tmpfs: avoid a little creat and stat slowdown
LKP reports that v4.2 commitafa2db2fb6
("tmpfs: truncate prealloc blocks past i_size") causes a 14.5% slowdown in the AIM9 creat-clo benchmark. creat-clo does just what you'd expect from the name, and creat's O_TRUNC on 0-length file does indeed get into more overhead now shmem_setattr() tests "0 <= 0" instead of "0 < 0". I'm not sure how much we care, but I think it would not be too VW-like to add in a check for whether any pages (or swap) are allocated: if none are allocated, there's none to remove from the radix_tree. At first I thought that check would be good enough for the unmaps too, but no: we should not skip the unlikely case of unmapping pages beyond the new EOF, which were COWed from holes which have now been reclaimed, leaving none. This gives me an 8.5% speedup: on Haswell instead of LKP's Westmere, and running a debug config before and after: I hope those account for the lesser speedup. And probably someone has a benchmark where a thousand threads keep on stat'ing the same file repeatedly: forestall that report by adjusting v4.3 commit44a30220bc
("shmem: recalculate file inode when fstat") not to take the spinlock in shmem_getattr() when there's no work to do. Signed-off-by: Hugh Dickins <hughd@google.com> Reported-by: Ying Huang <ying.huang@linux.intel.com> Tested-by: Ying Huang <ying.huang@linux.intel.com> Cc: Josef Bacik <jbacik@fb.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
b72bdfa736
commit
d0424c429f
22
mm/shmem.c
22
mm/shmem.c
@ -548,12 +548,12 @@ static int shmem_getattr(struct vfsmount *mnt, struct dentry *dentry,
|
|||||||
struct inode *inode = dentry->d_inode;
|
struct inode *inode = dentry->d_inode;
|
||||||
struct shmem_inode_info *info = SHMEM_I(inode);
|
struct shmem_inode_info *info = SHMEM_I(inode);
|
||||||
|
|
||||||
spin_lock(&info->lock);
|
if (info->alloced - info->swapped != inode->i_mapping->nrpages) {
|
||||||
shmem_recalc_inode(inode);
|
spin_lock(&info->lock);
|
||||||
spin_unlock(&info->lock);
|
shmem_recalc_inode(inode);
|
||||||
|
spin_unlock(&info->lock);
|
||||||
|
}
|
||||||
generic_fillattr(inode, stat);
|
generic_fillattr(inode, stat);
|
||||||
|
|
||||||
return 0;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -586,10 +586,16 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
|
|||||||
}
|
}
|
||||||
if (newsize <= oldsize) {
|
if (newsize <= oldsize) {
|
||||||
loff_t holebegin = round_up(newsize, PAGE_SIZE);
|
loff_t holebegin = round_up(newsize, PAGE_SIZE);
|
||||||
unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
|
if (oldsize > holebegin)
|
||||||
shmem_truncate_range(inode, newsize, (loff_t)-1);
|
unmap_mapping_range(inode->i_mapping,
|
||||||
|
holebegin, 0, 1);
|
||||||
|
if (info->alloced)
|
||||||
|
shmem_truncate_range(inode,
|
||||||
|
newsize, (loff_t)-1);
|
||||||
/* unmap again to remove racily COWed private pages */
|
/* unmap again to remove racily COWed private pages */
|
||||||
unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
|
if (oldsize > holebegin)
|
||||||
|
unmap_mapping_range(inode->i_mapping,
|
||||||
|
holebegin, 0, 1);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user