remarkable-linux/kernel
Mel Gorman 074c238177 mm: numa: slow PTE scan rate if migration failures occur
Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226

  Across the board the 4.0-rc1 numbers are much slower, and the degradation
  is far worse when using the large memory footprint configs. Perf points
  straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config:

   -   56.07%    56.07%  [kernel]            [k] default_send_IPI_mask_sequence_phys
      - default_send_IPI_mask_sequence_phys
         - 99.99% physflat_send_IPI_mask
            - 99.37% native_send_call_func_ipi
                 smp_call_function_many
               - native_flush_tlb_others
                  - 99.85% flush_tlb_page
                       ptep_clear_flush
                       try_to_unmap_one
                       rmap_walk
                       try_to_unmap
                       migrate_pages
                       migrate_misplaced_page
                     - handle_mm_fault
                        - 99.73% __do_page_fault
                             trace_do_page_fault
                             do_async_page_fault
                           + async_page_fault
              0.63% native_send_call_func_single_ipi
                 generic_exec_single
                 smp_call_function_single

This is showing excessive migration activity even though excessive
migrations are meant to get throttled.  Normally, the scan rate is tuned
on a per-task basis depending on the locality of faults.  However, if
migrations fail for any reason then the PTE scanner may scan faster if
the faults continue to be remote.  This means there is higher system CPU
overhead and fault trapping at exactly the time we know that migrations
cannot happen.  This patch tracks when migration failures occur and
slows the PTE scanner.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-25 16:20:31 -07:00
..
bpf Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2015-01-27 13:55:36 -08:00
configs x86: Add "make tinyconfig" to configure the tiniest possible kernel 2014-08-08 16:30:24 -07:00
debug debug: prevent entering debug mode on panic/exception. 2015-02-19 12:39:03 -06:00
events perf: Fix context leak in put_event() 2015-03-13 10:02:18 +01:00
gcov kbuild,gcov: simplify kernel/gcov/Makefile more 2015-01-09 17:25:44 +01:00
irq genirq / PM: Add flag for shared NO_SUSPEND interrupt lines 2015-03-04 21:42:19 +01:00
livepatch livepatch: Fix subtle race with coming and going modules 2015-03-17 10:31:54 +01:00
locking locking/rtmutex: Set state back to running on error 2015-03-01 09:45:06 +01:00
power PM / sleep: Re-implement suspend-to-idle handling 2015-02-13 23:49:36 +01:00
printk console: Fix console name size mismatch 2015-03-07 03:39:55 +01:00
rcu Merge branches 'core-urgent-for-linus' and 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-02-21 10:36:06 -08:00
sched mm: numa: slow PTE scan rate if migration failures occur 2015-03-25 16:20:31 -07:00
time Merge branch 'timers-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-02-21 11:05:22 -08:00
trace ftrace: Fix ftrace enable ordering of sysctl ftrace_enabled 2015-03-09 10:55:34 -04:00
.gitignore
acct.c new fs_pin killing logics 2015-01-25 23:17:28 -05:00
async.c kernel/async.c: switch to pr_foo() 2014-10-09 22:26:04 -04:00
audit.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2014-12-30 10:45:47 -08:00
audit.h audit: replace getname()/putname() hacks with reference counters 2015-01-23 00:23:58 -05:00
audit_tree.c fsnotify: unify inode and mount marks handling 2014-12-13 12:42:53 -08:00
audit_watch.c audit: invalid op= values for rules 2014-09-23 16:37:53 -04:00
auditfilter.c Merge branch 'upstream' of git://git.infradead.org/users/pcmoore/audit 2015-02-11 20:07:47 -08:00
auditsc.c Merge branch 'getname2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2015-02-17 15:27:47 -08:00
backtracetest.c
bounds.c page-cgroup: get rid of NR_PCG_FLAGS 2014-08-08 15:57:18 -07:00
capability.c CAPABILITIES: remove undefined caps from all processes 2014-07-24 21:53:47 +10:00
cgroup.c kernfs: remove KERNFS_STATIC_NAME 2015-02-13 21:21:36 -08:00
cgroup_freezer.c cgroup: rename cgroup_subsys->base_cftypes to ->legacy_cftypes 2014-07-15 11:05:09 -04:00
compat.c all arches, signal: move restart_block to struct task_struct 2015-02-12 18:54:12 -08:00
configs.c
context_tracking.c sched: stop the unbound recursion in preempt_schedule_context() 2014-10-28 10:46:05 +01:00
cpu.c hotplugcpu: Avoid deadlocks by waking active_writer 2015-01-06 11:01:14 -08:00
cpu_pm.c
cpuset.c cpuset: Fix cpuset sched_relax_domain_level 2015-03-02 11:55:04 -05:00
crash_dump.c crash_dump: Make is_kdump_kernel() accessible from modules 2014-08-25 15:42:19 -07:00
cred.c
delayacct.c delayacct: Remove braindamaged type conversions 2014-07-23 10:18:06 -07:00
dma.c
elfcore.c
exec_domain.c
exit.c oom, PM: make OOM detection in the freezer path raceless 2015-02-11 17:06:03 -08:00
extable.c ftrace/x86/extable: Add is_ftrace_trampoline() function 2014-11-19 15:25:26 -05:00
fork.c mm: do not use mm->nr_pmds on !MMU configurations 2015-02-12 18:54:10 -08:00
freezer.c freezer: remove obsolete comments in __thaw_task() 2014-10-21 23:44:20 +02:00
futex.c all arches, signal: move restart_block to struct task_struct 2015-02-12 18:54:12 -08:00
futex_compat.c
groups.c userns: Don't allow setgroups until a gid mapping has been setablished 2014-12-09 16:58:40 -06:00
hung_task.c
irq_work.c percpu: Convert remaining __get_cpu_var uses in 3.18-rcX 2014-10-29 11:18:18 -04:00
jump_label.c
kallsyms.c kernel/kallsyms.c: use __seq_open_private() 2014-10-14 02:18:16 +02:00
kcmp.c kcmp: fix standard comparison bug 2014-09-10 15:42:12 -07:00
Kconfig.freezer
Kconfig.hz
Kconfig.locks locking/mcs: Better differentiate between MCS variants 2015-01-14 15:07:32 +01:00
Kconfig.preempt
kexec.c kexec: simplify conditional 2015-02-17 14:34:51 -08:00
kmod.c usermodehelper: kill the kmod_thread_locker logic 2014-12-10 17:41:17 -08:00
kprobes.c kprobes: makes kprobes/enabled works correctly for optimized kprobes. 2015-02-13 21:21:42 -08:00
ksysfs.c
kthread.c kernel/kthread.c: partial revert of 81c98869fa ("kthread: ensure locality of task_struct allocations") 2014-10-09 22:25:51 -04:00
latencytop.c
Makefile Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2015-02-11 20:25:11 -08:00
module-internal.h
module.c kasan, module, vmalloc: rework shadow allocation for modules 2015-03-12 18:46:08 -07:00
module_signing.c
notifier.c rcu: Make SRCU optional by using CONFIG_SRCU 2015-01-06 11:04:29 -08:00
nsproxy.c bury struct proc_ns in fs/proc 2014-12-04 14:34:54 -05:00
padata.c padata: use %*pb[l] to print bitmaps including cpumasks and nodemasks 2015-02-13 21:21:38 -08:00
panic.c livepatch: kernel: add TAINT_LIVEPATCH 2014-12-22 15:40:48 +01:00
params.c param: fix uninitialized read with CONFIG_DEBUG_LOCK_ALLOC 2015-01-20 11:38:31 +10:30
pid.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2014-12-16 15:53:03 -08:00
pid_namespace.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2014-12-16 15:53:03 -08:00
profile.c profile: use %*pb[l] to print bitmaps including cpumasks and nodemasks 2015-02-13 21:21:38 -08:00
ptrace.c ptrace: remove linux/compat.h inclusion under CONFIG_COMPAT 2015-02-17 14:34:51 -08:00
range.c kernel: avoid overflow in cmp_range 2015-01-17 10:02:23 +13:00
reboot.c kernel: add support for kernel restart handler call chain 2014-09-26 00:00:06 -07:00
relay.c
resource.c resources: Move struct resource_list_entry from ACPI into resource core 2015-02-05 15:09:25 +01:00
seccomp.c seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO 2015-02-17 14:34:55 -08:00
signal.c signal: use current->state helpers 2015-02-17 14:34:51 -08:00
smp.c Merge branch 'for-3.18-consistent-ops' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu 2014-10-15 07:48:18 +02:00
smpboot.c smpboot: Add missing get_online_cpus() in smpboot_register_percpu_thread() 2015-01-23 11:33:51 +01:00
smpboot.h
softirq.c Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-02-09 15:24:03 -08:00
stacktrace.c stacktrace: introduce snprint_stack_trace for buffer output 2014-12-13 12:42:48 -08:00
stop_machine.c
sys.c kernel/sys.c: fix UNAME26 for 4.0 2015-02-28 09:57:51 -08:00
sys_ni.c syscalls: implement execveat() system call 2014-12-13 12:42:51 -08:00
sysctl.c mm, hugetlb: remove unnecessary lower bound on sysctl handlers"? 2015-02-10 14:30:34 -08:00
sysctl_binary.c kernel: add panic_on_warn 2014-12-10 17:41:10 -08:00
system_certificates.S
system_keyring.c KEYS: validate certificate trust only with builtin keys 2014-07-17 09:35:17 -04:00
task_work.c
taskstats.c netlink: make nlmsg_end() and genlmsg_end() void 2015-01-18 01:03:45 -05:00
test_kprobes.c kernel/test_kprobes.c: use current logging functions 2014-08-08 15:57:18 -07:00
torture.c torture: Address race in module cleanup 2014-09-16 13:41:06 -07:00
tracepoint.c
tsacct.c sched: Make task->start_time nanoseconds based 2014-07-23 10:18:05 -07:00
uid16.c groups: Consolidate the setgroups permission checks 2014-12-05 17:19:27 -06:00
up.c
user-return-notifier.c scheduler: Replace __get_cpu_var with this_cpu_ptr 2014-08-26 13:45:45 -04:00
user.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2014-12-17 12:31:40 -08:00
user_namespace.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace 2014-12-17 12:31:40 -08:00
utsname.c copy address of proc_ns_ops into ns_common 2014-12-04 14:34:47 -05:00
utsname_sysctl.c
watchdog.c kernel/sched/clock.c: add another clock for use with the soft lockup watchdog 2015-02-12 18:54:13 -08:00
workqueue.c workqueue: fix hang involving racing cancel[_delayed]_work_sync()'s for PREEMPT_NONE 2015-03-05 08:04:13 -05:00
workqueue_internal.h