72cdd117c4
During memory hot-add, dlpar_add_lmb() calls memory_add_physaddr_to_nid()
to determine which node id (nid) to use when later calling __add_memory().
This is wasteful. On pseries, memory_add_physaddr_to_nid() finds an
appropriate nid for a given address by looking up the LMB containing the
address and then passing that LMB to of_drconf_to_nid_single() to get the
nid. In dlpar_add_lmb() we get this address from the LMB itself.
In short, we have a pointer to an LMB and then we are searching for
that LMB *again* in order to find its nid.
If we call of_drconf_to_nid_single() directly from dlpar_add_lmb() we
can skip the redundant lookup. The only error handling we need to
duplicate from memory_add_physaddr_to_nid() is the fallback to the
default nid when drconf_to_nid_single() returns -1 (NUMA_NO_NODE) or
an invalid nid.
Skipping the extra lookup makes hot-add operations faster, especially
on machines with many LMBs.
Consider an LPAR with 126976 LMBs. In one test, hot-adding 126000
LMBs on an upatched kernel took ~3.5 hours while a patched kernel
completed the same operation in ~2 hours:
Unpatched (12450 seconds):
Sep 9 04:06:31 ltc-brazos1 drmgr[810169]: drmgr: -c mem -a -q 126000
Sep 9 04:06:31 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s)
[...]
Sep 9 07:34:01 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added
Patched (7065 seconds):
Sep 8 21:49:57 ltc-brazos1 drmgr[877703]: drmgr: -c mem -a -q 126000
Sep 8 21:49:57 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s)
[...]
Sep 8 23:27:42 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added
It should be noted that the speedup grows more substantial when
hot-adding LMBs at the end of the drconf range. This is because we
are skipping a linear LMB search.
To see the distinction, consider smaller hot-add test on the same
LPAR. A perf-stat run with 10 iterations showed that hot-adding 4096
LMBs completed less than 1 second faster on a patched kernel:
Unpatched:
Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs):
104,753.42 msec task-clock # 0.992 CPUs utilized ( +- 0.55% )
4,708 context-switches # 0.045 K/sec ( +- 0.69% )
2,444 cpu-migrations # 0.023 K/sec ( +- 1.25% )
394 page-faults # 0.004 K/sec ( +- 0.22% )
445,902,503,057 cycles # 4.257 GHz ( +- 0.55% ) (66.67%)
8,558,376,740 stalled-cycles-frontend # 1.92% frontend cycles idle ( +- 0.88% ) (49.99%)
300,346,181,651 stalled-cycles-backend # 67.36% backend cycles idle ( +- 0.76% ) (50.01%)
258,091,488,691 instructions # 0.58 insn per cycle
# 1.16 stalled cycles per insn ( +- 0.22% ) (66.67%)
70,568,169,256 branches # 673.660 M/sec ( +- 0.17% ) (50.01%)
3,100,725,426 branch-misses # 4.39% of all branches ( +- 0.20% ) (49.99%)
105.583 +- 0.589 seconds time elapsed ( +- 0.56% )
Patched:
Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs):
104,055.69 msec task-clock # 0.993 CPUs utilized ( +- 0.32% )
4,606 context-switches # 0.044 K/sec ( +- 0.20% )
2,463 cpu-migrations # 0.024 K/sec ( +- 0.93% )
394 page-faults # 0.004 K/sec ( +- 0.25% )
442,951,129,921 cycles # 4.257 GHz ( +- 0.32% ) (66.66%)
8,710,413,329 stalled-cycles-frontend # 1.97% frontend cycles idle ( +- 0.47% ) (50.06%)
299,656,905,836 stalled-cycles-backend # 67.65% backend cycles idle ( +- 0.39% ) (50.02%)
252,731,168,193 instructions # 0.57 insn per cycle
# 1.19 stalled cycles per insn ( +- 0.20% ) (66.66%)
68,902,851,121 branches # 662.173 M/sec ( +- 0.13% ) (49.94%)
3,100,242,882 branch-misses # 4.50% of all branches ( +- 0.15% ) (49.98%)
104.829 +- 0.325 seconds time elapsed ( +- 0.31% )
This is consistent. An add-by-count hot-add operation adds LMBs
greedily, so LMBs near the start of the drconf range are considered
first. On an otherwise idle LPAR with so many LMBs we would expect to
find the LMBs we need near the start of the drconf range, hence the
smaller speedup.
Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com>
Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200916145122.3408129-1-cheloha@linux.ibm.com
130 lines
2.8 KiB
C
130 lines
2.8 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_POWERPC_TOPOLOGY_H
|
|
#define _ASM_POWERPC_TOPOLOGY_H
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
struct device;
|
|
struct device_node;
|
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
/*
|
|
* If zone_reclaim_mode is enabled, a RECLAIM_DISTANCE of 10 will mean that
|
|
* all zones on all nodes will be eligible for zone_reclaim().
|
|
*/
|
|
#define RECLAIM_DISTANCE 10
|
|
|
|
#include <asm/mmzone.h>
|
|
|
|
#define cpumask_of_node(node) ((node) == -1 ? \
|
|
cpu_all_mask : \
|
|
node_to_cpumask_map[node])
|
|
|
|
struct pci_bus;
|
|
#ifdef CONFIG_PCI
|
|
extern int pcibus_to_node(struct pci_bus *bus);
|
|
#else
|
|
static inline int pcibus_to_node(struct pci_bus *bus)
|
|
{
|
|
return -1;
|
|
}
|
|
#endif
|
|
|
|
#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \
|
|
cpu_all_mask : \
|
|
cpumask_of_node(pcibus_to_node(bus)))
|
|
|
|
extern int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc);
|
|
extern int __node_distance(int, int);
|
|
#define node_distance(a, b) __node_distance(a, b)
|
|
|
|
extern void __init dump_numa_cpu_topology(void);
|
|
|
|
extern int sysfs_add_device_to_node(struct device *dev, int nid);
|
|
extern void sysfs_remove_device_from_node(struct device *dev, int nid);
|
|
|
|
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node)
|
|
{
|
|
numa_cpu_lookup_table[cpu] = node;
|
|
}
|
|
|
|
static inline int early_cpu_to_node(int cpu)
|
|
{
|
|
int nid;
|
|
|
|
nid = numa_cpu_lookup_table[cpu];
|
|
|
|
/*
|
|
* Fall back to node 0 if nid is unset (it should be, except bugs).
|
|
* This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
|
|
*/
|
|
return (nid < 0) ? 0 : nid;
|
|
}
|
|
#else
|
|
|
|
static inline int early_cpu_to_node(int cpu) { return 0; }
|
|
|
|
static inline void dump_numa_cpu_topology(void) {}
|
|
|
|
static inline int sysfs_add_device_to_node(struct device *dev, int nid)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void sysfs_remove_device_from_node(struct device *dev,
|
|
int nid)
|
|
{
|
|
}
|
|
|
|
static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {}
|
|
|
|
static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* CONFIG_NUMA */
|
|
|
|
struct drmem_lmb;
|
|
int of_drconf_to_nid_single(struct drmem_lmb *lmb);
|
|
|
|
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
|
|
extern int find_and_online_cpu_nid(int cpu);
|
|
extern int cpu_to_coregroup_id(int cpu);
|
|
#else
|
|
static inline int find_and_online_cpu_nid(int cpu)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int cpu_to_coregroup_id(int cpu)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
return cpu_to_core_id(cpu);
|
|
#else
|
|
return 0;
|
|
#endif
|
|
}
|
|
|
|
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
|
|
|
|
#include <asm-generic/topology.h>
|
|
|
|
#ifdef CONFIG_SMP
|
|
#include <asm/cputable.h>
|
|
|
|
#ifdef CONFIG_PPC64
|
|
#include <asm/smp.h>
|
|
|
|
#define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu))
|
|
|
|
#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
|
|
#define topology_core_cpumask(cpu) (cpu_cpu_mask(cpu))
|
|
#define topology_core_id(cpu) (cpu_to_core_id(cpu))
|
|
|
|
#endif
|
|
#endif
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_POWERPC_TOPOLOGY_H */
|