linux/mm
Wu Fengguang e98be2d599 writeback: bdi write bandwidth estimation
The estimation value will start from 100MB/s and adapt to the real
bandwidth in seconds.

It tries to update the bandwidth only when disk is fully utilized.
Any inactive period of more than one second will be skipped.

The estimated bandwidth will be reflecting how fast the device can
writeout when _fully utilized_, and won't drop to 0 when it goes idle.
The value will remain constant at disk idle time. At busy write time, if
not considering fluctuations, it will also remain high unless be knocked
down by possible concurrent reads that compete for the disk time and
bandwidth with async writes.

The estimation is not done purely in the flusher because there is no
guarantee for write_cache_pages() to return timely to update bandwidth.

The bdi->avg_write_bandwidth smoothing is very effective for filtering
out sudden spikes, however may be a little biased in long term.

The overheads are low because the bdi bandwidth update only occurs at
200ms intervals.

The 200ms update interval is suitable, because it's not possible to get
the real bandwidth for the instance at all, due to large fluctuations.

The NFS commits can be as large as seconds worth of data. One XFS
completion may be as large as half second worth of data if we are going
to increase the write chunk to half second worth of data. In ext4,
fluctuations with time period of around 5 seconds is observed. And there
is another pattern of irregular periods of up to 20 seconds on SSD tests.

That's why we are not only doing the estimation at 200ms intervals, but
also averaging them over a period of 3 seconds and then go further to do
another level of smoothing in avg_write_bandwidth.

CC: Li Shaohua <shaohua.li@intel.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
2011-07-09 22:09:01 -07:00
..
backing-dev.c writeback: bdi write bandwidth estimation 2011-07-09 22:09:01 -07:00
bootmem.c
bounce.c
cleancache.c mm: cleancache core ops functions and config 2011-05-26 10:01:36 -06:00
compaction.c
debug-pagealloc.c
dmapool.c
fadvise.c
failslab.c
filemap_xip.c mm: Convert i_mmap_lock to a mutex 2011-05-25 08:39:18 -07:00
filemap.c writeback: split inode_wb_list_lock into bdi_writeback.list_lock 2011-06-08 08:25:21 +08:00
fremap.c mm: don't access vm_flags as 'int' 2011-05-26 09:20:31 -07:00
highmem.c
huge_memory.c mm: thp: optimize memcg charge in khugepaged 2011-05-25 08:39:21 -07:00
hugetlb.c mm: fix ENOSPC returned by handle_mm_fault() 2011-06-06 18:00:27 +09:00
hwpoison-inject.c
init-mm.c mm: convert mm->cpu_vm_cpumask into cpumask_var_t 2011-05-25 08:39:21 -07:00
internal.h mm: nommu: sort mm->mmap list properly 2011-05-25 08:39:05 -07:00
Kconfig mm: cleancache core ops functions and config 2011-05-26 10:01:36 -06:00
Kconfig.debug
kmemcheck.c
kmemleak-test.c
kmemleak.c
ksm.c oom: replace PF_OOM_ORIGIN with toggling oom_score_adj 2011-05-25 08:39:10 -07:00
maccess.c maccess,probe_kernel: Make write/read src const void * 2011-05-25 19:56:23 -04:00
madvise.c
Makefile mm: cleancache core ops functions and config 2011-05-26 10:01:36 -06:00
memblock.c
memcontrol.c memcg: add the pagefault count into memcg stats 2011-05-26 17:12:36 -07:00
memory_hotplug.c mm: remove dependency on CONFIG_FLATMEM from online_page() 2011-05-25 08:39:28 -07:00
memory-failure.c vmscan: change shrinker API by passing shrink_control struct 2011-05-25 08:39:26 -07:00
memory.c memcg: add the pagefault count into memcg stats 2011-05-26 17:12:36 -07:00
mempolicy.c mm: proc: move show_numa_map() to fs/proc/task_mmu.c 2011-05-25 08:39:34 -07:00
mempool.c
migrate.c mm: use refcounts for page_lock_anon_vma() 2011-05-25 08:39:19 -07:00
mincore.c
mlock.c mm: don't access vm_flags as 'int' 2011-05-26 09:20:31 -07:00
mm_init.c
mmap.c mm: don't access vm_flags as 'int' 2011-05-26 09:20:31 -07:00
mmu_context.c
mmu_notifier.c
mmzone.c
mprotect.c
mremap.c mm: Convert i_mmap_lock to a mutex 2011-05-25 08:39:18 -07:00
msync.c
nobootmem.c memblock/nobootmem: remove unneeded code from alloc_bootmem_node_high() 2011-05-25 08:39:31 -07:00
nommu.c nommu: add page alignment to mmap 2011-05-25 08:39:38 -07:00
oom_kill.c oom: replace PF_OOM_ORIGIN with toggling oom_score_adj 2011-05-25 08:39:10 -07:00
page_alloc.c Revert "mm: fail GFP_DMA allocations when ZONE_DMA is not configured" 2011-06-02 06:11:24 +09:00
page_cgroup.c memcg: move page-freeing code out of lock 2011-05-26 17:12:35 -07:00
page_io.c
page_isolation.c
page-writeback.c writeback: bdi write bandwidth estimation 2011-07-09 22:09:01 -07:00
pagewalk.c
percpu-km.c
percpu-vm.c
percpu.c Merge branch 'for-2.6.40' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu 2011-05-24 11:53:42 -07:00
pgtable-generic.c
prio_tree.c sanitize <linux/prefetch.h> usage 2011-05-20 12:50:29 -07:00
quicklist.c
readahead.c readahead: readahead page allocations are OK to fail 2011-05-25 08:39:25 -07:00
rmap.c writeback: split inode_wb_list_lock into bdi_writeback.list_lock 2011-06-08 08:25:21 +08:00
shmem.c tmpfs: fix race between truncate and writepage 2011-05-28 16:09:26 -07:00
slab.c sanitize <linux/prefetch.h> usage 2011-05-20 12:50:29 -07:00
slob.c
slub.c slub: remove no-longer used 'unlock_out' label 2011-05-25 18:06:54 -07:00
sparse-vmemmap.c
sparse.c
swap_state.c
swap.c mm: batch activate_page() to reduce lock contention 2011-05-25 08:39:37 -07:00
swapfile.c oom: replace PF_OOM_ORIGIN with toggling oom_score_adj 2011-05-25 08:39:10 -07:00
thrash.c
truncate.c mm/fs: add hooks to support cleancache 2011-05-26 10:01:43 -06:00
util.c mm: nommu: sort mm->mmap list properly 2011-05-25 08:39:05 -07:00
vmalloc.c Merge branch 'upstream/tidy-xen-mmu-2.6.39' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen 2011-05-26 19:01:15 -07:00
vmscan.c memcg: rename mem_cgroup_zone_nr_pages() to mem_cgroup_zone_nr_lru_pages() 2011-05-26 17:12:35 -07:00
vmstat.c mm, mem-hotplug: update pcp->stat_threshold when memory hotplug occur 2011-05-25 08:39:09 -07:00