ddidderr/zstd-rs
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add salt into row hash (#3528 part 2) (#3533)

Browse Source 
Part 2 of #3528

Adds hash salt that helps to avoid regressions where consecutive compressions use the same tag space with similar data (running zstd -b5e7 enwik8 -B128K reproduces this regression).
This commit is contained in:
Yonatan Komornik
2023-03-13 15:34:13 -07:00
committed by GitHub
parent 9420bce8a4
commit 91f4c23e63
4 changed files with 104 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstd_lazy.c
+12 -32
View File
@@ -773,31 +773,6 @@ MEM_STATIC U32 ZSTD_VecMask_next(ZSTD_VecMask val) {
return ZSTD_countTrailingZeros64(val);
}
/* ZSTD_rotateRight_*():
* Rotates a bitfield to the right by "count" bits.
* https://en.wikipedia.org/w/index.php?title=Circular_shift&oldid=991635599#Implementing_circular_shifts
*/
FORCE_INLINE_TEMPLATE
U64 ZSTD_rotateRight_U64(U64 const value, U32 count) {
assert(count < 64);
count &= 0x3F; /* for fickle pattern recognition */
return (value >> count) | (U64)(value << ((0U - count) & 0x3F));
}
FORCE_INLINE_TEMPLATE
U32 ZSTD_rotateRight_U32(U32 const value, U32 count) {
assert(count < 32);
count &= 0x1F; /* for fickle pattern recognition */
return (value >> count) | (U32)(value << ((0U - count) & 0x1F));
}
FORCE_INLINE_TEMPLATE
U16 ZSTD_rotateRight_U16(U16 const value, U32 count) {
assert(count < 16);
count &= 0x0F; /* for fickle pattern recognition */
return (value >> count) | (U16)(value << ((0U - count) & 0x0F));
}
/* ZSTD_row_nextIndex():
* Returns the next index to insert at within a tagTable row, and updates the "head"
* value to reflect the update. Essentially cycles backwards from [1, {entries per row})
@@ -850,7 +825,7 @@ FORCE_INLINE_TEMPLATE void ZSTD_row_fillHashCache(ZSTD_matchState_t* ms, const B
U32 const lim = idx + MIN(ZSTD_ROW_HASH_CACHE_SIZE, maxElemsToPrefetch);
for (; idx < lim; ++idx) {
U32 const hash = (U32)ZSTD_hashPtr(base + idx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls);
U32 const hash = (U32)ZSTD_hashPtrSalted(base + idx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls, ms->hashSalt);
U32 const row = (hash >> ZSTD_ROW_HASH_TAG_BITS) << rowLog;
ZSTD_row_prefetch(hashTable, tagTable, row, rowLog);
ms->hashCache[idx & ZSTD_ROW_HASH_CACHE_MASK] = hash;
@@ -868,9 +843,10 @@ FORCE_INLINE_TEMPLATE void ZSTD_row_fillHashCache(ZSTD_matchState_t* ms, const B
FORCE_INLINE_TEMPLATE U32 ZSTD_row_nextCachedHash(U32* cache, U32 const* hashTable,
BYTE const* tagTable, BYTE const* base,
U32 idx, U32 const hashLog,
U32 const rowLog, U32 const mls)
U32 const rowLog, U32 const mls,
U64 const hashSalt)
{
U32 const newHash = (U32)ZSTD_hashPtr(base+idx+ZSTD_ROW_HASH_CACHE_SIZE, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls);
U32 const newHash = (U32)ZSTD_hashPtrSalted(base+idx+ZSTD_ROW_HASH_CACHE_SIZE, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls, hashSalt);
U32 const row = (newHash >> ZSTD_ROW_HASH_TAG_BITS) << rowLog;
ZSTD_row_prefetch(hashTable, tagTable, row, rowLog);
{ U32 const hash = cache[idx & ZSTD_ROW_HASH_CACHE_MASK];
@@ -890,21 +866,24 @@ FORCE_INLINE_TEMPLATE void ZSTD_row_update_internalImpl(ZSTD_matchState_t* ms,
U32* const hashTable = ms->hashTable;
BYTE* const tagTable = ms->tagTable;
U32 const hashLog = ms->rowHashLog;
U32 hashSaltEntropyCollected = 0;
const BYTE* const base = ms->window.base;
DEBUGLOG(6, "ZSTD_row_update_internalImpl(): updateStartIdx=%u, updateEndIdx=%u", updateStartIdx, updateEndIdx);
for (; updateStartIdx < updateEndIdx; ++updateStartIdx) {
U32 const hash = useCache ? ZSTD_row_nextCachedHash(ms->hashCache, hashTable, tagTable, base, updateStartIdx, hashLog, rowLog, mls)
: (U32)ZSTD_hashPtr(base + updateStartIdx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls);
U32 const hash = useCache ? ZSTD_row_nextCachedHash(ms->hashCache, hashTable, tagTable, base, updateStartIdx, hashLog, rowLog, mls, ms->hashSalt)
: (U32)ZSTD_hashPtrSalted(base + updateStartIdx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls, ms->hashSalt);
U32 const relRow = (hash >> ZSTD_ROW_HASH_TAG_BITS) << rowLog;
U32* const row = hashTable + relRow;
BYTE* tagRow = tagTable + relRow;
U32 const pos = ZSTD_row_nextIndex(tagRow, rowMask);
assert(hash == ZSTD_hashPtr(base + updateStartIdx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls));
assert(hash == ZSTD_hashPtrSalted(base + updateStartIdx, hashLog + ZSTD_ROW_HASH_TAG_BITS, mls, ms->hashSalt));
tagRow[pos] = hash & ZSTD_ROW_HASH_TAG_MASK;
row[pos] = updateStartIdx;
hashSaltEntropyCollected = hash;
}
ms->hashSaltEntropy += hashSaltEntropyCollected; /* collect salt entropy */
}
/* ZSTD_row_update_internal():
@@ -1162,6 +1141,7 @@ size_t ZSTD_RowFindBestMatch(
const U32 rowMask = rowEntries - 1;
const U32 cappedSearchLog = MIN(cParams->searchLog, rowLog); /* nb of searches is capped at nb entries per row */
const U32 groupWidth = ZSTD_row_matchMaskGroupWidth(rowEntries);
const U64 hashSalt = ms->hashSalt;
U32 nbAttempts = 1U << cappedSearchLog;
size_t ml=4-1;
@@ -1199,7 +1179,7 @@ size_t ZSTD_RowFindBestMatch(
/* Update the hashTable and tagTable up to (but not including) ip */
ZSTD_row_update_internal(ms, ip, mls, rowLog, rowMask, 1 /* useCache */);
{ /* Get the hash for ip, compute the appropriate row */
U32 const hash = ZSTD_row_nextCachedHash(hashCache, hashTable, tagTable, base, curr, hashLog, rowLog, mls);
U32 const hash = ZSTD_row_nextCachedHash(hashCache, hashTable, tagTable, base, curr, hashLog, rowLog, mls, hashSalt);
U32 const relRow = (hash >> ZSTD_ROW_HASH_TAG_BITS) << rowLog;
U32 const tag = hash & ZSTD_ROW_HASH_TAG_MASK;
U32* const row = hashTable + relRow;