Skip to contentSkip to conversation

hash table sizes

DISCUSSION Manfred Spraul 1 participant 1 message Nov 29, 2003

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

What about the attached patch?
- add command line overrides for the hash tables sizes. It's impossible to guess if the system is used as a HPC or as a file server. Doc update missing.
- limit the dcache hash to 8 mio entries, and the inode hash to 1 mio entries, regardless of the amount of memory in the system. The system admin can override the defaults at boot time if needed.
- distribute the memory allocations that happen during boot to all nodes - the memory will be touched by all cpus, binding all allocs to the boot node is wrong.

The patch compiles, but is untested due to lack of hardware.

--
Manfred

// $Header$
// Kernel Version:

//  VERSION = 2
//  PATCHLEVEL = 6
//  SUBLEVEL = 0
//  EXTRAVERSION = -test11
mm/page_alloc.c +40 -0
@@ -681,6 +681,42 @@
 
 EXPORT_SYMBOL(__alloc_pages);
 
+#ifdef CONFIG_NUMA
+/* Early boot: Everything is done by one cpu, but the data structures will be
+ * used by all cpus - spread them on all nodes.
+ */
+static __init unsigned long get_boot_pages(unsigned int gfp_mask, unsigned int order)
+{
+static int nodenr;
+	int i = nodenr;
+	struct page *page;
+
+	for (;;) {
+		if (i > nodenr + numnodes)
+			return 0;
+		if (node_present_pages(i%numnodes)) {
+			struct zone **z;
+			/* The node contains memory. Check that there is 
+			 * memory in the intended zonelist.
+			 */
+			z = NODE_DATA(i%numnodes)->node_zonelists[gfp_mask & GFP_ZONEMASK].zones;
+			while (*z) {
+				if ( (*z)->free_pages > (1UL<<order))
+					goto found_node;
+				z++;
+			}
+		}
+		i++;
+	}
+found_node:
+	nodenr = i+1;
+	page = alloc_pages_node(i%numnodes, gfp_mask, order);
+	if (!page)
+		return 0;
+	return (unsigned long) page_address(page);
+}
+#endif
+
 /*
  * Common helper functions.
  */
@@ -688,6 +724,10 @@
 {
 	struct page * page;
 
+#ifdef CONFIG_NUMA
+	if (unlikely(!system_running))
+		return get_boot_pages(gfp_mask, order);
+#endif
 	page = alloc_pages(gfp_mask, order);
 	if (!page)
 		return 0;
fs/inode.c +24 -2
@@ -1327,6 +1327,20 @@
 		wake_up_all(wq);
 }
 
+static __initdata int ihash_entries;
+
+static int __init set_ihash_entries(char *str)
+{
+	get_option(&str, &ihash_entries);
+	if (ihash_entries <= 0) {
+		ihash_entries = 0;
+		return 0;
+	}
+	return 1;
+}
+
+__setup("ihash_entries=", set_ihash_entries);
+
 /*
  * Initialize the waitqueues and inode hash table.
  */
@@ -1340,8 +1354,16 @@
 	for (i = 0; i < ARRAY_SIZE(i_wait_queue_heads); i++)
 		init_waitqueue_head(&i_wait_queue_heads[i].wqh);
 
-	mempages >>= (14 - PAGE_SHIFT);
-	mempages *= sizeof(struct hlist_head);
+	if (!ihash_entries) {
+		ihash_entries = mempages >> (14 - PAGE_SHIFT);
+		/* Limit inode hash size. Override for nfs servers
+		 * that handle lots of files.
+		 */
+		if (ihash_entries > 1024*1024)
+			ihash_entries = 1024*1024;
+	}
+
+	mempages = ihash_entries*sizeof(struct hlist_head);
 	for (order = 0; ((1UL << order) << PAGE_SHIFT) < mempages; order++)
 		;
 
fs/dcache.c +24 -2
@@ -1546,6 +1546,20 @@
 	return ino;
 }
 
+static __initdata int dhash_entries;
+
+static int __init set_dhash_entries(char *str)
+{
+	get_option(&str, &dhash_entries);
+	if (dhash_entries <= 0) {
+		dhash_entries = 0;
+		return 0;
+	}
+	return 1;
+}
+
+__setup("dhash_entries=", set_dhash_entries);
+
 static void __init dcache_init(unsigned long mempages)
 {
 	struct hlist_head *d;
@@ -1571,10 +1585,18 @@
 	
 	set_shrinker(DEFAULT_SEEKS, shrink_dcache_memory);
 
+	if (!dhash_entries) {
 #if PAGE_SHIFT < 13
-	mempages >>= (13 - PAGE_SHIFT);
+		mempages >>= (13 - PAGE_SHIFT);
 #endif
-	mempages *= sizeof(struct hlist_head);
+		dhash_entries = mempages;
+		/* 8 mio is enough for general purpose systems.
+		 * For file servers, override with "dhash_entries="
+		 */
+		if (dhash_entries > 8*1024*1024)
+			dhash_entries = 8*1024*1024;
+	}
+	mempages = dhash_entries*sizeof(struct hlist_head);
 	for (order = 0; ((1UL << order) << PAGE_SHIFT) < mempages; order++)
 		;