[RFC PATCH v0 2/3] erofs-utils: mkfs: support multiple block compression
Gao Xiang
hsiangkao at aol.com
Wed Dec 30 19:47:27 AEDT 2020
From: Gao Xiang <hsiangkao at aol.com>
Store compressed block count to the compressed index so that EROFS
can compress from variable-sized input to variable-sized compressed
blocks and make the in-place decompression possible as well.
TODO: support storing compressed block count for compact indexes.
Signed-off-by: Gao Xiang <hsiangkao at aol.com>
---
include/erofs/internal.h | 1 +
include/erofs_fs.h | 19 ++++++++---
lib/compress.c | 70 ++++++++++++++++++++++++++--------------
3 files changed, 62 insertions(+), 28 deletions(-)
diff --git a/include/erofs/internal.h b/include/erofs/internal.h
index ac5b270329e2..de307e7f3d8f 100644
--- a/include/erofs/internal.h
+++ b/include/erofs/internal.h
@@ -104,6 +104,7 @@ static inline void erofs_sb_clear_##name(void) \
}
EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
+EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
#define EROFS_I_EA_INITED (1 << 0)
diff --git a/include/erofs_fs.h b/include/erofs_fs.h
index a69f179a51a5..fa9467a2608c 100644
--- a/include/erofs_fs.h
+++ b/include/erofs_fs.h
@@ -20,7 +20,10 @@
* be incompatible with this kernel version.
*/
#define EROFS_FEATURE_INCOMPAT_LZ4_0PADDING 0x00000001
-#define EROFS_ALL_FEATURE_INCOMPAT EROFS_FEATURE_INCOMPAT_LZ4_0PADDING
+#define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER 0x00000002
+#define EROFS_ALL_FEATURE_INCOMPAT \
+ (EROFS_FEATURE_INCOMPAT_LZ4_0PADDING | \
+ EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER)
/* 128-byte erofs on-disk super block */
struct erofs_super_block {
@@ -201,10 +204,11 @@ enum {
* bit 0 : COMPACTED_2B indexes (0 - off; 1 - on)
* e.g. for 4k logical cluster size, 4B if compacted 2B is off;
* (4B) + 2B + (4B) if compacted 2B is on.
+ * bit 1 : HEAD1 big pcluster (0 - off; 1 - on)
+ * bit 2 : (reserved now) HEAD2 big pcluster (0 - off; 1 - on)
*/
-#define Z_EROFS_ADVISE_COMPACTED_2B_BIT 0
-
-#define Z_EROFS_ADVISE_COMPACTED_2B (1 << Z_EROFS_ADVISE_COMPACTED_2B_BIT)
+#define Z_EROFS_ADVISE_COMPACTED_2B 0x0001
+#define Z_EROFS_ADVISE_BIG_PCLUSTER_1 0x0002
struct z_erofs_map_header {
__le32 h_reserved1;
@@ -261,6 +265,13 @@ enum {
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0
+/*
+ * D0_CBLKCNT will be marked _only_ for the 1st non-head lcluster to
+ * store the compressed block count of a compressed extent (aka. block
+ * count of a pcluster).
+ */
+#define Z_EROFS_VLE_DI_D0_CBLKCNT 0x8000
+
struct z_erofs_vle_decompressed_index {
__le16 di_advise;
/* where to decompress in the head cluster */
diff --git a/lib/compress.c b/lib/compress.c
index 86db940b6edd..f340f432c6b7 100644
--- a/lib/compress.c
+++ b/lib/compress.c
@@ -29,8 +29,8 @@ struct z_erofs_vle_compress_ctx {
u8 queue[EROFS_CONFIG_COMPR_MAX_SZ * 2];
unsigned int head, tail;
-
- erofs_blk_t blkaddr; /* pointing to the next blkaddr */
+ unsigned int compressedblks;
+ erofs_blk_t blkaddr; /* pointing to the next blkaddr */
u16 clusterofs;
};
@@ -89,7 +89,13 @@ static void vle_write_indexes(struct z_erofs_vle_compress_ctx *ctx,
}
do {
- if (d0) {
+ /* XXX: big pcluster feature should be per-inode */
+ if (d0 == 1 && cfg.c_physical_clusterblks > 1) {
+ type = Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD;
+ di.di_u.delta[0] = cpu_to_le16(ctx->compressedblks |
+ Z_EROFS_VLE_DI_D0_CBLKCNT);
+ di.di_u.delta[1] = cpu_to_le16(d1);
+ } else if (d0) {
type = Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD;
di.di_u.delta[0] = cpu_to_le16(d0);
@@ -115,9 +121,8 @@ static void vle_write_indexes(struct z_erofs_vle_compress_ctx *ctx,
ctx->clusterofs = clusterofs + count;
}
-static int write_uncompressed_block(struct z_erofs_vle_compress_ctx *ctx,
- unsigned int *len,
- char *dst)
+static int write_uncompressed_extent(struct z_erofs_vle_compress_ctx *ctx,
+ unsigned int *len, char *dst)
{
int ret;
unsigned int count;
@@ -148,17 +153,19 @@ static int vle_compress_one(struct erofs_inode *inode,
struct z_erofs_vle_compress_ctx *ctx,
bool final)
{
+ const unsigned int pclusterblks = cfg.c_physical_clusterblks;
+ const unsigned int pclustersize = pclusterblks * EROFS_BLKSIZ;
struct erofs_compress *const h = &compresshandle;
unsigned int len = ctx->tail - ctx->head;
unsigned int count;
int ret;
- static char dstbuf[EROFS_BLKSIZ * 2];
+ static char dstbuf[EROFS_CONFIG_COMPR_MAX_SZ + EROFS_BLKSIZ];
char *const dst = dstbuf + EROFS_BLKSIZ;
while (len) {
bool raw;
- if (len <= EROFS_BLKSIZ) {
+ if (len <= pclustersize) {
if (final)
goto nocompression;
break;
@@ -167,7 +174,7 @@ static int vle_compress_one(struct erofs_inode *inode,
count = len;
ret = erofs_compress_destsize(h, compressionlevel,
ctx->queue + ctx->head,
- &count, dst, EROFS_BLKSIZ);
+ &count, dst, pclustersize);
if (ret <= 0) {
if (ret != -EAGAIN) {
erofs_err("failed to compress %s: %s",
@@ -175,32 +182,36 @@ static int vle_compress_one(struct erofs_inode *inode,
erofs_strerror(ret));
}
nocompression:
- ret = write_uncompressed_block(ctx, &len, dst);
+ ret = write_uncompressed_extent(ctx, &len, dst);
if (ret < 0)
return ret;
count = ret;
+ ctx->compressedblks = 1;
raw = true;
} else {
- /* write compressed data */
- erofs_dbg("Writing %u compressed data to block %u",
- count, ctx->blkaddr);
+ const unsigned int used = ret & (EROFS_BLKSIZ - 1);
+ const unsigned int margin =
+ erofs_sb_has_lz4_0padding() && used ?
+ EROFS_BLKSIZ - used : 0;
- if (erofs_sb_has_lz4_0padding())
- ret = blk_write(dst - (EROFS_BLKSIZ - ret),
- ctx->blkaddr, 1);
- else
- ret = blk_write(dst, ctx->blkaddr, 1);
+ ctx->compressedblks = DIV_ROUND_UP(ret, EROFS_BLKSIZ);
+ /* write compressed data */
+ erofs_dbg("Writing %u compressed data to %u of %u blocks",
+ count, ctx->blkaddr, ctx->compressedblks);
+
+ ret = blk_write(dst - margin, ctx->blkaddr,
+ ctx->compressedblks);
if (ret)
return ret;
raw = false;
}
ctx->head += count;
- /* write compression indexes for this blkaddr */
+ /* write compression indexes for this pcluster */
vle_write_indexes(ctx, count, raw);
- ++ctx->blkaddr;
+ ctx->blkaddr += ctx->compressedblks;
len -= count;
if (!final && ctx->head >= EROFS_CONFIG_COMPR_MAX_SZ) {
@@ -345,8 +356,6 @@ int z_erofs_convert_to_compacted_format(struct erofs_inode *inode,
out = in = inode->compressmeta;
- /* write out compacted header */
- memcpy(out, &mapheader, sizeof(mapheader));
out += sizeof(mapheader);
in += Z_EROFS_LEGACY_MAP_HEADER_SIZE;
@@ -415,6 +424,8 @@ int erofs_write_compressed_file(struct erofs_inode *inode)
}
memset(compressmeta, 0, Z_EROFS_LEGACY_MAP_HEADER_SIZE);
+ /* write out compressed header */
+ memcpy(compressmeta, &mapheader, sizeof(mapheader));
blkaddr = erofs_mapbh(bh->block, true); /* start_blkaddr */
ctx.blkaddr = blkaddr;
@@ -473,7 +484,8 @@ int erofs_write_compressed_file(struct erofs_inode *inode)
inode->u.i_blocks = compressed_blocks;
legacymetasize = ctx.metacur - compressmeta;
- if (cfg.c_legacy_compress) {
+ /* XXX: temporarily use legacy index instead for mbpcluster */
+ if (cfg.c_legacy_compress || cfg.c_physical_clusterblks > 1) {
inode->extent_isize = legacymetasize;
inode->datalayout = EROFS_INODE_FLAT_COMPRESSION_LEGACY;
} else {
@@ -531,7 +543,17 @@ int z_erofs_compress_init(void)
algorithmtype[0] = ret; /* primary algorithm (head 0) */
algorithmtype[1] = 0; /* secondary algorithm (head 1) */
- mapheader.h_advise |= Z_EROFS_ADVISE_COMPACTED_2B;
+ mapheader.h_advise = 0;
+ if (!cfg.c_legacy_compress)
+ mapheader.h_advise |= Z_EROFS_ADVISE_COMPACTED_2B;
+ /*
+ * if big pcluster is enabled, an extra CBLKCNT lcluster index needs
+ * to be loaded in order to get those compressed block counts.
+ */
+ if (cfg.c_physical_clusterblks > 1) {
+ erofs_sb_set_big_pcluster();
+ mapheader.h_advise |= Z_EROFS_ADVISE_BIG_PCLUSTER_1;
+ }
mapheader.h_algorithmtype = algorithmtype[1] << 4 |
algorithmtype[0];
mapheader.h_clusterbits = LOG_BLOCK_SIZE - 12;
--
2.24.0
More information about the Linux-erofs
mailing list