diff --git a/doc/src/sgml/ref/create_table.sgml b/doc/src/sgml/ref/create_table.sgml index e0b8a4e..c4ac2bd 100644 --- a/doc/src/sgml/ref/create_table.sgml +++ b/doc/src/sgml/ref/create_table.sgml @@ -1014,6 +1014,22 @@ CREATE [ [ GLOBAL | LOCAL ] { TEMPORARY | TEMP } | UNLOGGED ] TABLE [ IF NOT EXI + + wal_compress_update (boolean) + + + Enables or disables the WAL tuple compression for UPDATE + on this table. Default value of this option is false to maintain + backward compatability for the command. If true, all the update + operations on this table which will place the new tuple on same page + as it's original tuple will compress the WAL for new tuple and + subsequently reduce the WAL volume. It is recommended to enable + this option for tables where UPDATE changes less than + 50 percent of tuple data. + + + + diff --git a/src/backend/access/common/heaptuple.c b/src/backend/access/common/heaptuple.c index aea9d40..3bf5728 100644 --- a/src/backend/access/common/heaptuple.c +++ b/src/backend/access/common/heaptuple.c @@ -60,6 +60,7 @@ #include "access/sysattr.h" #include "access/tuptoaster.h" #include "executor/tuptable.h" +#include "utils/pg_rbcompress.h" /* Does att's datatype allow packing into the 1-byte-header varlena format? */ @@ -617,6 +618,44 @@ heap_copytuple_with_tuple(HeapTuple src, HeapTuple dest) memcpy((char *) dest->t_data, (char *) src->t_data, src->t_len); } +/* ---------------- + * heap_delta_encode + * + * Calculate the delta between two tuples and generate + * encoded wal tuple (EWT), using pgrb. The result is stored + * in *encdata. + * ---------------- + */ +bool +heap_delta_encode(TupleDesc tupleDesc, HeapTuple oldtup, HeapTuple newtup, + char *encdata, uint32 *enclen) +{ + return pgrb_delta_encode( + (char *) newtup->t_data + offsetof(HeapTupleHeaderData, t_bits), + newtup->t_len - offsetof(HeapTupleHeaderData, t_bits), + (char *) oldtup->t_data + offsetof(HeapTupleHeaderData, t_bits), + oldtup->t_len - offsetof(HeapTupleHeaderData, t_bits), + encdata, enclen, NULL + ); +} + +/* ---------------- + * heap_delta_decode + * + * Decode a tuple using delta-encoded WAL tuple and old tuple version. + * ---------------- + */ +void +heap_delta_decode(char *encdata, uint32 enclen, HeapTuple oldtup, HeapTuple newtup) +{ + pgrb_delta_decode(encdata, enclen, + (char *) newtup->t_data + offsetof(HeapTupleHeaderData, t_bits), + MaxHeapTupleSize - offsetof(HeapTupleHeaderData, t_bits), + &newtup->t_len, + (char *) oldtup->t_data + offsetof(HeapTupleHeaderData, t_bits), + oldtup->t_len - offsetof(HeapTupleHeaderData, t_bits)); +} + /* * heap_form_tuple * construct a tuple from the given values[] and isnull[] arrays, diff --git a/src/backend/access/common/reloptions.c b/src/backend/access/common/reloptions.c index fa08c45..2123a61 100644 --- a/src/backend/access/common/reloptions.c +++ b/src/backend/access/common/reloptions.c @@ -85,6 +85,14 @@ static relopt_bool boolRelOpts[] = }, false }, + { + { + "wal_compress_update", + "Compress the wal tuple for update operation on this relation", + RELOPT_KIND_HEAP + }, + true + }, /* list terminator */ {{NULL}} }; @@ -1175,7 +1183,9 @@ default_reloptions(Datum reloptions, bool validate, relopt_kind kind) {"check_option", RELOPT_TYPE_STRING, offsetof(StdRdOptions, check_option_offset)}, {"user_catalog_table", RELOPT_TYPE_BOOL, - offsetof(StdRdOptions, user_catalog_table)} + offsetof(StdRdOptions, user_catalog_table)}, + {"wal_compress_update", RELOPT_TYPE_BOOL, + offsetof(StdRdOptions, wal_compress_update)} }; options = parseRelOptions(reloptions, validate, kind, &numoptions); diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c index a771ccb..2724188 100644 --- a/src/backend/access/heap/heapam.c +++ b/src/backend/access/heap/heapam.c @@ -70,6 +70,7 @@ #include "utils/snapmgr.h" #include "utils/syscache.h" #include "utils/tqual.h" +#include "utils/pg_rbcompress.h" /* GUC variable */ @@ -6597,6 +6598,12 @@ log_heap_update(Relation reln, Buffer oldbuf, XLogRecPtr recptr; XLogRecData rdata[7]; Page page = BufferGetPage(newbuf); + char *newtupdata; + int newtuplen; + bool compressed = false; + + /* Structure which holds EWT */ + char buf[MaxHeapTupleSize]; bool need_tuple_data = RelationIsLogicallyLogged(reln); /* Caller should not call me on a non-WAL-logged relation */ @@ -6607,6 +6614,37 @@ log_heap_update(Relation reln, Buffer oldbuf, else info = XLOG_HEAP_UPDATE; + newtupdata = ((char *) newtup->t_data) + offsetof(HeapTupleHeaderData, t_bits); + newtuplen = newtup->t_len - offsetof(HeapTupleHeaderData, t_bits); + + /* + * EWT can be generated for all new tuple versions created by Update + * operation. Currently we do it when both the old and new tuple versions + * are on same page, because during recovery if the page containing old + * tuple is corrupt, it should not cascade that corruption to other pages. + * Under the general assumption that for long runs most updates tend to + * create new tuple version on same page, there should not be significant + * impact on WAL reduction or performance. + * + * We should not generate EWT when we need to backup the whole block in + * WAL as in that case there is no saving by reduced WAL size. + */ + + if (RelationIsEnabledForWalCompression(reln) && + (oldbuf == newbuf) && + !XLogCheckBufferNeedsBackup(newbuf)) + { + uint32 enclen; + + /* Delta-encode the new tuple using the old tuple */ + if (heap_delta_encode(reln->rd_att, oldtup, newtup, buf, &enclen)) + { + compressed = true; + newtupdata = buf; + newtuplen = enclen; + } + } + xlrec.target.node = reln->rd_node; xlrec.target.tid = oldtup->t_self; xlrec.old_xmax = HeapTupleHeaderGetRawXmax(oldtup->t_data); @@ -6619,6 +6657,8 @@ log_heap_update(Relation reln, Buffer oldbuf, xlrec.newtid = newtup->t_self; if (new_all_visible_cleared) xlrec.flags |= XLOG_HEAP_NEW_ALL_VISIBLE_CLEARED; + if (compressed) + xlrec.flags |= XLOG_HEAP_DELTA_ENCODED; rdata[0].data = (char *) &xlrec; rdata[0].len = SizeOfHeapUpdate; @@ -6634,7 +6674,7 @@ log_heap_update(Relation reln, Buffer oldbuf, xlhdr.header.t_infomask2 = newtup->t_data->t_infomask2; xlhdr.header.t_infomask = newtup->t_data->t_infomask; xlhdr.header.t_hoff = newtup->t_data->t_hoff; - xlhdr.t_len = newtup->t_len - offsetof(HeapTupleHeaderData, t_bits); + xlhdr.t_len = newtuplen; /* * As with insert records, we need not store the rdata[2] segment @@ -6647,10 +6687,13 @@ log_heap_update(Relation reln, Buffer oldbuf, rdata[2].buffer_std = true; rdata[2].next = &(rdata[3]); - /* PG73FORMAT: write bitmap [+ padding] [+ oid] + data */ - rdata[3].data = (char *) newtup->t_data - + offsetof(HeapTupleHeaderData, t_bits); - rdata[3].len = newtup->t_len - offsetof(HeapTupleHeaderData, t_bits); + /* + * PG73FORMAT: write bitmap [+ padding] [+ oid] + data OR + * PG94FORMAT [If encoded]: Control byte + history reference (2 - 3)bytes + * + literal byte + ... + */ + rdata[3].data = newtupdata; + rdata[3].len = newtuplen; rdata[3].buffer = need_tuple_data ? InvalidBuffer : newbuf; rdata[3].buffer_std = true; rdata[3].next = NULL; @@ -7739,7 +7782,10 @@ heap_xlog_update(XLogRecPtr lsn, XLogRecord *record, bool hot_update) Page page; OffsetNumber offnum; ItemId lp = NULL; + HeapTupleData newtup; + HeapTupleData oldtup; HeapTupleHeader htup; + HeapTupleHeader oldtupdata = NULL; struct { HeapTupleHeaderData hdr; @@ -7814,7 +7860,7 @@ heap_xlog_update(XLogRecPtr lsn, XLogRecord *record, bool hot_update) if (PageGetMaxOffsetNumber(page) < offnum || !ItemIdIsNormal(lp)) elog(PANIC, "heap_update_redo: invalid lp"); - htup = (HeapTupleHeader) PageGetItem(page, lp); + oldtupdata = htup = (HeapTupleHeader) PageGetItem(page, lp); htup->t_infomask &= ~(HEAP_XMAX_BITS | HEAP_MOVED); htup->t_infomask2 &= ~HEAP_KEYS_UPDATED; @@ -7923,10 +7969,31 @@ newsame:; Assert(newlen <= MaxHeapTupleSize); htup = &tbuf.hdr; MemSet((char *) htup, 0, sizeof(HeapTupleHeaderData)); - /* PG73FORMAT: get bitmap [+ padding] [+ oid] + data */ - memcpy((char *) htup + offsetof(HeapTupleHeaderData, t_bits), - (char *) xlrec + hsize, - newlen); + + /* + * If the record is EWT then decode it. + */ + if (xlrec->flags & XLOG_HEAP_DELTA_ENCODED) + { + /* + * PG94FORMAT: Control byte + history reference (2 - 3)bytes + * + literal byte + ... + */ + oldtup.t_data = oldtupdata; + oldtup.t_len = ItemIdGetLength(lp); + newtup.t_data = htup; + + heap_delta_decode((char *) xlrec + hsize, newlen, &oldtup, &newtup); + newlen = newtup.t_len; + } + else + { + /* PG73FORMAT: get bitmap [+ padding] [+ oid] + data */ + memcpy((char *) htup + offsetof(HeapTupleHeaderData, t_bits), + (char *) xlrec + hsize, + newlen); + } + newlen += offsetof(HeapTupleHeaderData, t_bits); htup->t_infomask2 = xlhdr.header.t_infomask2; htup->t_infomask = xlhdr.header.t_infomask; diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c index b333d82..92c4f00 100644 --- a/src/backend/access/transam/xlog.c +++ b/src/backend/access/transam/xlog.c @@ -2327,6 +2327,28 @@ XLogRecPtrToBytePos(XLogRecPtr ptr) } /* + * Determine whether the buffer referenced has to be backed up. Since we don't + * yet have the insert lock, fullPageWrites and forcePageWrites could change + * later, but will not cause any problem because this function is used only to + * identify whether EWT is required for update. + */ +bool +XLogCheckBufferNeedsBackup(Buffer buffer) +{ + bool doPageWrites; + Page page; + + page = BufferGetPage(buffer); + + doPageWrites = XLogCtl->Insert.fullPageWrites || XLogCtl->Insert.forcePageWrites; + + if (doPageWrites && PageGetLSN(page) <= RedoRecPtr) + return true; /* buffer requires backup */ + + return false; /* buffer does not need to be backed up */ +} + +/* * Determine whether the buffer referenced by an XLogRecData item has to * be backed up, and if so fill a BkpBlock struct for it. In any case * save the buffer's LSN at *lsn. diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile index 1ae9fa0..04dc17c 100644 --- a/src/backend/utils/adt/Makefile +++ b/src/backend/utils/adt/Makefile @@ -26,7 +26,7 @@ OBJS = acl.o arrayfuncs.o array_selfuncs.o array_typanalyze.o \ rowtypes.o regexp.o regproc.o ruleutils.o selfuncs.o \ tid.o timestamp.o varbit.o varchar.o varlena.o version.o xid.o \ network.o mac.o inet_cidr_ntop.o inet_net_pton.o \ - ri_triggers.o pg_lzcompress.o pg_locale.o formatting.o \ + ri_triggers.o pg_lzcompress.o pg_rbcompress.o pg_locale.o formatting.o \ ascii.o quote.o pgstatfuncs.o encode.o dbsize.o genfile.o trigfuncs.o \ tsginidx.o tsgistidx.o tsquery.o tsquery_cleanup.o tsquery_gist.o \ tsquery_op.o tsquery_rewrite.o tsquery_util.o tsrank.o \ diff --git a/src/backend/utils/adt/pg_rbcompress.c b/src/backend/utils/adt/pg_rbcompress.c new file mode 100644 index 0000000..bcebed2 --- /dev/null +++ b/src/backend/utils/adt/pg_rbcompress.c @@ -0,0 +1,353 @@ +/* ---------- + * pg_rbcompress.c - + * + * This is a delta encoding scheme specific to PostgreSQL and designed + * to compress similar tuples. It can be used as it is or extended for + * other purpose in PostgrSQL if required. + * + * Currently, this just checks for a common prefix and/or suffix, but + * the output format is similar to the LZ format used in pg_lzcompress.c. + * + * Copyright (c) 1999-2014, PostgreSQL Global Development Group + * + * src/backend/utils/adt/pg_rbcompress.c + * ---------- + */ +#include "postgres.h" + +#include + +#include "utils/pg_rbcompress.h" + + +/* ---------- + * Local definitions + * ---------- + */ +#define PGRB_HISTORY_SIZE 4096 +#define PGRB_MIN_MATCH 4 + + + +/* ---------- + * The provided standard strategies + * ---------- + */ +static const PGRB_Strategy strategy_default_data = { + 32, /* Data chunks less than 32 bytes are not + * compressed */ + INT_MAX, /* No upper limit on what we'll try to + * compress */ + 25, /* Require 25% compression rate, or not worth + * it */ +}; +const PGRB_Strategy *const PGRB_strategy_default = &strategy_default_data; + + +/* ---------- + * pgrb_out_ctrl - + * + * Outputs the last and allocates a new control byte if needed. + * ---------- + */ +#define pgrb_out_ctrl(__ctrlp,__ctrlb,__ctrl,__buf) \ +do { \ + if ((__ctrl & 0xff) == 0) \ + { \ + *(__ctrlp) = __ctrlb; \ + __ctrlp = (__buf)++; \ + __ctrlb = 0; \ + __ctrl = 1; \ + } \ +} while (0) + + +/* ---------- + * pgrb_out_literal - + * + * Outputs a literal byte to the destination buffer including the + * appropriate control bit. + * ---------- + */ +#define pgrb_out_literal(_ctrlp,_ctrlb,_ctrl,_buf,_byte) \ +do { \ + pgrb_out_ctrl(_ctrlp,_ctrlb,_ctrl,_buf); \ + *(_buf)++ = (unsigned char)(_byte); \ + _ctrl <<= 1; \ +} while (0) + + +/* ---------- + * pgrb_out_tag - + * + * Outputs a backward reference tag of 2-4 bytes (depending on + * offset and length) to the destination buffer including the + * appropriate control bit. + * ---------- + */ +#define pgrb_out_tag(_ctrlp,_ctrlb,_ctrl,_buf,_len,_off) \ +do { \ + pgrb_out_ctrl(_ctrlp,_ctrlb,_ctrl,_buf); \ + _ctrlb |= _ctrl; \ + _ctrl <<= 1; \ + if (_len > 17) \ + { \ + (_buf)[0] = (unsigned char)((((_off) & 0xf00) >> 4) | 0x0f); \ + (_buf)[1] = (unsigned char)(((_off) & 0xff)); \ + (_buf)[2] = (unsigned char)((_len) - 18); \ + (_buf) += 3; \ + } else { \ + (_buf)[0] = (unsigned char)((((_off) & 0xf00) >> 4) | ((_len) - 3)); \ + (_buf)[1] = (unsigned char)((_off) & 0xff); \ + (_buf) += 2; \ + } \ +} while (0) + +/* ---------- + * pgrb_delta_encode - find common prefix/suffix between inputs and encode. + * + * source is the input data to be compressed + * slen is the length of source data + * history is the data which is used as reference for compression + * hlen is the length of history data + * The encoded result is written to dest, and its length is returned in + * finallen. + * The return value is TRUE if compression succeeded, + * FALSE if not; in the latter case the contents of dest + * are undefined. + * ---------- + */ +bool +pgrb_delta_encode(const char *source, int32 slen, + const char *history, int32 hlen, + char *dest, uint32 *finallen, + const PGRB_Strategy *strategy) +{ + unsigned char *bp = ((unsigned char *) dest); + unsigned char *bstart = bp; + const char *dp = source; + const char *dend = source + slen; + const char *hp = history; + unsigned char ctrl_dummy = 0; + unsigned char *ctrlp = &ctrl_dummy; + unsigned char ctrlb = 0; + unsigned char ctrl = 0; + int32 result_size; + int32 result_max; + int32 need_rate; + int prefixlen; + int suffixlen; + + /* + * Tuples of length greater than PGRB_HISTORY_SIZE are not allowed for + * delta encode as this is the maximum size of history offset. + * XXX: still true? + */ + if (hlen >= PGRB_HISTORY_SIZE || hlen < PGRB_MIN_MATCH) + return false; + + /* + * Our fallback strategy is the default. + */ + if (strategy == NULL) + strategy = PGRB_strategy_default; + + /* + * If the strategy forbids compression (at all or if source chunk size out + * of range), fail. + */ + if (slen < strategy->min_input_size || + slen > strategy->max_input_size) + return false; + + need_rate = strategy->min_comp_rate; + if (need_rate < 0) + need_rate = 0; + else if (need_rate > 99) + need_rate = 99; + + /* + * Compute the maximum result size allowed by the strategy, namely the + * input size minus the minimum wanted compression rate. This had better + * be <= slen, else we might overrun the provided output buffer. + */ + if (slen > (INT_MAX / 100)) + { + /* Approximate to avoid overflow */ + result_max = (slen / 100) * (100 - need_rate); + } + else + { + result_max = (slen * (100 - need_rate)) / 100; + } + + for (prefixlen = 0; prefixlen < hlen && prefixlen < slen; prefixlen++) + { + if (history[prefixlen] != source[prefixlen]) + break; + } + if (prefixlen < PGRB_MIN_MATCH) + prefixlen = 0; + + hp = &history[hlen - 1]; + dp = &source[slen - 1]; + suffixlen = 0; + while (hp >= &history[prefixlen] && dp >= &source[prefixlen]) + { + if (*hp != *dp) + break; + hp--; + dp--; + suffixlen++; + } + if (suffixlen < PGRB_MIN_MATCH) + suffixlen = 0; + + /* FIXME: need to be more careful here, to make sure we don't + * overflow the buffer! + */ + if (slen - prefixlen - suffixlen > (slen * need_rate) / 100) + return false; + + /* Ok, this is worth delta encoding. */ + + /* output prefix as a tag */ + pgrb_out_tag(ctrlp, ctrlb, ctrl, bp, prefixlen, hlen); + + /* output bytes between prefix and suffix as literals */ + dp = &source[prefixlen]; + dend = &source[slen - suffixlen]; + while (dp < dend) + { + pgrb_out_literal(ctrlp, ctrlb, ctrl, bp, *dp); + dp++; /* Do not do this ++ in the line above! */ + } + + /* output suffix as a tag */ + pgrb_out_tag(ctrlp, ctrlb, ctrl, bp, suffixlen, 0); + + /* + * Write out the last control byte and check that we haven't overrun the + * output size allowed by the strategy. + */ + *ctrlp = ctrlb; + result_size = bp - bstart; + + if (result_size > result_max) + return false; + +#ifdef DELTA_DEBUG + elog(LOG, "old %d new %d compressed %d", hlen, slen, result_size); +#endif + + /* + * Success - need only fill in the actual length of the compressed datum. + */ + *finallen = result_size; + + return true; +} + +/* ---------- + * pgrb_delta_decode + * + * Decompresses source into dest. + * ---------- + */ +void +pgrb_delta_decode(const char *source, uint32 srclen, + char *dest, uint32 destlen, uint32 *finallen, + const char *history, uint32 histlen) +{ + const unsigned char *sp; + const unsigned char *srcend; + unsigned char *dp; + unsigned char *destend; + const char *hend; + + sp = ((const unsigned char *) source); + srcend = ((const unsigned char *) source) + srclen; + dp = (unsigned char *) dest; + destend = dp + destlen; + hend = history + histlen; + + while (sp < srcend && dp < destend) + { + /* + * Read one control byte and process the next 8 items (or as many as + * remain in the compressed input). + */ + unsigned char ctrl = *sp++; + int ctrlc; + + for (ctrlc = 0; ctrlc < 8 && sp < srcend; ctrlc++) + { + if (ctrl & 1) + { + /* + * Otherwise it contains the match length minus 3 and the + * upper 4 bits of the offset. The next following byte + * contains the lower 8 bits of the offset. If the length is + * coded as 18, another extension tag byte tells how much + * longer the match really was (0-255). + */ + int32 len; + int32 off; + + len = (sp[0] & 0x0f) + 3; + off = ((sp[0] & 0xf0) << 4) | sp[1]; + sp += 2; + if (len == 18) + len += *sp++; + + /* + * Check for output buffer overrun, to ensure we don't clobber + * memory in case of corrupt input. Note: we must advance dp + * here to ensure the error is detected below the loop. We + * don't simply put the elog inside the loop since that will + * probably interfere with optimization. + */ + if (dp + len > destend) + { + dp += len; + break; + } + + /* + * Now we copy the bytes specified by the tag from history to + * OUTPUT. We can safely use memcpy here because source and + * destination strings will not overlap as in case of LZ. + */ + memcpy(dp, hend - off, len); + dp += len; + } + else + { + /* + * An unset control bit means LITERAL BYTE. So we just copy + * one from INPUT to OUTPUT. + */ + if (dp >= destend) /* check for buffer overrun */ + break; /* do not clobber memory */ + + *dp++ = *sp++; + } + + /* + * Advance the control bit + */ + ctrl >>= 1; + } + } + + /* + * Check we decompressed the right amount. + */ + if (sp != srcend) + elog(PANIC, "compressed data is corrupt"); + + /* + * That's it. + */ + *finallen = ((char *) dp - dest); +} diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h index d4383ab..df64096 100644 --- a/src/include/access/heapam_xlog.h +++ b/src/include/access/heapam_xlog.h @@ -67,6 +67,7 @@ #define XLOG_HEAP_CONTAINS_OLD_TUPLE (1<<2) #define XLOG_HEAP_CONTAINS_OLD_KEY (1<<3) #define XLOG_HEAP_CONTAINS_NEW_TUPLE (1<<4) +#define XLOG_HEAP_DELTA_ENCODED (1<<5) /* convenience macro for checking whether any form of old tuple was logged */ #define XLOG_HEAP_CONTAINS_OLD \ diff --git a/src/include/access/htup_details.h b/src/include/access/htup_details.h index a3eba98..abb5620 100644 --- a/src/include/access/htup_details.h +++ b/src/include/access/htup_details.h @@ -740,6 +740,11 @@ extern HeapTuple heap_modify_tuple(HeapTuple tuple, extern void heap_deform_tuple(HeapTuple tuple, TupleDesc tupleDesc, Datum *values, bool *isnull); +extern bool heap_delta_encode(TupleDesc tupleDesc, HeapTuple oldtup, + HeapTuple newtup, char *encdata, uint32 *enclen); +extern void heap_delta_decode (char *encdata, uint32 enclen, HeapTuple oldtup, + HeapTuple newtup); + /* these three are deprecated versions of the three above: */ extern HeapTuple heap_formtuple(TupleDesc tupleDescriptor, Datum *values, char *nulls); diff --git a/src/include/access/xlog.h b/src/include/access/xlog.h index 47e3022..51d6925 100644 --- a/src/include/access/xlog.h +++ b/src/include/access/xlog.h @@ -279,6 +279,7 @@ typedef struct CheckpointStatsData extern CheckpointStatsData CheckpointStats; extern XLogRecPtr XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata); +extern bool XLogCheckBufferNeedsBackup(Buffer buffer); extern void XLogFlush(XLogRecPtr RecPtr); extern bool XLogBackgroundFlush(void); extern bool XLogNeedsFlush(XLogRecPtr RecPtr); diff --git a/src/include/utils/pg_rbcompress.h b/src/include/utils/pg_rbcompress.h new file mode 100644 index 0000000..effba23 --- /dev/null +++ b/src/include/utils/pg_rbcompress.h @@ -0,0 +1,58 @@ +/* ---------- + * pg_rbcompress.h - + * + * Definitions for the PostgreSQL specific encoding scheme + * + * src/include/utils/pg_rbcompress.h + * ---------- + */ + +#ifndef _PG_RBCOMPRESS_H_ +#define _PG_RBCOMPRESS_H_ + + +/* ---------- + * PGRB_Strategy - + * + * Some values that control the compression algorithm. + * + * min_input_size Minimum input data size to consider compression. + * + * max_input_size Maximum input data size to consider compression. + * + * min_comp_rate Minimum compression rate (0-99%) to require. + * Regardless of min_comp_rate, the output must be + * smaller than the input, else we don't store + * compressed. + * ---------- + */ +typedef struct PGRB_Strategy +{ + int32 min_input_size; + int32 max_input_size; + int32 min_comp_rate; +} PGRB_Strategy; + + +/* ---------- + * The standard strategies + * + * PGRB_strategy_default Recommended default strategy for WAL + * compression. + * ---------- + */ +extern const PGRB_Strategy *const PGRB_strategy_default; + + +/* ---------- + * Global function declarations + * ---------- + */ +extern bool pgrb_delta_encode(const char *source, int32 slen, + const char *history, int32 hlen, + char *dest, uint32 *finallen, const PGRB_Strategy *strategy); +extern void pgrb_delta_decode(const char *source, uint32 srclen, + char *dest, uint32 destlen, uint32 *finallen, + const char *history, uint32 histlen); + +#endif /* _PG_RBCOMPRESS_H_ */ diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h index 9b8a4c9..717b90b 100644 --- a/src/include/utils/rel.h +++ b/src/include/utils/rel.h @@ -218,6 +218,7 @@ typedef struct StdRdOptions bool security_barrier; /* for views */ int check_option_offset; /* for views */ bool user_catalog_table; /* use as an additional catalog relation */ + bool wal_compress_update; /* compress wal tuple for update */ } StdRdOptions; #define HEAP_MIN_FILLFACTOR 10 @@ -296,6 +297,15 @@ typedef struct StdRdOptions ((StdRdOptions *) (relation)->rd_options)->user_catalog_table : false) /* + * RelationIsEnabledForWalCompression + * Returns whether the wal for update operation on relation can + * be compressed. + */ +#define RelationIsEnabledForWalCompression(relation) \ + ((relation)->rd_options ? \ + ((StdRdOptions *) (relation)->rd_options)->wal_compress_update : true) + +/* * RelationIsValid * True iff relation descriptor is valid. */ diff --git a/src/test/regress/expected/update.out b/src/test/regress/expected/update.out index 71b856f..af46df2 100644 --- a/src/test/regress/expected/update.out +++ b/src/test/regress/expected/update.out @@ -97,3 +97,73 @@ SELECT a, b, char_length(c) FROM update_test; (2 rows) DROP TABLE update_test; +-- +-- Test to update continuos and non continuos columns +-- +DROP TABLE IF EXISTS update_test; +NOTICE: table "update_test" does not exist, skipping +CREATE TABLE update_test ( + bser bigserial, + bln boolean, + ename VARCHAR(25), + perf_f float(8), + grade CHAR, + dept CHAR(5) NOT NULL, + dob DATE, + idnum INT, + addr VARCHAR(30) NOT NULL, + destn CHAR(6), + Gend CHAR, + samba BIGINT, + hgt float, + ctime TIME +); +INSERT INTO update_test VALUES ( + nextval('update_test_bser_seq'::regclass), + TRUE, + 'Test', + 7.169, + 'B', + 'CSD', + '2000-01-01', + 520, + 'road2, + streeeeet2, + city2', + 'dcy2', + 'M', + 12000, + 50.4, + '00:00:00.0' +); +SELECT * from update_test; + bser | bln | ename | perf_f | grade | dept | dob | idnum | addr | destn | gend | samba | hgt | ctime +------+-----+-------+--------+-------+-------+------------+-------+-----------------------------+--------+------+-------+------+---------- + 1 | t | Test | 7.169 | B | CSD | 01-01-2000 | 520 | road2, +| dcy2 | M | 12000 | 50.4 | 00:00:00 + | | | | | | | | streeeeet2,+| | | | | + | | | | | | | | city2 | | | | | +(1 row) + +-- update first column +UPDATE update_test SET bser = bser - 1 + 1; +-- update middle column +UPDATE update_test SET perf_f = 8.9; +-- update last column +UPDATE update_test SET ctime = '00:00:00.1'; +-- update 3 continuos columns +UPDATE update_test SET destn = 'dcy2', samba = 0 WHERE Gend = 'M' and dept = 'CSD'; +-- update two non continuos columns +UPDATE update_test SET destn = 'moved', samba = 0; +UPDATE update_test SET bln = FALSE, hgt = 10.1; +-- update causing some column alignment difference +UPDATE update_test SET ename = 'Tes'; +UPDATE update_test SET dept = 'Test'; +SELECT * from update_test; + bser | bln | ename | perf_f | grade | dept | dob | idnum | addr | destn | gend | samba | hgt | ctime +------+-----+-------+--------+-------+-------+------------+-------+-----------------------------+--------+------+-------+------+------------ + 1 | f | Tes | 8.9 | B | Test | 01-01-2000 | 520 | road2, +| moved | M | 0 | 10.1 | 00:00:00.1 + | | | | | | | | streeeeet2,+| | | | | + | | | | | | | | city2 | | | | | +(1 row) + +DROP TABLE update_test; diff --git a/src/test/regress/sql/update.sql b/src/test/regress/sql/update.sql index a8a028f..1806992 100644 --- a/src/test/regress/sql/update.sql +++ b/src/test/regress/sql/update.sql @@ -59,3 +59,70 @@ UPDATE update_test SET c = repeat('x', 10000) WHERE c = 'car'; SELECT a, b, char_length(c) FROM update_test; DROP TABLE update_test; + + +-- +-- Test to update continuos and non continuos columns +-- + +DROP TABLE IF EXISTS update_test; +CREATE TABLE update_test ( + bser bigserial, + bln boolean, + ename VARCHAR(25), + perf_f float(8), + grade CHAR, + dept CHAR(5) NOT NULL, + dob DATE, + idnum INT, + addr VARCHAR(30) NOT NULL, + destn CHAR(6), + Gend CHAR, + samba BIGINT, + hgt float, + ctime TIME +); + +INSERT INTO update_test VALUES ( + nextval('update_test_bser_seq'::regclass), + TRUE, + 'Test', + 7.169, + 'B', + 'CSD', + '2000-01-01', + 520, + 'road2, + streeeeet2, + city2', + 'dcy2', + 'M', + 12000, + 50.4, + '00:00:00.0' +); + +SELECT * from update_test; + +-- update first column +UPDATE update_test SET bser = bser - 1 + 1; + +-- update middle column +UPDATE update_test SET perf_f = 8.9; + +-- update last column +UPDATE update_test SET ctime = '00:00:00.1'; + +-- update 3 continuos columns +UPDATE update_test SET destn = 'dcy2', samba = 0 WHERE Gend = 'M' and dept = 'CSD'; + +-- update two non continuos columns +UPDATE update_test SET destn = 'moved', samba = 0; +UPDATE update_test SET bln = FALSE, hgt = 10.1; + +-- update causing some column alignment difference +UPDATE update_test SET ename = 'Tes'; +UPDATE update_test SET dept = 'Test'; + +SELECT * from update_test; +DROP TABLE update_test;