Grouping high-order atomic allocations together was intended to allow
bursty users of atomic allocations to work such as e1000 in situations
where their preallocated buffers were depleted. This did not work in at
least one case with a wireless network adapter needing order-1 allocations
frequently. To resolve that, the free pages used for min_free_kbytes were
moved to separate contiguous blocks with the patch
bias-the-location-of-pages-freed-for-min_free_kbytes-in-the-same-max_order_nr_pages-blocks.
It is felt that keeping the free pages in the same contiguous blocks should
be sufficient for bursty short-lived high-order atomic allocations to
succeed, maybe even with the e1000. Even if there is a failure, increasing
the value of min_free_kbytes will free pages as contiguous bloks in
contrast to the standard buddy allocator which makes no attempt to keep the
minimum number of free pages contiguous.
This patch backs out grouping high order atomic allocations together to
determine if it is really needed or not. If a new report comes in about
high-order atomic allocations failing, the feature can be reintroduced to
determine if it fixes the problem or not. As a side-effect, this patch
reduces by 1 the number of bits required to track the mobility type of
pages within a MAX_ORDER_NR_PAGES block.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Grouping pages by mobility can be disabled at compile-time. This was
considered undesirable by a number of people. However, in the current stack of
patches, it is not a simple case of just dropping the configurable patch as it
would cause merge conflicts. This patch backs out the configuration option.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The standard buddy allocator always favours the smallest block of pages.
The effect of this is that the pages free to satisfy min_free_kbytes tends
to be preserved since boot time at the same location of memory ffor a very
long time and as a contiguous block. When an administrator sets the
reserve at 16384 at boot time, it tends to be the same MAX_ORDER blocks
that remain free. This allows the occasional high atomic allocation to
succeed up until the point the blocks are split. In practice, it is
difficult to split these blocks but when they do split, the benefit of
having min_free_kbytes for contiguous blocks disappears. Additionally,
increasing min_free_kbytes once the system has been running for some time
has no guarantee of creating contiguous blocks.
On the other hand, CONFIG_PAGE_GROUP_BY_MOBILITY favours splitting large
blocks when there are no free pages of the appropriate type available. A
side-effect of this is that all blocks in memory tends to be used up and
the contiguous free blocks from boot time are not preserved like in the
vanilla allocator. This can cause a problem if a new caller is unwilling
to reclaim or does not reclaim for long enough.
A failure scenario was found for a wireless network device allocating
order-1 atomic allocations but the allocations were not intense or frequent
enough for a whole block of pages to be preserved for MIGRATE_HIGHALLOC.
This was reproduced on a desktop by booting with mem=256mb, forcing the
driver to allocate at order-1, running a bittorrent client (downloading a
debian ISO) and building a kernel with -j2.
This patch addresses the problem on the desktop machine booted with
mem=256mb. It works by setting aside a reserve of MAX_ORDER_NR_PAGES
blocks, the number of which depends on the value of min_free_kbytes. These
blocks are only fallen back to when there is no other free pages. Then the
smallest possible page is used just like the normal buddy allocator instead
of the largest possible page to preserve contiguous pages The pages in free
lists in the reserve blocks are never taken for another migrate type. The
results is that even if min_free_kbytes is set to a low value, contiguous
blocks will be preserved in the MIGRATE_RESERVE blocks.
This works better than the vanilla allocator because if min_free_kbytes is
increased, a new reserve block will be chosen based on the location of
reclaimable pages and the block will free up as contiguous pages. In the
vanilla allocator, no effort is made to target a block of pages to free as
contiguous pages and min_free_kbytes pages are scattered randomly.
This effect has been observed on the test machine. min_free_kbytes was set
initially low but it was kept as a contiguous free block within
MIGRATE_RESERVE. min_free_kbytes was then set to a higher value and over a
period of time, the free blocks were within the reserve and coalescing.
How long it takes to free up depends on how quickly LRU is rotating.
Amusingly, this means that more activity will free the blocks faster.
This mechanism potentially replaces MIGRATE_HIGHALLOC as it may be more
effective than grouping contiguous free pages together. It all depends on
whether the number of active atomic high allocations exceeds
min_free_kbytes or not. If the number of active allocations exceeds
min_free_kbytes, it's worth it but maybe in that situation, min_free_kbytes
should be set higher. Once there are no more reports of allocation
failures, a patch will be submitted that backs out MIGRATE_HIGHALLOC and
see if the reports stay missing.
Credit to Mariusz Kozlowski for discovering the problem, describing the
failure scenario and testing patches and scenarios.
[akpm@linux-foundation.org: cleanups]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There are problems in the use of SPARSEMEM and pageblock flags that causes
problems on ia64.
The first part of the problem is that units are incorrect in
SECTION_BLOCKFLAGS_BITS computation. This results in a map_section's
section_mem_map being treated as part of a bitmap which isn't good. This
was evident with an invalid virtual address when mem_init attempted to free
bootmem pages while relinquishing control from the bootmem allocator.
The second part of the problem occurs because the pageblock flags bitmap is
be located with the mem_section. The SECTIONS_PER_ROOT computation using
sizeof (mem_section) may not be a power of 2 depending on the size of the
bitmap. This renders masks and other such things not power of 2 base.
This issue was seen with SPARSEMEM_EXTREME on ia64. This patch moves the
bitmap outside of mem_section and uses a pointer instead in the
mem_section. The bitmaps are allocated when the section is being
initialised.
Note that sparse_early_usemap_alloc() does not use alloc_remap() like
sparse_early_mem_map_alloc(). The allocation required for the bitmap on
x86, the only architecture that uses alloc_remap is typically smaller than
a cache line. alloc_remap() pads out allocations to the cache size which
would be a needless waste.
Credit to Bob Picco for identifying the original problem and effecting a
fix for the SECTION_BLOCKFLAGS_BITS calculation. Credit to Andy Whitcroft
for devising the best way of allocating the bitmaps only when required for
the section.
[wli@holomorphy.com: warning fix]
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: William Irwin <bill.irwin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In rare cases, the kernel needs to allocate a high-order block of pages
without sleeping. For example, this is the case with e1000 cards configured
to use jumbo frames. Migrating or reclaiming pages in this situation is not
an option.
This patch groups these allocations together as much as possible by adding a
new MIGRATE_TYPE. The MIGRATE_HIGHATOMIC type are exactly what they sound
like. Care is taken that pages of other migrate types do not use the same
blocks as high-order atomic allocations.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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>
The grouping mechanism has some memory overhead and a more complex allocation
path. This patch allows the strategy to be disabled for small memory systems
or if it is known the workload is suffering because of the strategy. It also
acts to show where the page groupings strategy interacts with the standard
buddy allocator.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Joel Schopp <jschopp@austin.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds the core of the fragmentation reduction strategy. It works by
grouping pages together based on their ability to migrate or be reclaimed.
Basically, it works by breaking the list in zone->free_area list into
MIGRATE_TYPES number of lists.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Here is the latest revision of the anti-fragmentation patches. Of particular
note in this version is special treatment of high-order atomic allocations.
Care is taken to group them together and avoid grouping pages of other types
near them. Artifical tests imply that it works. I'm trying to get the
hardware together that would allow setting up of a "real" test. If anyone
already has a setup and test that can trigger the atomic-allocation problem,
I'd appreciate a test of these patches and a report. The second major change
is that these patches will apply cleanly with patches that implement
anti-fragmentation through zones.
kernbench shows effectively no performance difference varying between -0.2%
and +2% on a variety of test machines. Success rates for huge page allocation
are dramatically increased. For example, on a ppc64 machine, the vanilla
kernel was only able to allocate 1% of memory as a hugepage and this was due
to a single hugepage reserved as min_free_kbytes. With these patches applied,
17% was allocatable as superpages. With reclaim-related fixes from Andy
Whitcroft, it was 40% and further reclaim-related improvements should increase
this further.
Changelog Since V28
o Group high-order atomic allocations together
o It is no longer required to set min_free_kbytes to 10% of memory. A value
of 16384 in most cases will be sufficient
o Now applied with zone-based anti-fragmentation
o Fix incorrect VM_BUG_ON within buffered_rmqueue()
o Reorder the stack so later patches do not back out work from earlier patches
o Fix bug were journal pages were being treated as movable
o Bias placement of non-movable pages to lower PFNs
o More agressive clustering of reclaimable pages in reactions to workloads
like updatedb that flood the size of inode caches
Changelog Since V27
o Renamed anti-fragmentation to Page Clustering. Anti-fragmentation was giving
the mistaken impression that it was the 100% solution for high order
allocations. Instead, it greatly increases the chances high-order
allocations will succeed and lays the foundation for defragmentation and
memory hot-remove to work properly
o Redefine page groupings based on ability to migrate or reclaim instead of
basing on reclaimability alone
o Get rid of spurious inits
o Per-cpu lists are no longer split up per-type. Instead the per-cpu list is
searched for a page of the appropriate type
o Added more explanation commentary
o Fix up bug in pageblock code where bitmap was used before being initalised
Changelog Since V26
o Fix double init of lists in setup_pageset
Changelog Since V25
o Fix loop order of for_each_rclmtype_order so that order of loop matches args
o gfpflags_to_rclmtype uses gfp_t instead of unsigned long
o Rename get_pageblock_type() to get_page_rclmtype()
o Fix alignment problem in move_freepages()
o Add mechanism for assigning flags to blocks of pages instead of page->flags
o On fallback, do not examine the preferred list of free pages a second time
The purpose of these patches is to reduce external fragmentation by grouping
pages of related types together. When pages are migrated (or reclaimed under
memory pressure), large contiguous pages will be freed.
This patch works by categorising allocations by their ability to migrate;
Movable - The pages may be moved with the page migration mechanism. These are
generally userspace pages.
Reclaimable - These are allocations for some kernel caches that are
reclaimable or allocations that are known to be very short-lived.
Unmovable - These are pages that are allocated by the kernel that
are not trivially reclaimed. For example, the memory allocated for a
loaded module would be in this category. By default, allocations are
considered to be of this type
HighAtomic - These are high-order allocations belonging to callers that
cannot sleep or perform any IO. In practice, this is restricted to
jumbo frame allocation for network receive. It is assumed that the
allocations are short-lived
Instead of having one MAX_ORDER-sized array of free lists in struct free_area,
there is one for each type of reclaimability. Once a 2^MAX_ORDER block of
pages is split for a type of allocation, it is added to the free-lists for
that type, in effect reserving it. Hence, over time, pages of the different
types can be clustered together.
When the preferred freelists are expired, the largest possible block is taken
from an alternative list. Buddies that are split from that large block are
placed on the preferred allocation-type freelists to mitigate fragmentation.
This implementation gives best-effort for low fragmentation in all zones.
Ideally, min_free_kbytes needs to be set to a value equal to 4 * (1 <<
(MAX_ORDER-1)) pages in most cases. This would be 16384 on x86 and x86_64 for
example.
Our tests show that about 60-70% of physical memory can be allocated on a
desktop after a few days uptime. In benchmarks and stress tests, we are
finding that 80% of memory is available as contiguous blocks at the end of the
test. To compare, a standard kernel was getting < 1% of memory as large pages
on a desktop and about 8-12% of memory as large pages at the end of stress
tests.
Following this email are 12 patches that implement thie page grouping feature.
The first patch introduces a mechanism for storing flags related to a whole
block of pages. Then allocations are split between movable and all other
allocations. Following that are patches to deal with per-cpu pages and make
the mechanism configurable. The next patch moves free pages between lists
when partially allocated blocks are used for pages of another migrate type.
The second last patch groups reclaimable kernel allocations such as inode
caches together. The final patch related to groupings keeps high-order atomic
allocations.
The last two patches are more concerned with control of fragmentation. The
second last patch biases placement of non-movable allocations towards the
start of memory. This is with a view of supporting memory hot-remove of DIMMs
with higher PFNs in the future. The biasing could be enforced a lot heavier
but it would cost. The last patch agressively clusters reclaimable pages like
inode caches together.
The fragmentation reduction strategy needs to track if pages within a block
can be moved or reclaimed so that pages are freed to the appropriate list.
This patch adds a bitmap for flags affecting a whole a MAX_ORDER block of
pages.
In non-SPARSEMEM configurations, the bitmap is stored in the struct zone and
allocated during initialisation. SPARSEMEM statically allocates the bitmap in
a struct mem_section so that bitmaps do not have to be resized during memory
hotadd. This wastes a small amount of memory per unused section (usually
sizeof(unsigned long)) but the complexity of dynamically allocating the memory
is quite high.
Additional credit to Andy Whitcroft who reviewed up an earlier implementation
of the mechanism an suggested how to make it a *lot* cleaner.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
GFP_THISNODE checks that the zone selected is within the pgdat (node) of the
first zone of a nodelist. That only works if the node has memory. A
memoryless node will have its first node on another pgdat (node).
GFP_THISNODE currently will return simply memory on the first pgdat. Thus it
is returning memory on other nodes. GFP_THISNODE should fail if there is no
local memory on a node.
Add a new set of zonelists for each node that only contain the nodes that
belong to the zones itself so that no fallback is possible.
Then modify gfp_type to pickup the right zone based on the presence of
__GFP_THISNODE.
Drop the existing GFP_THISNODE checks from the page_allocators hot path.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Nishanth Aravamudan <nacc@us.ibm.com>
Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Bob Picco <bob.picco@hp.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@skynet.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We have flags to indicate whether a section actually has a valid mem_map
associated with it. This is never set and we rely solely on the present bit
to indicate a section is valid. By definition a section is not valid if it
has no mem_map and there is a window during init where the present bit is set
but there is no mem_map, during which pfn_valid() will return true
incorrectly.
Use the existing SECTION_HAS_MEM_MAP flag to indicate the presence of a valid
mem_map. Switch valid_section{,_nr} and pfn_valid() to this bit. Add a new
present_section{,_nr} and pfn_present() interfaces for those users who care to
know that a section is going to be valid.
[akpm@linux-foundation.org: coding-syle fixes]
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The NUMA layer only supports NUMA policies for the highest zone. When
ZONE_MOVABLE is configured with kernelcore=, the the highest zone becomes
ZONE_MOVABLE. The result is that policies are only applied to allocations
like anonymous pages and page cache allocated from ZONE_MOVABLE when the
zone is used.
This patch applies policies to the two highest zones when the highest zone
is ZONE_MOVABLE. As ZONE_MOVABLE consists of pages from the highest "real"
zone, it's always functionally equivalent.
The patch has been tested on a variety of machines both NUMA and non-NUMA
covering x86, x86_64 and ppc64. No abnormal results were seen in
kernbench, tbench, dbench or hackbench. It passes regression tests from
the numactl package with and without kernelcore= once numactl tests are
patched to wait for vmstat counters to update.
akpm: this is the nasty hack to fix NUMA mempolicies in the presence of
ZONE_MOVABLE and kernelcore= in 2.6.23. Christoph says "For .24 either merge
the mobility or get the other solution that Mel is working on. That solution
would only use a single zonelist per node and filter on the fly. That may
help performance and also help to make memory policies work better."
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Tested-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-by: Christoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The arm26 port has been in a state where it was far from even compiling
for quite some time.
Ian Molton agreed with the removal.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Cc: Ian Molton <spyro@f2s.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When we are out of memory of a suitable size we enter reclaim. The current
reclaim algorithm targets pages in LRU order, which is great for fairness at
order-0 but highly unsuitable if you desire pages at higher orders. To get
pages of higher order we must shoot down a very high proportion of memory;
>95% in a lot of cases.
This patch set adds a lumpy reclaim algorithm to the allocator. It targets
groups of pages at the specified order anchored at the end of the active and
inactive lists. This encourages groups of pages at the requested orders to
move from active to inactive, and active to free lists. This behaviour is
only triggered out of direct reclaim when higher order pages have been
requested.
This patch set is particularly effective when utilised with an
anti-fragmentation scheme which groups pages of similar reclaimability
together.
This patch set is based on Peter Zijlstra's lumpy reclaim V2 patch which forms
the foundation. Credit to Mel Gorman for sanitity checking.
Mel said:
The patches have an application with hugepage pool resizing.
When lumpy-reclaim is used used with ZONE_MOVABLE, the hugepages pool can
be resized with greater reliability. Testing on a desktop machine with 2GB
of RAM showed that growing the hugepage pool with ZONE_MOVABLE on it's own
was very slow as the success rate was quite low. Without lumpy-reclaim,
each attempt to grow the pool by 100 pages would yield 1 or 2 hugepages.
With lumpy-reclaim, getting 40 to 70 hugepages on each attempt was typical.
[akpm@osdl.org: ia64 pfn_to_nid fixes and loop cleanup]
[bunk@stusta.de: static declarations for internal functions]
[a.p.zijlstra@chello.nl: initial lumpy V2 implementation]
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The following 8 patches against 2.6.20-mm2 create a zone called ZONE_MOVABLE
that is only usable by allocations that specify both __GFP_HIGHMEM and
__GFP_MOVABLE. This has the effect of keeping all non-movable pages within a
single memory partition while allowing movable allocations to be satisfied
from either partition. The patches may be applied with the list-based
anti-fragmentation patches that groups pages together based on mobility.
The size of the zone is determined by a kernelcore= parameter specified at
boot-time. This specifies how much memory is usable by non-movable
allocations and the remainder is used for ZONE_MOVABLE. Any range of pages
within ZONE_MOVABLE can be released by migrating the pages or by reclaiming.
When selecting a zone to take pages from for ZONE_MOVABLE, there are two
things to consider. First, only memory from the highest populated zone is
used for ZONE_MOVABLE. On the x86, this is probably going to be ZONE_HIGHMEM
but it would be ZONE_DMA on ppc64 or possibly ZONE_DMA32 on x86_64. Second,
the amount of memory usable by the kernel will be spread evenly throughout
NUMA nodes where possible. If the nodes are not of equal size, the amount of
memory usable by the kernel on some nodes may be greater than others.
By default, the zone is not as useful for hugetlb allocations because they are
pinned and non-migratable (currently at least). A sysctl is provided that
allows huge pages to be allocated from that zone. This means that the huge
page pool can be resized to the size of ZONE_MOVABLE during the lifetime of
the system assuming that pages are not mlocked. Despite huge pages being
non-movable, we do not introduce additional external fragmentation of note as
huge pages are always the largest contiguous block we care about.
Credit goes to Andy Whitcroft for catching a large variety of problems during
review of the patches.
This patch creates an additional zone, ZONE_MOVABLE. This zone is only usable
by allocations which specify both __GFP_HIGHMEM and __GFP_MOVABLE. Hot-added
memory continues to be placed in their existing destination as there is no
mechanism to redirect them to a specific zone.
[y-goto@jp.fujitsu.com: Fix section mismatch of memory hotplug related code]
[akpm@linux-foundation.org: various fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make zonelist creation policy selectable from sysctl/boot option v6.
This patch makes NUMA's zonelist (of pgdat) order selectable.
Available order are Default(automatic)/ Node-based / Zone-based.
[Default Order]
The kernel selects Node-based or Zone-based order automatically.
[Node-based Order]
This policy treats the locality of memory as the most important parameter.
Zonelist order is created by each zone's locality. This means lower zones
(ex. ZONE_DMA) can be used before higher zone (ex. ZONE_NORMAL) exhausion.
IOW. ZONE_DMA will be in the middle of zonelist.
current 2.6.21 kernel uses this.
Pros.
* A user can expect local memory as much as possible.
Cons.
* lower zone will be exhansted before higher zone. This may cause OOM_KILL.
Maybe suitable if ZONE_DMA is relatively big and you never see OOM_KILL
because of ZONE_DMA exhaution and you need the best locality.
(example)
assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL.
*node(0)'s memory allocation order:
node(0)'s NORMAL -> node(0)'s DMA -> node(1)'s NORMAL.
*node(1)'s memory allocation order:
node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA.
[Zone-based order]
This policy treats the zone type as the most important parameter.
Zonelist order is created by zone-type order. This means lower zone
never be used bofere higher zone exhaustion.
IOW. ZONE_DMA will be always at the tail of zonelist.
Pros.
* OOM_KILL(bacause of lower zone) occurs only if the whole zones are exhausted.
Cons.
* memory locality may not be best.
(example)
assume 2 node NUMA. node(0) has ZONE_DMA/ZONE_NORMAL, node(1) has ZONE_NORMAL.
*node(0)'s memory allocation order:
node(0)'s NORMAL -> node(1)'s NORMAL -> node(0)'s DMA.
*node(1)'s memory allocation order:
node(1)'s NORMAL -> node(0)'s NORMAL -> node(0)'s DMA.
bootoption "numa_zonelist_order=" and proc/sysctl is supporetd.
command:
%echo N > /proc/sys/vm/numa_zonelist_order
Will rebuild zonelist in Node-based order.
command:
%echo Z > /proc/sys/vm/numa_zonelist_order
Will rebuild zonelist in Zone-based order.
Thanks to Lee Schermerhorn, he gives me much help and codes.
[Lee.Schermerhorn@hp.com: add check_highest_zone to build_zonelists_in_zone_order]
[akpm@linux-foundation.org: build fix]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "jesse.barnes@intel.com" <jesse.barnes@intel.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently the slab allocators contain callbacks into the page allocator to
perform the draining of pagesets on remote nodes. This requires SLUB to have
a whole subsystem in order to be compatible with SLAB. Moving node draining
out of the slab allocators avoids a section of code in SLUB.
Move the node draining so that is is done when the vm statistics are updated.
At that point we are already touching all the cachelines with the pagesets of
a processor.
Add a expire counter there. If we have to update per zone or global vm
statistics then assume that the pageset will require subsequent draining.
The expire counter will be decremented on each vm stats update pass until it
reaches zero. Then we will drain one batch from the pageset. The draining
will cause vm counter updates which will then cause another expiration until
the pcp is empty. So we will drain a batch every 3 seconds.
Note that remote node draining is a somewhat esoteric feature that is required
on large NUMA systems because otherwise significant portions of system memory
can become trapped in pcp queues. The number of pcp is determined by the
number of processors and nodes in a system. A system with 4 processors and 2
nodes has 8 pcps which is okay. But a system with 1024 processors and 512
nodes has 512k pcps with a high potential for large amount of memory being
caught in them.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Generally we work under the assumption that memory the mem_map array is
contigious and valid out to MAX_ORDER_NR_PAGES block of pages, ie. that if we
have validated any page within this MAX_ORDER_NR_PAGES block we need not check
any other. This is not true when CONFIG_HOLES_IN_ZONE is set and we must
check each and every reference we make from a pfn.
Add a pfn_valid_within() helper which should be used when scanning pages
within a MAX_ORDER_NR_PAGES block when we have already checked the validility
of the block normally with pfn_valid(). This can then be optimised away when
we do not have holes within a MAX_ORDER_NR_PAGES block of pages.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make ZONE_DMA optional in core code.
- ifdef all code for ZONE_DMA and related definitions following the example
for ZONE_DMA32 and ZONE_HIGHMEM.
- Without ZONE_DMA, ZONE_HIGHMEM and ZONE_DMA32 we get to a ZONES_SHIFT of
0.
- Modify the VM statistics to work correctly without a DMA zone.
- Modify slab to not create DMA slabs if there is no ZONE_DMA.
[akpm@osdl.org: cleanup]
[jdike@addtoit.com: build fix]
[apw@shadowen.org: Simplify calculation of the number of bits we need for ZONES_SHIFT]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Matthew Wilcox <willy@debian.org>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Values are readily available via ZVC per node and global sums.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The global and per zone counter sums are in arrays of longs. Reorder the ZVCs
so that the most frequently used ZVCs are put into the same cacheline. That
way calculations of the global, node and per zone vm state touches only a
single cacheline. This is mostly important for 64 bit systems were one 128
byte cacheline takes only 8 longs.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is again simplifies some of the VM counter calculations through the use
of the ZVC consolidated counters.
[michal.k.k.piotrowski@gmail.com: build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Michal Piotrowski <michal.k.k.piotrowski@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The determination of the dirty ratio to determine writeback behavior is
currently based on the number of total pages on the system.
However, not all pages in the system may be dirtied. Thus the ratio is always
too low and can never reach 100%. The ratio may be particularly skewed if
large hugepage allocations, slab allocations or device driver buffers make
large sections of memory not available anymore. In that case we may get into
a situation in which f.e. the background writeback ratio of 40% cannot be
reached anymore which leads to undesired writeback behavior.
This patchset fixes that issue by determining the ratio based on the actual
pages that may potentially be dirty. These are the pages on the active and
the inactive list plus free pages.
The problem with those counts has so far been that it is expensive to
calculate these because counts from multiple nodes and multiple zones will
have to be summed up. This patchset makes these counters ZVC counters. This
means that a current sum per zone, per node and for the whole system is always
available via global variables and not expensive anymore to calculate.
The patchset results in some other good side effects:
- Removal of the various functions that sum up free, active and inactive
page counts
- Cleanup of the functions that display information via the proc filesystem.
This patch:
The use of a ZVC for nr_inactive and nr_active allows a simplification of some
counter operations. More ZVC functionality is used for sums etc in the
following patches.
[akpm@osdl.org: UP build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix an oops experienced on the Cell architecture when init-time functions,
early_*(), are called at runtime. It alters the call paths to make sure
that the callers explicitly say whether the call is being made on behalf of
a hotplug even, or happening at boot-time.
It has been compile tested on ppc64, ia64, s390, i386 and x86_64.
Acked-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Acked-by: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- move some file_operations structs into the .rodata section
- move static strings from policy_types[] array into the .rodata section
- fix generic seq_operations usages, so that those structs may be defined
as "const" as well
[akpm@osdl.org: couple of fixes]
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Rearrange the struct members in the 'struct zonelist_cache' structure, so
as to put the readonly (once initialized) z_to_n[] array first, where it
will come right after the zones[] array in struct zonelist.
This pretty much eliminates the chance that the two frequently written
elements of 'struct zonelist_cache', the fullzones bitmap and last_full_zap
times, will end up on the same cache line as the performance sensitive,
frequently read, never (after init) written zones[] array.
Keeping frequently written data off frequently read cache lines is good for
performance.
Thanks to Rohit Seth for the suggestion.
Signed-off-by: Paul Jackson <pj@sgi.com>
Cc: Rohit Seth <rohitseth@google.com>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Optimize the critical zonelist scanning for free pages in the kernel memory
allocator by caching the zones that were found to be full recently, and
skipping them.
Remembers the zones in a zonelist that were short of free memory in the
last second. And it stashes a zone-to-node table in the zonelist struct,
to optimize that conversion (minimize its cache footprint.)
Recent changes:
This differs in a significant way from a similar patch that I
posted a week ago. Now, instead of having a nodemask_t of
recently full nodes, I have a bitmask of recently full zones.
This solves a problem that last weeks patch had, which on
systems with multiple zones per node (such as DMA zone) would
take seeing any of these zones full as meaning that all zones
on that node were full.
Also I changed names - from "zonelist faster" to "zonelist cache",
as that seemed to better convey what we're doing here - caching
some of the key zonelist state (for faster access.)
See below for some performance benchmark results. After all that
discussion with David on why I didn't need them, I went and got
some ;). I wanted to verify that I had not hurt the normal case
of memory allocation noticeably. At least for my one little
microbenchmark, I found (1) the normal case wasn't affected, and
(2) workloads that forced scanning across multiple nodes for
memory improved up to 10% fewer System CPU cycles and lower
elapsed clock time ('sys' and 'real'). Good. See details, below.
I didn't have the logic in get_page_from_freelist() for various
full nodes and zone reclaim failures correct. That should be
fixed up now - notice the new goto labels zonelist_scan,
this_zone_full, and try_next_zone, in get_page_from_freelist().
There are two reasons I persued this alternative, over some earlier
proposals that would have focused on optimizing the fake numa
emulation case by caching the last useful zone:
1) Contrary to what I said before, we (SGI, on large ia64 sn2 systems)
have seen real customer loads where the cost to scan the zonelist
was a problem, due to many nodes being full of memory before
we got to a node we could use. Or at least, I think we have.
This was related to me by another engineer, based on experiences
from some time past. So this is not guaranteed. Most likely, though.
The following approach should help such real numa systems just as
much as it helps fake numa systems, or any combination thereof.
2) The effort to distinguish fake from real numa, using node_distance,
so that we could cache a fake numa node and optimize choosing
it over equivalent distance fake nodes, while continuing to
properly scan all real nodes in distance order, was going to
require a nasty blob of zonelist and node distance munging.
The following approach has no new dependency on node distances or
zone sorting.
See comment in the patch below for a description of what it actually does.
Technical details of note (or controversy):
- See the use of "zlc_active" and "did_zlc_setup" below, to delay
adding any work for this new mechanism until we've looked at the
first zone in zonelist. I figured the odds of the first zone
having the memory we needed were high enough that we should just
look there, first, then get fancy only if we need to keep looking.
- Some odd hackery was needed to add items to struct zonelist, while
not tripping up the custom zonelists built by the mm/mempolicy.c
code for MPOL_BIND. My usual wordy comments below explain this.
Search for "MPOL_BIND".
- Some per-node data in the struct zonelist is now modified frequently,
with no locking. Multiple CPU cores on a node could hit and mangle
this data. The theory is that this is just performance hint data,
and the memory allocator will work just fine despite any such mangling.
The fields at risk are the struct 'zonelist_cache' fields 'fullzones'
(a bitmask) and 'last_full_zap' (unsigned long jiffies). It should
all be self correcting after at most a one second delay.
- This still does a linear scan of the same lengths as before. All
I've optimized is making the scan faster, not algorithmically
shorter. It is now able to scan a compact array of 'unsigned
short' in the case of many full nodes, so one cache line should
cover quite a few nodes, rather than each node hitting another
one or two new and distinct cache lines.
- If both Andi and Nick don't find this too complicated, I will be
(pleasantly) flabbergasted.
- I removed the comment claiming we only use one cachline's worth of
zonelist. We seem, at least in the fake numa case, to have put the
lie to that claim.
- I pay no attention to the various watermarks and such in this performance
hint. A node could be marked full for one watermark, and then skipped
over when searching for a page using a different watermark. I think
that's actually quite ok, as it will tend to slightly increase the
spreading of memory over other nodes, away from a memory stressed node.
===============
Performance - some benchmark results and analysis:
This benchmark runs a memory hog program that uses multiple
threads to touch alot of memory as quickly as it can.
Multiple runs were made, touching 12, 38, 64 or 90 GBytes out of
the total 96 GBytes on the system, and using 1, 19, 37, or 55
threads (on a 56 CPU system.) System, user and real (elapsed)
timings were recorded for each run, shown in units of seconds,
in the table below.
Two kernels were tested - 2.6.18-mm3 and the same kernel with
this zonelist caching patch added. The table also shows the
percentage improvement the zonelist caching sys time is over
(lower than) the stock *-mm kernel.
number 2.6.18-mm3 zonelist-cache delta (< 0 good) percent
GBs N ------------ -------------- ---------------- systime
mem threads sys user real sys user real sys user real better
12 1 153 24 177 151 24 176 -2 0 -1 1%
12 19 99 22 8 99 22 8 0 0 0 0%
12 37 111 25 6 112 25 6 1 0 0 -0%
12 55 115 25 5 110 23 5 -5 -2 0 4%
38 1 502 74 576 497 73 570 -5 -1 -6 0%
38 19 426 78 48 373 76 39 -53 -2 -9 12%
38 37 544 83 36 547 82 36 3 -1 0 -0%
38 55 501 77 23 511 80 24 10 3 1 -1%
64 1 917 125 1042 890 124 1014 -27 -1 -28 2%
64 19 1118 138 119 965 141 103 -153 3 -16 13%
64 37 1202 151 94 1136 150 81 -66 -1 -13 5%
64 55 1118 141 61 1072 140 58 -46 -1 -3 4%
90 1 1342 177 1519 1275 174 1450 -67 -3 -69 4%
90 19 2392 199 192 2116 189 176 -276 -10 -16 11%
90 37 3313 238 175 2972 225 145 -341 -13 -30 10%
90 55 1948 210 104 1843 213 100 -105 3 -4 5%
Notes:
1) This test ran a memory hog program that started a specified number N of
threads, and had each thread allocate and touch 1/N'th of
the total memory to be used in the test run in a single loop,
writing a constant word to memory, one store every 4096 bytes.
Watching this test during some earlier trial runs, I would see
each of these threads sit down on one CPU and stay there, for
the remainder of the pass, a different CPU for each thread.
2) The 'real' column is not comparable to the 'sys' or 'user' columns.
The 'real' column is seconds wall clock time elapsed, from beginning
to end of that test pass. The 'sys' and 'user' columns are total
CPU seconds spent on that test pass. For a 19 thread test run,
for example, the sum of 'sys' and 'user' could be up to 19 times the
number of 'real' elapsed wall clock seconds.
3) Tests were run on a fresh, single-user boot, to minimize the amount
of memory already in use at the start of the test, and to minimize
the amount of background activity that might interfere.
4) Tests were done on a 56 CPU, 28 Node system with 96 GBytes of RAM.
5) Notice that the 'real' time gets large for the single thread runs, even
though the measured 'sys' and 'user' times are modest. I'm not sure what
that means - probably something to do with it being slow for one thread to
be accessing memory along ways away. Perhaps the fake numa system, running
ostensibly the same workload, would not show this substantial degradation
of 'real' time for one thread on many nodes -- lets hope not.
6) The high thread count passes (one thread per CPU - on 55 of 56 CPUs)
ran quite efficiently, as one might expect. Each pair of threads needed
to allocate and touch the memory on the node the two threads shared, a
pleasantly parallizable workload.
7) The intermediate thread count passes, when asking for alot of memory forcing
them to go to a few neighboring nodes, improved the most with this zonelist
caching patch.
Conclusions:
* This zonelist cache patch probably makes little difference one way or the
other for most workloads on real numa hardware, if those workloads avoid
heavy off node allocations.
* For memory intensive workloads requiring substantial off-node allocations
on real numa hardware, this patch improves both kernel and elapsed timings
up to ten per-cent.
* For fake numa systems, I'm optimistic, but will have to leave that up to
Rohit Seth to actually test (once I get him a 2.6.18 backport.)
Signed-off-by: Paul Jackson <pj@sgi.com>
Cc: Rohit Seth <rohitseth@google.com>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: David Rientjes <rientjes@cs.washington.edu>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The temp_priority field in zone is racy, as we can walk through a reclaim
path, and just before we copy it into prev_priority, it can be overwritten
(say with DEF_PRIORITY) by another reclaimer.
The same bug is contained in both try_to_free_pages and balance_pgdat, but
it is fixed slightly differently. In balance_pgdat, we keep a separate
priority record per zone in a local array. In try_to_free_pages there is
no need to do this, as the priority level is the same for all zones that we
reclaim from.
Impact of this bug is that temp_priority is copied into prev_priority, and
setting this artificially high causes reclaimers to set distress
artificially low. They then fail to reclaim mapped pages, when they are,
in fact, under severe memory pressure (their priority may be as low as 0).
This causes the OOM killer to fire incorrectly.
From: Andrew Morton <akpm@osdl.org>
__zone_reclaim() isn't modifying zone->prev_priority. But zone->prev_priority
is used in the decision whether or not to bring mapped pages onto the inactive
list. Hence there's a risk here that __zone_reclaim() will fail because
zone->prev_priority ir large (ie: low urgency) and lots of mapped pages end up
stuck on the active list.
Fix that up by decreasing (ie making more urgent) zone->prev_priority as
__zone_reclaim() scans the zone's pages.
This bug perhaps explains why ZONE_RECLAIM_PRIORITY was created. It should be
possible to remove that now, and to just start out at DEF_PRIORITY?
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Reintroduce NODES_SPAN_OTHER_NODES for powerpc
Revert "[PATCH] Remove SPAN_OTHER_NODES config definition"
This reverts commit f62859bb68.
Revert "[PATCH] mm: remove arch independent NODES_SPAN_OTHER_NODES"
This reverts commit a94b3ab7ea.
Also update the comments to indicate that this is still required
and where its used.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Kravetz <kravetz@us.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Will Schmidt <will_schmidt@vnet.ibm.com>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add the node in order to optimize zone_to_nid.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This moves the definition of struct page from mm.h to its own header file
page-struct.h. This is a prereq to fix SetPageUptodate which is broken on
s390:
#define SetPageUptodate(_page)
do {
struct page *__page = (_page);
if (!test_and_set_bit(PG_uptodate, &__page->flags))
page_test_and_clear_dirty(_page);
} while (0)
_page gets used twice in this macro which can cause subtle bugs. Using
__page for the page_test_and_clear_dirty call doesn't work since it causes
yet another problem with the page_test_and_clear_dirty macro as well.
In order to avoid all these problems caused by macros it seems to be a good
idea to get rid of them and convert them to static inline functions.
Because of header file include order it's necessary to have a seperate
header file for the struct page definition.
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The VM is supposed to minimise the number of pages which get written off the
LRU (for IO scheduling efficiency, and for high reclaim-success rates). But
we don't actually have a clear way of showing how true this is.
So add `nr_vmscan_write' to /proc/vmstat and /proc/zoneinfo - the number of
pages which have been written by the vm scanner in this zone and globally.
Cc: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
At a basic level, architectures define structures to record where active
ranges of page frames are located. Once located, the code to calculate zone
sizes and holes in each architecture is very similar. Some of this zone and
hole sizing code is difficult to read for no good reason. This set of patches
eliminates the similar-looking architecture-specific code.
The patches introduce a mechanism where architectures register where the
active ranges of page frames are with add_active_range(). When all areas have
been discovered, free_area_init_nodes() is called to initialise the pgdat and
zones. The zone sizes and holes are then calculated in an architecture
independent manner.
Patch 1 introduces the mechanism for registering and initialising PFN ranges
Patch 2 changes ppc to use the mechanism - 139 arch-specific LOC removed
Patch 3 changes x86 to use the mechanism - 136 arch-specific LOC removed
Patch 4 changes x86_64 to use the mechanism - 74 arch-specific LOC removed
Patch 5 changes ia64 to use the mechanism - 52 arch-specific LOC removed
Patch 6 accounts for mem_map as a memory hole as the pages are not reclaimable.
It adjusts the watermarks slightly
Tony Luck has successfully tested for ia64 on Itanium with tiger_defconfig,
gensparse_defconfig and defconfig. Bob Picco has also tested and debugged on
IA64. Jack Steiner successfully boot tested on a mammoth SGI IA64-based
machine. These were on patches against 2.6.17-rc1 and release 3 of these
patches but there have been no ia64-changes since release 3.
There are differences in the zone sizes for x86_64 as the arch-specific code
for x86_64 accounts the kernel image and the starting mem_maps as memory holes
but the architecture-independent code accounts the memory as present.
The big benefit of this set of patches is a sizable reduction of
architecture-specific code, some of which is very hairy. There should be a
greater reduction when other architectures use the same mechanisms for zone
and hole sizing but I lack the hardware to test on.
Additional credit;
Dave Hansen for the initial suggestion and comments on early patches
Andy Whitcroft for reviewing early versions and catching numerous
errors
Tony Luck for testing and debugging on IA64
Bob Picco for fixing bugs related to pfn registration, reviewing a
number of patch revisions, providing a number of suggestions
on future direction and testing heavily
Jack Steiner and Robin Holt for testing on IA64 and clarifying
issues related to memory holes
Yasunori for testing on IA64
Andi Kleen for reviewing and feeding back about x86_64
Christian Kujau for providing valuable information related to ACPI
problems on x86_64 and testing potential fixes
This patch:
Define the structure to represent an active range of page frames within a node
in an architecture independent manner. Architectures are expected to register
active ranges of PFNs using add_active_range(nid, start_pfn, end_pfn) and call
free_area_init_nodes() passing the PFNs of the end of each zone.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Andi Kleen <ak@muc.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Keith Mannthey" <kmannth@gmail.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Currently one can enable slab reclaim by setting an explicit option in
/proc/sys/vm/zone_reclaim_mode. Slab reclaim is then used as a final
option if the freeing of unmapped file backed pages is not enough to free
enough pages to allow a local allocation.
However, that means that the slab can grow excessively and that most memory
of a node may be used by slabs. We have had a case where a machine with
46GB of memory was using 40-42GB for slab. Zone reclaim was effective in
dealing with pagecache pages. However, slab reclaim was only done during
global reclaim (which is a bit rare on NUMA systems).
This patch implements slab reclaim during zone reclaim. Zone reclaim
occurs if there is a danger of an off node allocation. At that point we
1. Shrink the per node page cache if the number of pagecache
pages is more than min_unmapped_ratio percent of pages in a zone.
2. Shrink the slab cache if the number of the nodes reclaimable slab pages
(patch depends on earlier one that implements that counter)
are more than min_slab_ratio (a new /proc/sys/vm tunable).
The shrinking of the slab cache is a bit problematic since it is not node
specific. So we simply calculate what point in the slab we want to reach
(current per node slab use minus the number of pages that neeed to be
allocated) and then repeately run the global reclaim until that is
unsuccessful or we have reached the limit. I hope we will have zone based
slab reclaim at some point which will make that easier.
The default for the min_slab_ratio is 5%
Also remove the slab option from /proc/sys/vm/zone_reclaim_mode.
[akpm@osdl.org: cleanups]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Remove the atomic counter for slab_reclaim_pages and replace the counter
and NR_SLAB with two ZVC counter that account for unreclaimable and
reclaimable slab pages: NR_SLAB_RECLAIMABLE and NR_SLAB_UNRECLAIMABLE.
Change the check in vmscan.c to refer to to NR_SLAB_RECLAIMABLE. The
intend seems to be to check for slab pages that could be freed.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
*_pages is a better description of the role of the variable.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
I wonder why we need this bitmask indexing into zone->node_zonelists[]?
We always start with the highest zone and then include all lower zones
if we build zonelists.
Are there really cases where we need allocation from ZONE_DMA or
ZONE_HIGHMEM but not ZONE_NORMAL? It seems that the current implementation
of highest_zone() makes that already impossible.
If we go linear on the index then gfp_zone() == highest_zone() and a lot
of definitions fall by the wayside.
We can now revert back to the use of gfp_zone() in mempolicy.c ;-)
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make ZONE_HIGHMEM optional
- ifdef out code and definitions related to CONFIG_HIGHMEM
- __GFP_HIGHMEM falls back to normal allocations if there is no
ZONE_HIGHMEM
- GFP_ZONEMASK becomes 0x01 if there is no DMA32 and no HIGHMEM
zone.
[jdike@addtoit.com: build fix]
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make ZONE_DMA32 optional
- Add #ifdefs around ZONE_DMA32 specific code and definitions.
- Add CONFIG_ZONE_DMA32 config option and use that for x86_64
that alone needs this zone.
- Remove the use of CONFIG_DMA_IS_DMA32 and CONFIG_DMA_IS_NORMAL
for ia64 and fix up the way per node ZVCs are calculated.
- Fall back to prior GFP_ZONEMASK of 0x03 if there is no
DMA32 zone.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Use enum for zones and reformat zones dependent information
Add comments explaning the use of zones and add a zones_t type for zone
numbers.
Line up information that will be #ifdefd by the following patches.
[akpm@osdl.org: comment cleanups]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The ZVC counter update threshold is currently set to a fixed value of 32.
This patch sets up the threshold depending on the number of processors and
the sizes of the zones in the system.
With the current threshold of 32, I was able to observe slight contention
when more than 130-140 processors concurrently updated the counters. The
contention vanished when I either increased the threshold to 64 or used
Andrew's idea of overstepping the interval (see ZVC overstep patch).
However, we saw contention again at 220-230 processors. So we need higher
values for larger systems.
But the current default is already a bit of an overkill for smaller
systems. Some systems have tiny zones where precision matters. For
example i386 and x86_64 have 16M DMA zones and either 900M ZONE_NORMAL or
ZONE_DMA32. These are even present on SMP and NUMA systems.
The patch here sets up a threshold based on the number of processors in the
system and the size of the zone that these counters are used for. The
threshold should grow logarithmically, so we use fls() as an easy
approximation.
Results of tests on a system with 1024 processors (4TB RAM)
The following output is from a test allocating 1GB of memory concurrently
on each processor (Forking the process. So contention on mmap_sem and the
pte locks is not a factor):
X MIN
TYPE: CPUS WALL WALL SYS USER TOTCPU
fork 1 0.552 0.552 0.540 0.012 0.552
fork 4 0.552 0.548 2.164 0.036 2.200
fork 16 0.564 0.548 8.812 0.164 8.976
fork 128 0.580 0.572 72.204 1.208 73.412
fork 256 1.300 0.660 310.400 2.160 312.560
fork 512 3.512 0.696 1526.836 4.816 1531.652
fork 1020 20.024 0.700 17243.176 6.688 17249.863
So a threshold of 32 is fine up to 128 processors. At 256 processors contention
becomes a factor.
Overstepping the counter (earlier patch) improves the numbers a bit:
fork 4 0.552 0.548 2.164 0.040 2.204
fork 16 0.552 0.548 8.640 0.148 8.788
fork 128 0.556 0.548 69.676 0.956 70.632
fork 256 0.876 0.636 212.468 2.108 214.576
fork 512 2.276 0.672 997.324 4.260 1001.584
fork 1020 13.564 0.680 11586.436 6.088 11592.523
Still contention at 512 and 1020. Contention at 1020 is down by a third.
256 still has a slight bit of contention.
After this patch the counter threshold will be set to 125 which reduces
contention significantly:
fork 128 0.560 0.548 69.776 0.932 70.708
fork 256 0.636 0.556 143.460 2.036 145.496
fork 512 0.640 0.548 284.244 4.236 288.480
fork 1020 1.500 0.588 1326.152 8.892 1335.044
[akpm@osdl.org: !SMP build fix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
It turns out that it is advantageous to leave a small portion of unmapped file
backed pages if all of a zone's pages (or almost all pages) are allocated and
so the page allocator has to go off-node.
This allows recently used file I/O buffers to stay on the node and
reduces the times that zone reclaim is invoked if file I/O occurs
when we run out of memory in a zone.
The problem is that zone reclaim runs too frequently when the page cache is
used for file I/O (read write and therefore unmapped pages!) alone and we have
almost all pages of the zone allocated. Zone reclaim may remove 32 unmapped
pages. File I/O will use these pages for the next read/write requests and the
unmapped pages increase. After the zone has filled up again zone reclaim will
remove it again after only 32 pages. This cycle is too inefficient and there
are potentially too many zone reclaim cycles.
With the 1% boundary we may still remove all unmapped pages for file I/O in
zone reclaim pass. However. it will take a large number of read and writes
to get back to 1% again where we trigger zone reclaim again.
The zone reclaim 2.6.16/17 does not show this behavior because we have a 30
second timeout.
[akpm@osdl.org: rename the /proc file and the variable]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The numa statistics are really event counters. But they are per node and
so we have had special treatment for these counters through additional
fields on the pcp structure. We can now use the per zone nature of the
zoned VM counters to realize these.
This will shrink the size of the pcp structure on NUMA systems. We will
have some room to add additional per zone counters that will all still fit
in the same cacheline.
Bits Prior pcp size Size after patch We can add
------------------------------------------------------------------
64 128 bytes (16 words) 80 bytes (10 words) 48
32 76 bytes (19 words) 56 bytes (14 words) 8 (64 byte cacheline)
72 (128 byte)
Remove the special statistics for numa and replace them with zoned vm
counters. This has the side effect that global sums of these events now
show up in /proc/vmstat.
Also take the opportunity to move the zone_statistics() function from
page_alloc.c into vmstat.c.
Discussions:
V2 http://marc.theaimsgroup.com/?t=115048227000002&r=1&w=2
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Acked-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Conversion of nr_bounce to a per zone counter
nr_bounce is only used for proc output. So it could be left as an event
counter. However, the event counters may not be accurate and nr_bounce is
categorizing types of pages in a zone. So we really need this to also be a
per zone counter.
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Conversion of nr_unstable to a per zone counter
We need to do some special modifications to the nfs code since there are
multiple cases of disposition and we need to have a page ref for proper
accounting.
This converts the last critical page state of the VM and therefore we need to
remove several functions that were depending on GET_PAGE_STATE_LAST in order
to make the kernel compile again. We are only left with event type counters
in page state.
[akpm@osdl.org: bugfixes]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Conversion of nr_writeback to per zone counter.
This removes the last page_state counter from arch/i386/mm/pgtable.c so we
drop the page_state from there.
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This makes nr_dirty a per zone counter. Looping over all processors is
avoided during writeback state determination.
The counter aggregation for nr_dirty had to be undone in the NFS layer since
we summed up the page counts from multiple zones. Someone more familiar with
NFS should probably review what I have done.
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Conversion of nr_page_table_pages to a per zone counter
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
- Allows reclaim to access counter without looping over processor counts.
- Allows accurate statistics on how many pages are used in a zone by
the slab. This may become useful to balance slab allocations over
various zones.
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The zone_reclaim_interval was necessary because we were not able to determine
how many unmapped pages exist in a zone. Therefore we had to scan in
intervals to figure out if any pages were unmapped.
With the zoned counters and NR_ANON_PAGES we now know the number of pagecache
pages and the number of mapped pages in a zone. So we can simply skip the
reclaim if there is an insufficient number of unmapped pages. We use
SWAP_CLUSTER_MAX as the boundary.
Drop all support for /proc/sys/vm/zone_reclaim_interval.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The current NR_FILE_MAPPED is used by zone reclaim and the dirty load
calculation as the number of mapped pagecache pages. However, that is not
true. NR_FILE_MAPPED includes the mapped anonymous pages. This patch
separates those and therefore allows an accurate tracking of the anonymous
pages per zone.
It then becomes possible to determine the number of unmapped pages per zone
and we can avoid scanning for unmapped pages if there are none.
Also it may now be possible to determine the mapped/unmapped ratio in
get_dirty_limit. Isnt the number of anonymous pages irrelevant in that
calculation?
Note that this will change the meaning of the number of mapped pages reported
in /proc/vmstat /proc/meminfo and in the per node statistics. This may affect
user space tools that monitor these counters! NR_FILE_MAPPED works like
NR_FILE_DIRTY. It is only valid for pagecache pages.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Currently a single atomic variable is used to establish the size of the page
cache in the whole machine. The zoned VM counters have the same method of
implementation as the nr_pagecache code but also allow the determination of
the pagecache size per zone.
Remove the special implementation for nr_pagecache and make it a zoned counter
named NR_FILE_PAGES.
Updates of the page cache counters are always performed with interrupts off.
We can therefore use the __ variant here.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
nr_mapped is important because it allows a determination of how many pages of
a zone are not mapped, which would allow a more efficient means of determining
when we need to reclaim memory in a zone.
We take the nr_mapped field out of the page state structure and define a new
per zone counter named NR_FILE_MAPPED (the anonymous pages will be split off
from NR_MAPPED in the next patch).
We replace the use of nr_mapped in various kernel locations. This avoids the
looping over all processors in try_to_free_pages(), writeback, reclaim (swap +
zone reclaim).
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Per zone counter infrastructure
The counters that we currently have for the VM are split per processor. The
processor however has not much to do with the zone these pages belong to. We
cannot tell f.e. how many ZONE_DMA pages are dirty.
So we are blind to potentially inbalances in the usage of memory in various
zones. F.e. in a NUMA system we cannot tell how many pages are dirty on a
particular node. If we knew then we could put measures into the VM to balance
the use of memory between different zones and different nodes in a NUMA
system. For example it would be possible to limit the dirty pages per node so
that fast local memory is kept available even if a process is dirtying huge
amounts of pages.
Another example is zone reclaim. We do not know how many unmapped pages exist
per zone. So we just have to try to reclaim. If it is not working then we
pause and try again later. It would be better if we knew when it makes sense
to reclaim unmapped pages from a zone. This patchset allows the determination
of the number of unmapped pages per zone. We can remove the zone reclaim
interval with the counters introduced here.
Futhermore the ability to have various usage statistics available will allow
the development of new NUMA balancing algorithms that may be able to improve
the decision making in the scheduler of when to move a process to another node
and hopefully will also enable automatic page migration through a user space
program that can analyse the memory load distribution and then rebalance
memory use in order to increase performance.
The counter framework here implements differential counters for each processor
in struct zone. The differential counters are consolidated when a threshold
is exceeded (like done in the current implementation for nr_pageache), when
slab reaping occurs or when a consolidation function is called.
Consolidation uses atomic operations and accumulates counters per zone in the
zone structure and also globally in the vm_stat array. VM functions can
access the counts by simply indexing a global or zone specific array.
The arrangement of counters in an array also simplifies processing when output
has to be generated for /proc/*.
Counters can be updated by calling inc/dec_zone_page_state or
_inc/dec_zone_page_state analogous to *_page_state. The second group of
functions can be called if it is known that interrupts are disabled.
Special optimized increment and decrement functions are provided. These can
avoid certain checks and use increment or decrement instructions that an
architecture may provide.
We also add a new CONFIG_DMA_IS_NORMAL that signifies that an architecture can
do DMA to all memory and therefore ZONE_NORMAL will not be populated. This is
only currently set for IA64 SGI SN2 and currently only affects
node_page_state(). In the best case node_page_state can be reduced to
retrieving a single counter for the one zone on the node.
[akpm@osdl.org: cleanups]
[akpm@osdl.org: export vm_stat[] for filesystems]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Record the node id as we mark sections for instantiation. Use this nid
during instantiation to direct allocations.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Cc: Mike Kravetz <kravetz@us.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Bob Picco <bob.picco@hp.com>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Martin Bligh <mbligh@google.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
When add_zone() is called against empty zone (not populated zone), we have to
initialize the zone which didn't initialize at boot time. But,
init_currently_empty_zone() may fail due to allocation of wait table. So,
this patch is to catch its error code.
Changes against wait_table is in the next patch.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This is just to rename from wait_table_size() to wait_table_hash_nr_entries().
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* git://git.infradead.org/hdrcleanup-2.6: (63 commits)
[S390] __FD_foo definitions.
Switch to __s32 types in joystick.h instead of C99 types for consistency.
Add <sys/types.h> to headers included for userspace in <linux/input.h>
Move inclusion of <linux/compat.h> out of user scope in asm-x86_64/mtrr.h
Remove struct fddi_statistics from user view in <linux/if_fddi.h>
Move user-visible parts of drivers/s390/crypto/z90crypt.h to include/asm-s390
Revert include/media changes: Mauro says those ioctls are only used in-kernel(!)
Include <linux/types.h> and use __uXX types in <linux/cramfs_fs.h>
Use __uXX types in <linux/i2o_dev.h>, include <linux/ioctl.h> too
Remove private struct dx_hash_info from public view in <linux/ext3_fs.h>
Include <linux/types.h> and use __uXX types in <linux/affs_hardblocks.h>
Use __uXX types in <linux/divert.h> for struct divert_blk et al.
Use __u32 for elf_addr_t in <asm-powerpc/elf.h>, not u32. It's user-visible.
Remove PPP_FCS from user view in <linux/ppp_defs.h>, remove __P mess entirely
Use __uXX types in user-visible structures in <linux/nbd.h>
Don't use 'u32' in user-visible struct ip_conntrack_old_tuple.
Use __uXX types for S390 DASD volume label definitions which are user-visible
S390 BIODASDREADCMB ioctl should use __u64 not u64 type.
Remove unneeded inclusion of <linux/time.h> from <linux/ufs_fs.h>
Fix private integer types used in V4L2 ioctls.
...
Manually resolve conflict in include/linux/mtd/physmap.h
From: Ralf Baechle <ralf@linux-mips.org>
<linux/mmzone.h> uses PAGE_SIZE, PAGE_SHIFT from <asm/page.h> without
including that header itself. For some sparsemem configurations this may
result in build errors like:
CC init/initramfs.o
In file included from include/linux/gfp.h:4,
from include/linux/slab.h:15,
from include/linux/percpu.h:4,
from include/linux/rcupdate.h:41,
from include/linux/dcache.h:10,
from include/linux/fs.h:226,
from init/initramfs.c:2:
include/linux/mmzone.h:498:22: warning: "PAGE_SHIFT" is not defined
In file included from include/linux/gfp.h:4,
from include/linux/slab.h:15,
from include/linux/percpu.h:4,
from include/linux/rcupdate.h:41,
from include/linux/dcache.h:10,
from include/linux/fs.h:226,
from init/initramfs.c:2:
include/linux/mmzone.h:526: error: `PAGE_SIZE' undeclared here (not in a function)
include/linux/mmzone.h: In function `__pfn_to_section':
include/linux/mmzone.h:573: error: `PAGE_SHIFT' undeclared (first use in this function)
include/linux/mmzone.h:573: error: (Each undeclared identifier is reported only once
include/linux/mmzone.h:573: error: for each function it appears in.)
include/linux/mmzone.h: In function `pfn_valid':
include/linux/mmzone.h:578: error: `PAGE_SHIFT' undeclared (first use in this function)
make[1]: *** [init/initramfs.o] Error 1
make: *** [init] Error 2
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Seems-reasonable-to: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Andy added code to buddy allocator which does not require the zone's
endpoints to be aligned to MAX_ORDER. An issue is that the buddy allocator
requires the node_mem_map's endpoints to be MAX_ORDER aligned. Otherwise
__page_find_buddy could compute a buddy not in node_mem_map for partial
MAX_ORDER regions at zone's endpoints. page_is_buddy will detect that
these pages at endpoints are not PG_buddy (they were zeroed out by bootmem
allocator and not part of zone). Of course the negative here is we could
waste a little memory but the positive is eliminating all the old checks
for zone boundary conditions.
SPARSEMEM won't encounter this issue because of MAX_ORDER size constraint
when SPARSEMEM is configured. ia64 VIRTUAL_MEM_MAP doesn't need the logic
either because the holes and endpoints are handled differently. This
leaves checking alloc_remap and other arches which privately allocate for
node_mem_map.
Signed-off-by: Bob Picco <bob.picco@hp.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Helper functions for for_each_online_pgdat/for_each_zone look too big to be
inlined. Speed of these helper macro itself is not very important. (inner
loops are tend to do more work than this)
This patch make helper function to be out-of-lined.
inline out-of-line
.text 005c0680 005bf6a0
005c0680 - 005bf6a0 = FE0 = 4Kbytes.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
By using for_each_online_pgdat(), pgdat_list is not necessary now. This patch
removes it.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch defines for_each_online_pgdat() as a replacement of
for_each_pgdat()
Now, online nodes are managed by node_online_map. But for_each_pgdat()
uses pgdat_link to iterate over all nodes(pgdat). This means management
structure for online pgdat is duplicated.
I think using node_online_map for for_each_pgdat() is simple and sane
rather ather than pgdat_link. New macro is named as
for_each_online_pgdat(). Following patch will fix callers of
for_each_pgdat().
The bootmem allocater uses for_each_pgdat() before pgdat initialization. I
don't think it's sane. Following patch will fix it.
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes zone_mem_map.
pfn_to_page uses pgdat, page_to_pfn uses zone. page_to_pfn can use pgdat
instead of zone, which is only one user of zone_mem_map. By modifing it,
we can remove zone_mem_map.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There are 3 memory models, FLATMEM, DISCONTIGMEM, SPARSEMEM.
Each arch has its own page_to_pfn(), pfn_to_page() for each models.
But most of them can use the same arithmetic.
This patch adds asm-generic/memory_model.h, which includes generic
page_to_pfn(), pfn_to_page() definitions for each memory model.
When CONFIG_OUT_OF_LINE_PFN_TO_PAGE=y, out-of-line functions are
used instead of macro. This is enabled by some archs and reduces
text size.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Andi Kleen <ak@muc.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ian Molton <spyro@f2s.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Hirokazu Takata <takata.hirokazu@renesas.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp>
Cc: Chris Zankel <chris@zankel.net>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
GFP_ZONETYPES calculate from GFP_ZONEMASK
GFP_ZONETYPES's value is directly related to the value of GFP_ZONEMASK. It
takes one of two forms depending whether the top bit of GFP_ZONEMASK is a
'loner'. Supply both forms, enabling the loner.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
GFP_ZONETYPES define using GFP_ZONEMASK and add commentry
Add commentry explaining the optimisation that we can apply to GFP_ZONETYPES
when the leftmost bit is a 'loaner', it can only be set in isolation.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Some bits for zone reclaim exists in 2.6.15 but they are not usable. This
patch fixes them up, removes unused code and makes zone reclaim usable.
Zone reclaim allows the reclaiming of pages from a zone if the number of
free pages falls below the watermarks even if other zones still have enough
pages available. Zone reclaim is of particular importance for NUMA
machines. It can be more beneficial to reclaim a page than taking the
performance penalties that come with allocating a page on a remote zone.
Zone reclaim is enabled if the maximum distance to another node is higher
than RECLAIM_DISTANCE, which may be defined by an arch. By default
RECLAIM_DISTANCE is 20. 20 is the distance to another node in the same
component (enclosure or motherboard) on IA64. The meaning of the NUMA
distance information seems to vary by arch.
If zone reclaim is not successful then no further reclaim attempts will
occur for a certain time period (ZONE_RECLAIM_INTERVAL).
This patch was discussed before. See
http://marc.theaimsgroup.com/?l=linux-kernel&m=113519961504207&w=2http://marc.theaimsgroup.com/?l=linux-kernel&m=113408418232531&w=2http://marc.theaimsgroup.com/?l=linux-kernel&m=113389027420032&w=2http://marc.theaimsgroup.com/?l=linux-kernel&m=113380938612205&w=2
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
____cacheline_maxaligned_in_smp is currently used to align critical structures
and avoid false sharing. It uses per-arch L1_CACHE_SHIFT_MAX and people find
L1_CACHE_SHIFT_MAX useless.
However, we have been using ____cacheline_maxaligned_in_smp to align
structures on the internode cacheline size. As per Andi's suggestion,
following patch kills ____cacheline_maxaligned_in_smp and introduces
INTERNODE_CACHE_SHIFT, which defaults to L1_CACHE_SHIFT for all arches.
Arches needing L3/Internode cacheline alignment can define
INTERNODE_CACHE_SHIFT in the arch asm/cache.h. Patch replaces
____cacheline_maxaligned_in_smp with ____cacheline_internodealigned_in_smp
With this patch, L1_CACHE_SHIFT_MAX can be killed
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
As recently there has been lot of traffic on the right values for batch and
high water marks for per_cpu_pagelists. This patch makes these two
variables configurable through /proc interface.
A new tunable /proc/sys/vm/percpu_pagelist_fraction is added. This entry
controls the fraction of pages at most in each zone that are allocated for
each per cpu page list. The min value for this is 8. It means that we
don't allow more than 1/8th of pages in each zone to be allocated in any
single per_cpu_pagelist.
The batch value of each per cpu pagelist is also updated as a result. It
is set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8)
Signed-off-by: Rohit Seth <rohit.seth@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There are numerous places we check whether a zone is populated or not.
Provide a helper function to check for populated zones and convert all
checks for zone->present_pages.
Signed-off-by: Con Kolivas <kernel@kolivas.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add dma32 to zone statistics. Also attempt to arrange struct page_state a
bit better (visually).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Before SPARSEMEM is initialised we cannot provide an efficient pfn_to_nid()
implmentation; before initialisation is complete we use early_pfn_to_nid()
to provide location information. Until recently there was no non-init user
of this functionality. Provide a post init pfn_to_nid() implementation.
Note that this implmentation assumes that the pfn passed has been validated
with pfn_valid(). The current single user of this function already has
this check.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There are three places we define pfn_to_nid(). Two in linux/mmzone.h and one
in asm/mmzone.h. These in essence represent the three memory models. The
definition in linux/mmzone.h under !NEED_MULTIPLE_NODES is both the FLATMEM
definition and the optimisation for single NUMA nodes; the one under SPARSEMEM
is the NUMA sparsemem one; the one in asm/mmzone.h under DISCONTIGMEM is the
discontigmem one. This is not in the least bit obvious, particularly the
connection between the non-NUMA optimisations and the memory models.
Two patches:
flatmem-split-out-memory-model: simplifies the selection of pfn_to_nid()
implementations. The selection is based primarily off the memory model
selected. Optimisations for non-NUMA are applied where needed.
sparse-provide-pfn_to_nid: implement pfn_to_nid() for SPARSEMEM
This patch:
pfn_to_nid is memory model specific
The pfn_to_nid() call is memory model specific. It represents the locality
identifier for the memory passed. Classically this would be a NUMA node,
but not a chunk of memory under DISCONTIGMEM.
The SPARSEMEM and FLATMEM memory model non-NUMA versions of pfn_to_nid()
are folded together under NEED_MULTIPLE_NODES, while DISCONTIGMEM has its
own optimisation. This is all very confusing.
This patch splits out each implementation of pfn_to_nid() so that we can
see them and the optimisations to each.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The NODES_SPAN_OTHER_NODES config option was created so that DISCONTIGMEM
could handle pSeries numa layouts. However, support for DISCONTIGMEM has
been replaced by SPARSEMEM on powerpc. As a result, this config option and
supporting code is no longer needed.
I have already sent a patch to Paul that removes the option from powerpc
specific code. This removes the arch independent piece. Doesn't really
matter which is applied first.
Signed-off-by: Mike Kravetz <kravetz@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
pfn_to_pgdat() isn't used in common code. Remove definition.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
kvaddr_to_nid() isn't used in common code nor in i386 code. Remove these
definitions.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There was some confusion about the different zone usage, this should fix
up the resulting mess in the GFP zonemask handling.
The different zone usage is still confusing (it's very easy to mix up
the individual zone numbers with the GFP zone _list_ numbers), so we
might want to clean up some of this in the future, but in the meantime
this should fix the actual problems.
Acked-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Not go from the CPU number to an mapping array.
Mode number is often used now in fast paths.
This also adds a generic numa_node_id to all the topology includes
Suggested by Eric Dumazet
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Has been introduced for x86-64 at some point to save memory
in struct page, but has been obsolete for some time. Just
remove it.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Add a new 4GB GFP_DMA32 zone between the GFP_DMA and GFP_NORMAL zones.
As a bit of historical background: when the x86-64 port
was originally designed we had some discussion if we should
use a 16MB DMA zone like i386 or a 4GB DMA zone like IA64 or
both. Both was ruled out at this point because it was in early
2.4 when VM is still quite shakey and had bad troubles even
dealing with one DMA zone. We settled on the 16MB DMA zone mainly
because we worried about older soundcards and the floppy.
But this has always caused problems since then because
device drivers had trouble getting enough DMA able memory. These days
the VM works much better and the wide use of NUMA has proven
it can deal with many zones successfully.
So this patch adds both zones.
This helps drivers who need a lot of memory below 4GB because
their hardware is not accessing more (graphic drivers - proprietary
and free ones, video frame buffer drivers, sound drivers etc.).
Previously they could only use IOMMU+16MB GFP_DMA, which
was not enough memory.
Another common problem is that hardware who has full memory
addressing for >4GB misses it for some control structures in memory
(like transmit rings or other metadata). They tended to allocate memory
in the 16MB GFP_DMA or the IOMMU/swiotlb then using pci_alloc_consistent,
but that can tie up a lot of precious 16MB GFPDMA/IOMMU/swiotlb memory
(even on AMD systems the IOMMU tends to be quite small) especially if you have
many devices. With the new zone pci_alloc_consistent can just put
this stuff into memory below 4GB which works better.
One argument was still if the zone should be 4GB or 2GB. The main
motivation for 2GB would be an unnamed not so unpopular hardware
raid controller (mostly found in older machines from a particular four letter
company) who has a strange 2GB restriction in firmware. But
that one works ok with swiotlb/IOMMU anyways, so it doesn't really
need GFP_DMA32. I chose 4GB to be compatible with IA64 and because
it seems to be the most common restriction.
The new zone is so far added only for x86-64.
For other architectures who don't set up this
new zone nothing changes. Architectures can set a compatibility
define in Kconfig CONFIG_DMA_IS_DMA32 that will define GFP_DMA32
as GFP_DMA. Otherwise it's a nop because on 32bit architectures
it's normally not needed because GFP_NORMAL (=0) is DMA able
enough.
One problem is still that GFP_DMA means different things on different
architectures. e.g. some drivers used to have #ifdef ia64 use GFP_DMA
(trusting it to be 4GB) #elif __x86_64__ (use other hacks like
the swiotlb because 16MB is not enough) ... . This was quite
ugly and is now obsolete.
These should be now converted to use GFP_DMA32 unconditionally. I haven't done
this yet. Or best only use pci_alloc_consistent/dma_alloc_coherent
which will use GFP_DMA32 transparently.
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Clean up of __alloc_pages.
Restoration of previous behaviour, plus further cleanups by introducing an
'alloc_flags', removing the last of should_reclaim_zone.
Signed-off-by: Rohit Seth <rohit.seth@intel.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
See the "fixup bad_range()" patch for more information, but this actually
creates a the lock to protect things making assumptions about a zone's size
staying constant at runtime.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
pgdat->node_size_lock is basically only neeeded in one place in the normal
code: show_mem(), which is the arch-specific sysrq-m printing function.
Strictly speaking, the architectures not doing memory hotplug do no need this
locking in show_mem(). However, they are all included for completeness. This
should also make any future consolidation of all of the implementations a
little more straightforward.
This lock is also held in the sparsemem code during a memory removal, as
sections are invalidated. This is the place there pfn_valid() is made false
for a memory area that's being removed. The lock is only required when doing
pfn_valid() operations on memory which the user does not already have a
reference on the page, such as in show_mem().
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
A little helper that we use in the hotplug code.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This splits up sparse_index_alloc() into two pieces. This is needed
because we'll allocate the memory for the second level in a different place
from where we actually consume it to keep the allocation from happening
underneath a lock
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
With cleanups from Dave Hansen <haveblue@us.ibm.com>
SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to
mem_sections. This two level layout scheme is able to achieve smaller
memory requirements for SPARSEMEM with the tradeoff of an additional shift
and load when fetching the memory section. The current SPARSEMEM
implementation is a one dimensional array of mem_sections which is the
default SPARSEMEM configuration. The patch attempts isolates the
implementation details of the physical layout of the sparsemem section
array.
SPARSEMEM_EXTREME requires bootmem to be functioning at the time of
memory_present() calls. This is not always feasible, so architectures
which do not need it may allocate everything statically by using
SPARSEMEM_STATIC.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
A new option for SPARSEMEM is ARCH_SPARSEMEM_EXTREME. Architecture
platforms with a very sparse physical address space would likely want to
select this option. For those architecture platforms that don't select the
option, the code generated is equivalent to SPARSEMEM currently in -mm.
I'll be posting a patch on ia64 ml which uses this new SPARSEMEM feature.
ARCH_SPARSEMEM_EXTREME makes mem_section a one dimensional array of
pointers to mem_sections. This two level layout scheme is able to achieve
smaller memory requirements for SPARSEMEM with the tradeoff of an
additional shift and load when fetching the memory section. The current
SPARSEMEM -mm implementation is a one dimensional array of mem_sections
which is the default SPARSEMEM configuration. The patch attempts isolates
the implementation details of the physical layout of the sparsemem section
array.
ARCH_SPARSEMEM_EXTREME depends on 64BIT and is by default boolean false.
I've boot tested under aim load ia64 configured for ARCH_SPARSEMEM_EXTREME.
I've also boot tested a 4 way Opteron machine with !ARCH_SPARSEMEM_EXTREME
and tested with aim.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make sparse's initalization be accessible at runtime. This allows sparse
mappings to be created after boot in a hotplug situation.
This patch is separated from the previous one just to give an indication how
much of the sparse infrastructure is *just* for hotplug memory.
The section_mem_map doesn't really store a pointer. It stores something that
is convenient to do some math against to get a pointer. It isn't valid to
just do *section_mem_map, so I don't think it should be stored as a pointer.
There are a couple of things I'd like to store about a section. First of all,
the fact that it is !NULL does not mean that it is present. There could be
such a combination where section_mem_map *is* NULL, but the math gets you
properly to a real mem_map. So, I don't think that check is safe.
Since we're storing 32-bit-aligned structures, we have a few bits in the
bottom of the pointer to play with. Use one bit to encode whether there's
really a mem_map there, and the other one to tell whether there's a valid
section there. We need to distinguish between the two because sometimes
there's a gap between when a section is discovered to be present and when we
can get the mem_map for it.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Jack Steiner <steiner@sgi.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The part of the sparsemem patch which modifies memmap_init_zone() has recently
become a problem. It changes behavior so that there is a call to
pfn_to_page() for each individual page inside of a node's range:
node_start_pfn through node_end_pfn. It used to simply do this once, at the
beginning of the node, but having sparsemem's non-contiguous mem_map[]s inside
of a node made it necessary to change.
Mike Kravetz recently wrote a patch which made the NUMA code accept some new
kinds of layouts. The system's memory was laid out like this, with node 0's
memory in two pieces: one before and one after node 1's memory:
Node 0: +++++ +++++
Node 1: +++++
Previous behavior before Mike's patch was to assign nodes like this:
Node 0: 00000 XXXXX
Node 1: 11111
Where the 'X' areas were simply thrown away. The new behavior was to make the
pg_data_t span node 0 across all of its areas, including areas that are really
node 1's: Node 0: 000000000000000 Node 1: 11111
This wastes a little bit of mem_map space, but ends up being OK, and more
fully utilizes the system's memory. memmap_init_zone() initializes all of the
"struct page"s for node 0, even for the "hole", but those never get used,
because there is no pfn_to_page() that resolves to those pages. However, only
calling pfn_to_page() once, memmap_init_zone() always uses the pages that were
allocated for node0->node_mem_map because:
struct page *start = pfn_to_page(start_pfn);
// effectively start = &node->node_mem_map[0]
for (page = start; page < (start + size); page++) {
init_page_here();...
page++;
}
Slow, and wasteful, but generally harmless.
But, modify that to call pfn_to_page() for each loop iteration (like sparsemem
does):
for (pfn = start_pfn; pfn < < (start_pfn + size); pfn++++) {
page = pfn_to_page(pfn);
}
And you end up trying to initialize node 1's pages too early, along with bogus
data from node 0. This patch checks for those weird layouts and declines to
touch the pages, making the more frequent pfn_to_page() calls OK to do.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of
mem_map[] is needed by discontiguous memory machines (like in the old
CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem
replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually
become a complete replacement.
A significant advantage over DISCONTIGMEM is that it's completely separated
from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA
and DISCONTIG are often confused.
Another advantage is that sparse doesn't require each NUMA node's ranges to be
contiguous. It can handle overlapping ranges between nodes with no problems,
where DISCONTIGMEM currently throws away that memory.
Sparsemem uses an array to provide different pfn_to_page() translations for
each SECTION_SIZE area of physical memory. This is what allows the mem_map[]
to be chopped up.
In order to do quick pfn_to_page() operations, the section number of the page
is encoded in page->flags. Part of the sparsemem infrastructure enables
sharing of these bits more dynamically (at compile-time) between the
page_zone() and sparsemem operations. However, on 32-bit architectures, the
number of bits is quite limited, and may require growing the size of the
page->flags type in certain conditions. Several things might force this to
occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of
memory), an increase in the physical address space, or an increase in the
number of used page->flags.
One thing to note is that, once sparsemem is present, the NUMA node
information no longer needs to be stored in the page->flags. It might provide
speed increases on certain platforms and will be stored there if there is
room. But, if out of room, an alternate (theoretically slower) mechanism is
used.
This patch introduces CONFIG_FLATMEM. It is used in almost all cases where
there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM
often have to compile out the same areas of code.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Provide a default implementation for early_pfn_to_nid returning node 0. Allow
architectures to override this with their own implementation out of
asm/mmzone.h.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There is some confusion that arose when working on SPARSEMEM patch between
what is needed for DISCONTIG vs. NUMA.
Multiple pg_data_t's are needed for DISCONTIGMEM or NUMA, independently.
All of the current NUMA implementations require an implementation of
DISCONTIG. Because of this, quite a lot of code which is really needed for
NUMA is actually under DISCONTIG #ifdefs. For SPARSEMEM, we changed some
of these #ifdefs to CONFIG_NUMA, but that broke the DISCONTIG=y and NUMA=n
case.
Introducing this new NEED_MULTIPLE_NODES config option allows code that is
needed for both NUMA or DISCONTIG to be separated out from code that is
specific to DISCONTIG.
One great advantage of this approach is that it doesn't require every
architecture to be converted over. All of the current implementations
should "just work", only the ones implementing SPARSEMEM will have to be
fixed up.
The change to free_area_init() makes it work inside, or out of the new
config option.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Generify the value fields in the page_flags. The aim is to allow the location
and size of these fields to be varied. Additionally we want to move away from
fixed allocations per field whilst still enforcing the overall bit utilisation
limits. We rely on the compiler to spot and optimise the accessor functions.
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch effectively eliminates direct use of pgdat->node_mem_map outside
of the DISCONTIG code. On a flat memory system, these fields aren't
currently used, neither are they on a sparsemem system.
There was also a node_mem_map(nid) macro on many architectures. Its use
along with the use of ->node_mem_map itself was not consistent. It has
been removed in favor of two new, more explicit, arch-independent macros:
pgdat_page_nr(pgdat, pagenr)
nid_page_nr(nid, pagenr)
I called them "pgdat" and "nid" because we overload the term "node" to mean
"NUMA node", "DISCONTIG node" or "pg_data_t" in very confusing ways. I
believe the newer names are much clearer.
These macros can be overridden in the sparsemem case with a theoretically
slower operation using node_start_pfn and pfn_to_page(), instead. We could
make this the only behavior if people want, but I don't want to change too
much at once. One thing at a time.
This patch removes more code than it adds.
Compile tested on alpha, alpha discontig, arm, arm-discontig, i386, i386
generic, NUMAQ, Summit, ppc64, ppc64 discontig, and x86_64. Full list
here: http://sr71.net/patches/2.6.12/2.6.12-rc1-mhp2/configs/
Boot tested on NUMAQ, x86 SMP and ppc64 power4/5 LPARs.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Martin J. Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch modifies the way pagesets in struct zone are managed.
Each zone has a per-cpu array of pagesets. So any particular CPU has some
memory in each zone structure which belongs to itself. Even if that CPU is
not local to that zone.
So the patch relocates the pagesets for each cpu to the node that is nearest
to the cpu instead of allocating the pagesets in the (possibly remote) target
zone. This means that the operations to manage pages on remote zone can be
done with information available locally.
We play a macro trick so that non-NUMA pmachines avoid the additional
pointer chase on the page allocator fastpath.
AIM7 benchmark on a 32 CPU SGI Altix
w/o patches:
Tasks jobs/min jti jobs/min/task real cpu
1 484.68 100 484.6769 12.01 1.97 Fri Mar 25 11:01:42 2005
100 27140.46 89 271.4046 21.44 148.71 Fri Mar 25 11:02:04 2005
200 30792.02 82 153.9601 37.80 296.72 Fri Mar 25 11:02:42 2005
300 32209.27 81 107.3642 54.21 451.34 Fri Mar 25 11:03:37 2005
400 34962.83 78 87.4071 66.59 588.97 Fri Mar 25 11:04:44 2005
500 31676.92 75 63.3538 91.87 742.71 Fri Mar 25 11:06:16 2005
600 36032.69 73 60.0545 96.91 885.44 Fri Mar 25 11:07:54 2005
700 35540.43 77 50.7720 114.63 1024.28 Fri Mar 25 11:09:49 2005
800 33906.70 74 42.3834 137.32 1181.65 Fri Mar 25 11:12:06 2005
900 34120.67 73 37.9119 153.51 1325.26 Fri Mar 25 11:14:41 2005
1000 34802.37 74 34.8024 167.23 1465.26 Fri Mar 25 11:17:28 2005
with slab API changes and pageset patch:
Tasks jobs/min jti jobs/min/task real cpu
1 485.00 100 485.0000 12.00 1.96 Fri Mar 25 11:46:18 2005
100 28000.96 89 280.0096 20.79 150.45 Fri Mar 25 11:46:39 2005
200 32285.80 79 161.4290 36.05 293.37 Fri Mar 25 11:47:16 2005
300 40424.15 84 134.7472 43.19 438.42 Fri Mar 25 11:47:59 2005
400 39155.01 79 97.8875 59.46 590.05 Fri Mar 25 11:48:59 2005
500 37881.25 82 75.7625 76.82 730.19 Fri Mar 25 11:50:16 2005
600 39083.14 78 65.1386 89.35 872.79 Fri Mar 25 11:51:46 2005
700 38627.83 77 55.1826 105.47 1022.46 Fri Mar 25 11:53:32 2005
800 39631.94 78 49.5399 117.48 1169.94 Fri Mar 25 11:55:30 2005
900 36903.70 79 41.0041 141.94 1310.78 Fri Mar 25 11:57:53 2005
1000 36201.23 77 36.2012 160.77 1458.31 Fri Mar 25 12:00:34 2005
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Shobhit Dayal <shobhit@calsoftinc.com>
Signed-off-by: Shai Fultheim <Shai@Scalex86.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
When early zone reclaim is turned on the LRU is scanned more frequently when a
zone is low on memory. This limits when the zone reclaim can be called by
skipping the scan if another thread (either via kswapd or sync reclaim) is
already reclaiming from the zone.
Signed-off-by: Martin Hicks <mort@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This is the core of the (much simplified) early reclaim. The goal of this
patch is to reclaim some easily-freed pages from a zone before falling back
onto another zone.
One of the major uses of this is NUMA machines. With the default allocator
behavior the allocator would look for memory in another zone, which might be
off-node, before trying to reclaim from the current zone.
This adds a zone tuneable to enable early zone reclaim. It is selected on a
per-zone basis and is turned on/off via syscall.
Adding some extra throttling on the reclaim was also required (patch
4/4). Without the machine would grind to a crawl when doing a "make -j"
kernel build. Even with this patch the System Time is higher on
average, but it seems tolerable. Here are some numbers for kernbench
runs on a 2-node, 4cpu, 8Gig RAM Altix in the "make -j" run:
wall user sys %cpu ctx sw. sleeps
---- ---- --- ---- ------ ------
No patch 1009 1384 847 258 298170 504402
w/patch, no reclaim 880 1376 667 288 254064 396745
w/patch & reclaim 1079 1385 926 252 291625 548873
These numbers are the average of 2 runs of 3 "make -j" runs done right
after system boot. Run-to-run variability for "make -j" is huge, so
these numbers aren't terribly useful except to seee that with reclaim
the benchmark still finishes in a reasonable amount of time.
I also looked at the NUMA hit/miss stats for the "make -j" runs and the
reclaim doesn't make any difference when the machine is thrashing away.
Doing a "make -j8" on a single node that is filled with page cache pages
takes 700 seconds with reclaim turned on and 735 seconds without reclaim
(due to remote memory accesses).
The simple zone_reclaim syscall program is at
http://www.bork.org/~mort/sgi/zone_reclaim.c
Signed-off-by: Martin Hicks <mort@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch implements a number of smp_processor_id() cleanup ideas that
Arjan van de Ven and I came up with.
The previous __smp_processor_id/_smp_processor_id/smp_processor_id API
spaghetti was hard to follow both on the implementational and on the
usage side.
Some of the complexity arose from picking wrong names, some of the
complexity comes from the fact that not all architectures defined
__smp_processor_id.
In the new code, there are two externally visible symbols:
- smp_processor_id(): debug variant.
- raw_smp_processor_id(): nondebug variant. Replaces all existing
uses of _smp_processor_id() and __smp_processor_id(). Defined
by every SMP architecture in include/asm-*/smp.h.
There is one new internal symbol, dependent on DEBUG_PREEMPT:
- debug_smp_processor_id(): internal debug variant, mapped to
smp_processor_id().
Also, i moved debug_smp_processor_id() from lib/kernel_lock.c into a new
lib/smp_processor_id.c file. All related comments got updated and/or
clarified.
I have build/boot tested the following 8 .config combinations on x86:
{SMP,UP} x {PREEMPT,!PREEMPT} x {DEBUG_PREEMPT,!DEBUG_PREEMPT}
I have also build/boot tested x64 on UP/PREEMPT/DEBUG_PREEMPT. (Other
architectures are untested, but should work just fine.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
Mel Gorman