From e073ae1b34d5600ffc550407625dcb2d4cf46c6e Mon Sep 17 00:00:00 2001 From: Ravikiran G Thirumalai Date: Wed, 2 May 2007 19:27:08 +0200 Subject: [PATCH] x86-64: Set HASHDIST_DEFAULT to 1 for x86_64 NUMA Enable system hashtable memory to be distributed among nodes on x86_64 NUMA Forcing the kernel to use node interleaved vmalloc instead of bootmem for the system hashtable memory (alloc_large_system_hash) reduces the memory imbalance on node 0 by around 40MB on a 8 node x86_64 NUMA box: Before the following patch, on bootup of a 8 node box: Node 0 MemTotal: 3407488 kB Node 0 MemFree: 3206296 kB Node 0 MemUsed: 201192 kB Node 0 Active: 7012 kB Node 0 Inactive: 512 kB Node 0 Dirty: 0 kB Node 0 Writeback: 0 kB Node 0 FilePages: 1912 kB Node 0 Mapped: 420 kB Node 0 AnonPages: 5612 kB Node 0 PageTables: 468 kB Node 0 NFS_Unstable: 0 kB Node 0 Bounce: 0 kB Node 0 Slab: 5408 kB Node 0 SReclaimable: 644 kB Node 0 SUnreclaim: 4764 kB After the patch (or using hashdist=1 on the kernel command line): Node 0 MemTotal: 3407488 kB Node 0 MemFree: 3247608 kB Node 0 MemUsed: 159880 kB Node 0 Active: 3012 kB Node 0 Inactive: 616 kB Node 0 Dirty: 0 kB Node 0 Writeback: 0 kB Node 0 FilePages: 2424 kB Node 0 Mapped: 380 kB Node 0 AnonPages: 1200 kB Node 0 PageTables: 396 kB Node 0 NFS_Unstable: 0 kB Node 0 Bounce: 0 kB Node 0 Slab: 6304 kB Node 0 SReclaimable: 1596 kB Node 0 SUnreclaim: 4708 kB I guess it is a good idea to keep HASHDIST_DEFAULT "on" for x86_64 NUMA since x86_64 has no dearth of vmalloc space? Or maybe enable hash distribution for all 64bit NUMA arches? The following patch does it only for x86_64. I ran a HPC MPI benchmark -- 'Ansys wingsolid', which takes up quite a bit of memory and uses up tlb entries. This was on a 4 way, 2 socket Tyan AMD box (non vsmp), with 8G total memory (4G pernode). The results with and without hash distribution are: 1. Vanilla - runtime of 1188.000s 2. With hashdist=1 runtime of 1154.000s Oprofile output for the duration of run is: 1. Vanilla: PU: AMD64 processors, speed 2411.16 MHz (estimated) Counted L1_AND_L2_DTLB_MISSES events (L1 and L2 DTLB misses) with a unit mask of 0x00 (No unit mask) count 500 samples % app name symbol name 163054 6.5513 libansys1.so MultiFront::decompose(int, int, Elemset *, int *, int, int, int) 162061 6.5114 libansys3.so blockSaxpy6L_fd 162042 6.5107 libansys3.so blockInnerProduct6L_fd 156286 6.2794 libansys3.so maxb33_ 87879 3.5309 libansys1.so elmatrixmultpcg_ 84857 3.4095 libansys4.so saxpy_pcg 58637 2.3560 libansys4.so .st4560 46612 1.8728 libansys4.so .st4282 43043 1.7294 vmlinux-t copy_user_generic_string 41326 1.6604 libansys3.so blockSaxpyBackSolve6L_fd 41288 1.6589 libansys3.so blockInnerProductBackSolve6L_fd 2. With hashdist=1 CPU: AMD64 processors, speed 2411.13 MHz (estimated) Counted L1_AND_L2_DTLB_MISSES events (L1 and L2 DTLB misses) with a unit mask of 0x00 (No unit mask) count 500 samples % app name symbol name 162993 6.9814 libansys1.so MultiFront::decompose(int, int, Elemset *, int *, int, int, int) 160799 6.8874 libansys3.so blockInnerProduct6L_fd 160459 6.8729 libansys3.so blockSaxpy6L_fd 156018 6.6826 libansys3.so maxb33_ 84700 3.6279 libansys4.so saxpy_pcg 83434 3.5737 libansys1.so elmatrixmultpcg_ 58074 2.4875 libansys4.so .st4560 46000 1.9703 libansys4.so .st4282 41166 1.7632 libansys3.so blockSaxpyBackSolve6L_fd 41033 1.7575 libansys3.so blockInnerProductBackSolve6L_fd 35762 1.5318 libansys1.so inner_product_sub 35591 1.5245 libansys1.so inner_product_sub2 28259 1.2104 libansys4.so addVectors Signed-off-by: Pravin B. Shelar Signed-off-by: Ravikiran Thirumalai Signed-off-by: Shai Fultheim Signed-off-by: Andi Kleen Acked-by: Christoph Lameter Cc: Andi Kleen Signed-off-by: Andrew Morton --- include/linux/bootmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/bootmem.h') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 81c07cd..0365ec9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -122,9 +122,9 @@ extern void *alloc_large_system_hash(const char *tablename, #define HASH_EARLY 0x00000001 /* Allocating during early boot? */ /* Only NUMA needs hash distribution. - * IA64 is known to have sufficient vmalloc space. + * IA64 and x86_64 have sufficient vmalloc space. */ -#if defined(CONFIG_NUMA) && defined(CONFIG_IA64) +#if defined(CONFIG_NUMA) && (defined(CONFIG_IA64) || defined(CONFIG_X86_64)) #define HASHDIST_DEFAULT 1 #else #define HASHDIST_DEFAULT 0 -- cgit v1.1