[PATCH] swap: get_swap_page drop swap_list_lock

Rewrite get_swap_page to allocate in just the same sequence as before, but
without holding swap_list_lock across its scan_swap_map.  Decrement
nr_swap_pages and update swap_list.next in advance, while still holding
swap_list_lock.  Skip full devices by testing highest_bit.  Swapoff hold
swap_device_lock as well as swap_list_lock to clear SWP_WRITEOK.  Reduces lock
contention when there are parallel swap devices of the same priority.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Hugh Dickins 2005-09-03 15:54:37 -07:00 committed by Linus Torvalds
parent 89d09a2c80
commit fb4f88dcab
1 changed files with 35 additions and 38 deletions

View File

@ -139,7 +139,6 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
}
si->swap_map[offset] = 1;
si->inuse_pages++;
nr_swap_pages--;
si->cluster_next = offset+1;
return offset;
}
@ -150,50 +149,45 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
swp_entry_t get_swap_page(void)
{
struct swap_info_struct * p;
unsigned long offset;
swp_entry_t entry;
int type, wrapped = 0;
struct swap_info_struct *si;
pgoff_t offset;
int type, next;
int wrapped = 0;
entry.val = 0; /* Out of memory */
swap_list_lock();
type = swap_list.next;
if (type < 0)
goto out;
if (nr_swap_pages <= 0)
goto out;
goto noswap;
nr_swap_pages--;
while (1) {
p = &swap_info[type];
if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) {
swap_device_lock(p);
offset = scan_swap_map(p);
swap_device_unlock(p);
if (offset) {
entry = swp_entry(type,offset);
type = swap_info[type].next;
if (type < 0 ||
p->prio != swap_info[type].prio) {
swap_list.next = swap_list.head;
} else {
swap_list.next = type;
}
goto out;
}
for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
si = swap_info + type;
next = si->next;
if (next < 0 ||
(!wrapped && si->prio != swap_info[next].prio)) {
next = swap_list.head;
wrapped++;
}
type = p->next;
if (!wrapped) {
if (type < 0 || p->prio != swap_info[type].prio) {
type = swap_list.head;
wrapped = 1;
}
} else
if (type < 0)
goto out; /* out of swap space */
if (!si->highest_bit)
continue;
if (!(si->flags & SWP_WRITEOK))
continue;
swap_list.next = next;
swap_device_lock(si);
swap_list_unlock();
offset = scan_swap_map(si);
swap_device_unlock(si);
if (offset)
return swp_entry(type, offset);
swap_list_lock();
next = swap_list.next;
}
out:
nr_swap_pages++;
noswap:
swap_list_unlock();
return entry;
return (swp_entry_t) {0};
}
static struct swap_info_struct * swap_info_get(swp_entry_t entry)
@ -1105,8 +1099,11 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
}
nr_swap_pages -= p->pages;
total_swap_pages -= p->pages;
swap_device_lock(p);
p->flags &= ~SWP_WRITEOK;
swap_device_unlock(p);
swap_list_unlock();
current->flags |= PF_SWAPOFF;
err = try_to_unuse(type);
current->flags &= ~PF_SWAPOFF;