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

Adding --long support for --patch-from (#1959)

Browse Source 
* adding long support for patch-from

* adding refPrefix to dictionary_decompress

* adding refPrefix to dictionary_loader

* conversion nit

* triggering log mode on chainLog < fileLog and removing old threshold

* adding refPrefix to dictionary_round_trip

* adding docs

* adding enableldm + forceWindow test for dict

* separate patch-from logic into FIO_adjustParamsForPatchFromMode

* moving memLimit adjustment to outside ifdefs (need for decomp)

* removing refPrefix gate on dictionary_round_trip

* rebase on top of dev refPrefix change

* making sure refPrefx + ldm is < 1% of srcSize

* combining notes for patch-from

* moving memlimit logic inside fileio.c

* adding display for optimal parser and long mode trigger

* conversion nit

* fuzzer found heap-overflow fix

* another conversion nit

* moving FIO_adjustMemLimitForPatchFromMode outside ifndef

* making params immutable

* moving memLimit update before createDictBuffer call

* making maxSrcSize unsigned long long

* making dictSize and maxSrcSize params unsigned long long

* error on files larger than 4gb

* extend refPrefix test to include round trip

* conversion to size_t

* making sure ldm is at least 10x better

* removing break

* including zstd_compress_internal and removing redundant macros

* exposing ZSTD_cycleLog()

* using cycleLog instead of chainLog

* add some more docs about user optimizations

* formatting
This commit is contained in:
Bimba Shrestha
2020-04-17 15:58:53 -05:00
committed by GitHub
parent 88ecdc939b
commit 5b0a452cac
12 changed files with 318 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstdmt_compress.c
+12 -3
View File
@@ -461,7 +461,9 @@ typedef struct {
ZSTD_window_t ldmWindow; /* A thread-safe copy of ldmState.window */
} serialState_t;
static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool* seqPool, ZSTD_CCtx_params params, size_t jobSize)
static int ZSTDMT_serialState_reset(serialState_t* serialState,
ZSTDMT_seqPool* seqPool, ZSTD_CCtx_params params,
size_t jobSize, const void* dict, size_t const dictSize)
{
/* Adjust parameters */
if (params.ldmParams.enableLdm) {
@@ -507,6 +509,13 @@ static int ZSTDMT_serialState_reset(serialState_t* serialState, ZSTDMT_seqPool*
memset(serialState->ldmState.hashTable, 0, hashSize);
memset(serialState->ldmState.bucketOffsets, 0, bucketSize);
}
/* Update window state and fill hash table with dict */
if (params.ldmParams.enableLdm && dict) {
ZSTD_window_update(&serialState->ldmState.window, dict, dictSize);
ZSTD_ldm_fillHashTable(&serialState->ldmState, (const BYTE*)dict, (const BYTE*)dict + dictSize, &params.ldmParams);
}
serialState->params = params;
serialState->params.jobSize = (U32)jobSize;
return 0;
@@ -1267,7 +1276,7 @@ static size_t ZSTDMT_compress_advanced_internal(
assert(avgJobSize >= 256 KB); /* condition for ZSTD_compressBound(A) + ZSTD_compressBound(B) <= ZSTD_compressBound(A+B), required to compress directly into Dst (no additional buffer) */
ZSTDMT_setBufferSize(mtctx->bufPool, ZSTD_compressBound(avgJobSize) );
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize))
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize, NULL, 0))
return ERROR(memory_allocation);
FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) ); /* only expands if necessary */
@@ -1500,7 +1509,7 @@ size_t ZSTDMT_initCStream_internal(
mtctx->allJobsCompleted = 0;
mtctx->consumed = 0;
mtctx->produced = 0;
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, mtctx->targetSectionSize))
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, mtctx->targetSectionSize, dict, dictSize))
return ERROR(memory_allocation);
return 0;
}