twx-linux/kernel
Mel Gorman e12ba74d8f Group short-lived and reclaimable kernel allocations
This patch marks a number of allocations that are either short-lived such as
network buffers or are reclaimable such as inode allocations.  When something
like updatedb is called, long-lived and unmovable kernel allocations tend to
be spread throughout the address space which increases fragmentation.

This patch groups these allocations together as much as possible by adding a
new MIGRATE_TYPE.  The MIGRATE_RECLAIMABLE type is for allocations that can be
reclaimed on demand, but not moved.  i.e.  they can be migrated by deleting
them and re-reading the information from elsewhere.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 09:43:00 -07:00
..
irq
power
time clockevents: introduce force broadcast notifier 2007-10-14 22:57:45 +02:00
.gitignore
acct.c
audit.c [NET]: make netlink user -> kernel interface synchronious 2007-10-10 21:15:29 -07:00
audit.h
auditfilter.c
auditsc.c
capability.c
compat.c
configs.c
cpu.c
cpuset.c Group short-lived and reclaimable kernel allocations 2007-10-16 09:43:00 -07:00
delayacct.c sched: clean up schedstats, cnt -> count 2007-10-15 17:00:12 +02:00
die_notifier.c
dma.c
exec_domain.c
exit.c sched: guest CPU accounting: add guest-CPU /proc/<pid>/stat fields 2007-10-15 17:00:19 +02:00
extable.c
fork.c sched: guest CPU accounting: add guest-CPU /proc/<pid>/stat fields 2007-10-15 17:00:19 +02:00
futex_compat.c
futex.c
hrtimer.c
itimer.c
kallsyms.c
Kconfig.hz
Kconfig.preempt
kexec.c
kfifo.c
kmod.c
kprobes.c x86: optimize page faults like all other achitectures and kill notifier cruft 2007-10-16 09:42:50 -07:00
ksysfs.c sched: group scheduling, sysfs tunables 2007-10-15 17:00:14 +02:00
kthread.c
latency.c
lockdep_internals.h
lockdep_proc.c lockdep: Avoid /proc/lockdep & lock_stat infinite output 2007-10-11 22:11:11 +02:00
lockdep.c lockdep: syscall exit check 2007-10-11 22:11:12 +02:00
Makefile
module.c
mutex-debug.c
mutex-debug.h
mutex.c lockdep: fixup mutex annotations 2007-10-11 22:11:12 +02:00
mutex.h
nsproxy.c
panic.c
params.c
pid.c
posix-cpu-timers.c
posix-timers.c more low-hanging fruits - kernel, fs, lib signedness 2007-10-14 12:41:52 -07:00
printk.c slow down printk during boot 2007-10-16 09:42:49 -07:00
profile.c Memoryless nodes: Allow profiling data to fall back to other nodes 2007-10-16 09:42:58 -07:00
ptrace.c Consolidate PTRACE_DETACH 2007-10-16 09:42:49 -07:00
rcupdate.c lockdep: annotate rcu_read_{,un}lock{,_bh} 2007-10-11 22:11:12 +02:00
rcutorture.c
relay.c
resource.c
rtmutex_common.h
rtmutex-debug.c
rtmutex-debug.h
rtmutex-tester.c
rtmutex.c
rtmutex.h
rwsem.c
sched_debug.c Make scheduler debug file operations const 2007-10-15 17:00:19 +02:00
sched_fair.c sched: reintroduce cache-hot affinity 2007-10-15 17:00:18 +02:00
sched_idletask.c sched: mark scheduling classes as const 2007-10-15 17:00:12 +02:00
sched_rt.c sched: tidy up SCHED_RR 2007-10-15 17:00:13 +02:00
sched_stats.h sched: clean up schedstats, cnt -> count 2007-10-15 17:00:12 +02:00
sched.c Convert cpu_sibling_map to be a per cpu variable 2007-10-16 09:42:50 -07:00
seccomp.c
signal.c
softirq.c
softlockup.c
spinlock.c
srcu.c
stacktrace.c
stop_machine.c
sys_ni.c
sys.c
sysctl.c sched: reintroduce cache-hot affinity 2007-10-15 17:00:18 +02:00
taskstats.c
time.c
timer.c
tsacct.c
uid16.c
user_namespace.c
user.c sched: generate uevents for user creation/destruction 2007-10-15 17:00:18 +02:00
utsname_sysctl.c
utsname.c
wait.c
workqueue.c