mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-07 15:36:42 +07:00
38d8b4e6bd
Patch series "THP swap: Delay splitting THP during swapping out", v11. This patchset is to optimize the performance of Transparent Huge Page (THP) swap. Recently, the performance of the storage devices improved so fast that we cannot saturate the disk bandwidth with single logical CPU when do page swap out even on a high-end server machine. Because the performance of the storage device improved faster than that of single logical CPU. And it seems that the trend will not change in the near future. On the other hand, the THP becomes more and more popular because of increased memory size. So it becomes necessary to optimize THP swap performance. The advantages of the THP swap support include: - Batch the swap operations for the THP to reduce lock acquiring/releasing, including allocating/freeing the swap space, adding/deleting to/from the swap cache, and writing/reading the swap space, etc. This will help improve the performance of the THP swap. - The THP swap space read/write will be 2M sequential IO. It is particularly helpful for the swap read, which are usually 4k random IO. This will improve the performance of the THP swap too. - It will help the memory fragmentation, especially when the THP is heavily used by the applications. The 2M continuous pages will be free up after THP swapping out. - It will improve the THP utilization on the system with the swap turned on. Because the speed for khugepaged to collapse the normal pages into the THP is quite slow. After the THP is split during the swapping out, it will take quite long time for the normal pages to collapse back into the THP after being swapped in. The high THP utilization helps the efficiency of the page based memory management too. There are some concerns regarding THP swap in, mainly because possible enlarged read/write IO size (for swap in/out) may put more overhead on the storage device. To deal with that, the THP swap in should be turned on only when necessary. For example, it can be selected via "always/never/madvise" logic, to be turned on globally, turned off globally, or turned on only for VMA with MADV_HUGEPAGE, etc. This patchset is the first step for the THP swap support. The plan is to delay splitting THP step by step, finally avoid splitting THP during the THP swapping out and swap out/in the THP as a whole. As the first step, in this patchset, the splitting huge page is delayed from almost the first step of swapping out to after allocating the swap space for the THP and adding the THP into the swap cache. This will reduce lock acquiring/releasing for the locks used for the swap cache management. With the patchset, the swap out throughput improves 15.5% (from about 3.73GB/s to about 4.31GB/s) in the vm-scalability swap-w-seq test case with 8 processes. The test is done on a Xeon E5 v3 system. The swap device used is a RAM simulated PMEM (persistent memory) device. To test the sequential swapping out, the test case creates 8 processes, which sequentially allocate and write to the anonymous pages until the RAM and part of the swap device is used up. This patch (of 5): In this patch, splitting huge page is delayed from almost the first step of swapping out to after allocating the swap space for the THP (Transparent Huge Page) and adding the THP into the swap cache. This will batch the corresponding operation, thus improve THP swap out throughput. This is the first step for the THP swap optimization. The plan is to delay splitting the THP step by step and avoid splitting the THP finally. In this patch, one swap cluster is used to hold the contents of each THP swapped out. So, the size of the swap cluster is changed to that of the THP (Transparent Huge Page) on x86_64 architecture (512). For other architectures which want such THP swap optimization, ARCH_USES_THP_SWAP_CLUSTER needs to be selected in the Kconfig file for the architecture. In effect, this will enlarge swap cluster size by 2 times on x86_64. Which may make it harder to find a free cluster when the swap space becomes fragmented. So that, this may reduce the continuous swap space allocation and sequential write in theory. The performance test in 0day shows no regressions caused by this. In the future of THP swap optimization, some information of the swapped out THP (such as compound map count) will be recorded in the swap_cluster_info data structure. The mem cgroup swap accounting functions are enhanced to support charge or uncharge a swap cluster backing a THP as a whole. The swap cluster allocate/free functions are added to allocate/free a swap cluster for a THP. A fair simple algorithm is used for swap cluster allocation, that is, only the first swap device in priority list will be tried to allocate the swap cluster. The function will fail if the trying is not successful, and the caller will fallback to allocate a single swap slot instead. This works good enough for normal cases. If the difference of the number of the free swap clusters among multiple swap devices is significant, it is possible that some THPs are split earlier than necessary. For example, this could be caused by big size difference among multiple swap devices. The swap cache functions is enhanced to support add/delete THP to/from the swap cache as a set of (HPAGE_PMD_NR) sub-pages. This may be enhanced in the future with multi-order radix tree. But because we will split the THP soon during swapping out, that optimization doesn't make much sense for this first step. The THP splitting functions are enhanced to support to split THP in swap cache during swapping out. The page lock will be held during allocating the swap cluster, adding the THP into the swap cache and splitting the THP. So in the code path other than swapping out, if the THP need to be split, the PageSwapCache(THP) will be always false. The swap cluster is only available for SSD, so the THP swap optimization in this patchset has no effect for HDD. [ying.huang@intel.com: fix two issues in THP optimize patch] Link: http://lkml.kernel.org/r/87k25ed8zo.fsf@yhuang-dev.intel.com [hannes@cmpxchg.org: extensive cleanups and simplifications, reduce code size] Link: http://lkml.kernel.org/r/20170515112522.32457-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Suggested-by: Andrew Morton <akpm@linux-foundation.org> [for config option] Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> [for changes in huge_memory.c and huge_mm.h] Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Shaohua Li <shli@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
233 lines
5.2 KiB
C
233 lines
5.2 KiB
C
#include <linux/swap_cgroup.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/swapops.h> /* depends on mm.h include */
|
|
|
|
static DEFINE_MUTEX(swap_cgroup_mutex);
|
|
struct swap_cgroup_ctrl {
|
|
struct page **map;
|
|
unsigned long length;
|
|
spinlock_t lock;
|
|
};
|
|
|
|
static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
|
|
|
|
struct swap_cgroup {
|
|
unsigned short id;
|
|
};
|
|
#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup))
|
|
|
|
/*
|
|
* SwapCgroup implements "lookup" and "exchange" operations.
|
|
* In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
|
|
* against SwapCache. At swap_free(), this is accessed directly from swap.
|
|
*
|
|
* This means,
|
|
* - we have no race in "exchange" when we're accessed via SwapCache because
|
|
* SwapCache(and its swp_entry) is under lock.
|
|
* - When called via swap_free(), there is no user of this entry and no race.
|
|
* Then, we don't need lock around "exchange".
|
|
*
|
|
* TODO: we can push these buffers out to HIGHMEM.
|
|
*/
|
|
|
|
/*
|
|
* allocate buffer for swap_cgroup.
|
|
*/
|
|
static int swap_cgroup_prepare(int type)
|
|
{
|
|
struct page *page;
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
unsigned long idx, max;
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
for (idx = 0; idx < ctrl->length; idx++) {
|
|
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
|
|
if (!page)
|
|
goto not_enough_page;
|
|
ctrl->map[idx] = page;
|
|
|
|
if (!(idx % SWAP_CLUSTER_MAX))
|
|
cond_resched();
|
|
}
|
|
return 0;
|
|
not_enough_page:
|
|
max = idx;
|
|
for (idx = 0; idx < max; idx++)
|
|
__free_page(ctrl->map[idx]);
|
|
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static struct swap_cgroup *__lookup_swap_cgroup(struct swap_cgroup_ctrl *ctrl,
|
|
pgoff_t offset)
|
|
{
|
|
struct page *mappage;
|
|
struct swap_cgroup *sc;
|
|
|
|
mappage = ctrl->map[offset / SC_PER_PAGE];
|
|
sc = page_address(mappage);
|
|
return sc + offset % SC_PER_PAGE;
|
|
}
|
|
|
|
static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
|
|
struct swap_cgroup_ctrl **ctrlp)
|
|
{
|
|
pgoff_t offset = swp_offset(ent);
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
ctrl = &swap_cgroup_ctrl[swp_type(ent)];
|
|
if (ctrlp)
|
|
*ctrlp = ctrl;
|
|
return __lookup_swap_cgroup(ctrl, offset);
|
|
}
|
|
|
|
/**
|
|
* swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
|
|
* @ent: swap entry to be cmpxchged
|
|
* @old: old id
|
|
* @new: new id
|
|
*
|
|
* Returns old id at success, 0 at failure.
|
|
* (There is no mem_cgroup using 0 as its id)
|
|
*/
|
|
unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
|
|
unsigned short old, unsigned short new)
|
|
{
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
struct swap_cgroup *sc;
|
|
unsigned long flags;
|
|
unsigned short retval;
|
|
|
|
sc = lookup_swap_cgroup(ent, &ctrl);
|
|
|
|
spin_lock_irqsave(&ctrl->lock, flags);
|
|
retval = sc->id;
|
|
if (retval == old)
|
|
sc->id = new;
|
|
else
|
|
retval = 0;
|
|
spin_unlock_irqrestore(&ctrl->lock, flags);
|
|
return retval;
|
|
}
|
|
|
|
/**
|
|
* swap_cgroup_record - record mem_cgroup for a set of swap entries
|
|
* @ent: the first swap entry to be recorded into
|
|
* @id: mem_cgroup to be recorded
|
|
* @nr_ents: number of swap entries to be recorded
|
|
*
|
|
* Returns old value at success, 0 at failure.
|
|
* (Of course, old value can be 0.)
|
|
*/
|
|
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
|
|
unsigned int nr_ents)
|
|
{
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
struct swap_cgroup *sc;
|
|
unsigned short old;
|
|
unsigned long flags;
|
|
pgoff_t offset = swp_offset(ent);
|
|
pgoff_t end = offset + nr_ents;
|
|
|
|
sc = lookup_swap_cgroup(ent, &ctrl);
|
|
|
|
spin_lock_irqsave(&ctrl->lock, flags);
|
|
old = sc->id;
|
|
for (;;) {
|
|
VM_BUG_ON(sc->id != old);
|
|
sc->id = id;
|
|
offset++;
|
|
if (offset == end)
|
|
break;
|
|
if (offset % SC_PER_PAGE)
|
|
sc++;
|
|
else
|
|
sc = __lookup_swap_cgroup(ctrl, offset);
|
|
}
|
|
spin_unlock_irqrestore(&ctrl->lock, flags);
|
|
|
|
return old;
|
|
}
|
|
|
|
/**
|
|
* lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
|
|
* @ent: swap entry to be looked up.
|
|
*
|
|
* Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
|
|
*/
|
|
unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
|
|
{
|
|
return lookup_swap_cgroup(ent, NULL)->id;
|
|
}
|
|
|
|
int swap_cgroup_swapon(int type, unsigned long max_pages)
|
|
{
|
|
void *array;
|
|
unsigned long array_size;
|
|
unsigned long length;
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
if (!do_swap_account)
|
|
return 0;
|
|
|
|
length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
|
|
array_size = length * sizeof(void *);
|
|
|
|
array = vzalloc(array_size);
|
|
if (!array)
|
|
goto nomem;
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
mutex_lock(&swap_cgroup_mutex);
|
|
ctrl->length = length;
|
|
ctrl->map = array;
|
|
spin_lock_init(&ctrl->lock);
|
|
if (swap_cgroup_prepare(type)) {
|
|
/* memory shortage */
|
|
ctrl->map = NULL;
|
|
ctrl->length = 0;
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
vfree(array);
|
|
goto nomem;
|
|
}
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
|
|
return 0;
|
|
nomem:
|
|
pr_info("couldn't allocate enough memory for swap_cgroup\n");
|
|
pr_info("swap_cgroup can be disabled by swapaccount=0 boot option\n");
|
|
return -ENOMEM;
|
|
}
|
|
|
|
void swap_cgroup_swapoff(int type)
|
|
{
|
|
struct page **map;
|
|
unsigned long i, length;
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
if (!do_swap_account)
|
|
return;
|
|
|
|
mutex_lock(&swap_cgroup_mutex);
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
map = ctrl->map;
|
|
length = ctrl->length;
|
|
ctrl->map = NULL;
|
|
ctrl->length = 0;
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
|
|
if (map) {
|
|
for (i = 0; i < length; i++) {
|
|
struct page *page = map[i];
|
|
if (page)
|
|
__free_page(page);
|
|
if (!(i % SWAP_CLUSTER_MAX))
|
|
cond_resched();
|
|
}
|
|
vfree(map);
|
|
}
|
|
}
|