Merge pull request #3895 from facebook/fix_3793

Improve compression of Arrays of Integers (High compression mode)

Makefile

@@ -328,8 +328,9 @@ asan-%: clean
 msan: clean
 	$(MAKE) test CC=clang MOREFLAGS="-g -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" HAVE_LZMA=0   # datagen.c fails this test for no obvious reason
 
-msan-%: clean
-	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -C $(TESTDIR) HAVE_LZMA=0 $*
+msan-%:
+	$(MAKE) clean
+	LDFLAGS=-fuse-ld=gold MOREFLAGS="-g -fno-sanitize-recover=all -fsanitize=memory -fno-omit-frame-pointer -Werror $(MOREFLAGS)" FUZZER_FLAGS="--no-big-tests $(FUZZER_FLAGS)" $(MAKE) -j -C $(TESTDIR) HAVE_LZMA=0 $*
 
 asan32: clean
 	$(MAKE) -C $(TESTDIR) test32 CC=clang MOREFLAGS="-g -fsanitize=address $(MOREFLAGS)"

lib/compress/zstd_compress.c

@@ -1661,8 +1661,8 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams,
       + ZSTD_cwksp_aligned_alloc_size((MaxLL+1) * sizeof(U32))
       + ZSTD_cwksp_aligned_alloc_size((MaxOff+1) * sizeof(U32))
       + ZSTD_cwksp_aligned_alloc_size((1<<Litbits) * sizeof(U32))
-      + ZSTD_cwksp_aligned_alloc_size((ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t))
-      + ZSTD_cwksp_aligned_alloc_size((ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t));
+      + ZSTD_cwksp_aligned_alloc_size(ZSTD_OPT_SIZE * sizeof(ZSTD_match_t))
+      + ZSTD_cwksp_aligned_alloc_size(ZSTD_OPT_SIZE * sizeof(ZSTD_optimal_t));
     size_t const lazyAdditionalSpace = ZSTD_rowMatchFinderUsed(cParams->strategy, useRowMatchFinder)
                                             ? ZSTD_cwksp_aligned_alloc_size(hSize)
                                             : 0;
@@ -2045,8 +2045,8 @@ ZSTD_reset_matchState(ZSTD_matchState_t* ms,
         ms->opt.litLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxLL+1) * sizeof(unsigned));
         ms->opt.matchLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxML+1) * sizeof(unsigned));
         ms->opt.offCodeFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxOff+1) * sizeof(unsigned));
-        ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t));
-        ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t));
+        ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned(ws, ZSTD_OPT_SIZE * sizeof(ZSTD_match_t));
+        ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned(ws, ZSTD_OPT_SIZE * sizeof(ZSTD_optimal_t));
     }
 
     ms->cParams = *cParams;

lib/compress/zstd_compress_internal.h

@@ -159,23 +159,24 @@ typedef struct {
 UNUSED_ATTR static const rawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0};
 
 typedef struct {
-    int price;
-    U32 off;
-    U32 mlen;
-    U32 litlen;
-    U32 rep[ZSTD_REP_NUM];
+    int price;  /* price from beginning of segment to this position */
+    U32 off;    /* offset of previous match */
+    U32 mlen;   /* length of previous match */
+    U32 litlen; /* nb of literals since previous match */
+    U32 rep[ZSTD_REP_NUM];  /* offset history after previous match */
 } ZSTD_optimal_t;
 
 typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e;
 
+#define ZSTD_OPT_SIZE (ZSTD_OPT_NUM+2)
 typedef struct {
     /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */
     unsigned* litFreq;           /* table of literals statistics, of size 256 */
     unsigned* litLengthFreq;     /* table of litLength statistics, of size (MaxLL+1) */
     unsigned* matchLengthFreq;   /* table of matchLength statistics, of size (MaxML+1) */
     unsigned* offCodeFreq;       /* table of offCode statistics, of size (MaxOff+1) */
-    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_NUM+1 */
-    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */
+    ZSTD_match_t* matchTable;    /* list of found matches, of size ZSTD_OPT_SIZE */
+    ZSTD_optimal_t* priceTable;  /* All positions tracked by optimal parser, of size ZSTD_OPT_SIZE */
 
     U32  litSum;                 /* nb of literals */
     U32  litLengthSum;           /* nb of litLength codes */