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

[zstdmt] Rip out the zstdmt API

Browse Source 
This commit leaves only the functions used by zstd_compress.c. All other
functions have been removed from the API. The ZSTDMT unit tests in
fuzzer.c and zstreamtest.c have been rewritten to use the ZSTD API. And
the --mt zstreamtest tests have been ripped out.
This commit is contained in:
Nick Terrell
2020-10-12 12:55:16 -07:00
parent 1784c4b4ab
commit c51a9e79b9
5 changed files with 48 additions and 735 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/compress/zstdmt_compress.c
+1 -320
View File
@@ -884,7 +884,7 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) {
/* ZSTDMT_CCtxParam_setNbWorkers():
* Internal use only */
size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
static size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
{
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers);
}
@@ -943,11 +943,6 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem,
#endif
}
ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers)
{
return ZSTDMT_createCCtx_advanced(nbWorkers, ZSTD_defaultCMem, NULL);
}
/* ZSTDMT_releaseAllJobResources() :
* note : ensure all workers are killed first ! */
@@ -1019,65 +1014,6 @@ size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx)
+ mtctx->roundBuff.capacity;
}
/* Internal only */
size_t
ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params,
ZSTDMT_parameter parameter,
int value)
{
DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter");
switch(parameter)
{
case ZSTDMT_p_jobSize :
DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter : set jobSize to %i", value);
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, value);
case ZSTDMT_p_overlapLog :
DEBUGLOG(4, "ZSTDMT_p_overlapLog : %i", value);
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, value);
case ZSTDMT_p_rsyncable :
DEBUGLOG(4, "ZSTD_p_rsyncable : %i", value);
return ZSTD_CCtxParams_setParameter(params, ZSTD_c_rsyncable, value);
default :
return ERROR(parameter_unsupported);
}
}
size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value)
{
DEBUGLOG(4, "ZSTDMT_setMTCtxParameter");
return ZSTDMT_CCtxParam_setMTCtxParameter(&mtctx->params, parameter, value);
}
size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value)
{
switch (parameter) {
case ZSTDMT_p_jobSize:
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_jobSize, value);
case ZSTDMT_p_overlapLog:
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_overlapLog, value);
case ZSTDMT_p_rsyncable:
return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_rsyncable, value);
default:
return ERROR(parameter_unsupported);
}
}
/* Sets parameters relevant to the compression job,
* initializing others to default values. */
static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(const ZSTD_CCtx_params* params)
{
ZSTD_CCtx_params jobParams = *params;
/* Clear parameters related to multithreading */
jobParams.forceWindow = 0;
jobParams.nbWorkers = 0;
jobParams.jobSize = 0;
jobParams.overlapLog = 0;
jobParams.rsyncable = 0;
ZSTD_memset(&jobParams.ldmParams, 0, sizeof(ldmParams_t));
ZSTD_memset(&jobParams.customMem, 0, sizeof(ZSTD_customMem));
return jobParams;
}
/* ZSTDMT_resize() :
* @return : error code if fails, 0 on success */
@@ -1248,174 +1184,6 @@ static size_t ZSTDMT_computeOverlapSize(const ZSTD_CCtx_params* params)
return (ovLog==0) ? 0 : (size_t)1 << ovLog;
}
static unsigned
ZSTDMT_computeNbJobs(const ZSTD_CCtx_params* params, size_t srcSize, unsigned nbWorkers)
{
assert(nbWorkers>0);
{ size_t const jobSizeTarget = (size_t)1 << ZSTDMT_computeTargetJobLog(params);
size_t const jobMaxSize = jobSizeTarget << 2;
size_t const passSizeMax = jobMaxSize * nbWorkers;
unsigned const multiplier = (unsigned)(srcSize / passSizeMax) + 1;
unsigned const nbJobsLarge = multiplier * nbWorkers;
unsigned const nbJobsMax = (unsigned)(srcSize / jobSizeTarget) + 1;
unsigned const nbJobsSmall = MIN(nbJobsMax, nbWorkers);
return (multiplier>1) ? nbJobsLarge : nbJobsSmall;
} }
/* ZSTDMT_compress_advanced_internal() :
* This is a blocking function : it will only give back control to caller after finishing its compression job.
*/
static size_t
ZSTDMT_compress_advanced_internal(
ZSTDMT_CCtx* mtctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict,
ZSTD_CCtx_params params)
{
ZSTD_CCtx_params const jobParams = ZSTDMT_initJobCCtxParams(&params);
size_t const overlapSize = ZSTDMT_computeOverlapSize(&params);
unsigned const nbJobs = ZSTDMT_computeNbJobs(&params, srcSize, params.nbWorkers);
size_t const proposedJobSize = (srcSize + (nbJobs-1)) / nbJobs;
size_t const avgJobSize = (((proposedJobSize-1) & 0x1FFFF) < 0x7FFF) ? proposedJobSize + 0xFFFF : proposedJobSize; /* avoid too small last block */
const char* const srcStart = (const char*)src;
size_t remainingSrcSize = srcSize;
unsigned const compressWithinDst = (dstCapacity >= ZSTD_compressBound(srcSize)) ? nbJobs : (unsigned)(dstCapacity / ZSTD_compressBound(avgJobSize)); /* presumes avgJobSize >= 256 KB, which should be the case */
size_t frameStartPos = 0, dstBufferPos = 0;
assert(jobParams.nbWorkers == 0);
assert(mtctx->cctxPool->totalCCtx == params.nbWorkers);
params.jobSize = (U32)avgJobSize;
DEBUGLOG(4, "ZSTDMT_compress_advanced_internal: nbJobs=%2u (rawSize=%u bytes; fixedSize=%u) ",
nbJobs, (U32)proposedJobSize, (U32)avgJobSize);
if ((nbJobs==1) | (params.nbWorkers<=1)) { /* fallback to single-thread mode : this is a blocking invocation anyway */
ZSTD_CCtx* const cctx = mtctx->cctxPool->cctx[0];
DEBUGLOG(4, "ZSTDMT_compress_advanced_internal: fallback to single-thread mode");
if (cdict) return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, jobParams.fParams);
return ZSTD_compress_advanced_internal(cctx, dst, dstCapacity, src, srcSize, NULL, 0, &jobParams);
}
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) );
/* LDM doesn't even try to load the dictionary in single-ingestion mode */
if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize, NULL, 0, ZSTD_dct_auto))
return ERROR(memory_allocation);
FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) , ""); /* only expands if necessary */
{ unsigned u;
for (u=0; u<nbJobs; u++) {
size_t const jobSize = MIN(remainingSrcSize, avgJobSize);
size_t const dstBufferCapacity = ZSTD_compressBound(jobSize);
buffer_t const dstAsBuffer = { (char*)dst + dstBufferPos, dstBufferCapacity };
buffer_t const dstBuffer = u < compressWithinDst ? dstAsBuffer : g_nullBuffer;
size_t dictSize = u ? overlapSize : 0;
mtctx->jobs[u].prefix.start = srcStart + frameStartPos - dictSize;
mtctx->jobs[u].prefix.size = dictSize;
mtctx->jobs[u].src.start = srcStart + frameStartPos;
mtctx->jobs[u].src.size = jobSize; assert(jobSize > 0); /* avoid job.src.size == 0 */
mtctx->jobs[u].consumed = 0;
mtctx->jobs[u].cSize = 0;
mtctx->jobs[u].cdict = (u==0) ? cdict : NULL;
mtctx->jobs[u].fullFrameSize = srcSize;
mtctx->jobs[u].params = jobParams;
/* do not calculate checksum within sections, but write it in header for first section */
mtctx->jobs[u].dstBuff = dstBuffer;
mtctx->jobs[u].cctxPool = mtctx->cctxPool;
mtctx->jobs[u].bufPool = mtctx->bufPool;
mtctx->jobs[u].seqPool = mtctx->seqPool;
mtctx->jobs[u].serial = &mtctx->serial;
mtctx->jobs[u].jobID = u;
mtctx->jobs[u].firstJob = (u==0);
mtctx->jobs[u].lastJob = (u==nbJobs-1);
DEBUGLOG(5, "ZSTDMT_compress_advanced_internal: posting job %u (%u bytes)", u, (U32)jobSize);
DEBUG_PRINTHEX(6, mtctx->jobs[u].prefix.start, 12);
POOL_add(mtctx->factory, ZSTDMT_compressionJob, &mtctx->jobs[u]);
frameStartPos += jobSize;
dstBufferPos += dstBufferCapacity;
remainingSrcSize -= jobSize;
} }
/* collect result */
{ size_t error = 0, dstPos = 0;
unsigned jobID;
for (jobID=0; jobID<nbJobs; jobID++) {
DEBUGLOG(5, "waiting for job %u ", jobID);
ZSTD_PTHREAD_MUTEX_LOCK(&mtctx->jobs[jobID].job_mutex);
while (mtctx->jobs[jobID].consumed < mtctx->jobs[jobID].src.size) {
DEBUGLOG(5, "waiting for jobCompleted signal from job %u", jobID);
ZSTD_pthread_cond_wait(&mtctx->jobs[jobID].job_cond, &mtctx->jobs[jobID].job_mutex);
}
ZSTD_pthread_mutex_unlock(&mtctx->jobs[jobID].job_mutex);
DEBUGLOG(5, "ready to write job %u ", jobID);
{ size_t const cSize = mtctx->jobs[jobID].cSize;
if (ZSTD_isError(cSize)) error = cSize;
if ((!error) && (dstPos + cSize > dstCapacity)) error = ERROR(dstSize_tooSmall);
if (jobID) { /* note : job 0 is written directly at dst, which is correct position */
if (!error)
ZSTD_memmove((char*)dst + dstPos, mtctx->jobs[jobID].dstBuff.start, cSize); /* may overlap when job compressed within dst */
if (jobID >= compressWithinDst) { /* job compressed into its own buffer, which must be released */
DEBUGLOG(5, "releasing buffer %u>=%u", jobID, compressWithinDst);
ZSTDMT_releaseBuffer(mtctx->bufPool, mtctx->jobs[jobID].dstBuff);
} }
mtctx->jobs[jobID].dstBuff = g_nullBuffer;
mtctx->jobs[jobID].cSize = 0;
dstPos += cSize ;
}
} /* for (jobID=0; jobID<nbJobs; jobID++) */
DEBUGLOG(4, "checksumFlag : %u ", params.fParams.checksumFlag);
if (params.fParams.checksumFlag) {
U32 const checksum = (U32)XXH64_digest(&mtctx->serial.xxhState);
if (dstPos + 4 > dstCapacity) {
error = ERROR(dstSize_tooSmall);
} else {
DEBUGLOG(4, "writing checksum : %08X \n", checksum);
MEM_writeLE32((char*)dst + dstPos, checksum);
dstPos += 4;
} }
if (!error) DEBUGLOG(4, "compressed size : %u ", (U32)dstPos);
return error ? error : dstPos;
}
}
size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
const ZSTD_CDict* cdict,
ZSTD_parameters params,
int overlapLog)
{
ZSTD_CCtx_params cctxParams = mtctx->params;
cctxParams.cParams = params.cParams;
cctxParams.fParams = params.fParams;
assert(ZSTD_OVERLAPLOG_MIN <= overlapLog && overlapLog <= ZSTD_OVERLAPLOG_MAX);
cctxParams.overlapLog = overlapLog;
return ZSTDMT_compress_advanced_internal(mtctx,
dst, dstCapacity,
src, srcSize,
cdict, cctxParams);
}
size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
void* dst, size_t dstCapacity,
const void* src, size_t srcSize,
int compressionLevel)
{
ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0);
int const overlapLog = ZSTDMT_overlapLog_default(params.cParams.strategy);
params.fParams.contentSizeFlag = 1;
return ZSTDMT_compress_advanced(mtctx, dst, dstCapacity, src, srcSize, NULL, params, overlapLog);
}
/* ====================================== */
/* ======= Streaming API ======= */
/* ====================================== */
@@ -1528,53 +1296,6 @@ size_t ZSTDMT_initCStream_internal(
return 0;
}
size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
const void* dict, size_t dictSize,
ZSTD_parameters params,
unsigned long long pledgedSrcSize)
{
ZSTD_CCtx_params cctxParams = mtctx->params; /* retrieve sticky params */
DEBUGLOG(4, "ZSTDMT_initCStream_advanced (pledgedSrcSize=%u)", (U32)pledgedSrcSize);
cctxParams.cParams = params.cParams;
cctxParams.fParams = params.fParams;
return ZSTDMT_initCStream_internal(mtctx, dict, dictSize, ZSTD_dct_auto, NULL,
cctxParams, pledgedSrcSize);
}
size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
const ZSTD_CDict* cdict,
ZSTD_frameParameters fParams,
unsigned long long pledgedSrcSize)
{
ZSTD_CCtx_params cctxParams = mtctx->params;
if (cdict==NULL) return ERROR(dictionary_wrong); /* method incompatible with NULL cdict */
cctxParams.cParams = ZSTD_getCParamsFromCDict(cdict);
cctxParams.fParams = fParams;
return ZSTDMT_initCStream_internal(mtctx, NULL, 0 /*dictSize*/, ZSTD_dct_auto, cdict,
cctxParams, pledgedSrcSize);
}
/* ZSTDMT_resetCStream() :
* pledgedSrcSize can be zero == unknown (for the time being)
* prefer using ZSTD_CONTENTSIZE_UNKNOWN,
* as `0` might mean "empty" in the future */
size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize)
{
if (!pledgedSrcSize) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;
return ZSTDMT_initCStream_internal(mtctx, NULL, 0, ZSTD_dct_auto, 0, mtctx->params,
pledgedSrcSize);
}
size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel) {
ZSTD_parameters const params = ZSTD_getParams(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0);
ZSTD_CCtx_params cctxParams = mtctx->params; /* retrieve sticky params */
DEBUGLOG(4, "ZSTDMT_initCStream (cLevel=%i)", compressionLevel);
cctxParams.cParams = params.cParams;
cctxParams.fParams = params.fParams;
return ZSTDMT_initCStream_internal(mtctx, NULL, 0, ZSTD_dct_auto, NULL, cctxParams, ZSTD_CONTENTSIZE_UNKNOWN);
}
/* ZSTDMT_writeLastEmptyBlock()
* Write a single empty block with an end-of-frame to finish a frame.
@@ -2072,43 +1793,3 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
return remainingToFlush;
}
}
size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
{
FORWARD_IF_ERROR( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) , "");
/* recommended next input size : fill current input buffer */
return mtctx->targetSectionSize - mtctx->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */
}
static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_EndDirective endFrame)
{
size_t const srcSize = mtctx->inBuff.filled;
DEBUGLOG(5, "ZSTDMT_flushStream_internal");
if ( mtctx->jobReady /* one job ready for a worker to pick up */
|| (srcSize > 0) /* still some data within input buffer */
|| ((endFrame==ZSTD_e_end) && !mtctx->frameEnded)) { /* need a last 0-size block to end frame */
DEBUGLOG(5, "ZSTDMT_flushStream_internal : create a new job (%u bytes, end:%u)",
(U32)srcSize, (U32)endFrame);
FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) , "");
}
/* check if there is any data available to flush */
return ZSTDMT_flushProduced(mtctx, output, 1 /* blockToFlush */, endFrame);
}
size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output)
{
DEBUGLOG(5, "ZSTDMT_flushStream");
return ZSTDMT_flushStream_internal(mtctx, output, ZSTD_e_flush);
}
size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output)
{
DEBUGLOG(4, "ZSTDMT_endStream");
return ZSTDMT_flushStream_internal(mtctx, output, ZSTD_e_end);
}