提交 dc644a07 编写于 作者: H Hugh Dickins 提交者: Linus Torvalds

mm: add three more cond_resched() in swapoff

Add a cond_resched() in the unuse_pmd_range() loop (so as to call it
even when pmd none or trans_huge, like zap_pmd_range() does); and in the
unuse_mm() loop (since that might skip over many vmas).  shmem_unuse()
and radix_tree_locate_item() look good enough already.

Those were the obvious places, but in fact the stalls came from
find_next_to_unuse(), which sometimes scans through many unused entries.
Apply scan_swap_map()'s LATENCY_LIMIT of 256 there too; and only go off
to test frontswap_map when a used entry is found.

Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1612052155140.13021@eggly.anvilsSigned-off-by: NHugh Dickins <hughd@google.com>
Reported-by: NEric Dumazet <edumazet@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 a6de734b
......@@ -1234,6 +1234,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
pmd = pmd_offset(pud, addr);
do {
cond_resched();
next = pmd_addr_end(addr, end);
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
continue;
......@@ -1313,6 +1314,7 @@ static int unuse_mm(struct mm_struct *mm,
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma->anon_vma && (ret = unuse_vma(vma, entry, page)))
break;
cond_resched();
}
up_read(&mm->mmap_sem);
return (ret < 0)? ret: 0;
......@@ -1350,15 +1352,12 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
prev = 0;
i = 1;
}
if (frontswap) {
if (frontswap_test(si, i))
break;
else
continue;
}
count = READ_ONCE(si->swap_map[i]);
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
if (!frontswap || frontswap_test(si, i))
break;
if ((i % LATENCY_LIMIT) == 0)
cond_resched();
}
return i;
}
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册