Fix crash when algo init function returns error.
Fix LZFX error handling. More updates to README.
This commit is contained in:
parent
203008def9
commit
2c516c009c
4 changed files with 38 additions and 8 deletions
8
Changelog
Normal file
8
Changelog
Normal file
|
@ -0,0 +1,8 @@
|
||||||
|
== Changes since 0.5 Alpha release ==
|
||||||
|
Further improve LZMA compression parameters to utilize all the 14 levels.
|
||||||
|
Tweak some Rabin parmeters for better reduction with zlib and Bzip2.
|
||||||
|
Increase the small size slabs a bit.
|
||||||
|
Fix slab sizing.
|
||||||
|
Fix buffer size computation when allocating Rabin block array.
|
||||||
|
Reduce memory usage of Rabin block array.
|
||||||
|
Add an SSE optimization for bsdiff.
|
23
README.md
23
README.md
|
@ -99,18 +99,31 @@ Zlib - Fast, better compression.
|
||||||
Levels: 1 - 9
|
Levels: 1 - 9
|
||||||
Bzip2 - Slow, much better compression than Zlib.
|
Bzip2 - Slow, much better compression than Zlib.
|
||||||
Levels: 1 - 9
|
Levels: 1 - 9
|
||||||
|
|
||||||
LZMA - Very slow. Extreme compression.
|
LZMA - Very slow. Extreme compression.
|
||||||
Levels: 1 - 14
|
Levels: 1 - 14
|
||||||
|
Till level 9 it is standard LZMA parameters. Levels 10 - 12 use
|
||||||
|
more memory and higher match iterations so are slower. Levels
|
||||||
|
13 and 14 use larger dictionaries upto 256MB and really suck up
|
||||||
|
RAM. Use these levels only if you have at the minimum 4GB RAM on
|
||||||
|
your system.
|
||||||
|
|
||||||
PPMD - Slow. Extreme compression for Text, average compression for binary.
|
PPMD - Slow. Extreme compression for Text, average compression for binary.
|
||||||
|
This also requires lots of RAM similar to LZMA.
|
||||||
Levels: 1 - 14.
|
Levels: 1 - 14.
|
||||||
|
|
||||||
Adapt - Very slow synthetic mode. Both Bzip2 and PPMD are tried per chunk and
|
Adapt - Very slow synthetic mode. Both Bzip2 and PPMD are tried per chunk and
|
||||||
better result selected.
|
better result selected.
|
||||||
Levels: 1 - 14
|
Levels: 1 - 14
|
||||||
Adapt2 - Ultra slow synthetic mode. Both LZMA and PPMD are tried per chunk and
|
Adapt2 - Ultra slow synthetic mode. Both LZMA and PPMD are tried per chunk and
|
||||||
better result selected. Can give best compression ration when splitting
|
better result selected. Can give best compression ratio when splitting
|
||||||
file into multiple chunks.
|
file into multiple chunks.
|
||||||
Levels: 1 - 14
|
Levels: 1 - 14
|
||||||
|
Since both LZMA and PPMD are used together memory requirements are
|
||||||
|
quite extensive especially if you are also using extreme levels above
|
||||||
|
10. For example with 64MB chunk, Level 14, 2 threads and with or without
|
||||||
|
dedupe, it uses upto 3.5GB physical RAM. So minimum requirement is 6GB
|
||||||
|
RAM *and* at least 4GB physical swap.
|
||||||
|
|
||||||
It is possible for a single chunk to span the entire file if enough RAM is
|
It is possible for a single chunk to span the entire file if enough RAM is
|
||||||
available. However for adaptive modes to be effective for large files, especially
|
available. However for adaptive modes to be effective for large files, especially
|
||||||
|
@ -119,10 +132,14 @@ algorithm can be selected for textual and binary portions.
|
||||||
|
|
||||||
Caveats
|
Caveats
|
||||||
=======
|
=======
|
||||||
This utility can gobble up RAM depending on compression algorithm,
|
This utility is not meant for resource constrained environments. Minimum memory
|
||||||
|
usage (RES/RSS) with barely meaningful settings is around 10MB. This occurs when
|
||||||
|
using the minimal LZFX compression algorithm at level 2 with a 1MB chunk size and
|
||||||
|
running 2 threads.
|
||||||
|
Normally this utility requires lots of RAM depending on compression algorithm,
|
||||||
compression level, and dedupe being enabled. Larger chunk sizes can give
|
compression level, and dedupe being enabled. Larger chunk sizes can give
|
||||||
better compression ratio but at the same time use more RAM.
|
better compression ratio but at the same time use more RAM.
|
||||||
|
|
||||||
In some cases for files less than a gigabyte. Using Delta Compression in addition
|
In some cases for files less than a gigabyte. Using Delta Compression in addition
|
||||||
to exact Dedupe can have a slight negative impact on LZMA compression ratio
|
to exact Dedupe can have a slight negative impact on LZMA compression ratio
|
||||||
especially when using the large-window ultra compression levels above 12.
|
especially when using the large-window ultra compression levels above 10.
|
||||||
|
|
|
@ -103,8 +103,9 @@ lz_fx_compress(void *src, size_t srclen, void *dst, size_t *dstlen,
|
||||||
unsigned int _dstlen = *dstlen;
|
unsigned int _dstlen = *dstlen;
|
||||||
|
|
||||||
rv = lzfx_compress(src, _srclen, dst, &_dstlen, lzdat->htab_bits);
|
rv = lzfx_compress(src, _srclen, dst, &_dstlen, lzdat->htab_bits);
|
||||||
if (rv == -1) {
|
if (rv != 0) {
|
||||||
lz_fx_err(rv);
|
if (rv != LZFX_ESIZE)
|
||||||
|
lz_fx_err(rv);
|
||||||
return (-1);
|
return (-1);
|
||||||
}
|
}
|
||||||
*dstlen = _dstlen;
|
*dstlen = _dstlen;
|
||||||
|
@ -121,7 +122,7 @@ lz_fx_decompress(void *src, size_t srclen, void *dst, size_t *dstlen,
|
||||||
unsigned int _dstlen = *dstlen;
|
unsigned int _dstlen = *dstlen;
|
||||||
|
|
||||||
rv = lzfx_decompress(src, _srclen, dst, &_dstlen);
|
rv = lzfx_decompress(src, _srclen, dst, &_dstlen);
|
||||||
if (rv == -1) {
|
if (rv != 0) {
|
||||||
lz_fx_err(rv);
|
lz_fx_err(rv);
|
||||||
return (-1);
|
return (-1);
|
||||||
}
|
}
|
||||||
|
|
8
main.c
8
main.c
|
@ -890,7 +890,7 @@ start_compress(const char *filename, uint64_t chunksize, int level)
|
||||||
if (nprocs > 1) fprintf(stderr, "s");
|
if (nprocs > 1) fprintf(stderr, "s");
|
||||||
fprintf(stderr, "\n");
|
fprintf(stderr, "\n");
|
||||||
|
|
||||||
dary = (struct cmp_data **)slab_alloc(NULL, sizeof (struct cmp_data *) * nprocs);
|
dary = (struct cmp_data **)slab_calloc(NULL, nprocs, sizeof (struct cmp_data *));
|
||||||
if (enable_rabin_scan)
|
if (enable_rabin_scan)
|
||||||
cread_buf = (uchar_t *)slab_alloc(NULL, compressed_chunksize + CHDR_SZ);
|
cread_buf = (uchar_t *)slab_alloc(NULL, compressed_chunksize + CHDR_SZ);
|
||||||
else
|
else
|
||||||
|
@ -1101,7 +1101,10 @@ comp_done:
|
||||||
if (err) {
|
if (err) {
|
||||||
if (compfd != -1 && !pipe_mode)
|
if (compfd != -1 && !pipe_mode)
|
||||||
unlink(tmpfile1);
|
unlink(tmpfile1);
|
||||||
fprintf(stderr, "Error compressing file: %s\n", filename);
|
if (filename)
|
||||||
|
fprintf(stderr, "Error compressing file: %s\n", filename);
|
||||||
|
else
|
||||||
|
fprintf(stderr, "Error compressing\n");
|
||||||
} else {
|
} else {
|
||||||
/*
|
/*
|
||||||
* Write a trailer of zero chunk length.
|
* Write a trailer of zero chunk length.
|
||||||
|
@ -1133,6 +1136,7 @@ comp_done:
|
||||||
}
|
}
|
||||||
if (dary != NULL) {
|
if (dary != NULL) {
|
||||||
for (i = 0; i < nprocs; i++) {
|
for (i = 0; i < nprocs; i++) {
|
||||||
|
if (!dary[i]) continue;
|
||||||
slab_free(NULL, dary[i]->uncompressed_chunk);
|
slab_free(NULL, dary[i]->uncompressed_chunk);
|
||||||
slab_free(NULL, dary[i]->cmp_seg);
|
slab_free(NULL, dary[i]->cmp_seg);
|
||||||
if (enable_rabin_scan) {
|
if (enable_rabin_scan) {
|
||||||
|
|
Loading…
Reference in a new issue