static ctl_table vm_table[] = { .mode = 0644, .proc_handler = &proc_doulongvec_minmax, }, +#ifdef CONFIG_NUMA + { + .ctl_name = CTL_UNNUMBERED, + .procname = "numa_zonelist_order", + .data = &numa_zonelist_order, + .maxlen = NUMA_ZONELIST_ORDER_LEN, + .mode = 0644, + .proc_handler = &numa_zonelist_order_handler, + .strategy = &sysctl_string, + }, +#endif #endif #if defined(CONFIG_X86_32) || \ (defined(CONFIG_SUPERH) && defined(CONFIG_VSYSCALL)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 05ace44852e..092b2d8f2f0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1621,8 +1621,8 @@ void show_free_areas(void) * * Add all populated zones of a node to the zonelist. */ -static int __meminit build_zonelists_node(pg_data_t *pgdat, - struct zonelist *zonelist, int nr_zones, enum zone_type zone_type) +static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, + int nr_zones, enum zone_type zone_type) { struct zone *zone; @@ -1641,9 +1641,102 @@ static int __meminit build_zonelists_node(pg_data_t *pgdat, return nr_zones; } + +/* + * zonelist_order: + * 0 = automatic detection of better ordering. + * 1 = order by ([node] distance, -zonetype) + * 2 = order by (-zonetype, [node] distance) + * + * If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create + * the same zonelist. So only NUMA can configure this param. + */ +#define ZONELIST_ORDER_DEFAULT 0 +#define ZONELIST_ORDER_NODE 1 +#define ZONELIST_ORDER_ZONE 2 + +/* zonelist order in the kernel. + * set_zonelist_order() will set this to NODE or ZONE. + */ +static int current_zonelist_order = ZONELIST_ORDER_DEFAULT; +static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"}; + + #ifdef CONFIG_NUMA +/* The value user specified ....changed by config */ +static int user_zonelist_order = ZONELIST_ORDER_DEFAULT; +/* string for sysctl */ +#define NUMA_ZONELIST_ORDER_LEN 16 +char numa_zonelist_order[16] = "default"; + +/* + * interface for configure zonelist ordering. + * command line option "numa_zonelist_order" + * = "[dD]efault - default, automatic configuration. + * = "[nN]ode - order by node locality, then by zone within node + * = "[zZ]one - order by zone, then by locality within zone + */ + +static int __parse_numa_zonelist_order(char *s) +{ + if (*s == 'd' || *s == 'D') { + user_zonelist_order = ZONELIST_ORDER_DEFAULT; + } else if (*s == 'n' || *s == 'N') { + user_zonelist_order = ZONELIST_ORDER_NODE; + } else if (*s == 'z' || *s == 'Z') { + user_zonelist_order = ZONELIST_ORDER_ZONE; + } else { + printk(KERN_WARNING + "Ignoring invalid numa_zonelist_order value: " + "%s\n", s); + return -EINVAL; + } + return 0; +} + +static __init int setup_numa_zonelist_order(char *s) +{ + if (s) + return __parse_numa_zonelist_order(s); + return 0; +} +early_param("numa_zonelist_order", setup_numa_zonelist_order); + +/* + * sysctl handler for numa_zonelist_order + */ +int numa_zonelist_order_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, + loff_t *ppos) +{ + char saved_string[NUMA_ZONELIST_ORDER_LEN]; + int ret; + + if (write) + strncpy(saved_string, (char*)table->data, + NUMA_ZONELIST_ORDER_LEN); + ret = proc_dostring(table, write, file, buffer, length, ppos); + if (ret) + return ret; + if (write) { + int oldval = user_zonelist_order; + if (__parse_numa_zonelist_order((char*)table->data)) { + /* + * bogus value. restore saved string + */ + strncpy((char*)table->data, saved_string, + NUMA_ZONELIST_ORDER_LEN); + user_zonelist_order = oldval; + } else if (oldval != user_zonelist_order) + build_all_zonelists(); + } + return 0; +} + + #define MAX_NODE_LOAD (num_online_nodes()) -static int __meminitdata node_load[MAX_NUMNODES]; +static int node_load[MAX_NUMNODES]; + /** * find_next_best_node - find the next node that should appear in a given node's fallback list * @node: node whose fallback list we're appending @@ -1658,7 +1751,7 @@ static int __meminitdata node_load[MAX_NUMNODES]; * on them otherwise. * It returns -1 if no node is found. */ -static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) +static int find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; @@ -1704,13 +1797,129 @@ static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) return best_node; } -static void __meminit build_zonelists(pg_data_t *pgdat) + +/* + * Build zonelists ordered by node and zones within node. + * This results in maximum locality--normal zone overflows into local + * DMA zone, if any--but risks exhausting DMA zone. + */ +static void build_zonelists_in_node_order(pg_data_t *pgdat, int node) { - int j, node, local_node; enum zone_type i; - int prev_node, load; + int j; struct zonelist *zonelist; + + for (i = 0; i < MAX_NR_ZONES; i++) { + zonelist = pgdat->node_zonelists + i; + for (j = 0; zonelist->zones[j] != NULL; j++) + ; + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); + zonelist->zones[j] = NULL; + } +} + +/* + * Build zonelists ordered by zone and nodes within zones. + * This results in conserving DMA zone[s] until all Normal memory is + * exhausted, but results in overflowing to remote node while memory + * may still exist in local DMA zone. + */ +static int node_order[MAX_NUMNODES]; + +static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) +{ + enum zone_type i; + int pos, j, node; + int zone_type; /* needs to be signed */ + struct zone *z; + struct zonelist *zonelist; + + for (i = 0; i < MAX_NR_ZONES; i++) { + zonelist = pgdat->node_zonelists + i; + pos = 0; + for (zone_type = i; zone_type >= 0; zone_type--) { + for (j = 0; j < nr_nodes; j++) { + node = node_order[j]; + z = &NODE_DATA(node)->node_zones[zone_type]; + if (populated_zone(z)) { + zonelist->zones[pos++] = z; + check_highest_zone(zone_type); + } + } + } + zonelist->zones[pos] = NULL; + } +} + +static int default_zonelist_order(void) +{ + int nid, zone_type; + unsigned long low_kmem_size,total_size; + struct zone *z; + int average_size; + /* + * ZONE_DMA and ZONE_DMA32 can be very small area in the sytem. + * If they are really small and used heavily, the system can fall + * into OOM very easily. + * This function detect ZONE_DMA/DMA32 size and confgigures zone order. + */ + /* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */ + low_kmem_size = 0; + total_size = 0; + for_each_online_node(nid) { + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { + z = &NODE_DATA(nid)->node_zones[zone_type]; + if (populated_zone(z)) { + if (zone_type < ZONE_NORMAL) + low_kmem_size += z->present_pages; + total_size += z->present_pages; + } + } + } + if (!low_kmem_size || /* there are no DMA area. */ + low_kmem_size > total_size/2) /* DMA/DMA32 is big. */ + return ZONELIST_ORDER_NODE; + /* + * look into each node's config. + * If there is a node whose DMA/DMA32 memory is very big area on + * local memory, NODE_ORDER may be suitable. + */ + average_size = total_size / (num_online_nodes() + 1); + for_each_online_node(nid) { + low_kmem_size = 0; + total_size = 0; + for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { + z = &NODE_DATA(nid)->node_zones[zone_type]; + if (populated_zone(z)) { + if (zone_type < ZONE_NORMAL) + low_kmem_size += z->present_pages; + total_size += z->present_pages; + } + } + if (low_kmem_size && + total_size > average_size && /* ignore small node */ + low_kmem_size > total_size * 70/100) + return ZONELIST_ORDER_NODE; + } + return ZONELIST_ORDER_ZONE; +} + +static void set_zonelist_order(void) +{ + if (user_zonelist_order == ZONELIST_ORDER_DEFAULT) + current_zonelist_order = default_zonelist_order(); + else + current_zonelist_order = user_zonelist_order; +} + +static void build_zonelists(pg_data_t *pgdat) +{ + int j, node, load; + enum zone_type i; nodemask_t used_mask; + int local_node, prev_node; + struct zonelist *zonelist; + int order = current_zonelist_order; /* initialize zonelists */ for (i = 0; i < MAX_NR_ZONES; i++) { @@ -1723,6 +1932,11 @@ static void __meminit build_zonelists(pg_data_t *pgdat) load = num_online_nodes(); prev_node = local_node; nodes_clear(used_mask); + + memset(node_load, 0, sizeof(node_load)); + memset(node_order, 0, sizeof(node_order)); + j = 0; + while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { int distance = node_distance(local_node, node); @@ -1738,23 +1952,25 @@ static void __meminit build_zonelists(pg_data_t *pgdat) * So adding penalty to the first node in same * distance group to make it round-robin. */ - if (distance != node_distance(local_node, prev_node)) - node_load[node] += load; + node_load[node] = load; + prev_node = node; load--; - for (i = 0; i < MAX_NR_ZONES; i++) { - zonelist = pgdat->node_zonelists + i; - for (j = 0; zonelist->zones[j] != NULL; j++); + if (order == ZONELIST_ORDER_NODE) + build_zonelists_in_node_order(pgdat, node); + else + node_order[j++] = node; /* remember order */ + } - j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); - zonelist->zones[j] = NULL; - } + if (order == ZONELIST_ORDER_ZONE) { + /* calculate node order -- i.e., DMA last! */ + build_zonelists_in_zone_order(pgdat, j); } } /* Construct the zonelist performance cache - see further mmzone.h */ -static void __meminit build_zonelist_cache(pg_data_t *pgdat) +static void build_zonelist_cache(pg_data_t *pgdat) { int i; @@ -1771,9 +1987,15 @@ static void __meminit build_zonelist_cache(pg_data_t *pgdat) } } + #else /* CONFIG_NUMA */ -static void __meminit build_zonelists(pg_data_t *pgdat) +static void set_zonelist_order(void) +{ + current_zonelist_order = ZONELIST_ORDER_ZONE; +} + +static void build_zonelists(pg_data_t *pgdat) { int node, local_node; enum zone_type i,j; @@ -1809,7 +2031,7 @@ static void __meminit build_zonelists(pg_data_t *pgdat) } /* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */ -static void __meminit build_zonelist_cache(pg_data_t *pgdat) +static void build_zonelist_cache(pg_data_t *pgdat) { int i; @@ -1820,7 +2042,7 @@ static void __meminit build_zonelist_cache(pg_data_t *pgdat) #endif /* CONFIG_NUMA */ /* return values int ....just for stop_machine_run() */ -static int __meminit __build_all_zonelists(void *dummy) +static int __build_all_zonelists(void *dummy) { int nid; @@ -1831,8 +2053,10 @@ static int __meminit __build_all_zonelists(void *dummy) return 0; } -void __meminit build_all_zonelists(void) +void build_all_zonelists(void) { + set_zonelist_order(); + if (system_state == SYSTEM_BOOTING) { __build_all_zonelists(NULL); cpuset_init_current_mems_allowed(); @@ -1843,8 +2067,13 @@ void __meminit build_all_zonelists(void) /* cpuset refresh routine should be here */ } vm_total_pages = nr_free_pagecache_pages(); - printk("Built %i zonelists. Total pages: %ld\n", - num_online_nodes(), vm_total_pages); + printk("Built %i zonelists in %s order. Total pages: %ld\n", + num_online_nodes(), + zonelist_order_name[current_zonelist_order], + vm_total_pages); +#ifdef CONFIG_NUMA + printk("Policy zone: %s\n", zone_names[policy_zone]); +#endif } /* -- cgit v1.2.3-18-g5258