mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![akpm@osdl.org](/assets/img/avatar_default.png)
) From: Ingo Molnar <mingo@elte.hu> This is the latest version of the scheduler cache-hot-auto-tune patch. The first problem was that detection time scaled with O(N^2), which is unacceptable on larger SMP and NUMA systems. To solve this: - I've added a 'domain distance' function, which is used to cache measurement results. Each distance is only measured once. This means that e.g. on NUMA distances of 0, 1 and 2 might be measured, on HT distances 0 and 1, and on SMP distance 0 is measured. The code walks the domain tree to determine the distance, so it automatically follows whatever hierarchy an architecture sets up. This cuts down on the boot time significantly and removes the O(N^2) limit. The only assumption is that migration costs can be expressed as a function of domain distance - this covers the overwhelming majority of existing systems, and is a good guess even for more assymetric systems. [ People hacking systems that have assymetries that break this assumption (e.g. different CPU speeds) should experiment a bit with the cpu_distance() function. Adding a ->migration_distance factor to the domain structure would be one possible solution - but lets first see the problem systems, if they exist at all. Lets not overdesign. ] Another problem was that only a single cache-size was used for measuring the cost of migration, and most architectures didnt set that variable up. Furthermore, a single cache-size does not fit NUMA hierarchies with L3 caches and does not fit HT setups, where different CPUs will often have different 'effective cache sizes'. To solve this problem: - Instead of relying on a single cache-size provided by the platform and sticking to it, the code now auto-detects the 'effective migration cost' between two measured CPUs, via iterating through a wide range of cachesizes. The code searches for the maximum migration cost, which occurs when the working set of the test-workload falls just below the 'effective cache size'. I.e. real-life optimized search is done for the maximum migration cost, between two real CPUs. This, amongst other things, has the positive effect hat if e.g. two CPUs share a L2/L3 cache, a different (and accurate) migration cost will be found than between two CPUs on the same system that dont share any caches. (The reliable measurement of migration costs is tricky - see the source for details.) Furthermore i've added various boot-time options to override/tune migration behavior. Firstly, there's a blanket override for autodetection: migration_cost=1000,2000,3000 will override the depth 0/1/2 values with 1msec/2msec/3msec values. Secondly, there's a global factor that can be used to increase (or decrease) the autodetected values: migration_factor=120 will increase the autodetected values by 20%. This option is useful to tune things in a workload-dependent way - e.g. if a workload is cache-insensitive then CPU utilization can be maximized by specifying migration_factor=0. I've tested the autodetection code quite extensively on x86, on 3 P3/Xeon/2MB, and the autodetected values look pretty good: Dual Celeron (128K L2 cache): --------------------- migration cost matrix (max_cache_size: 131072, cpu: 467 MHz): --------------------- [00] [01] [00]: - 1.7(1) [01]: 1.7(1) - --------------------- cacheflush times [2]: 0.0 (0) 1.7 (1784008) --------------------- Here the slow memory subsystem dominates system performance, and even though caches are small, the migration cost is 1.7 msecs. Dual HT P4 (512K L2 cache): --------------------- migration cost matrix (max_cache_size: 524288, cpu: 2379 MHz): --------------------- [00] [01] [02] [03] [00]: - 0.4(1) 0.0(0) 0.4(1) [01]: 0.4(1) - 0.4(1) 0.0(0) [02]: 0.0(0) 0.4(1) - 0.4(1) [03]: 0.4(1) 0.0(0) 0.4(1) - --------------------- cacheflush times [2]: 0.0 (33900) 0.4 (448514) --------------------- Here it can be seen that there is no migration cost between two HT siblings (CPU#0/2 and CPU#1/3 are separate physical CPUs). A fast memory system makes inter-physical-CPU migration pretty cheap: 0.4 msecs. 8-way P3/Xeon [2MB L2 cache]: --------------------- migration cost matrix (max_cache_size: 2097152, cpu: 700 MHz): --------------------- [00] [01] [02] [03] [04] [05] [06] [07] [00]: - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [01]: 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [02]: 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) [03]: 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) 19.2(1) [04]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) 19.2(1) [05]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) 19.2(1) [06]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - 19.2(1) [07]: 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) 19.2(1) - --------------------- cacheflush times [2]: 0.0 (0) 19.2 (19281756) --------------------- This one has huge caches and a relatively slow memory subsystem - so the migration cost is 19 msecs. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Ken Chen <kenneth.w.chen@intel.com> Cc: <wilder@us.ibm.com> Signed-off-by: John Hawkes <hawkes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
106 lines
2.9 KiB
C
106 lines
2.9 KiB
C
/*
|
|
* linux/include/asm-i386/topology.h
|
|
*
|
|
* Written by: Matthew Dobson, IBM Corporation
|
|
*
|
|
* Copyright (C) 2002, IBM Corp.
|
|
*
|
|
* All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or
|
|
* (at your option) any later version.
|
|
*
|
|
* This program is distributed in the hope that it will be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
|
|
* NON INFRINGEMENT. See the GNU General Public License for more
|
|
* details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write to the Free Software
|
|
* Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
|
*
|
|
* Send feedback to <colpatch@us.ibm.com>
|
|
*/
|
|
#ifndef _ASM_I386_TOPOLOGY_H
|
|
#define _ASM_I386_TOPOLOGY_H
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
#include <asm/mpspec.h>
|
|
|
|
#include <linux/cpumask.h>
|
|
|
|
/* Mappings between logical cpu number and node number */
|
|
extern cpumask_t node_2_cpu_mask[];
|
|
extern int cpu_2_node[];
|
|
|
|
/* Returns the number of the node containing CPU 'cpu' */
|
|
static inline int cpu_to_node(int cpu)
|
|
{
|
|
return cpu_2_node[cpu];
|
|
}
|
|
|
|
/* Returns the number of the node containing Node 'node'. This architecture is flat,
|
|
so it is a pretty simple function! */
|
|
#define parent_node(node) (node)
|
|
|
|
/* Returns a bitmask of CPUs on Node 'node'. */
|
|
static inline cpumask_t node_to_cpumask(int node)
|
|
{
|
|
return node_2_cpu_mask[node];
|
|
}
|
|
|
|
/* Returns the number of the first CPU on Node 'node'. */
|
|
static inline int node_to_first_cpu(int node)
|
|
{
|
|
cpumask_t mask = node_to_cpumask(node);
|
|
return first_cpu(mask);
|
|
}
|
|
|
|
#define pcibus_to_node(bus) ((long) (bus)->sysdata)
|
|
#define pcibus_to_cpumask(bus) node_to_cpumask(pcibus_to_node(bus))
|
|
|
|
/* sched_domains SD_NODE_INIT for NUMAQ machines */
|
|
#define SD_NODE_INIT (struct sched_domain) { \
|
|
.span = CPU_MASK_NONE, \
|
|
.parent = NULL, \
|
|
.groups = NULL, \
|
|
.min_interval = 8, \
|
|
.max_interval = 32, \
|
|
.busy_factor = 32, \
|
|
.imbalance_pct = 125, \
|
|
.cache_nice_tries = 1, \
|
|
.busy_idx = 3, \
|
|
.idle_idx = 1, \
|
|
.newidle_idx = 2, \
|
|
.wake_idx = 1, \
|
|
.per_cpu_gain = 100, \
|
|
.flags = SD_LOAD_BALANCE \
|
|
| SD_BALANCE_EXEC \
|
|
| SD_BALANCE_FORK \
|
|
| SD_WAKE_BALANCE, \
|
|
.last_balance = jiffies, \
|
|
.balance_interval = 1, \
|
|
.nr_balance_failed = 0, \
|
|
}
|
|
|
|
extern unsigned long node_start_pfn[];
|
|
extern unsigned long node_end_pfn[];
|
|
extern unsigned long node_remap_size[];
|
|
|
|
#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
|
|
|
|
#else /* !CONFIG_NUMA */
|
|
/*
|
|
* Other i386 platforms should define their own version of the
|
|
* above macros here.
|
|
*/
|
|
|
|
#include <asm-generic/topology.h>
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
#endif /* _ASM_I386_TOPOLOGY_H */
|