kernel-fxtec-pro1x/kernel
Davidlohr Bueso 615d6e8756 mm: per-thread vma caching
This patch is a continuation of efforts trying to optimize find_vma(),
avoiding potentially expensive rbtree walks to locate a vma upon faults.
The original approach (https://lkml.org/lkml/2013/11/1/410), where the
largest vma was also cached, ended up being too specific and random,
thus further comparison with other approaches were needed.  There are
two things to consider when dealing with this, the cache hit rate and
the latency of find_vma().  Improving the hit-rate does not necessarily
translate in finding the vma any faster, as the overhead of any fancy
caching schemes can be too high to consider.

We currently cache the last used vma for the whole address space, which
provides a nice optimization, reducing the total cycles in find_vma() by
up to 250%, for workloads with good locality.  On the other hand, this
simple scheme is pretty much useless for workloads with poor locality.
Analyzing ebizzy runs shows that, no matter how many threads are
running, the mmap_cache hit rate is less than 2%, and in many situations
below 1%.

The proposed approach is to replace this scheme with a small per-thread
cache, maximizing hit rates at a very low maintenance cost.
Invalidations are performed by simply bumping up a 32-bit sequence
number.  The only expensive operation is in the rare case of a seq
number overflow, where all caches that share the same address space are
flushed.  Upon a miss, the proposed replacement policy is based on the
page number that contains the virtual address in question.  Concretely,
the following results are seen on an 80 core, 8 socket x86-64 box:

1) System bootup: Most programs are single threaded, so the per-thread
   scheme does improve ~50% hit rate by just adding a few more slots to
   the cache.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 50.61%   | 19.90            |
| patched        | 73.45%   | 13.58            |
+----------------+----------+------------------+

2) Kernel build: This one is already pretty good with the current
   approach as we're dealing with good locality.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 75.28%   | 11.03            |
| patched        | 88.09%   | 9.31             |
+----------------+----------+------------------+

3) Oracle 11g Data Mining (4k pages): Similar to the kernel build workload.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 70.66%   | 17.14            |
| patched        | 91.15%   | 12.57            |
+----------------+----------+------------------+

4) Ebizzy: There's a fair amount of variation from run to run, but this
   approach always shows nearly perfect hit rates, while baseline is just
   about non-existent.  The amounts of cycles can fluctuate between
   anywhere from ~60 to ~116 for the baseline scheme, but this approach
   reduces it considerably.  For instance, with 80 threads:

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 1.06%    | 91.54            |
| patched        | 99.97%   | 14.18            |
+----------------+----------+------------------+

[akpm@linux-foundation.org: fix nommu build, per Davidlohr]
[akpm@linux-foundation.org: document vmacache_valid() logic]
[akpm@linux-foundation.org: attempt to untangle header files]
[akpm@linux-foundation.org: add vmacache_find() BUG_ON]
[hughd@google.com: add vmacache_valid_mm() (from Oleg)]
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: adjust and enhance comments]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-07 16:35:53 -07:00
..
debug mm: per-thread vma caching 2014-04-07 16:35:53 -07:00
events Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm 2014-04-05 13:20:43 -07:00
gcov
irq genirq: Export symbol no_action() 2014-03-22 11:33:09 +01:00
locking Merge branch 'x86-asmlinkage-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-03-31 14:13:25 -07:00
power Merge branches 'pm-runtime' and 'pm-sleep' 2014-03-20 13:25:54 +01:00
printk printk: fix one circular lockdep warning about console_lock 2014-04-03 16:21:08 -07:00
rcu Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-03-31 11:21:19 -07:00
sched Merge branch 'akpm' (incoming from Andrew) 2014-04-03 16:22:16 -07:00
time Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-04-01 11:00:07 -07:00
trace Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm 2014-04-05 13:20:43 -07:00
.gitignore Ignore generated file kernel/x509_certificate_list 2013-12-10 18:21:34 +00:00
acct.c
async.c
audit.c AUDIT: Allow login in non-init namespaces 2014-03-30 17:02:53 -07:00
audit.h audit: Use struct net not pid_t to remember the network namespce to reply in 2014-02-28 04:04:33 -08:00
audit_tree.c inotify: Fix reporting of cookies for inotify events 2014-02-18 11:17:17 +01:00
audit_watch.c inotify: Fix reporting of cookies for inotify events 2014-02-18 11:17:17 +01:00
auditfilter.c audit: Update kdoc for audit_send_reply and audit_list_rules_send 2014-03-08 15:31:54 -08:00
auditsc.c execve: use 'struct filename *' for executable name passing 2014-02-05 12:54:53 -08:00
backtracetest.c
bounds.c mm: do not allocate page->ptl dynamically, if spinlock_t fits to long 2013-12-20 12:25:45 -08:00
capability.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2014-04-03 09:26:18 -07:00
cgroup.c Merge branch 'for-3.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup 2014-04-03 13:05:42 -07:00
cgroup_freezer.c cgroup: drop const from @buffer of cftype->write_string() 2014-03-19 10:23:54 -04:00
compat.c Merge branch 'x86-x32-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-04-02 12:51:41 -07:00
configs.c
context_tracking.c context_tracking: Wrap static key check into more intuitive function name 2013-12-02 20:43:14 +01:00
cpu.c
cpu_pm.c
cpuset.c Merge branch 'akpm' (incoming from Andrew) 2014-04-03 16:22:16 -07:00
crash_dump.c
cred.c
delayacct.c
dma.c
elfcore.c
exec_domain.c
exit.c cgroup: remove useless argument from cgroup_exit() 2014-03-29 09:15:54 -04:00
extable.c asmlinkage: Make main_extable_sort_needed visible 2014-02-13 18:13:22 -08:00
fork.c mm: per-thread vma caching 2014-04-07 16:35:53 -07:00
freezer.c libata, freezer: avoid block device removal while system is frozen 2013-12-19 13:50:32 -05:00
futex.c Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-03-31 10:59:39 -07:00
futex_compat.c compat: Get rid of (get|put)_compat_time(val|spec) 2014-02-02 14:09:12 -08:00
groups.c kernel/groups.c: remove return value of set_groups 2014-04-03 16:21:05 -07:00
hrtimer.c timer: Remove code redundancy while calling get_nohz_timer_target() 2014-03-20 12:35:46 +01:00
hung_task.c kernel: audit/fix non-modular users of module_init in core code 2014-04-03 16:21:07 -07:00
irq_work.c perf/x86: Warn to early_printk() in case irq_work is too slow 2014-02-21 21:49:07 +01:00
itimer.c
jump_label.c
kallsyms.c
kcmp.c
Kconfig.freezer
Kconfig.hz kernel: remove CONFIG_USE_GENERIC_SMP_HELPERS 2013-11-15 09:32:22 +09:00
Kconfig.locks
Kconfig.preempt
kexec.c kernel: audit/fix non-modular users of module_init in core code 2014-04-03 16:21:07 -07:00
kmod.c execve: use 'struct filename *' for executable name passing 2014-02-05 12:54:53 -08:00
kprobes.c
ksysfs.c rcu: Fix sparse warning for rcu_expedited from kernel/ksysfs.c 2014-02-26 06:35:16 -08:00
kthread.c kthread: ensure locality of task_struct allocations 2014-04-03 16:20:49 -07:00
latencytop.c
Makefile Merge branch 'x86-asmlinkage-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-03-31 14:13:25 -07:00
module-internal.h
module.c Nothing major: the stricter permissions checking for sysfs broke 2014-04-06 09:38:07 -07:00
module_signing.c
notifier.c notifier: Substitute rcu_access_pointer() for rcu_dereference_raw() 2014-02-26 06:35:13 -08:00
nsproxy.c
padata.c padata: Fix wrong usage of rcu_dereference() 2013-12-05 21:28:42 +08:00
panic.c Nothing major: the stricter permissions checking for sysfs broke 2014-04-06 09:38:07 -07:00
params.c params: improve standard definitions 2013-12-04 14:09:46 +10:30
pid.c
pid_namespace.c pid_namespace: pidns_get() should check task_active_pid_ns() != NULL 2014-04-02 16:20:21 -07:00
posix-cpu-timers.c posix-timers: Convert abuses of BUG_ON to WARN_ON 2013-12-09 16:56:29 +01:00
posix-timers.c
profile.c kernel: audit/fix non-modular users of module_init in core code 2014-04-03 16:21:07 -07:00
ptrace.c kernel/compat: convert to COMPAT_SYSCALL_DEFINE 2014-03-06 15:35:10 +01:00
range.c
reboot.c kexec: migrate to reboot cpu 2013-12-18 19:04:50 -08:00
relay.c treewide: Fix typo in Documentation/DocBook 2014-02-19 14:58:17 +01:00
res_counter.c
resource.c kernel/resource.c: make reallocate_resource() static 2014-04-03 16:21:07 -07:00
seccomp.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security 2014-04-03 09:26:18 -07:00
signal.c Merge branch 'master' into for-next 2014-02-20 14:54:28 +01:00
smp.c smp: Rename __smp_call_function_single() to smp_call_function_single_async() 2014-02-24 14:47:15 -08:00
smpboot.c
smpboot.h
softirq.c softirq: Add linux/irq.h to make it compile again 2014-03-19 11:28:14 +01:00
stacktrace.c
stop_machine.c stop_machine: Fix^2 race between stop_two_cpus() and stop_cpus() 2014-03-11 11:33:47 +01:00
sys.c mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE 2014-04-07 16:35:52 -07:00
sys_ni.c fs, kernel: permit disabling the uselib syscall 2014-04-03 16:21:05 -07:00
sysctl.c drop_caches: add some documentation and info message 2014-04-03 16:21:04 -07:00
sysctl_binary.c
system_certificates.S KEYS: correct alignment of system_certificate_list content in assembly file 2013-12-10 18:25:28 +00:00
system_keyring.c KEYS: correct alignment of system_certificate_list content in assembly file 2013-12-10 18:25:28 +00:00
task_work.c
taskstats.c genetlink: only pass array to genl_register_family_with_ops() 2013-11-19 16:39:05 -05:00
test_kprobes.c
time.c
timeconst.bc
timer.c Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-04-01 11:00:07 -07:00
torture.c rcutorture: Gracefully handle NULL cleanup hooks 2014-02-23 09:04:39 -08:00
tracepoint.c Nothing major: the stricter permissions checking for sysfs broke 2014-04-06 09:38:07 -07:00
tsacct.c
uid16.c
up.c smp: Rename __smp_call_function_single() to smp_call_function_single_async() 2014-02-24 14:47:15 -08:00
user-return-notifier.c
user.c kernel: audit/fix non-modular users of module_init in core code 2014-04-03 16:21:07 -07:00
user_namespace.c kernel: audit/fix non-modular users of module_init in core code 2014-04-03 16:21:07 -07:00
utsname.c
utsname_sysctl.c
watchdog.c kernel/watchdog.c: touch_nmi_watchdog should only touch local cpu not every one 2014-04-03 16:20:58 -07:00
workqueue.c Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-04-01 11:00:07 -07:00
workqueue_internal.h