agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v27 1/9] Refactor COPY TO to use format callback functions. 8+ messages / 2 participants [nested] [flat]
* [PATCH v27 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 57 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 358 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index f55e6d96751..f81dadcc12b 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return COPY TO routines for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..eccc875d0e8 --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,57 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" +#include "executor/tuptable.h" +#include "nodes/execnodes.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index b54428b38cd..8edb41cce2e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -503,6 +503,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.45.2 ----Next_Part(Wed_Nov_27_16_53_44_2024_871)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v27-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v28 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 57 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 358 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 99cb23cb347..a885779666b 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return COPY TO routines for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..eccc875d0e8 --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,57 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" +#include "executor/tuptable.h" +#include "nodes/execnodes.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index d5aa5c295ae..18b2595300e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -508,6 +508,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.47.1 ----Next_Part(Thu_Jan_23_18_12_10_2025_763)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v28-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v29 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 57 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 358 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 99cb23cb347..26c67ddc351 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return a COPY TO routine for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..be29e3fbdef --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,57 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" +#include "executor/tuptable.h" +#include "nodes/execnodes.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a2644a2e653..1cbb3628857 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -508,6 +508,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.47.1 ----Next_Part(Fri_Jan_31_00_42_13_2025_303)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v29-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v30 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 57 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 358 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 99cb23cb347..26c67ddc351 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return a COPY TO routine for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..be29e3fbdef --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,57 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" +#include "executor/tuptable.h" +#include "nodes/execnodes.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a2644a2e653..1cbb3628857 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -508,6 +508,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.47.1 ----Next_Part(Sat_Feb__1_08_10_23_2025_403)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v30-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v31 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 55 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 356 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 99cb23cb347..26c67ddc351 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return a COPY TO routine for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..de5dae9cc38 --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,55 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a2644a2e653..1cbb3628857 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -508,6 +508,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.47.1 ----Next_Part(Sat_Feb__1_19_12_01_2025_760)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v31-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v32 1/9] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 55 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 356 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index 99cb23cb347..26c67ddc351 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return a COPY TO routine for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..de5dae9cc38 --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,55 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 9a3bee93dec..6b2f22d8555 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -508,6 +508,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.47.1 ----Next_Part(Thu_Feb__6_21_06_31_2025_538)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v32-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v26 1/8] Refactor COPY TO to use format callback functions. @ 2024-09-28 14:24 Sutou Kouhei <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Sutou Kouhei @ 2024-09-28 14:24 UTC (permalink / raw) This commit introduces a new CopyToRoutine struct, which is a set of callback routines to copy tuples in a specific format. It also makes the existing formats (text, CSV, and binary) utilize these format callbacks. This change is a preliminary step towards making the COPY TO command extensible in terms of output formats. Additionally, this refactoring contributes to a performance improvement by reducing the number of "if" branches that need to be checked on a per-row basis when sending field representations in text or CSV mode. The performance benchmark results showed ~5% performance gain in text or CSV mode. Author: Sutou Kouhei Reviewed-by: Michael Paquier, Tomas Vondra, Masahiko Sawada Reviewed-by: Junwang Zhao Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/copyto.c | 441 +++++++++++++++++++++---------- src/include/commands/copyapi.h | 57 ++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 358 insertions(+), 141 deletions(-) create mode 100644 src/include/commands/copyapi.h diff --git a/src/backend/commands/copyto.c b/src/backend/commands/copyto.c index f55e6d96751..f81dadcc12b 100644 --- a/src/backend/commands/copyto.c +++ b/src/backend/commands/copyto.c @@ -19,7 +19,7 @@ #include <sys/stat.h> #include "access/tableam.h" -#include "commands/copy.h" +#include "commands/copyapi.h" #include "commands/progress.h" #include "executor/execdesc.h" #include "executor/executor.h" @@ -64,6 +64,9 @@ typedef enum CopyDest */ typedef struct CopyToStateData { + /* format-specific routines */ + const CopyToRoutine *routine; + /* low-level state data */ CopyDest copy_dest; /* type of copy source/destination */ FILE *copy_file; /* used if copy_dest == COPY_FILE */ @@ -114,6 +117,19 @@ static void CopyAttributeOutText(CopyToState cstate, const char *string); static void CopyAttributeOutCSV(CopyToState cstate, const char *string, bool use_quote); +/* built-in format-specific routines */ +static void CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToTextLikeOneRow(CopyToState cstate, TupleTableSlot *slot, + bool is_csv); +static void CopyToTextLikeEnd(CopyToState cstate); +static void CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc); +static void CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo); +static void CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot); +static void CopyToBinaryEnd(CopyToState cstate); + /* Low-level communications functions */ static void SendCopyBegin(CopyToState cstate); static void SendCopyEnd(CopyToState cstate); @@ -121,9 +137,254 @@ static void CopySendData(CopyToState cstate, const void *databuf, int datasize); static void CopySendString(CopyToState cstate, const char *str); static void CopySendChar(CopyToState cstate, char c); static void CopySendEndOfRow(CopyToState cstate); +static void CopySendTextLikeEndOfRow(CopyToState cstate); static void CopySendInt32(CopyToState cstate, int32 val); static void CopySendInt16(CopyToState cstate, int16 val); +/* + * COPY TO routines for built-in formats. + * + * CSV and text formats share the same TextLike routines except for the + * one-row callback. + */ + +/* text format */ +static const CopyToRoutine CopyToRoutineText = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToTextOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* CSV format */ +static const CopyToRoutine CopyToRoutineCSV = { + .CopyToStart = CopyToTextLikeStart, + .CopyToOutFunc = CopyToTextLikeOutFunc, + .CopyToOneRow = CopyToCSVOneRow, + .CopyToEnd = CopyToTextLikeEnd, +}; + +/* binary format */ +static const CopyToRoutine CopyToRoutineBinary = { + .CopyToStart = CopyToBinaryStart, + .CopyToOutFunc = CopyToBinaryOutFunc, + .CopyToOneRow = CopyToBinaryOneRow, + .CopyToEnd = CopyToBinaryEnd, +}; + +/* Return COPY TO routines for the given options */ +static const CopyToRoutine * +CopyToGetRoutine(CopyFormatOptions opts) +{ + if (opts.csv_mode) + return &CopyToRoutineCSV; + else if (opts.binary) + return &CopyToRoutineBinary; + + /* default is text */ + return &CopyToRoutineText; +} + +/* Implementation of the start callback for text and CSV formats */ +static void +CopyToTextLikeStart(CopyToState cstate, TupleDesc tupDesc) +{ + /* + * For non-binary copy, we need to convert null_print to file encoding, + * because it will be sent directly with CopySendString. + */ + if (cstate->need_transcoding) + cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, + cstate->opts.null_print_len, + cstate->file_encoding); + + /* if a header has been requested send the line */ + if (cstate->opts.header_line) + { + ListCell *cur; + bool hdr_delim = false; + + foreach(cur, cstate->attnumlist) + { + int attnum = lfirst_int(cur); + char *colname; + + if (hdr_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + hdr_delim = true; + + colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); + + if (cstate->opts.csv_mode) + CopyAttributeOutCSV(cstate, colname, false); + else + CopyAttributeOutText(cstate, colname); + } + + CopySendTextLikeEndOfRow(cstate); + } +} + +/* + * Implementation of the outfunc callback for text and CSV formats. Assign + * the output function data to the given *finfo. + */ +static void +CopyToTextLikeOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for text format */ +static void +CopyToTextOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, false); +} + +/* Implementation of the per-row callback for CSV format */ +static void +CopyToCSVOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + CopyToTextLikeOneRow(cstate, slot, true); +} + +/* + * Workhorse for CopyToTextOneRow() and CopyToCSVOneRow(). + * + * We use pg_attribute_always_inline to reduce function call overheads. + */ +static pg_attribute_always_inline void +CopyToTextLikeOneRow(CopyToState cstate, + TupleTableSlot *slot, + bool is_csv) +{ + bool need_delim = false; + FmgrInfo *out_functions = cstate->out_functions; + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (need_delim) + CopySendChar(cstate, cstate->opts.delim[0]); + need_delim = true; + + if (isnull) + { + CopySendString(cstate, cstate->opts.null_print_client); + } + else + { + char *string; + + string = OutputFunctionCall(&out_functions[attnum - 1], + value); + + /* + * is_csv will be optimized away by compiler, as argument is + * constant at caller. + */ + if (is_csv) + CopyAttributeOutCSV(cstate, string, + cstate->opts.force_quote_flags[attnum - 1]); + else + CopyAttributeOutText(cstate, string); + } + } + + CopySendTextLikeEndOfRow(cstate); +} + +/* Implementation of the end callback for text and CSV formats */ +static void +CopyToTextLikeEnd(CopyToState cstate) +{ + /* Nothing to do here */ +} + +/* + * Implementation of the start callback for binary format. Send a header + * for a binary copy. + */ +static void +CopyToBinaryStart(CopyToState cstate, TupleDesc tupDesc) +{ + int32 tmp; + + /* Signature */ + CopySendData(cstate, BinarySignature, 11); + /* Flags field */ + tmp = 0; + CopySendInt32(cstate, tmp); + /* No header extension */ + tmp = 0; + CopySendInt32(cstate, tmp); +} + +/* + * Implementation of the outfunc callback for binary format. Assign + * the binary output function to the given *finfo. + */ +static void +CopyToBinaryOutFunc(CopyToState cstate, Oid atttypid, FmgrInfo *finfo) +{ + Oid func_oid; + bool is_varlena; + + /* Set output function for an attribute */ + getTypeBinaryOutputInfo(atttypid, &func_oid, &is_varlena); + fmgr_info(func_oid, finfo); +} + +/* Implementation of the per-row callback for binary format */ +static void +CopyToBinaryOneRow(CopyToState cstate, TupleTableSlot *slot) +{ + FmgrInfo *out_functions = cstate->out_functions; + + /* Binary per-tuple header */ + CopySendInt16(cstate, list_length(cstate->attnumlist)); + + foreach_int(attnum, cstate->attnumlist) + { + Datum value = slot->tts_values[attnum - 1]; + bool isnull = slot->tts_isnull[attnum - 1]; + + if (isnull) + { + CopySendInt32(cstate, -1); + } + else + { + bytea *outputbytes; + + outputbytes = SendFunctionCall(&out_functions[attnum - 1], + value); + CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); + CopySendData(cstate, VARDATA(outputbytes), + VARSIZE(outputbytes) - VARHDRSZ); + } + } + + CopySendEndOfRow(cstate); +} + +/* Implementation of the end callback for binary format */ +static void +CopyToBinaryEnd(CopyToState cstate) +{ + /* Generate trailer for a binary copy */ + CopySendInt16(cstate, -1); + /* Need to flush out the trailer */ + CopySendEndOfRow(cstate); +} /* * Send copy start/stop messages for frontend copies. These have changed @@ -191,16 +452,6 @@ CopySendEndOfRow(CopyToState cstate) switch (cstate->copy_dest) { case COPY_FILE: - if (!cstate->opts.binary) - { - /* Default line termination depends on platform */ -#ifndef WIN32 - CopySendChar(cstate, '\n'); -#else - CopySendString(cstate, "\r\n"); -#endif - } - if (fwrite(fe_msgbuf->data, fe_msgbuf->len, 1, cstate->copy_file) != 1 || ferror(cstate->copy_file)) @@ -235,10 +486,6 @@ CopySendEndOfRow(CopyToState cstate) } break; case COPY_FRONTEND: - /* The FE/BE protocol uses \n as newline for all platforms */ - if (!cstate->opts.binary) - CopySendChar(cstate, '\n'); - /* Dump the accumulated row as one CopyData message */ (void) pq_putmessage(PqMsg_CopyData, fe_msgbuf->data, fe_msgbuf->len); break; @@ -254,6 +501,35 @@ CopySendEndOfRow(CopyToState cstate) resetStringInfo(fe_msgbuf); } +/* + * Wrapper function of CopySendEndOfRow for text and CSV formats. Sends the + * the line termination and do common appropriate things for the end of row. + */ +static inline void +CopySendTextLikeEndOfRow(CopyToState cstate) +{ + switch (cstate->copy_dest) + { + case COPY_FILE: + /* Default line termination depends on platform */ +#ifndef WIN32 + CopySendChar(cstate, '\n'); +#else + CopySendString(cstate, "\r\n"); +#endif + break; + case COPY_FRONTEND: + /* The FE/BE protocol uses \n as newline for all platforms */ + CopySendChar(cstate, '\n'); + break; + default: + break; + } + + /* Now take the actions related to the end of a row */ + CopySendEndOfRow(cstate); +} + /* * These functions do apply some data conversion */ @@ -426,6 +702,9 @@ BeginCopyTo(ParseState *pstate, /* Extract options from the statement node tree */ ProcessCopyOptions(pstate, &cstate->opts, false /* is_from */ , options); + /* Set format routine */ + cstate->routine = CopyToGetRoutine(cstate->opts); + /* Process the source/target relation or query */ if (rel) { @@ -771,19 +1050,10 @@ DoCopyTo(CopyToState cstate) foreach(cur, cstate->attnumlist) { int attnum = lfirst_int(cur); - Oid out_func_oid; - bool isvarlena; Form_pg_attribute attr = TupleDescAttr(tupDesc, attnum - 1); - if (cstate->opts.binary) - getTypeBinaryOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - else - getTypeOutputInfo(attr->atttypid, - &out_func_oid, - &isvarlena); - fmgr_info(out_func_oid, &cstate->out_functions[attnum - 1]); + cstate->routine->CopyToOutFunc(cstate, attr->atttypid, + &cstate->out_functions[attnum - 1]); } /* @@ -796,56 +1066,7 @@ DoCopyTo(CopyToState cstate) "COPY TO", ALLOCSET_DEFAULT_SIZES); - if (cstate->opts.binary) - { - /* Generate header for a binary copy */ - int32 tmp; - - /* Signature */ - CopySendData(cstate, BinarySignature, 11); - /* Flags field */ - tmp = 0; - CopySendInt32(cstate, tmp); - /* No header extension */ - tmp = 0; - CopySendInt32(cstate, tmp); - } - else - { - /* - * For non-binary copy, we need to convert null_print to file - * encoding, because it will be sent directly with CopySendString. - */ - if (cstate->need_transcoding) - cstate->opts.null_print_client = pg_server_to_any(cstate->opts.null_print, - cstate->opts.null_print_len, - cstate->file_encoding); - - /* if a header has been requested send the line */ - if (cstate->opts.header_line) - { - bool hdr_delim = false; - - foreach(cur, cstate->attnumlist) - { - int attnum = lfirst_int(cur); - char *colname; - - if (hdr_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - hdr_delim = true; - - colname = NameStr(TupleDescAttr(tupDesc, attnum - 1)->attname); - - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, colname, false); - else - CopyAttributeOutText(cstate, colname); - } - - CopySendEndOfRow(cstate); - } - } + cstate->routine->CopyToStart(cstate, tupDesc); if (cstate->rel) { @@ -884,13 +1105,7 @@ DoCopyTo(CopyToState cstate) processed = ((DR_copy *) cstate->queryDesc->dest)->processed; } - if (cstate->opts.binary) - { - /* Generate trailer for a binary copy */ - CopySendInt16(cstate, -1); - /* Need to flush out the trailer */ - CopySendEndOfRow(cstate); - } + cstate->routine->CopyToEnd(cstate); MemoryContextDelete(cstate->rowcontext); @@ -903,74 +1118,18 @@ DoCopyTo(CopyToState cstate) /* * Emit one row during DoCopyTo(). */ -static void +static inline void CopyOneRowTo(CopyToState cstate, TupleTableSlot *slot) { - FmgrInfo *out_functions = cstate->out_functions; MemoryContext oldcontext; MemoryContextReset(cstate->rowcontext); oldcontext = MemoryContextSwitchTo(cstate->rowcontext); - if (cstate->opts.binary) - { - /* Binary per-tuple header */ - CopySendInt16(cstate, list_length(cstate->attnumlist)); - } - /* Make sure the tuple is fully deconstructed */ slot_getallattrs(slot); - if (!cstate->opts.binary) - { - bool need_delim = false; - - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - char *string; - - if (need_delim) - CopySendChar(cstate, cstate->opts.delim[0]); - need_delim = true; - - if (isnull) - CopySendString(cstate, cstate->opts.null_print_client); - else - { - string = OutputFunctionCall(&out_functions[attnum - 1], - value); - if (cstate->opts.csv_mode) - CopyAttributeOutCSV(cstate, string, - cstate->opts.force_quote_flags[attnum - 1]); - else - CopyAttributeOutText(cstate, string); - } - } - } - else - { - foreach_int(attnum, cstate->attnumlist) - { - Datum value = slot->tts_values[attnum - 1]; - bool isnull = slot->tts_isnull[attnum - 1]; - bytea *outputbytes; - - if (isnull) - CopySendInt32(cstate, -1); - else - { - outputbytes = SendFunctionCall(&out_functions[attnum - 1], - value); - CopySendInt32(cstate, VARSIZE(outputbytes) - VARHDRSZ); - CopySendData(cstate, VARDATA(outputbytes), - VARSIZE(outputbytes) - VARHDRSZ); - } - } - } - - CopySendEndOfRow(cstate); + cstate->routine->CopyToOneRow(cstate, slot); MemoryContextSwitchTo(oldcontext); } diff --git a/src/include/commands/copyapi.h b/src/include/commands/copyapi.h new file mode 100644 index 00000000000..eccc875d0e8 --- /dev/null +++ b/src/include/commands/copyapi.h @@ -0,0 +1,57 @@ +/*------------------------------------------------------------------------- + * + * copyapi.h + * API for COPY TO handlers + * + * + * Portions Copyright (c) 1996-2024, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/commands/copyapi.h + * + *------------------------------------------------------------------------- + */ +#ifndef COPYAPI_H +#define COPYAPI_H + +#include "commands/copy.h" +#include "executor/tuptable.h" +#include "nodes/execnodes.h" + +/* + * API structure for a COPY TO format implementation. Note this must be + * allocated in a server-lifetime manner, typically as a static const struct. + */ +typedef struct CopyToRoutine +{ + /* + * Set output function information. This callback is called once at the + * beginning of COPY TO. + * + * 'finfo' can be optionally filled to provide the catalog information of + * the output function. + * + * 'atttypid' is the OID of data type used by the relation's attribute. + */ + void (*CopyToOutFunc) (CopyToState cstate, Oid atttypid, + FmgrInfo *finfo); + + /* + * Start a COPY TO. This callback is called once at the beginning of COPY + * FROM. + * + * 'tupDesc' is the tuple descriptor of the relation from where the data + * is read. + */ + void (*CopyToStart) (CopyToState cstate, TupleDesc tupDesc); + + /* + * Write one row to the 'slot'. + */ + void (*CopyToOneRow) (CopyToState cstate, TupleTableSlot *slot); + + /* End a COPY TO. This callback is called once at the end of COPY FROM */ + void (*CopyToEnd) (CopyToState cstate); +} CopyToRoutine; + +#endif /* COPYAPI_H */ diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index b54428b38cd..8edb41cce2e 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -503,6 +503,7 @@ CopyMultiInsertInfo CopyOnErrorChoice CopySource CopyStmt +CopyToRoutine CopyToState CopyToStateData Cost -- 2.45.2 ----Next_Part(Mon_Nov_25_15_01_50_2024_156)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v26-0002-Refactor-COPY-FROM-to-use-format-callback-functi.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
* [PATCH v54 4/5] Error out any process that would block at REPACK @ 2026-04-01 15:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 8+ messages in thread From: Antonin Houska @ 2026-04-01 15:35 UTC (permalink / raw) Any process waiting on REPACK to release its lock would actually cause it to deadlock when it tries to upgrade its lock to AEL, losing all work done to that point. We avoid this by teaching the deadlock detector to raise an error when this condition is detected. --- src/backend/commands/repack.c | 47 ++++++++--- src/backend/storage/lmgr/deadlock.c | 15 ++++ src/include/storage/proc.h | 6 +- src/test/modules/injection_points/Makefile | 1 + .../expected/repack_deadlock.out | 63 ++++++++++++++ src/test/modules/injection_points/meson.build | 1 + .../specs/repack_deadlock.spec | 83 +++++++++++++++++++ 7 files changed, 201 insertions(+), 15 deletions(-) create mode 100644 src/test/modules/injection_points/expected/repack_deadlock.out create mode 100644 src/test/modules/injection_points/specs/repack_deadlock.spec diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index b0898ce52d9..d1be6c60e88 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -292,6 +292,18 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) * to understand and we don't lose any functionality. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); + + /* + * Also set the PROC_IN_CONCURRENT_REPACK flag. This makes the + * deadlock checker cause anyone that would conflict with us to error + * out. It's important to set this flag ahead of actually locking the + * relation; it won't of course affect anyone until we do have a lock + * that others can conflict with. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); } /* @@ -494,11 +506,8 @@ RepackLockLevel(bool concurrent) * If indexOid is InvalidOid, the table will be rewritten in physical order * instead of index order. * - * Note that, in the concurrent case, the function releases the lock at some - * point, in order to get AccessExclusiveLock for the final steps (i.e. to - * swap the relation files). To make things simpler, the caller should expect - * OldHeap to be closed on return, regardless CLUOPT_CONCURRENT. (The - * AccessExclusiveLock is kept till the end of the transaction.) + * On return, OldHeap is closed but locked with AccessExclusiveLock - the lock + * will be released at end of the transaction. * * 'cmd' indicates which command is being executed, to be used for error * messages. @@ -1004,10 +1013,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, * Note that the worker has to wait for all transactions with XID * already assigned to finish. If some of those transactions is * waiting for a lock conflicting with ShareUpdateExclusiveLock on our - * table (e.g. it runs CREATE INDEX), we can end up in a deadlock. - * Not sure this risk is worth unlocking/locking the table (and its - * clustering index) and checking again if it's still eligible for - * REPACK CONCURRENTLY. + * table (e.g. it runs CREATE INDEX), it should encounter ERROR in the + * deadlock checking code. */ start_repack_decoding_worker(tableOid); @@ -3096,7 +3103,19 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock); /* - * Tuples and pages of the old heap will be gone, but the heap will stay. + * Now that we have all access-exclusive locks on all relations, we no + * longer want other processes to error out when trying to acquire a + * conflicting lock. Therefore, unset our flag. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags &= ~PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + + /* + * Tuples and pages of the old heap will be gone, but the heap itself will + * stay. In order for predicate locks to continue to work, convert them + * to relation-level locks. We do this both for table and indexes. */ TransferPredicateLocksToHeapRelation(OldHeap); foreach_ptr(RelationData, index, indexrels) @@ -3370,9 +3389,11 @@ start_repack_decoding_worker(Oid relid) /* * The decoding setup must be done before the caller can have XID assigned - * for any reason, otherwise the worker might end up in a deadlock, - * waiting for the caller's transaction to end. Therefore wait here until - * the worker indicates that it has the logical decoding initialized. + * for any reason, otherwise the worker might end up waiting for the + * caller's transaction to end. (Deadlock detector does not consider this + * a conflict because the worker is in the same locking group as the + * backend that launched it.) Therefore wait here until the worker + * indicates that it has the logical decoding initialized. */ ConditionVariablePrepareToSleep(&shared->cv); for (;;) diff --git a/src/backend/storage/lmgr/deadlock.c b/src/backend/storage/lmgr/deadlock.c index b8962d875b6..c20ac682b0d 100644 --- a/src/backend/storage/lmgr/deadlock.c +++ b/src/backend/storage/lmgr/deadlock.c @@ -620,6 +620,21 @@ FindLockCycleRecurseMember(PGPROC *checkProc, proc->statusFlags & PROC_IS_AUTOVACUUM) blocking_autovacuum_proc = proc; + /* + * Similarly, if we note that we're blocked by some + * process running REPACK (CONCURRENTLY), just fail. That + * process is going to upgrade its lock at some point, and + * it would be inappropriate for any other process to + * cause that to fail. + */ + if (checkProc == MyProc && + proc->statusFlags & PROC_IN_CONCURRENT_REPACK) + ereport(ERROR, + errcode(ERRCODE_OBJECT_IN_USE), + errmsg("could not wait for concurrent REPACK"), + errdetail("Process %d waits for REPACK running on process %d", + MyProc->pid, proc->pid)); + /* We're done looking at this proclock */ break; } diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 22822fc68d7..a43cfe53558 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -70,10 +70,12 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_CONCURRENT_REPACK 0x40 /* REPACK (CONCURRENTLY) */ -/* flags reset at EOXact */ +/* flags reset at EOXact. A bit of a misnomer ... */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | \ + PROC_IN_CONCURRENT_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/test/modules/injection_points/Makefile b/src/test/modules/injection_points/Makefile index 2cd7d87c533..f7663859fe2 100644 --- a/src/test/modules/injection_points/Makefile +++ b/src/test/modules/injection_points/Makefile @@ -15,6 +15,7 @@ REGRESS_OPTS = --dlpath=$(top_builddir)/src/test/regress ISOLATION = basic \ inplace \ repack \ + repack_deadlock \ repack_toast \ syscache-update-pruned \ heap_lock_update diff --git a/src/test/modules/injection_points/expected/repack_deadlock.out b/src/test/modules/injection_points/expected/repack_deadlock.out new file mode 100644 index 00000000000..a86e4767536 --- /dev/null +++ b/src/test/modules/injection_points/expected/repack_deadlock.out @@ -0,0 +1,63 @@ +Parsed test spec with 2 sessions + +starting permutation: wait_before_lock add_column wakeup_before_lock check1 +injection_points_attach +----------------------- + +(1 row) + +step wait_before_lock: + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; + <waiting ...> +step add_column: + alter table repack_deadlock add column noise text; + <waiting ...> +step add_column: <... completed> +ERROR: could not wait for concurrent REPACK +step wakeup_before_lock: + SELECT injection_points_wakeup('repack-concurrently-before-lock'); + +injection_points_wakeup +----------------------- + +(1 row) + +step wait_before_lock: <... completed> +step check1: + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; + +count +----- + 1 +(1 row) + +i|j +-+- +1|1 +2|2 +3|3 +4|4 +(4 rows) + +count +----- + 4 +(1 row) + +injection_points_detach +----------------------- + +(1 row) + diff --git a/src/test/modules/injection_points/meson.build b/src/test/modules/injection_points/meson.build index a414abb924b..1cd88d6db65 100644 --- a/src/test/modules/injection_points/meson.build +++ b/src/test/modules/injection_points/meson.build @@ -46,6 +46,7 @@ tests += { 'basic', 'inplace', 'repack', + 'repack_deadlock', 'repack_toast', 'syscache-update-pruned', 'heap_lock_update', diff --git a/src/test/modules/injection_points/specs/repack_deadlock.spec b/src/test/modules/injection_points/specs/repack_deadlock.spec new file mode 100644 index 00000000000..9d23a6588c2 --- /dev/null +++ b/src/test/modules/injection_points/specs/repack_deadlock.spec @@ -0,0 +1,83 @@ +# Test REPACK with a concurrent transaction that would cause a deadlock +setup +{ + CREATE EXTENSION injection_points; + + CREATE TABLE repack_deadlock(i int PRIMARY KEY, j int); + INSERT INTO repack_deadlock(i, j) VALUES (1, 1), (2, 2), (3, 3), (4, 4); + + CREATE TABLE relfilenodes(node oid); + + CREATE TABLE data_s1(i int, j int); + CREATE TABLE data_s2(i int, j int); +} + +teardown +{ + DROP TABLE repack_deadlock; + DROP EXTENSION injection_points; + + DROP TABLE relfilenodes; + DROP TABLE data_s1; + DROP TABLE data_s2; +} + +session s1 +setup +{ + SELECT injection_points_set_local(); + SELECT injection_points_attach('repack-concurrently-before-lock', 'wait'); +} +# Perform the initial load and wait for s2 to do some data changes. +step wait_before_lock +{ + REPACK (CONCURRENTLY) repack_deadlock USING INDEX repack_deadlock_pkey; +} +# Check the table from the perspective of s1. +# +# Besides the contents, we also check that relfilenode has changed. + +# Have each session write the contents into a table and use FULL JOIN to check +# if the outputs are identical. +step check1 +{ + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_deadlock'; + + SELECT count(DISTINCT node) FROM relfilenodes; + + SELECT i, j FROM repack_deadlock ORDER BY i, j; + + INSERT INTO data_s1(i, j) + SELECT i, j FROM repack_deadlock; + + SELECT count(*) + FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) + WHERE d1.i ISNULL OR d2.i ISNULL; +} +teardown +{ + SELECT injection_points_detach('repack-concurrently-before-lock'); +} + +session s2 +# Change the existing data. UPDATE changes both key and non-key columns. Also +# update one row twice to test whether tuple version generated by this session +# can be found. +step add_column +{ + alter table repack_deadlock add column noise text; +} + +step wakeup_before_lock +{ + SELECT injection_points_wakeup('repack-concurrently-before-lock'); +} + +# Test if data changes introduced while one session is performing REPACK +# CONCURRENTLY find their way into the table. +permutation + wait_before_lock + add_column + wakeup_before_lock + check1 -- 2.47.3 --cdhh4t7ukb6tnjoq Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v54-0005-Reserve-replication-slots-specifically-for-REPAC.patch" ^ permalink raw reply [nested|flat] 8+ messages in thread
end of thread, other threads:[~2026-04-01 15:35 UTC | newest] Thread overview: 8+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2024-09-28 14:24 [PATCH v30 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v31 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v32 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v26 1/8] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v27 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v28 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2024-09-28 14:24 [PATCH v29 1/9] Refactor COPY TO to use format callback functions. Sutou Kouhei <[email protected]> 2026-04-01 15:35 [PATCH v54 4/5] Error out any process that would block at REPACK Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox