NOTE: The patch is not fully complete yet, with this patch I just want to
present rough idea of what I am trying to achieve.

The patch does following :
1) Detect holes (of size EROFS_BLKSIZ) in uncompressed files.
2) Keep track of holes per file.

In-order to track holes, I used an array of size = (file_size / blocksize)
The array basically tracks number of holes before a particular logical file 
block.
e.g blks[i] = 10 meaning ith block has 10 holes before it.
If a particular block is a hole we set the index to '-1'.

how read logic will change:
1) currently we simply map read offset to a fs block.
2) with holes in place the calculation of block number would be:

   blkno = start_block + (offset >> block_size_shift) - (number of 
                                                         holes before block in 
which offset falls)

3) If a read offset falls inside a hole (which can be found using above array). 
We
   fill the user buffer with '\0' on the fly.

through this,block no. lookup would still be performed in constant time.

The biggest problem with this approach is - we have to store the hole tracking
array for every file to the disk.Which doesn't seems to be practical.we can use 
a linkedlist,
but that will make size of inode variable.

Signed-off-by: Pratik Shinde <pratikshinde...@gmail.com>
---
 lib/inode.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/lib/inode.c b/lib/inode.c
index 0e19b11..af31949 100644
--- a/lib/inode.c
+++ b/lib/inode.c
@@ -38,6 +38,61 @@ static unsigned char erofs_type_by_mode[S_IFMT >> S_SHIFT] = 
{
 
 struct list_head inode_hashtable[NR_INODE_HASHTABLE];
 
+
+#define IS_HOLE(start, end) (roundup(start, EROFS_BLKSIZ) == start &&  \
+                            roundup(end, EROFS_BLKSIZ) == end &&       \
+                           (end - start) % EROFS_BLKSIZ == 0)
+#define HOLE_BLK               -1
+unsigned int erofs_detect_holes(struct erofs_inode *inode, int *blks)
+{
+       int i, fd, st, en;
+       unsigned int nblocks;
+       erofs_off_t data, hole, len;
+
+       nblocks = inode->i_size / EROFS_BLKSIZ;
+       for (i = 0; i < nblocks; i++)
+               blks[i] = 0;
+       fd = open(inode->i_srcpath, O_RDONLY);
+       if (fd < 0) {
+               return -errno;
+       }
+       len = lseek(fd, 0, SEEK_END);
+       if (lseek(fd, 0, SEEK_SET) == -1)
+               return -errno;
+       data = 0;
+       while (data < len) {
+               hole = lseek(fd, data, SEEK_HOLE);
+               if (hole == len)
+                       break;
+               data = lseek(fd, hole, SEEK_DATA);
+               if (data < 0 || hole > data) {
+                       return -EINVAL;
+               }
+               if (IS_HOLE(hole, data)) {
+                       st = hole >> S_SHIFT;
+                       en = data >> S_SHIFT;
+                       nblocks -= (en - st);
+                       for (i = st; i < en; i++)
+                               blks[i] = HOLE_BLK;
+               }
+       }
+       return nblocks;
+}
+
+int erofs_fill_holedata(int *blks, unsigned int nblocks) {
+       int i, nholes = 0;
+       for (i = 0; i < nblocks; i++) {
+               if (blks[i] == -1)
+                       nholes++;
+               else {
+                       blks[i] = nholes;
+                       if (nholes >= (i + 1))
+                               return -EINVAL;
+               }
+       }
+       return 0;
+}
+
 void erofs_inode_manager_init(void)
 {
        unsigned int i;
@@ -305,6 +360,7 @@ static bool erofs_file_is_compressible(struct erofs_inode 
*inode)
 int erofs_write_file(struct erofs_inode *inode)
 {
        unsigned int nblocks, i;
+       int *blks;
        int ret, fd;
 
        if (!inode->i_size) {
@@ -322,7 +378,13 @@ int erofs_write_file(struct erofs_inode *inode)
        /* fallback to all data uncompressed */
        inode->datalayout = EROFS_INODE_FLAT_INLINE;
        nblocks = inode->i_size / EROFS_BLKSIZ;
-
+       blks = malloc(sizeof(int) * nblocks);
+       nblocks = erofs_detect_holes(inode, blks);
+       if (nblocks < 0)
+               return nblocks;
+       if ((ret = erofs_fill_holedata(blks, nblocks)) != 0) {
+               return ret;
+       }
        ret = __allocate_inode_bh_data(inode, nblocks);
        if (ret)
                return ret;
@@ -332,6 +394,8 @@ int erofs_write_file(struct erofs_inode *inode)
                return -errno;
 
        for (i = 0; i < nblocks; ++i) {
+               if (blks[i] == HOLE_BLK)
+                       continue;
                char buf[EROFS_BLKSIZ];
 
                ret = read(fd, buf, EROFS_BLKSIZ);
@@ -962,3 +1026,4 @@ struct erofs_inode *erofs_mkfs_build_tree_from_path(struct 
erofs_inode *parent,
        return erofs_mkfs_build_tree(inode);
 }
 
+
-- 
2.9.3

Reply via email to