parallel_pgdump_nopgpipe.patch
text/x-patch
Filename: parallel_pgdump_nopgpipe.patch
Type: text/x-patch
Part: 0
Message:
Re: patch for parallel pg_dump
Patch
Same data as JSON:
GET /api/v1/attachments/:id/patch
the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes.
API reference →
Format: context
| File | + | − |
|---|---|---|
| src/bin/pg_dump/compress_io.c | 10 | 0 |
| src/bin/pg_dump/dumputils.c | 58 | 0 |
| src/bin/pg_dump/dumputils.h | 4 | 0 |
| src/bin/pg_dump/Makefile | 2 | 0 |
| src/bin/pg_dump/parallel.c | 1321 | 0 |
| src/bin/pg_dump/parallel.h | 86 | 0 |
| src/bin/pg_dump/pg_backup_archiver.c | 255 | 66 |
| src/bin/pg_dump/pg_backup_archiver.h | 46 | 0 |
| src/bin/pg_dump/pg_backup_custom.c | 88 | 0 |
| src/bin/pg_dump/pg_backup_db.c | 19 | 0 |
| src/bin/pg_dump/pg_backup_directory.c | 211 | 0 |
| src/bin/pg_dump/pg_backup.h | 7 | 0 |
| src/bin/pg_dump/pg_backup_tar.c | 7 | 0 |
| src/bin/pg_dump/pg_dumpall.c | 3 | 0 |
| src/bin/pg_dump/pg_dump.c | 164 | 0 |
| src/bin/pg_dump/pg_dump.h | 3 | 0 |
| src/bin/pg_dump/pg_dump_sort.c | 87 | 0 |
| src/bin/pg_dump/pg_restore.c | 21 | 0 |
| src/tools/msvc/Mkvcbuild.pm | 4 | 0 |
*** a/src/bin/pg_dump/Makefile
--- b/src/bin/pg_dump/Makefile
***************
*** 20,26 **** override CPPFLAGS := -I$(libpq_srcdir) $(CPPFLAGS)
OBJS= pg_backup_archiver.o pg_backup_db.o pg_backup_custom.o \
pg_backup_null.o pg_backup_tar.o \
! pg_backup_directory.o dumpmem.o dumputils.o compress_io.o $(WIN32RES)
KEYWRDOBJS = keywords.o kwlookup.o
--- 20,27 ----
OBJS= pg_backup_archiver.o pg_backup_db.o pg_backup_custom.o \
pg_backup_null.o pg_backup_tar.o \
! pg_backup_directory.o dumpmem.o dumputils.o compress_io.o \
! parallel.o $(WIN32RES)
KEYWRDOBJS = keywords.o kwlookup.o
*** a/src/bin/pg_dump/compress_io.c
--- b/src/bin/pg_dump/compress_io.c
***************
*** 55,60 ****
--- 55,61 ----
#include "compress_io.h"
#include "dumpmem.h"
#include "dumputils.h"
+ #include "parallel.h"
/*----------------------
* Compressor API
***************
*** 182,187 **** size_t
--- 183,191 ----
WriteDataToArchive(ArchiveHandle *AH, CompressorState *cs,
const void *data, size_t dLen)
{
+ /* Are we aborting? */
+ checkAborting(AH);
+
switch (cs->comprAlg)
{
case COMPR_ALG_LIBZ:
***************
*** 351,356 **** ReadDataFromArchiveZlib(ArchiveHandle *AH, ReadFunc readF)
--- 355,363 ----
/* no minimal chunk size for zlib */
while ((cnt = readF(AH, &buf, &buflen)))
{
+ /* Are we aborting? */
+ checkAborting(AH);
+
zp->next_in = (void *) buf;
zp->avail_in = cnt;
***************
*** 411,416 **** ReadDataFromArchiveNone(ArchiveHandle *AH, ReadFunc readF)
--- 418,426 ----
while ((cnt = readF(AH, &buf, &buflen)))
{
+ /* Are we aborting? */
+ checkAborting(AH);
+
ahwrite(buf, 1, cnt, AH);
}
*** a/src/bin/pg_dump/dumputils.c
--- b/src/bin/pg_dump/dumputils.c
***************
*** 16,21 ****
--- 16,22 ----
#include <ctype.h>
+ #include "dumpmem.h"
#include "dumputils.h"
#include "pg_backup.h"
***************
*** 35,40 **** static struct
--- 36,42 ----
} on_exit_nicely_list[MAX_ON_EXIT_NICELY];
static int on_exit_nicely_index;
+ void (*on_exit_msg_func)(const char *modulename, const char *fmt, va_list ap) = vwrite_msg;
#define supports_grant_options(version) ((version) >= 70400)
***************
*** 45,50 **** static bool parseAclItem(const char *item, const char *type,
--- 47,53 ----
static char *copyAclUserName(PQExpBuffer output, char *input);
static void AddAcl(PQExpBuffer aclbuf, const char *keyword,
const char *subname);
+ static PQExpBuffer getThreadLocalPQExpBuffer(void);
#ifdef WIN32
static bool parallel_init_done = false;
***************
*** 66,80 **** init_parallel_dump_utils(void)
}
/*
! * Quotes input string if it's not a legitimate SQL identifier as-is.
! *
! * Note that the returned string must be used before calling fmtId again,
! * since we re-use the same return buffer each time. Non-reentrant but
! * reduces memory leakage. (On Windows the memory leakage will be one buffer
! * per thread, which is at least better than one per call).
*/
! const char *
! fmtId(const char *rawid)
{
/*
* The Tls code goes awry if we use a static var, so we provide for both
--- 69,79 ----
}
/*
! * Non-reentrant but reduces memory leakage. (On Windows the memory leakage
! * will be one buffer per thread, which is at least better than one per call).
*/
! static PQExpBuffer
! getThreadLocalPQExpBuffer(void)
{
/*
* The Tls code goes awry if we use a static var, so we provide for both
***************
*** 83,91 **** fmtId(const char *rawid)
static PQExpBuffer s_id_return = NULL;
PQExpBuffer id_return;
- const char *cp;
- bool need_quotes = false;
-
#ifdef WIN32
if (parallel_init_done)
id_return = (PQExpBuffer) TlsGetValue(tls_index); /* 0 when not set */
--- 82,87 ----
***************
*** 112,120 **** fmtId(const char *rawid)
#else
s_id_return = id_return;
#endif
-
}
/*
* These checks need to match the identifier production in scan.l. Don't
* use islower() etc.
--- 108,132 ----
#else
s_id_return = id_return;
#endif
}
+ return id_return;
+ }
+
+ /*
+ * Quotes input string if it's not a legitimate SQL identifier as-is.
+ *
+ * Note that the returned string must be used before calling fmtId again,
+ * since we re-use the same return buffer each time.
+ */
+ const char *
+ fmtId(const char *rawid)
+ {
+ PQExpBuffer id_return = getThreadLocalPQExpBuffer();
+
+ const char *cp;
+ bool need_quotes = false;
+
/*
* These checks need to match the identifier production in scan.l. Don't
* use islower() etc.
***************
*** 182,187 **** fmtId(const char *rawid)
--- 194,228 ----
return id_return->data;
}
+ /*
+ * fmtQualifiedId - convert a qualified name to the proper format for
+ * the source database.
+ *
+ * Like fmtId, use the result before calling again.
+ *
+ * Since we call fmtId and it also uses getThreadLocalPQExpBuffer() we cannot
+ * use it until we're finished with calling fmtId().
+ */
+ const char *
+ fmtQualifiedId(int remoteVersion, const char *schema, const char *id)
+ {
+ PQExpBuffer id_return;
+ PQExpBuffer lcl_pqexp = createPQExpBuffer();
+
+ /* Suppress schema name if fetching from pre-7.3 DB */
+ if (remoteVersion >= 70300 && schema && *schema)
+ {
+ appendPQExpBuffer(lcl_pqexp, "%s.", fmtId(schema));
+ }
+ appendPQExpBuffer(lcl_pqexp, "%s", fmtId(id));
+
+ id_return = getThreadLocalPQExpBuffer();
+
+ appendPQExpBuffer(id_return, "%s", lcl_pqexp->data);
+ destroyPQExpBuffer(lcl_pqexp);
+
+ return id_return->data;
+ }
/*
* Convert a string value to an SQL string literal and append it to
***************
*** 1269,1275 **** exit_horribly(const char *modulename, const char *fmt,...)
va_list ap;
va_start(ap, fmt);
! vwrite_msg(modulename, fmt, ap);
va_end(ap);
exit_nicely(1);
--- 1310,1316 ----
va_list ap;
va_start(ap, fmt);
! on_exit_msg_func(modulename, fmt, ap);
va_end(ap);
exit_nicely(1);
***************
*** 1319,1327 **** on_exit_nicely(on_exit_nicely_callback function, void *arg)
void
exit_nicely(int code)
{
! while (--on_exit_nicely_index >= 0)
! (*on_exit_nicely_list[on_exit_nicely_index].function)(code,
! on_exit_nicely_list[on_exit_nicely_index].arg);
#ifdef WIN32
if (parallel_init_done && GetCurrentThreadId() != mainThreadId)
ExitThread(code);
--- 1360,1369 ----
void
exit_nicely(int code)
{
! int i;
! for (i = 0; i < on_exit_nicely_index; i++)
! (*on_exit_nicely_list[i].function)(code,
! on_exit_nicely_list[i].arg);
#ifdef WIN32
if (parallel_init_done && GetCurrentThreadId() != mainThreadId)
ExitThread(code);
*** a/src/bin/pg_dump/dumputils.h
--- b/src/bin/pg_dump/dumputils.h
***************
*** 24,29 **** extern const char *progname;
--- 24,31 ----
extern void init_parallel_dump_utils(void);
extern const char *fmtId(const char *identifier);
+ extern const char *fmtQualifiedId(int remoteVersion,
+ const char *schema, const char *id);
extern void appendStringLiteral(PQExpBuffer buf, const char *str,
int encoding, bool std_strings);
extern void appendStringLiteralConn(PQExpBuffer buf, const char *str,
***************
*** 60,65 **** extern void exit_horribly(const char *modulename, const char *fmt,...)
--- 62,69 ----
__attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 3), noreturn));
extern void set_section (const char *arg, int *dumpSections);
+ extern void (*on_exit_msg_func)(const char *modulename, const char *fmt, va_list ap)
+ __attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 0)));
typedef void (*on_exit_nicely_callback) (int code, void *arg);
extern void on_exit_nicely(on_exit_nicely_callback function, void *arg);
extern void exit_nicely(int code) __attribute__((noreturn));
*** /dev/null
--- b/src/bin/pg_dump/parallel.c
***************
*** 0 ****
--- 1,1321 ----
+ /*-------------------------------------------------------------------------
+ *
+ * parallel.c
+ *
+ * Parallel support for the pg_dump archiver
+ *
+ * Portions Copyright (c) 1996-2011, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * The author is not responsible for loss or damages that may
+ * result from its use.
+ *
+ * IDENTIFICATION
+ * src/bin/pg_dump/parallel.c
+ *
+ *-------------------------------------------------------------------------
+ */
+
+ #include "pg_backup_db.h"
+
+ #include "dumpmem.h"
+ #include "dumputils.h"
+ #include "parallel.h"
+
+ #ifndef WIN32
+ #include <sys/types.h>
+ #include <sys/wait.h>
+ #include "signal.h"
+ #include <unistd.h>
+ #include <fcntl.h>
+ #endif
+
+ #define PIPE_READ 0
+ #define PIPE_WRITE 1
+
+ /* file-scope variables */
+ #ifdef WIN32
+ static unsigned int tMasterThreadId = 0;
+ static HANDLE termEvent = INVALID_HANDLE_VALUE;
+ static int pgpipe(int handles[2]);
+ static int piperead(int s, char *buf, int len);
+ #define pipewrite(a,b,c) send(a,b,c,0)
+ #else
+ static volatile sig_atomic_t wantAbort = 0;
+ static bool aborting = false;
+ #define pipewrite(a,b,c) write(a,b,c)
+ #endif
+
+ typedef struct ShutdownInformation
+ {
+ ParallelState *pstate;
+ Archive *AHX;
+ } ShutdownInformation;
+
+ static ShutdownInformation shutdown_info;
+
+ static const char *modulename = gettext_noop("parallel archiver");
+
+ static ParallelSlot *GetMyPSlot(ParallelState *pstate);
+ static void parallel_exit_msg_func(const char *modulename,
+ const char *fmt, va_list ap)
+ __attribute__((format(PG_PRINTF_ATTRIBUTE, 2, 0)));
+ static void parallel_msg_master(ParallelSlot *slot, const char *modulename,
+ const char *fmt, va_list ap)
+ __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 0)));
+ static void archive_close_connection(int code, void *arg);
+ static void ShutdownWorkersHard(ParallelState *pstate);
+ static void ShutdownWorkersSoft(ParallelState *pstate, bool do_wait);
+ static void WaitForTerminatingWorkers(ParallelState *pstate);
+ #ifndef WIN32
+ static void sigTermHandler(int signum);
+ #endif
+ static void SetupWorker(ArchiveHandle *AH, int pipefd[2], int worker,
+ RestoreOptions *ropt);
+ static void PrintStatus(ParallelState *pstate);
+ static bool HasEveryWorkerTerminated(ParallelState *pstate);
+
+ static void lockTableNoWait(ArchiveHandle *AH, TocEntry *te);
+ static void WaitForCommands(ArchiveHandle *AH, int pipefd[2]);
+ static char *getMessageFromMaster(int pipefd[2]);
+ static void sendMessageToMaster(int pipefd[2], const char *str);
+ static int select_loop(int maxFd, fd_set *workerset);
+ static char *getMessageFromWorker(ParallelState *pstate,
+ bool do_wait, int *worker);
+ static void sendMessageToWorker(ParallelState *pstate,
+ int worker, const char *str);
+ static char *readMessageFromPipe(int fd);
+
+ #define messageStartsWith(msg, prefix) \
+ (strncmp(msg, prefix, strlen(prefix)) == 0)
+ #define messageEquals(msg, pattern) \
+ (strcmp(msg, pattern) == 0)
+
+ static ParallelSlot *
+ GetMyPSlot(ParallelState *pstate)
+ {
+ int i;
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ #ifdef WIN32
+ if (pstate->parallelSlot[i].threadId == GetCurrentThreadId())
+ #else
+ if (pstate->parallelSlot[i].pid == getpid())
+ #endif
+ return &(pstate->parallelSlot[i]);
+
+ return NULL;
+ }
+
+ /*
+ * This is the function that will be called from exit_horribly() to print the
+ * error message. If the worker process does exit_horribly(), we forward its
+ * last words to the master process. The master process then does exit_horribly()
+ * with this error message itself and prints it normally. After printing the
+ * message, exit_horribly() on the master will shut down the remaining worker
+ * processes.
+ */
+ static void
+ parallel_exit_msg_func(const char *modulename, const char *fmt, va_list ap)
+ {
+ ParallelState *pstate = shutdown_info.pstate;
+ ParallelSlot *slot;
+
+ Assert(pstate);
+
+ slot = GetMyPSlot(pstate);
+
+ if (!slot)
+ /* We're the parent, just write the message out */
+ vwrite_msg(modulename, fmt, ap);
+ else
+ /* If we're a worker process, send the msg to the master process */
+ parallel_msg_master(slot, modulename, fmt, ap);
+ }
+
+ /* Sends the error message from the worker to the master process */
+ static void
+ parallel_msg_master(ParallelSlot *slot, const char *modulename,
+ const char *fmt, va_list ap)
+ {
+ char buf[512];
+ int pipefd[2];
+
+ pipefd[PIPE_READ] = slot->pipeRevRead;
+ pipefd[PIPE_WRITE] = slot->pipeRevWrite;
+
+ strcpy(buf, "ERROR ");
+ vsnprintf(buf + strlen("ERROR "),
+ sizeof(buf) - strlen("ERROR "), fmt, ap);
+
+ sendMessageToMaster(pipefd, buf);
+ }
+
+ /*
+ * pg_dump and pg_restore register the Archive pointer for the exit handler
+ * (called from exit_horribly). This function mainly exists so that we can keep
+ * shutdown_info in file scope only.
+ */
+ void
+ on_exit_close_archive(Archive *AHX)
+ {
+ shutdown_info.AHX = AHX;
+ on_exit_nicely(archive_close_connection, &shutdown_info);
+ }
+
+ /* This function can close archives in both the parallel and non-parallel case. */
+ static void
+ archive_close_connection(int code, void *arg)
+ {
+ ShutdownInformation *si = (ShutdownInformation *) arg;
+
+ if (si->pstate)
+ {
+ ParallelSlot *slot = GetMyPSlot(si->pstate);
+
+ if (!slot) {
+ /*
+ * We're the master: We have already printed out the message passed
+ * to exit_horribly() either from the master itself or from a
+ * worker process. Now we need to close our own database connection
+ * (only open during parallel dump but not restore) and shut down
+ * the remaining workers.
+ */
+ DisconnectDatabase(si->AHX);
+ #ifndef WIN32
+ /*
+ * Setting aborting to true switches to best-effort-mode
+ * (send/receive but ignore errors) in communicating with our
+ * workers.
+ */
+ aborting = true;
+ #endif
+ ShutdownWorkersHard(si->pstate);
+ }
+ else if (slot->args->AH)
+ DisconnectDatabase(&(slot->args->AH->public));
+ }
+ else if (si->AHX)
+ DisconnectDatabase(si->AHX);
+ }
+
+ /*
+ * If we have one worker that terminates for some reason, we'd like the other
+ * threads to terminate as well (and not finish with their 70 GB table dump
+ * first...). Now in UNIX we can just kill these processes, and let the signal
+ * handler set wantAbort to 1. In Windows we set a termEvent and this serves as
+ * the signal for everyone to terminate.
+ */
+ void
+ checkAborting(ArchiveHandle *AH)
+ {
+ #ifdef WIN32
+ if (WaitForSingleObject(termEvent, 0) == WAIT_OBJECT_0)
+ #else
+ if (wantAbort)
+ #endif
+ exit_horribly(modulename, "worker is terminating\n");
+ }
+
+ /*
+ * Shut down any remaining workers, this has an implicit do_wait == true.
+ *
+ * The fastest way we can make the workers terminate gracefully is when
+ * they are listening for new commands and we just tell them to terminate.
+ */
+ static void
+ ShutdownWorkersHard(ParallelState *pstate)
+ {
+ #ifndef WIN32
+ int i;
+ signal(SIGPIPE, SIG_IGN);
+ ShutdownWorkersSoft(pstate, false);
+ for (i = 0; i < pstate->numWorkers; i++)
+ kill(pstate->parallelSlot[i].pid, SIGTERM);
+ WaitForTerminatingWorkers(pstate);
+ #else
+ /* The workers monitor this event via checkAborting(). */
+ SetEvent(termEvent);
+ /* No hard shutdown on Windows, wait for the workers to terminate */
+ ShutdownWorkersSoft(pstate, true);
+ #endif
+ }
+
+ /*
+ * Performs a soft shutdown and optionally waits for every worker to terminate.
+ * A soft shutdown sends a "TERMINATE" message to every worker only.
+ */
+ static void
+ ShutdownWorkersSoft(ParallelState *pstate, bool do_wait)
+ {
+ int i;
+
+ /* soft shutdown */
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ if (pstate->parallelSlot[i].workerStatus != WRKR_TERMINATED)
+ {
+ sendMessageToWorker(pstate, i, "TERMINATE");
+ pstate->parallelSlot[i].workerStatus = WRKR_WORKING;
+ }
+ }
+
+ if (!do_wait)
+ return;
+
+ WaitForTerminatingWorkers(pstate);
+ }
+
+ /*
+ * Wait for the termination of the processes using the OS-specific method.
+ */
+ static void
+ WaitForTerminatingWorkers(ParallelState *pstate)
+ {
+ while (!HasEveryWorkerTerminated(pstate))
+ {
+ ParallelSlot *slot;
+ int j;
+ #ifndef WIN32
+ int status;
+ pid_t pid = wait(&status);
+ for (j = 0; j < pstate->numWorkers; j++)
+ if (pstate->parallelSlot[j].pid == pid)
+ slot = &(pstate->parallelSlot[j]);
+ #else
+ uintptr_t hThread;
+ DWORD ret;
+ uintptr_t *lpHandles = pg_malloc(sizeof(HANDLE) * pstate->numWorkers);
+ int nrun = 0;
+ for (j = 0; j < pstate->numWorkers; j++)
+ if (pstate->parallelSlot[j].workerStatus != WRKR_TERMINATED)
+ {
+ lpHandles[nrun] = pstate->parallelSlot[j].hThread;
+ nrun++;
+ }
+ ret = WaitForMultipleObjects(nrun, (HANDLE*) lpHandles, false, INFINITE);
+ Assert(ret != WAIT_FAILED);
+ hThread = lpHandles[ret - WAIT_OBJECT_0];
+
+ for (j = 0; j < pstate->numWorkers; j++)
+ if (pstate->parallelSlot[j].hThread == hThread)
+ slot = &(pstate->parallelSlot[j]);
+
+ free(lpHandles);
+ #endif
+ Assert(slot);
+
+ slot->workerStatus = WRKR_TERMINATED;
+
+ PrintStatus(pstate);
+ }
+ Assert(HasEveryWorkerTerminated(pstate));
+ }
+
+ #ifndef WIN32
+ /* Signal handling (UNIX only) */
+ static void
+ sigTermHandler(int signum)
+ {
+ wantAbort = 1;
+ }
+ #endif
+
+ /*
+ * This function is called by both UNIX and Windows variants to set up a
+ * worker process.
+ */
+ static void
+ SetupWorker(ArchiveHandle *AH, int pipefd[2], int worker,
+ RestoreOptions *ropt)
+ {
+ /*
+ * In dump mode (pg_dump) this calls _SetupWorker() as defined in
+ * pg_dump.c, while in restore mode (pg_restore) it calls _SetupWorker() as
+ * defined in pg_restore.c.
+ *
+ * We get the raw connection only for the reason that we can close it
+ * properly when we shut down. This happens only that way when it is
+ * brought down because of an error.
+ */
+ _SetupWorker((Archive *) AH, ropt);
+
+ Assert(AH->connection != NULL);
+
+ WaitForCommands(AH, pipefd);
+
+ closesocket(pipefd[PIPE_READ]);
+ closesocket(pipefd[PIPE_WRITE]);
+ }
+
+ #ifdef WIN32
+ /*
+ * On Windows the _beginthreadex() function allows us to pass one parameter.
+ * Since we need to pass a few values however, we define a structure here
+ * and then pass a pointer to such a structure in _beginthreadex().
+ */
+ typedef struct {
+ ArchiveHandle *AH;
+ RestoreOptions *ropt;
+ int worker;
+ int pipeRead;
+ int pipeWrite;
+ } WorkerInfo;
+
+ static unsigned __stdcall
+ init_spawned_worker_win32(WorkerInfo *wi)
+ {
+ ArchiveHandle *AH;
+ int pipefd[2] = { wi->pipeRead, wi->pipeWrite };
+ int worker = wi->worker;
+ RestoreOptions *ropt = wi->ropt;
+
+ AH = CloneArchive(wi->AH);
+
+ free(wi);
+ SetupWorker(AH, pipefd, worker, ropt);
+
+ DeCloneArchive(AH);
+ _endthreadex(0);
+ return 0;
+ }
+ #endif
+
+ /*
+ * This function starts the parallel dump or restore by spawning off the worker
+ * processes in both Unix and Windows. For Windows, it creates a number of
+ * threads while it does a fork() on Unix.
+ */
+ ParallelState *
+ ParallelBackupStart(ArchiveHandle *AH, RestoreOptions *ropt)
+ {
+ ParallelState *pstate;
+ int i;
+ const size_t slotSize = AH->public.numWorkers * sizeof(ParallelSlot);
+
+ Assert(AH->public.numWorkers > 0);
+
+ /* Ensure stdio state is quiesced before forking */
+ fflush(NULL);
+
+ pstate = (ParallelState *) pg_malloc(sizeof(ParallelState));
+
+ pstate->numWorkers = AH->public.numWorkers;
+ pstate->parallelSlot = NULL;
+
+ if (AH->public.numWorkers == 1)
+ return pstate;
+
+ pstate->parallelSlot = (ParallelSlot *) pg_malloc(slotSize);
+ memset((void *) pstate->parallelSlot, 0, slotSize);
+
+ /*
+ * Set the pstate in the shutdown_info. The exit handler uses pstate if
+ * set and falls back to AHX otherwise.
+ */
+ shutdown_info.pstate = pstate;
+ on_exit_msg_func = parallel_exit_msg_func;
+
+ #ifdef WIN32
+ tMasterThreadId = GetCurrentThreadId();
+ termEvent = CreateEvent(NULL, true, false, "Terminate");
+ #else
+ signal(SIGTERM, sigTermHandler);
+ signal(SIGINT, sigTermHandler);
+ signal(SIGQUIT, sigTermHandler);
+ #endif
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ #ifdef WIN32
+ WorkerInfo *wi;
+ uintptr_t handle;
+ #else
+ pid_t pid;
+ #endif
+ int pipeMW[2], pipeWM[2];
+
+ if (pgpipe(pipeMW) < 0 || pgpipe(pipeWM) < 0)
+ exit_horribly(modulename, "Cannot create communication channels: %s\n",
+ strerror(errno));
+
+ pstate->parallelSlot[i].workerStatus = WRKR_IDLE;
+ pstate->parallelSlot[i].args = (ParallelArgs *) pg_malloc(sizeof(ParallelArgs));
+ pstate->parallelSlot[i].args->AH = NULL;
+ pstate->parallelSlot[i].args->te = NULL;
+ #ifdef WIN32
+ /* Allocate a new structure for every worker */
+ wi = (WorkerInfo *) pg_malloc(sizeof(WorkerInfo));
+
+ wi->ropt = ropt;
+ wi->worker = i;
+ wi->AH = AH;
+ wi->pipeRead = pstate->parallelSlot[i].pipeRevRead = pipeMW[PIPE_READ];
+ wi->pipeWrite = pstate->parallelSlot[i].pipeRevWrite = pipeWM[PIPE_WRITE];
+
+ handle = _beginthreadex(NULL, 0, (void *) &init_spawned_worker_win32,
+ wi, 0, &(pstate->parallelSlot[i].threadId));
+ pstate->parallelSlot[i].hThread = handle;
+ #else
+ pid = fork();
+ if (pid == 0)
+ {
+ /* we are the worker */
+ int j;
+ int pipefd[2] = { pipeMW[PIPE_READ], pipeWM[PIPE_WRITE] };
+
+ /*
+ * Store the fds for the reverse communication in pstate. Actually
+ * we only use this in case of an error and don't use pstate
+ * otherwise in the worker process. On Windows we write to the
+ * global pstate, in Unix we write to our process-local copy but
+ * that's also where we'd retrieve this information back from.
+ */
+ pstate->parallelSlot[i].pipeRevRead = pipefd[PIPE_READ];
+ pstate->parallelSlot[i].pipeRevWrite = pipefd[PIPE_WRITE];
+ pstate->parallelSlot[i].pid = getpid();
+
+ /*
+ * Call CloneArchive on Unix as well even though technically we
+ * don't need to because fork() gives us a copy in our own address space
+ * already. But CloneArchive resets the state information and also
+ * clones the database connection (for parallel dump) which both
+ * seem kinda helpful.
+ */
+ pstate->parallelSlot[i].args->AH = CloneArchive(AH);
+
+ closesocket(pipeWM[PIPE_READ]); /* close read end of Worker -> Master */
+ closesocket(pipeMW[PIPE_WRITE]); /* close write end of Master -> Worker */
+
+ /*
+ * Close all inherited fds for communication of the master with
+ * the other workers.
+ */
+ for (j = 0; j < i; j++)
+ {
+ closesocket(pstate->parallelSlot[j].pipeRead);
+ closesocket(pstate->parallelSlot[j].pipeWrite);
+ }
+
+ SetupWorker(pstate->parallelSlot[i].args->AH, pipefd, i, ropt);
+
+ exit(0);
+ }
+ else if (pid < 0)
+ /* fork failed */
+ exit_horribly(modulename,
+ "could not create worker process: %s\n",
+ strerror(errno));
+
+ /* we are the Master, pid > 0 here */
+ Assert(pid > 0);
+ closesocket(pipeMW[PIPE_READ]); /* close read end of Master -> Worker */
+ closesocket(pipeWM[PIPE_WRITE]); /* close write end of Worker -> Master */
+
+ pstate->parallelSlot[i].pid = pid;
+ #endif
+
+ pstate->parallelSlot[i].pipeRead = pipeWM[PIPE_READ];
+ pstate->parallelSlot[i].pipeWrite = pipeMW[PIPE_WRITE];
+ }
+
+ return pstate;
+ }
+
+ /*
+ * Tell all of our workers to terminate.
+ *
+ * Pretty straightforward routine, first we tell everyone to terminate, then we
+ * listen to the workers' replies and finally close the sockets that we have
+ * used for communication.
+ */
+ void
+ ParallelBackupEnd(ArchiveHandle *AH, ParallelState *pstate)
+ {
+ int i;
+
+ if (pstate->numWorkers == 1)
+ return;
+
+ PrintStatus(pstate);
+ Assert(IsEveryWorkerIdle(pstate));
+
+ /* no hard shutdown, let workers exit by themselves and wait for them */
+ ShutdownWorkersSoft(pstate, true);
+
+ PrintStatus(pstate);
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ closesocket(pstate->parallelSlot[i].pipeRead);
+ closesocket(pstate->parallelSlot[i].pipeWrite);
+ }
+
+ /*
+ * Remove the pstate again, so the exit handler in the parent will now
+ * again fall back to closing AH->connection (if connected).
+ */
+ shutdown_info.pstate = NULL;
+
+ free(pstate->parallelSlot);
+ free(pstate);
+ }
+
+
+ /*
+ * The sequence is the following (for dump, similar for restore):
+ *
+ * The master process starts the parallel backup in ParllelBackupStart, this
+ * forks the worker processes which enter WaitForCommand().
+ *
+ * The master process dispatches an individual work item to one of the worker
+ * processes in DispatchJobForTocEntry(). It calls
+ * AH->MasterStartParallelItemPtr, a routine of the output format. This
+ * function's arguments are the parents archive handle AH (containing the full
+ * catalog information), the TocEntry that the worker should work on and a
+ * T_Action act indicating whether this is a backup or a restore item. The
+ * function then converts the TocEntry assignment into a string that is then
+ * sent over to the worker process. In the simplest case that would be
+ * something like "DUMP 1234", with 1234 being the TocEntry id.
+ *
+ * The worker receives the message in the routine pointed to by
+ * WorkerJobDumpPtr or WorkerJobRestorePtr. These are also pointers to
+ * corresponding routines of the respective output format, e.g.
+ * _WorkerJobDumpDirectory().
+ *
+ * Remember that we have forked off the workers only after we have read in the
+ * catalog. That's why our worker processes can also access the catalog
+ * information. Now they re-translate the textual representation to a TocEntry
+ * on their side and do the required action (restore or dump).
+ *
+ * The result is again a textual string that is sent back to the master and is
+ * interpreted by AH->MasterEndParallelItemPtr. This function can update state
+ * or catalog information on the master's side, depending on the reply from the
+ * worker process. In the end it returns status which is 0 for successful
+ * execution.
+ *
+ * ---------------------------------------------------------------------
+ * Master Worker
+ *
+ * enters WaitForCommands()
+ * DispatchJobForTocEntry(...te...)
+ *
+ * [ Worker is IDLE ]
+ *
+ * arg = (MasterStartParallelItemPtr)()
+ * send: DUMP arg
+ * receive: DUMP arg
+ * str = (WorkerJobDumpPtr)(arg)
+ * [ Worker is WORKING ] ... gets te from arg ...
+ * ... dump te ...
+ * send: OK DUMP info
+ *
+ * In ListenToWorkers():
+ *
+ * [ Worker is FINISHED ]
+ * receive: OK DUMP info
+ * status = (MasterEndParallelItemPtr)(info)
+ *
+ * In ReapWorkerStatus(&ptr):
+ * *ptr = status;
+ * [ Worker is IDLE ]
+ * ---------------------------------------------------------------------
+ */
+ void
+ DispatchJobForTocEntry(ArchiveHandle *AH, ParallelState *pstate, TocEntry *te,
+ T_Action act)
+ {
+ int worker;
+ char *arg;
+
+ /* our caller makes sure that at least one worker is idle */
+ Assert(GetIdleWorker(pstate) != NO_SLOT);
+ worker = GetIdleWorker(pstate);
+ Assert(worker != NO_SLOT);
+
+ arg = (AH->MasterStartParallelItemPtr)(AH, te, act);
+
+ sendMessageToWorker(pstate, worker, arg);
+
+ pstate->parallelSlot[worker].workerStatus = WRKR_WORKING;
+ pstate->parallelSlot[worker].args->te = te;
+ PrintStatus(pstate);
+ }
+
+ static void
+ PrintStatus(ParallelState *pstate)
+ {
+ int i;
+ printf("------Status------\n");
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ printf("Status of worker %d: ", i);
+ switch (pstate->parallelSlot[i].workerStatus)
+ {
+ case WRKR_IDLE:
+ printf("IDLE");
+ break;
+ case WRKR_WORKING:
+ printf("WORKING");
+ break;
+ case WRKR_FINISHED:
+ printf("FINISHED");
+ break;
+ case WRKR_TERMINATED:
+ printf("TERMINATED");
+ break;
+ }
+ printf("\n");
+ }
+ printf("------------\n");
+ }
+
+
+ /*
+ * Find the first free parallel slot (if any).
+ */
+ int
+ GetIdleWorker(ParallelState *pstate)
+ {
+ int i;
+ for (i = 0; i < pstate->numWorkers; i++)
+ if (pstate->parallelSlot[i].workerStatus == WRKR_IDLE)
+ return i;
+ return NO_SLOT;
+ }
+
+ /*
+ * Return true iff every worker process is in the WRKR_TERMINATED state.
+ */
+ static bool
+ HasEveryWorkerTerminated(ParallelState *pstate)
+ {
+ int i;
+ for (i = 0; i < pstate->numWorkers; i++)
+ if (pstate->parallelSlot[i].workerStatus != WRKR_TERMINATED)
+ return false;
+ return true;
+ }
+
+ /*
+ * Return true iff every worker is in the WRKR_IDLE state.
+ */
+ bool
+ IsEveryWorkerIdle(ParallelState *pstate)
+ {
+ int i;
+ for (i = 0; i < pstate->numWorkers; i++)
+ if (pstate->parallelSlot[i].workerStatus != WRKR_IDLE)
+ return false;
+ return true;
+ }
+
+ /*
+ * ---------------------------------------------------------------------
+ * One danger of the parallel backup is a possible deadlock:
+ *
+ * 1) Master dumps the schema and locks all tables in ACCESS SHARE mode.
+ * 2) Another process requests an ACCESS EXCLUSIVE lock (which is not granted
+ * because the master holds a conflicting ACCESS SHARE lock).
+ * 3) The worker process also requests an ACCESS SHARE lock to read the table.
+ * The worker's not granted that lock but is enqueued behind the ACCESS
+ * EXCLUSIVE lock request.
+ * ---------------------------------------------------------------------
+ *
+ * Now what we do here is to just request a lock in ACCESS SHARE but with
+ * NOWAIT in the worker prior to touching the table. If we don't get the lock,
+ * then we know that somebody else has requested an ACCESS EXCLUSIVE lock and
+ * are good to just fail the whole backup because we have detected a deadlock.
+ */
+ static void
+ lockTableNoWait(ArchiveHandle *AH, TocEntry *te)
+ {
+ Archive *AHX = (Archive *) AH;
+ const char *qualId;
+ PQExpBuffer query = createPQExpBuffer();
+ PGresult *res;
+
+ Assert(AH->format == archDirectory);
+ Assert(strcmp(te->desc, "BLOBS") != 0);
+
+ appendPQExpBuffer(query, "SELECT pg_namespace.nspname,"
+ " pg_class.relname "
+ " FROM pg_class "
+ " JOIN pg_namespace on pg_namespace.oid = relnamespace "
+ " WHERE pg_class.oid = %d", te->catalogId.oid);
+
+ res = PQexec(AH->connection, query->data);
+
+ if (!res || PQresultStatus(res) != PGRES_TUPLES_OK)
+ exit_horribly(modulename, "could not get relation name for oid %d: %s\n",
+ te->catalogId.oid, PQerrorMessage(AH->connection));
+
+ resetPQExpBuffer(query);
+
+ qualId = fmtQualifiedId(AHX->remoteVersion, PQgetvalue(res, 0, 0), PQgetvalue(res, 0, 1));
+
+ appendPQExpBuffer(query, "LOCK TABLE %s IN ACCESS SHARE MODE NOWAIT", qualId);
+ PQclear(res);
+
+ res = PQexec(AH->connection, query->data);
+
+ if (!res || PQresultStatus(res) != PGRES_COMMAND_OK)
+ exit_horribly(modulename, "could not obtain lock on relation \"%s\". This "
+ "usually means that someone requested an ACCESS EXCLUSIVE lock "
+ "on the table after the pg_dump parent process has gotten the "
+ "initial ACCESS SHARE lock on the table.\n", qualId);
+
+ PQclear(res);
+ destroyPQExpBuffer(query);
+ }
+
+ /*
+ * That's the main routine for the worker.
+ * When it starts up it enters this routine and waits for commands from the
+ * master process. After having processed a command it comes back to here to
+ * wait for the next command. Finally it will receive a TERMINATE command and
+ * exit.
+ */
+ static void
+ WaitForCommands(ArchiveHandle *AH, int pipefd[2])
+ {
+ char *command;
+ DumpId dumpId;
+ int nBytes;
+ char *str = NULL;
+ TocEntry *te;
+
+ for(;;)
+ {
+ command = getMessageFromMaster(pipefd);
+
+ if (messageStartsWith(command, "DUMP "))
+ {
+ Assert(AH->format == archDirectory);
+ sscanf(command + strlen("DUMP "), "%d%n", &dumpId, &nBytes);
+ Assert(nBytes == strlen(command) - strlen("DUMP "));
+
+ te = getTocEntryByDumpId(AH, dumpId);
+ Assert(te != NULL);
+
+ /*
+ * Lock the table but with NOWAIT. Note that the parent is already
+ * holding a lock. If we cannot acquire another ACCESS SHARE MODE
+ * lock, then somebody else has requested an exclusive lock in the
+ * meantime. lockTableNoWait dies in this case to prevent a
+ * deadlock.
+ */
+ if (strcmp(te->desc, "BLOBS") != 0)
+ lockTableNoWait(AH, te);
+
+ /*
+ * The message we return here has been pg_malloc()ed and we are
+ * responsible for free()ing it.
+ */
+ str = (AH->WorkerJobDumpPtr)(AH, te);
+ Assert(AH->connection != NULL);
+ sendMessageToMaster(pipefd, str);
+ free(str);
+ }
+ else if (messageStartsWith(command, "RESTORE "))
+ {
+ Assert(AH->format == archDirectory || AH->format == archCustom);
+ Assert(AH->connection != NULL);
+
+ sscanf(command + strlen("RESTORE "), "%d%n", &dumpId, &nBytes);
+ Assert(nBytes == strlen(command) - strlen("RESTORE "));
+
+ te = getTocEntryByDumpId(AH, dumpId);
+ Assert(te != NULL);
+ /*
+ * The message we return here has been pg_malloc()ed and we are
+ * responsible for free()ing it.
+ */
+ str = (AH->WorkerJobRestorePtr)(AH, te);
+ Assert(AH->connection != NULL);
+ sendMessageToMaster(pipefd, str);
+ free(str);
+ }
+ else if (messageEquals(command, "TERMINATE"))
+ {
+ PQfinish(AH->connection);
+ AH->connection = NULL;
+ return;
+ }
+ else
+ exit_horribly(modulename,
+ "Unknown command on communication channel: %s\n",
+ command);
+ }
+ }
+
+ /*
+ * ---------------------------------------------------------------------
+ * Note the status change:
+ *
+ * DispatchJobForTocEntry WRKR_IDLE -> WRKR_WORKING
+ * ListenToWorkers WRKR_WORKING -> WRKR_FINISHED / WRKR_TERMINATED
+ * ReapWorkerStatus WRKR_FINISHED -> WRKR_IDLE
+ * ---------------------------------------------------------------------
+ *
+ * Just calling ReapWorkerStatus() when all workers are working might or might
+ * not give you an idle worker because you need to call ListenToWorkers() in
+ * between and only thereafter ReapWorkerStatus(). This is necessary in order to
+ * get and deal with the status (=result) of the worker's execution.
+ */
+ void
+ ListenToWorkers(ArchiveHandle *AH, ParallelState *pstate, bool do_wait)
+ {
+ int worker;
+ char *msg;
+
+ msg = getMessageFromWorker(pstate, do_wait, &worker);
+
+ if (!msg)
+ {
+ if (do_wait)
+ exit_horribly(modulename, "A worker process died unexpectedly\n");
+ return;
+ }
+
+ if (messageStartsWith(msg, "OK "))
+ {
+ char *statusString;
+ TocEntry *te;
+
+ pstate->parallelSlot[worker].workerStatus = WRKR_FINISHED;
+ te = pstate->parallelSlot[worker].args->te;
+ if (messageStartsWith(msg, "OK RESTORE "))
+ {
+ statusString = msg + strlen("OK RESTORE ");
+ pstate->parallelSlot[worker].status =
+ (AH->MasterEndParallelItemPtr)
+ (AH, te, statusString, ACT_RESTORE);
+ }
+ else if (messageStartsWith(msg, "OK DUMP "))
+ {
+ statusString = msg + strlen("OK DUMP ");
+ pstate->parallelSlot[worker].status =
+ (AH->MasterEndParallelItemPtr)
+ (AH, te, statusString, ACT_DUMP);
+ }
+ else
+ exit_horribly(modulename,
+ "Invalid message received from worker: %s\n", msg);
+ }
+ else if (messageStartsWith(msg, "ERROR "))
+ {
+ Assert(AH->format == archDirectory || AH->format == archCustom);
+ pstate->parallelSlot[worker].workerStatus = WRKR_TERMINATED;
+ exit_horribly(modulename, "%s", msg + strlen("ERROR "));
+ }
+ else
+ exit_horribly(modulename, "Invalid message received from worker: %s\n", msg);
+
+ PrintStatus(pstate);
+
+ /* both Unix and Win32 return pg_malloc()ed space, so we free it */
+ free(msg);
+ }
+
+ /*
+ * This function is executed in the master process.
+ *
+ * This function is used to get the return value of a terminated worker
+ * process. If a process has terminated, its status is stored in *status and
+ * the id of the worker is returned.
+ */
+ int
+ ReapWorkerStatus(ParallelState *pstate, int *status)
+ {
+ int i;
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ if (pstate->parallelSlot[i].workerStatus == WRKR_FINISHED)
+ {
+ *status = pstate->parallelSlot[i].status;
+ pstate->parallelSlot[i].status = 0;
+ pstate->parallelSlot[i].workerStatus = WRKR_IDLE;
+ PrintStatus(pstate);
+ return i;
+ }
+ }
+ return NO_SLOT;
+ }
+
+ /*
+ * This function is executed in the master process.
+ *
+ * It looks for an idle worker process and only returns if there is one.
+ */
+ void
+ EnsureIdleWorker(ArchiveHandle *AH, ParallelState *pstate)
+ {
+ int ret_worker;
+ int work_status;
+
+ for (;;)
+ {
+ int nTerm = 0;
+ while ((ret_worker = ReapWorkerStatus(pstate, &work_status)) != NO_SLOT)
+ {
+ if (work_status != 0)
+ exit_horribly(modulename, "Error processing a parallel work item.\n");
+
+ nTerm++;
+ }
+
+ /* We need to make sure that we have an idle worker before dispatching
+ * the next item. If nTerm > 0 we already have that (quick check). */
+ if (nTerm > 0)
+ return;
+
+ /* explicit check for an idle worker */
+ if (GetIdleWorker(pstate) != NO_SLOT)
+ return;
+
+ /*
+ * If we have no idle worker, read the result of one or more
+ * workers and loop the loop to call ReapWorkerStatus() on them
+ */
+ ListenToWorkers(AH, pstate, true);
+ }
+ }
+
+ /*
+ * This function is executed in the master process.
+ *
+ * It waits for all workers to terminate.
+ */
+ void
+ EnsureWorkersFinished(ArchiveHandle *AH, ParallelState *pstate)
+ {
+ int work_status;
+
+ if (!pstate || pstate->numWorkers == 1)
+ return;
+
+ /* Waiting for the remaining worker processes to finish */
+ while (!IsEveryWorkerIdle(pstate))
+ {
+ if (ReapWorkerStatus(pstate, &work_status) == NO_SLOT)
+ ListenToWorkers(AH, pstate, true);
+ else if (work_status != 0)
+ exit_horribly(modulename, "Error processing a parallel work item\n");
+ }
+ }
+
+ /*
+ * This function is executed in the worker process.
+ *
+ * It returns the next message on the communication channel, blocking until it
+ * becomes available.
+ */
+ static char *
+ getMessageFromMaster(int pipefd[2])
+ {
+ return readMessageFromPipe(pipefd[PIPE_READ]);
+ }
+
+ /*
+ * This function is executed in the worker process.
+ *
+ * It sends a message to the master on the communication channel.
+ */
+ static void
+ sendMessageToMaster(int pipefd[2], const char *str)
+ {
+ int len = strlen(str) + 1;
+
+ if (pipewrite(pipefd[PIPE_WRITE], str, len) != len)
+ exit_horribly(modulename,
+ "Error writing to the communication channel: %s\n",
+ strerror(errno));
+ }
+
+ /*
+ * A select loop that repeats calling select until a descriptor in the read set
+ * becomes readable. On Windows we have to check for the termination event from
+ * time to time, on Unix we can just block forever.
+ */
+ #ifdef WIN32
+ static int
+ select_loop(int maxFd, fd_set *workerset)
+ {
+ int i;
+ fd_set saveSet = *workerset;
+
+ /* should always be the master */
+ Assert(tMasterThreadId == GetCurrentThreadId());
+
+ for (;;)
+ {
+ /*
+ * sleep a quarter of a second before checking if we should
+ * terminate.
+ */
+ struct timeval tv = { 0, 250000 };
+ *workerset = saveSet;
+ i = select(maxFd + 1, workerset, NULL, NULL, &tv);
+
+ if (i == SOCKET_ERROR && WSAGetLastError() == WSAEINTR)
+ continue;
+ if (i)
+ break;
+ }
+
+ return i;
+ }
+ #else /* UNIX */
+ static int
+ select_loop(int maxFd, fd_set *workerset)
+ {
+ int i;
+
+ fd_set saveSet = *workerset;
+ for (;;)
+ {
+ *workerset = saveSet;
+ i = select(maxFd + 1, workerset, NULL, NULL, NULL);
+
+ /*
+ * If we Ctrl-C the master process , it's likely that we interrupt
+ * select() here. The signal handler will set wantAbort == true and the
+ * shutdown journey starts from here. Note that we'll come back here
+ * later when we tell all workers to terminate and read their
+ * responses. But then we have aborting set to true.
+ */
+ if (wantAbort && !aborting)
+ exit_horribly(modulename, "terminated by user\n");
+
+ if (i < 0 && errno == EINTR)
+ continue;
+ break;
+ }
+
+ return i;
+ }
+ #endif
+
+ /*
+ * This function is executed in the master process.
+ *
+ * It returns the next message from the worker on the communication channel,
+ * optionally blocking (do_wait) until it becomes available.
+ *
+ * The id of the worker is returned in *worker.
+ */
+ static char *
+ getMessageFromWorker(ParallelState *pstate, bool do_wait, int *worker)
+ {
+ int i;
+ fd_set workerset;
+ int maxFd = -1;
+ struct timeval nowait = { 0, 0 };
+
+ FD_ZERO(&workerset);
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ if (pstate->parallelSlot[i].workerStatus == WRKR_TERMINATED)
+ continue;
+ FD_SET(pstate->parallelSlot[i].pipeRead, &workerset);
+ /* actually WIN32 ignores the first parameter to select()... */
+ if (pstate->parallelSlot[i].pipeRead > maxFd)
+ maxFd = pstate->parallelSlot[i].pipeRead;
+ }
+
+ if (do_wait)
+ {
+ i = select_loop(maxFd, &workerset);
+ Assert(i != 0);
+ }
+ else
+ {
+ if ((i = select(maxFd + 1, &workerset, NULL, NULL, &nowait)) == 0)
+ return NULL;
+ }
+
+ if (i < 0)
+ exit_horribly(modulename, "Error in ListenToWorkers(): %s", strerror(errno));
+
+ for (i = 0; i < pstate->numWorkers; i++)
+ {
+ char *msg;
+
+ if (!FD_ISSET(pstate->parallelSlot[i].pipeRead, &workerset))
+ continue;
+
+ msg = readMessageFromPipe(pstate->parallelSlot[i].pipeRead);
+ *worker = i;
+ return msg;
+ }
+ Assert(false);
+ return NULL;
+ }
+
+ /*
+ * This function is executed in the master process.
+ *
+ * It sends a message to a certain worker on the communication channel.
+ */
+ static void
+ sendMessageToWorker(ParallelState *pstate, int worker, const char *str)
+ {
+ int len = strlen(str) + 1;
+
+ if (pipewrite(pstate->parallelSlot[worker].pipeWrite, str, len) != len)
+ {
+ /*
+ * If we're already aborting anyway, don't care if we succeed or not.
+ * The child might have gone already.
+ */
+ #ifndef WIN32
+ if (!aborting)
+ #endif
+ exit_horribly(modulename,
+ "Error writing to the communication channel: %s\n",
+ strerror(errno));
+ }
+ }
+
+ /*
+ * The underlying function to read a message from the communication channel (fd)
+ * with optional blocking (do_wait).
+ */
+ static char *
+ readMessageFromPipe(int fd)
+ {
+ char *msg;
+ int msgsize, bufsize;
+ int ret;
+
+ /*
+ * The problem here is that we need to deal with several possibilites:
+ * we could receive only a partial message or several messages at once.
+ * The caller expects us to return exactly one message however.
+ *
+ * We could either read in as much as we can and keep track of what we
+ * delivered back to the caller or we just read byte by byte. Once we see
+ * (char) 0, we know that it's the message's end. This would be quite
+ * inefficient for more data but since we are reading only on the command
+ * channel, the performance loss does not seem worth the trouble of keeping
+ * internal states for different file descriptors.
+ */
+
+ bufsize = 64; /* could be any number */
+ msg = (char *) pg_malloc(bufsize);
+
+ msgsize = 0;
+ for (;;)
+ {
+ Assert(msgsize <= bufsize);
+ ret = piperead(fd, msg + msgsize, 1);
+
+ /* worker has closed the connection or another error happened */
+ if (ret <= 0)
+ return NULL;
+
+ Assert(ret == 1);
+
+ if (msg[msgsize] == '\0')
+ return msg;
+
+ msgsize++;
+ if (msgsize == bufsize)
+ {
+ /* could be any number */
+ bufsize += 16;
+ msg = (char *) realloc(msg, bufsize);
+ }
+ }
+ }
+
+ #ifdef WIN32
+ /*
+ * This is a replacement version of pipe for Win32 which allows returned
+ * handles to be used in select(). Note that read/write calls must be replaced
+ * with recv/send.
+ */
+
+ static int
+ pgpipe(int handles[2])
+ {
+ SOCKET s;
+ struct sockaddr_in serv_addr;
+ int len = sizeof(serv_addr);
+
+ handles[0] = handles[1] = INVALID_SOCKET;
+
+ if ((s = socket(AF_INET, SOCK_STREAM, 0)) == INVALID_SOCKET)
+ {
+ write_msg(modulename, "pgpipe could not create socket: %ui",
+ WSAGetLastError());
+ return -1;
+ }
+
+ memset((void *) &serv_addr, 0, sizeof(serv_addr));
+ serv_addr.sin_family = AF_INET;
+ serv_addr.sin_port = htons(0);
+ serv_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ if (bind(s, (SOCKADDR *) &serv_addr, len) == SOCKET_ERROR)
+ {
+ write_msg(modulename, "pgpipe could not bind: %ui",
+ WSAGetLastError());
+ closesocket(s);
+ return -1;
+ }
+ if (listen(s, 1) == SOCKET_ERROR)
+ {
+ write_msg(modulename, "pgpipe could not listen: %ui",
+ WSAGetLastError());
+ closesocket(s);
+ return -1;
+ }
+ if (getsockname(s, (SOCKADDR *) &serv_addr, &len) == SOCKET_ERROR)
+ {
+ write_msg(modulename, "pgpipe could not getsockname: %ui",
+ WSAGetLastError());
+ closesocket(s);
+ return -1;
+ }
+ if ((handles[1] = socket(PF_INET, SOCK_STREAM, 0)) == INVALID_SOCKET)
+ {
+ write_msg(modulename, "pgpipe could not create socket 2: %ui",
+ WSAGetLastError());
+ closesocket(s);
+ return -1;
+ }
+
+ if (connect(handles[1], (SOCKADDR *) &serv_addr, len) == SOCKET_ERROR)
+ {
+ write_msg(modulename, "pgpipe could not connect socket: %ui",
+ WSAGetLastError());
+ closesocket(s);
+ return -1;
+ }
+ if ((handles[0] = accept(s, (SOCKADDR *) &serv_addr, &len)) == INVALID_SOCKET)
+ {
+ write_msg(modulename, "pgpipe could not accept socket: %ui",
+ WSAGetLastError());
+ closesocket(handles[1]);
+ handles[1] = INVALID_SOCKET;
+ closesocket(s);
+ return -1;
+ }
+ closesocket(s);
+ return 0;
+ }
+
+ static int
+ piperead(int s, char *buf, int len)
+ {
+ int ret = recv(s, buf, len, 0);
+
+ if (ret < 0 && WSAGetLastError() == WSAECONNRESET)
+ /* EOF on the pipe! (win32 socket based implementation) */
+ ret = 0;
+ return ret;
+ }
+ #endif
*** /dev/null
--- b/src/bin/pg_dump/parallel.h
***************
*** 0 ****
--- 1,86 ----
+ /*-------------------------------------------------------------------------
+ *
+ * parallel.h
+ *
+ * Parallel support header file for the pg_dump archiver
+ *
+ * Portions Copyright (c) 1996-2011, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * The author is not responsible for loss or damages that may
+ * result from its use.
+ *
+ * IDENTIFICATION
+ * src/bin/pg_dump/parallel.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+ #include "pg_backup_db.h"
+
+ struct _archiveHandle;
+ struct _tocEntry;
+
+ typedef enum
+ {
+ WRKR_TERMINATED = 0,
+ WRKR_IDLE,
+ WRKR_WORKING,
+ WRKR_FINISHED
+ } T_WorkerStatus;
+
+ typedef enum _action
+ {
+ ACT_DUMP,
+ ACT_RESTORE,
+ } T_Action;
+
+ /* Arguments needed for a worker process */
+ typedef struct _parallel_args
+ {
+ struct _archiveHandle *AH;
+ struct _tocEntry *te;
+ } ParallelArgs;
+
+ /* State for each parallel activity slot */
+ typedef struct _parallel_slot
+ {
+ ParallelArgs *args;
+ T_WorkerStatus workerStatus;
+ int status;
+ int pipeRead;
+ int pipeWrite;
+ int pipeRevRead;
+ int pipeRevWrite;
+ #ifdef WIN32
+ uintptr_t hThread;
+ unsigned int threadId;
+ #else
+ pid_t pid;
+ #endif
+ } ParallelSlot;
+
+ #define NO_SLOT (-1)
+
+ typedef struct _parallel_state
+ {
+ int numWorkers;
+ ParallelSlot *parallelSlot;
+ } ParallelState;
+
+ extern int GetIdleWorker(ParallelState *pstate);
+ extern bool IsEveryWorkerIdle(ParallelState *pstate);
+ extern void ListenToWorkers(struct _archiveHandle *AH, ParallelState *pstate, bool do_wait);
+ extern int ReapWorkerStatus(ParallelState *pstate, int *status);
+ extern void EnsureIdleWorker(struct _archiveHandle *AH, ParallelState *pstate);
+ extern void EnsureWorkersFinished(struct _archiveHandle *AH, ParallelState *pstate);
+
+ extern ParallelState *ParallelBackupStart(struct _archiveHandle *AH,
+ RestoreOptions *ropt);
+ extern void DispatchJobForTocEntry(struct _archiveHandle *AH,
+ ParallelState *pstate,
+ struct _tocEntry *te, T_Action act);
+ extern void ParallelBackupEnd(struct _archiveHandle *AH, ParallelState *pstate);
+
+ extern void checkAborting(struct _archiveHandle *AH);
+
*** a/src/bin/pg_dump/pg_backup.h
--- b/src/bin/pg_dump/pg_backup.h
***************
*** 89,97 **** struct Archive
--- 89,101 ----
int minRemoteVersion; /* allowable range */
int maxRemoteVersion;
+ int numWorkers; /* number of parallel processes */
+ char *sync_snapshot_id; /* sync snapshot id for parallel operation */
+
/* info needed for string escaping */
int encoding; /* libpq code for client_encoding */
bool std_strings; /* standard_conforming_strings */
+ char *use_role; /* Issue SET ROLE to this */
/* error handling */
bool exit_on_error; /* whether to exit on SQL errors... */
***************
*** 149,155 **** typedef struct _restoreOptions
int suppressDumpWarnings; /* Suppress output of WARNING entries
* to stderr */
bool single_txn;
- int number_of_jobs;
bool *idWanted; /* array showing which dump IDs to emit */
} RestoreOptions;
--- 153,158 ----
***************
*** 201,206 **** extern void PrintTOCSummary(Archive *AH, RestoreOptions *ropt);
--- 204,212 ----
extern RestoreOptions *NewRestoreOptions(void);
+ /* We have one in pg_dump.c and another one in pg_restore.c */
+ extern void _SetupWorker(Archive *AHX, RestoreOptions *ropt);
+
/* Rearrange and filter TOC entries */
extern void SortTocFromFile(Archive *AHX, RestoreOptions *ropt);
extern void InitDummyWantedList(Archive *AHX, RestoreOptions *ropt);
*** a/src/bin/pg_dump/pg_backup_archiver.c
--- b/src/bin/pg_dump/pg_backup_archiver.c
***************
*** 23,30 ****
--- 23,32 ----
#include "pg_backup_db.h"
#include "dumpmem.h"
#include "dumputils.h"
+ #include "parallel.h"
#include <ctype.h>
+ #include <fcntl.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/types.h>
***************
*** 36,107 ****
#include "libpq/libpq-fs.h"
- /*
- * Special exit values from worker children. We reserve 0 for normal
- * success; 1 and other small values should be interpreted as crashes.
- */
- #define WORKER_CREATE_DONE 10
- #define WORKER_INHIBIT_DATA 11
- #define WORKER_IGNORED_ERRORS 12
-
- /*
- * Unix uses exit to return result from worker child, so function is void.
- * Windows thread result comes via function return.
- */
- #ifndef WIN32
- #define parallel_restore_result void
- #else
- #define parallel_restore_result DWORD
- #endif
-
- /* IDs for worker children are either PIDs or thread handles */
- #ifndef WIN32
- #define thandle pid_t
- #else
- #define thandle HANDLE
- #endif
-
- typedef struct ParallelStateEntry
- {
- #ifdef WIN32
- unsigned int threadId;
- #else
- pid_t pid;
- #endif
- ArchiveHandle *AH;
- } ParallelStateEntry;
-
- typedef struct ParallelState
- {
- int numWorkers;
- ParallelStateEntry *pse;
- } ParallelState;
-
- /* Arguments needed for a worker child */
- typedef struct _restore_args
- {
- ArchiveHandle *AH;
- TocEntry *te;
- ParallelStateEntry *pse;
- } RestoreArgs;
-
- /* State for each parallel activity slot */
- typedef struct _parallel_slot
- {
- thandle child_id;
- RestoreArgs *args;
- } ParallelSlot;
-
- typedef struct ShutdownInformation
- {
- ParallelState *pstate;
- Archive *AHX;
- } ShutdownInformation;
-
- static ShutdownInformation shutdown_info;
-
- #define NO_SLOT (-1)
-
#define TEXT_DUMP_HEADER "--\n-- PostgreSQL database dump\n--\n\n"
#define TEXT_DUMPALL_HEADER "--\n-- PostgreSQL database cluster dump\n--\n\n"
--- 38,43 ----
***************
*** 141,147 **** static teReqs _tocEntryRequired(TocEntry *te, RestoreOptions *ropt, bool include
static bool _tocEntryIsACL(TocEntry *te);
static void _disableTriggersIfNecessary(ArchiveHandle *AH, TocEntry *te, RestoreOptions *ropt);
static void _enableTriggersIfNecessary(ArchiveHandle *AH, TocEntry *te, RestoreOptions *ropt);
- static TocEntry *getTocEntryByDumpId(ArchiveHandle *AH, DumpId id);
static void _moveBefore(ArchiveHandle *AH, TocEntry *pos, TocEntry *te);
static int _discoverArchiveFormat(ArchiveHandle *AH);
--- 77,82 ----
***************
*** 154,174 **** static void RestoreOutput(ArchiveHandle *AH, OutputContext savedContext);
static int restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
RestoreOptions *ropt, bool is_parallel);
! static void restore_toc_entries_parallel(ArchiveHandle *AH);
! static thandle spawn_restore(RestoreArgs *args);
! static thandle reap_child(ParallelSlot *slots, int n_slots, int *work_status);
! static bool work_in_progress(ParallelSlot *slots, int n_slots);
! static int get_next_slot(ParallelSlot *slots, int n_slots);
static void par_list_header_init(TocEntry *l);
static void par_list_append(TocEntry *l, TocEntry *te);
static void par_list_remove(TocEntry *te);
static TocEntry *get_next_work_item(ArchiveHandle *AH,
TocEntry *ready_list,
! ParallelSlot *slots, int n_slots);
! static parallel_restore_result parallel_restore(RestoreArgs *args);
static void mark_work_done(ArchiveHandle *AH, TocEntry *ready_list,
! thandle worker, int status,
! ParallelSlot *slots, int n_slots);
static void fix_dependencies(ArchiveHandle *AH);
static bool has_lock_conflicts(TocEntry *te1, TocEntry *te2);
static void repoint_table_dependencies(ArchiveHandle *AH,
--- 89,107 ----
static int restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
RestoreOptions *ropt, bool is_parallel);
! static void restore_toc_entries_prefork(ArchiveHandle *AH);
! static void restore_toc_entries_parallel(ArchiveHandle *AH, ParallelState *pstate,
! TocEntry *pending_list);
! static void restore_toc_entries_postfork(ArchiveHandle *AH, TocEntry *pending_list);
static void par_list_header_init(TocEntry *l);
static void par_list_append(TocEntry *l, TocEntry *te);
static void par_list_remove(TocEntry *te);
static TocEntry *get_next_work_item(ArchiveHandle *AH,
TocEntry *ready_list,
! ParallelState *pstate);
static void mark_work_done(ArchiveHandle *AH, TocEntry *ready_list,
! int worker, int status,
! ParallelState *pstate);
static void fix_dependencies(ArchiveHandle *AH);
static bool has_lock_conflicts(TocEntry *te1, TocEntry *te2);
static void repoint_table_dependencies(ArchiveHandle *AH,
***************
*** 178,191 **** static void reduce_dependencies(ArchiveHandle *AH, TocEntry *te,
TocEntry *ready_list);
static void mark_create_done(ArchiveHandle *AH, TocEntry *te);
static void inhibit_data_for_failed_table(ArchiveHandle *AH, TocEntry *te);
- static ArchiveHandle *CloneArchive(ArchiveHandle *AH);
- static void DeCloneArchive(ArchiveHandle *AH);
-
- static void setProcessIdentifier(ParallelStateEntry *pse, ArchiveHandle *AH);
- static void unsetProcessIdentifier(ParallelStateEntry *pse);
- static ParallelStateEntry *GetMyPSEntry(ParallelState *pstate);
- static void archive_close_connection(int code, void *arg);
-
/*
* Wrapper functions.
--- 111,116 ----
***************
*** 272,278 **** RestoreArchive(Archive *AHX, RestoreOptions *ropt)
/*
* If we're going to do parallel restore, there are some restrictions.
*/
! parallel_mode = (ropt->number_of_jobs > 1 && ropt->useDB);
if (parallel_mode)
{
/* We haven't got round to making this work for all archive formats */
--- 197,203 ----
/*
* If we're going to do parallel restore, there are some restrictions.
*/
! parallel_mode = (AH->public.numWorkers > 1 && ropt->useDB);
if (parallel_mode)
{
/* We haven't got round to making this work for all archive formats */
***************
*** 438,444 **** RestoreArchive(Archive *AHX, RestoreOptions *ropt)
* In parallel mode, turn control over to the parallel-restore logic.
*/
if (parallel_mode)
! restore_toc_entries_parallel(AH);
else
{
for (te = AH->toc->next; te != AH->toc; te = te->next)
--- 363,387 ----
* In parallel mode, turn control over to the parallel-restore logic.
*/
if (parallel_mode)
! {
! ParallelState *pstate;
! TocEntry pending_list;
!
! par_list_header_init(&pending_list);
!
! /* This runs PRE_DATA items and then disconnects from the database */
! restore_toc_entries_prefork(AH);
! Assert(AH->connection == NULL);
!
! /* ParallelBackupStart() will actually fork the processes */
! pstate = ParallelBackupStart(AH, ropt);
! restore_toc_entries_parallel(AH, pstate, &pending_list);
! ParallelBackupEnd(AH, pstate);
!
! /* reconnect the master and see if we missed something */
! restore_toc_entries_postfork(AH, &pending_list);
! Assert(AH->connection != NULL);
! }
else
{
for (te = AH->toc->next; te != AH->toc; te = te->next)
***************
*** 500,506 **** static int
restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
RestoreOptions *ropt, bool is_parallel)
{
! int retval = 0;
teReqs reqs;
bool defnDumped;
--- 443,449 ----
restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
RestoreOptions *ropt, bool is_parallel)
{
! int status = WORKER_OK;
teReqs reqs;
bool defnDumped;
***************
*** 542,548 **** restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
if (ropt->noDataForFailedTables)
{
if (is_parallel)
! retval = WORKER_INHIBIT_DATA;
else
inhibit_data_for_failed_table(AH, te);
}
--- 485,491 ----
if (ropt->noDataForFailedTables)
{
if (is_parallel)
! status = WORKER_INHIBIT_DATA;
else
inhibit_data_for_failed_table(AH, te);
}
***************
*** 557,563 **** restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
* just set the return value.
*/
if (is_parallel)
! retval = WORKER_CREATE_DONE;
else
mark_create_done(AH, te);
}
--- 500,506 ----
* just set the return value.
*/
if (is_parallel)
! status = WORKER_CREATE_DONE;
else
mark_create_done(AH, te);
}
***************
*** 675,681 **** restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
}
}
! return retval;
}
/*
--- 618,627 ----
}
}
! if (AH->public.n_errors > 0 && status == WORKER_OK)
! status = WORKER_IGNORED_ERRORS;
!
! return status;
}
/*
***************
*** 1447,1453 **** ahwrite(const void *ptr, size_t size, size_t nmemb, ArchiveHandle *AH)
/* on some error, we may decide to go on... */
void
warn_or_exit_horribly(ArchiveHandle *AH,
! const char *modulename, const char *fmt,...)
{
va_list ap;
--- 1393,1399 ----
/* on some error, we may decide to go on... */
void
warn_or_exit_horribly(ArchiveHandle *AH,
! const char *modulename, const char *fmt,...)
{
va_list ap;
***************
*** 1524,1530 **** _moveBefore(ArchiveHandle *AH, TocEntry *pos, TocEntry *te)
pos->prev = te;
}
! static TocEntry *
getTocEntryByDumpId(ArchiveHandle *AH, DumpId id)
{
TocEntry *te;
--- 1470,1476 ----
pos->prev = te;
}
! TocEntry *
getTocEntryByDumpId(ArchiveHandle *AH, DumpId id)
{
TocEntry *te;
***************
*** 2021,2068 **** _allocAH(const char *FileSpec, const ArchiveFormat fmt,
void
! WriteDataChunks(ArchiveHandle *AH)
{
TocEntry *te;
- StartDataPtr startPtr;
- EndDataPtr endPtr;
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
! if (te->dataDumper != NULL)
! {
! AH->currToc = te;
! /* printf("Writing data for %d (%x)\n", te->id, te); */
!
! if (strcmp(te->desc, "BLOBS") == 0)
! {
! startPtr = AH->StartBlobsPtr;
! endPtr = AH->EndBlobsPtr;
! }
! else
! {
! startPtr = AH->StartDataPtr;
! endPtr = AH->EndDataPtr;
! }
!
! if (startPtr != NULL)
! (*startPtr) (AH, te);
/*
! * printf("Dumper arg for %d is %x\n", te->id, te->dataDumperArg);
*/
! /*
! * The user-provided DataDumper routine needs to call
! * AH->WriteData
! */
! (*te->dataDumper) ((Archive *) AH, te->dataDumperArg);
! if (endPtr != NULL)
! (*endPtr) (AH, te);
! AH->currToc = NULL;
! }
}
}
void
--- 1967,2029 ----
void
! WriteDataChunks(ArchiveHandle *AH, ParallelState *pstate)
{
TocEntry *te;
for (te = AH->toc->next; te != AH->toc; te = te->next)
{
! if (!te->hadDumper)
! continue;
+ if (pstate && pstate->numWorkers > 1)
+ {
/*
! * If we are in a parallel backup, then we are always the master
! * process.
*/
+ EnsureIdleWorker(AH, pstate);
+ Assert(GetIdleWorker(pstate) != NO_SLOT);
+ DispatchJobForTocEntry(AH, pstate, te, ACT_DUMP);
+ }
+ else
+ WriteDataChunksForTocEntry(AH, te);
+ }
+ EnsureWorkersFinished(AH, pstate);
+ }
! void
! WriteDataChunksForTocEntry(ArchiveHandle *AH, TocEntry *te)
! {
! StartDataPtr startPtr;
! EndDataPtr endPtr;
! AH->currToc = te;
!
! if (strcmp(te->desc, "BLOBS") == 0)
! {
! startPtr = AH->StartBlobsPtr;
! endPtr = AH->EndBlobsPtr;
! }
! else
! {
! startPtr = AH->StartDataPtr;
! endPtr = AH->EndDataPtr;
}
+
+ if (startPtr != NULL)
+ (*startPtr) (AH, te);
+
+ /*
+ * The user-provided DataDumper routine needs to call
+ * AH->WriteData
+ */
+ (*te->dataDumper) ((Archive *) AH, te->dataDumperArg);
+
+ if (endPtr != NULL)
+ (*endPtr) (AH, te);
+
+ AH->currToc = NULL;
}
void
***************
*** 3276,3342 **** dumpTimestamp(ArchiveHandle *AH, const char *msg, time_t tim)
ahprintf(AH, "-- %s %s\n\n", msg, buf);
}
- static void
- setProcessIdentifier(ParallelStateEntry *pse, ArchiveHandle *AH)
- {
- #ifdef WIN32
- pse->threadId = GetCurrentThreadId();
- #else
- pse->pid = getpid();
- #endif
- pse->AH = AH;
- }
-
- static void
- unsetProcessIdentifier(ParallelStateEntry *pse)
- {
- #ifdef WIN32
- pse->threadId = 0;
- #else
- pse->pid = 0;
- #endif
- pse->AH = NULL;
- }
-
- static ParallelStateEntry *
- GetMyPSEntry(ParallelState *pstate)
- {
- int i;
-
- for (i = 0; i < pstate->numWorkers; i++)
- #ifdef WIN32
- if (pstate->pse[i].threadId == GetCurrentThreadId())
- #else
- if (pstate->pse[i].pid == getpid())
- #endif
- return &(pstate->pse[i]);
-
- return NULL;
- }
-
- static void
- archive_close_connection(int code, void *arg)
- {
- ShutdownInformation *si = (ShutdownInformation *) arg;
-
- if (si->pstate)
- {
- ParallelStateEntry *entry = GetMyPSEntry(si->pstate);
-
- if (entry != NULL && entry->AH)
- DisconnectDatabase(&(entry->AH->public));
- }
- else if (si->AHX)
- DisconnectDatabase(si->AHX);
- }
-
- void
- on_exit_close_archive(Archive *AHX)
- {
- shutdown_info.AHX = AHX;
- on_exit_nicely(archive_close_connection, &shutdown_info);
- }
-
/*
* Main engine for parallel restore.
*
--- 3237,3242 ----
***************
*** 3349,3378 **** on_exit_close_archive(Archive *AHX)
* RestoreArchive).
*/
static void
! restore_toc_entries_parallel(ArchiveHandle *AH)
{
RestoreOptions *ropt = AH->ropt;
- int n_slots = ropt->number_of_jobs;
- ParallelSlot *slots;
- int work_status;
- int next_slot;
bool skipped_some;
- TocEntry pending_list;
- TocEntry ready_list;
TocEntry *next_work_item;
- thandle ret_child;
- TocEntry *te;
- ParallelState *pstate;
- int i;
! ahlog(AH, 2, "entering restore_toc_entries_parallel\n");
! slots = (ParallelSlot *) pg_calloc(n_slots, sizeof(ParallelSlot));
! pstate = (ParallelState *) pg_malloc(sizeof(ParallelState));
! pstate->pse = (ParallelStateEntry *) pg_calloc(n_slots, sizeof(ParallelStateEntry));
! pstate->numWorkers = ropt->number_of_jobs;
! for (i = 0; i < pstate->numWorkers; i++)
! unsetProcessIdentifier(&(pstate->pse[i]));
/* Adjust dependency information */
fix_dependencies(AH);
--- 3249,3269 ----
* RestoreArchive).
*/
static void
! restore_toc_entries_prefork(ArchiveHandle *AH)
{
RestoreOptions *ropt = AH->ropt;
bool skipped_some;
TocEntry *next_work_item;
! ahlog(AH, 2, "entering restore_toc_entries_prefork\n");
! /* we haven't got round to making this work for all archive formats */
! if (AH->ClonePtr == NULL || AH->ReopenPtr == NULL)
! exit_horribly(modulename, "parallel restore is not supported with this archive file format\n");
!
! /* doesn't work if the archive represents dependencies as OIDs, either */
! if (AH->version < K_VERS_1_8)
! exit_horribly(modulename, "parallel restore is not supported with archives made by pre-8.0 pg_dump\n");
/* Adjust dependency information */
fix_dependencies(AH);
***************
*** 3428,3439 **** restore_toc_entries_parallel(ArchiveHandle *AH)
*/
DisconnectDatabase(&AH->public);
- /*
- * Set the pstate in the shutdown_info. The exit handler uses pstate if set
- * and falls back to AHX otherwise.
- */
- shutdown_info.pstate = pstate;
-
/* blow away any transient state from the old connection */
if (AH->currUser)
free(AH->currUser);
--- 3319,3324 ----
***************
*** 3445,3461 **** restore_toc_entries_parallel(ArchiveHandle *AH)
free(AH->currTablespace);
AH->currTablespace = NULL;
AH->currWithOids = -1;
/*
! * Initialize the lists of pending and ready items. After this setup, the
! * pending list is everything that needs to be done but is blocked by one
! * or more dependencies, while the ready list contains items that have no
! * remaining dependencies. Note: we don't yet filter out entries that
! * aren't going to be restored. They might participate in dependency
! * chains connecting entries that should be restored, so we treat them as
! * live until we actually process them.
*/
- par_list_header_init(&pending_list);
par_list_header_init(&ready_list);
skipped_some = false;
for (next_work_item = AH->toc->next; next_work_item != AH->toc; next_work_item = next_work_item->next)
--- 3330,3371 ----
free(AH->currTablespace);
AH->currTablespace = NULL;
AH->currWithOids = -1;
+ }
+
+ /*
+ * Main engine for parallel restore.
+ *
+ * Work is done in three phases.
+ * First we process all SECTION_PRE_DATA tocEntries, in a single connection,
+ * just as for a standard restore. This is done in restore_toc_entries_prefork().
+ * Second we process the remaining non-ACL steps in parallel worker children
+ * (threads on Windows, processes on Unix), these fork off and set up their
+ * connections before we call restore_toc_entries_parallel_forked.
+ * Finally we process all the ACL entries in a single connection (that happens
+ * back in RestoreArchive).
+ */
+ static void
+ restore_toc_entries_parallel(ArchiveHandle *AH, ParallelState *pstate,
+ TocEntry *pending_list)
+ {
+ int work_status;
+ bool skipped_some;
+ TocEntry ready_list;
+ TocEntry *next_work_item;
+ int ret_child;
+
+ ahlog(AH, 2, "entering restore_toc_entries_parallel\n");
/*
! * Initialize the lists of ready items, the list for pending items has
! * already been initialized in the parent. After this setup, the pending
! * list is everything that needs to be done but is blocked by one or more
! * dependencies, while the ready list contains items that have no remaining
! * dependencies. Note: we don't yet filter out entries that aren't going
! * to be restored. They might participate in dependency chains connecting
! * entries that should be restored, so we treat them as live until we
! * actually process them.
*/
par_list_header_init(&ready_list);
skipped_some = false;
for (next_work_item = AH->toc->next; next_work_item != AH->toc; next_work_item = next_work_item->next)
***************
*** 3480,3486 **** restore_toc_entries_parallel(ArchiveHandle *AH)
}
if (next_work_item->depCount > 0)
! par_list_append(&pending_list, next_work_item);
else
par_list_append(&ready_list, next_work_item);
}
--- 3390,3396 ----
}
if (next_work_item->depCount > 0)
! par_list_append(pending_list, next_work_item);
else
par_list_append(&ready_list, next_work_item);
}
***************
*** 3494,3502 **** restore_toc_entries_parallel(ArchiveHandle *AH)
ahlog(AH, 1, "entering main parallel loop\n");
! while ((next_work_item = get_next_work_item(AH, &ready_list,
! slots, n_slots)) != NULL ||
! work_in_progress(slots, n_slots))
{
if (next_work_item != NULL)
{
--- 3404,3411 ----
ahlog(AH, 1, "entering main parallel loop\n");
! while ((next_work_item = get_next_work_item(AH, &ready_list, pstate)) != NULL ||
! !IsEveryWorkerIdle(pstate))
{
if (next_work_item != NULL)
{
***************
*** 3516,3577 **** restore_toc_entries_parallel(ArchiveHandle *AH)
continue;
}
! if ((next_slot = get_next_slot(slots, n_slots)) != NO_SLOT)
! {
! /* There is work still to do and a worker slot available */
! thandle child;
! RestoreArgs *args;
! ahlog(AH, 1, "launching item %d %s %s\n",
! next_work_item->dumpId,
! next_work_item->desc, next_work_item->tag);
! par_list_remove(next_work_item);
!
! /* this memory is dealloced in mark_work_done() */
! args = pg_malloc(sizeof(RestoreArgs));
! args->AH = CloneArchive(AH);
! args->te = next_work_item;
! args->pse = &pstate->pse[next_slot];
! /* run the step in a worker child */
! child = spawn_restore(args);
! slots[next_slot].child_id = child;
! slots[next_slot].args = args;
! continue;
}
- }
! /*
! * If we get here there must be work being done. Either there is no
! * work available to schedule (and work_in_progress returned true) or
! * there are no slots available. So we wait for a worker to finish,
! * and process the result.
! */
! ret_child = reap_child(slots, n_slots, &work_status);
! if (WIFEXITED(work_status))
! {
! mark_work_done(AH, &ready_list,
! ret_child, WEXITSTATUS(work_status),
! slots, n_slots);
! }
! else
! {
! exit_horribly(modulename, "worker process crashed: status %d\n",
! work_status);
}
}
ahlog(AH, 1, "finished main parallel loop\n");
! /*
! * Remove the pstate again, so the exit handler will now fall back to
! * closing AH->connection again.
! */
! shutdown_info.pstate = NULL;
/*
* Now reconnect the single parent connection.
--- 3425,3495 ----
continue;
}
! ahlog(AH, 1, "launching item %d %s %s\n",
! next_work_item->dumpId,
! next_work_item->desc, next_work_item->tag);
! par_list_remove(next_work_item);
! Assert(GetIdleWorker(pstate) != NO_SLOT);
! DispatchJobForTocEntry(AH, pstate, next_work_item, ACT_RESTORE);
! }
! else
! /* at least one child is working and we have nothing ready. */
! Assert(!IsEveryWorkerIdle(pstate));
! for (;;)
! {
! int nTerm = 0;
! /*
! * In order to reduce dependencies as soon as possible and
! * especially to reap the status of workers who are working on
! * items that pending items depend on, we do a non-blocking check
! * for ended workers first.
! *
! * However, if we do not have any other work items currently that
! * workers can work on, we do not busy-loop here but instead
! * really wait for at least one worker to terminate. Hence we call
! * ListenToWorkers(..., ..., do_wait = true) in this case.
! */
! ListenToWorkers(AH, pstate, !next_work_item);
! while ((ret_child = ReapWorkerStatus(pstate, &work_status)) != NO_SLOT)
! {
! nTerm++;
! mark_work_done(AH, &ready_list, ret_child, work_status, pstate);
}
! /*
! * We need to make sure that we have an idle worker before re-running the
! * loop. If nTerm > 0 we already have that (quick check).
! */
! if (nTerm > 0)
! break;
! /* if nobody terminated, explicitly check for an idle worker */
! if (GetIdleWorker(pstate) != NO_SLOT)
! break;
!
! /*
! * If we have no idle worker, read the result of one or more
! * workers and loop the loop to call ReapWorkerStatus() on them.
! */
! ListenToWorkers(AH, pstate, true);
}
}
ahlog(AH, 1, "finished main parallel loop\n");
+ }
! static void
! restore_toc_entries_postfork(ArchiveHandle *AH, TocEntry *pending_list)
! {
! RestoreOptions *ropt = AH->ropt;
! TocEntry *te;
!
! ahlog(AH, 2, "entering restore_toc_entries_postfork\n");
/*
* Now reconnect the single parent connection.
***************
*** 3587,3593 **** restore_toc_entries_parallel(ArchiveHandle *AH)
* dependencies, or some other pathological condition. If so, do it in the
* single parent connection.
*/
! for (te = pending_list.par_next; te != &pending_list; te = te->par_next)
{
ahlog(AH, 1, "processing missed item %d %s %s\n",
te->dumpId, te->desc, te->tag);
--- 3505,3511 ----
* dependencies, or some other pathological condition. If so, do it in the
* single parent connection.
*/
! for (te = pending_list->par_next; te != pending_list; te = te->par_next)
{
ahlog(AH, 1, "processing missed item %d %s %s\n",
te->dumpId, te->desc, te->tag);
***************
*** 3598,3718 **** restore_toc_entries_parallel(ArchiveHandle *AH)
}
/*
- * create a worker child to perform a restore step in parallel
- */
- static thandle
- spawn_restore(RestoreArgs *args)
- {
- thandle child;
-
- /* Ensure stdio state is quiesced before forking */
- fflush(NULL);
-
- #ifndef WIN32
- child = fork();
- if (child == 0)
- {
- /* in child process */
- parallel_restore(args);
- exit_horribly(modulename,
- "parallel_restore should not return\n");
- }
- else if (child < 0)
- {
- /* fork failed */
- exit_horribly(modulename,
- "could not create worker process: %s\n",
- strerror(errno));
- }
- #else
- child = (HANDLE) _beginthreadex(NULL, 0, (void *) parallel_restore,
- args, 0, NULL);
- if (child == 0)
- exit_horribly(modulename,
- "could not create worker thread: %s\n",
- strerror(errno));
- #endif
-
- return child;
- }
-
- /*
- * collect status from a completed worker child
- */
- static thandle
- reap_child(ParallelSlot *slots, int n_slots, int *work_status)
- {
- #ifndef WIN32
- /* Unix is so much easier ... */
- return wait(work_status);
- #else
- static HANDLE *handles = NULL;
- int hindex,
- snum,
- tnum;
- thandle ret_child;
- DWORD res;
-
- /* first time around only, make space for handles to listen on */
- if (handles == NULL)
- handles = (HANDLE *) pg_calloc(sizeof(HANDLE), n_slots);
-
- /* set up list of handles to listen to */
- for (snum = 0, tnum = 0; snum < n_slots; snum++)
- if (slots[snum].child_id != 0)
- handles[tnum++] = slots[snum].child_id;
-
- /* wait for one to finish */
- hindex = WaitForMultipleObjects(tnum, handles, false, INFINITE);
-
- /* get handle of finished thread */
- ret_child = handles[hindex - WAIT_OBJECT_0];
-
- /* get the result */
- GetExitCodeThread(ret_child, &res);
- *work_status = res;
-
- /* dispose of handle to stop leaks */
- CloseHandle(ret_child);
-
- return ret_child;
- #endif
- }
-
- /*
- * are we doing anything now?
- */
- static bool
- work_in_progress(ParallelSlot *slots, int n_slots)
- {
- int i;
-
- for (i = 0; i < n_slots; i++)
- {
- if (slots[i].child_id != 0)
- return true;
- }
- return false;
- }
-
- /*
- * find the first free parallel slot (if any).
- */
- static int
- get_next_slot(ParallelSlot *slots, int n_slots)
- {
- int i;
-
- for (i = 0; i < n_slots; i++)
- {
- if (slots[i].child_id == 0)
- return i;
- }
- return NO_SLOT;
- }
-
-
- /*
* Check if te1 has an exclusive lock requirement for an item that te2 also
* requires, whether or not te2's requirement is for an exclusive lock.
*/
--- 3516,3521 ----
***************
*** 3785,3791 **** par_list_remove(TocEntry *te)
*/
static TocEntry *
get_next_work_item(ArchiveHandle *AH, TocEntry *ready_list,
! ParallelSlot *slots, int n_slots)
{
bool pref_non_data = false; /* or get from AH->ropt */
TocEntry *data_te = NULL;
--- 3588,3594 ----
*/
static TocEntry *
get_next_work_item(ArchiveHandle *AH, TocEntry *ready_list,
! ParallelState *pstate)
{
bool pref_non_data = false; /* or get from AH->ropt */
TocEntry *data_te = NULL;
***************
*** 3800,3810 **** get_next_work_item(ArchiveHandle *AH, TocEntry *ready_list,
{
int count = 0;
! for (k = 0; k < n_slots; k++)
! if (slots[k].args->te != NULL &&
! slots[k].args->te->section == SECTION_DATA)
count++;
! if (n_slots == 0 || count * 4 < n_slots)
pref_non_data = false;
}
--- 3603,3613 ----
{
int count = 0;
! for (k = 0; k < pstate->numWorkers; k++)
! if (pstate->parallelSlot[k].args->te != NULL &&
! pstate->parallelSlot[k].args->te->section == SECTION_DATA)
count++;
! if (pstate->numWorkers == 0 || count * 4 < pstate->numWorkers)
pref_non_data = false;
}
***************
*** 3820,3832 **** get_next_work_item(ArchiveHandle *AH, TocEntry *ready_list,
* that a currently running item also needs lock on, or vice versa. If
* so, we don't want to schedule them together.
*/
! for (i = 0; i < n_slots && !conflicts; i++)
{
TocEntry *running_te;
! if (slots[i].args == NULL)
continue;
! running_te = slots[i].args->te;
if (has_lock_conflicts(te, running_te) ||
has_lock_conflicts(running_te, te))
--- 3623,3635 ----
* that a currently running item also needs lock on, or vice versa. If
* so, we don't want to schedule them together.
*/
! for (i = 0; i < pstate->numWorkers && !conflicts; i++)
{
TocEntry *running_te;
! if (pstate->parallelSlot[i].workerStatus != WRKR_WORKING)
continue;
! running_te = pstate->parallelSlot[i].args->te;
if (has_lock_conflicts(te, running_te) ||
has_lock_conflicts(running_te, te))
***************
*** 3861,3923 **** get_next_work_item(ArchiveHandle *AH, TocEntry *ready_list,
/*
* Restore a single TOC item in parallel with others
*
! * this is the procedure run as a thread (Windows) or a
! * separate process (everything else).
*/
! static parallel_restore_result
! parallel_restore(RestoreArgs *args)
{
ArchiveHandle *AH = args->AH;
TocEntry *te = args->te;
RestoreOptions *ropt = AH->ropt;
! int retval;
!
! setProcessIdentifier(args->pse, AH);
!
! /*
! * Close and reopen the input file so we have a private file pointer that
! * doesn't stomp on anyone else's file pointer, if we're actually going to
! * need to read from the file. Otherwise, just close it except on Windows,
! * where it will possibly be needed by other threads.
! *
! * Note: on Windows, since we are using threads not processes, the reopen
! * call *doesn't* close the original file pointer but just open a new one.
! */
! if (te->section == SECTION_DATA)
! (AH->ReopenPtr) (AH);
! #ifndef WIN32
! else
! (AH->ClosePtr) (AH);
! #endif
!
! /*
! * We need our own database connection, too
! */
! ConnectDatabase((Archive *) AH, ropt->dbname,
! ropt->pghost, ropt->pgport, ropt->username,
! ropt->promptPassword);
_doSetFixedOutputState(AH);
! /* Restore the TOC item */
! retval = restore_toc_entry(AH, te, ropt, true);
!
! /* And clean up */
! DisconnectDatabase((Archive *) AH);
! unsetProcessIdentifier(args->pse);
! /* If we reopened the file, we are done with it, so close it now */
! if (te->section == SECTION_DATA)
! (AH->ClosePtr) (AH);
! if (retval == 0 && AH->public.n_errors)
! retval = WORKER_IGNORED_ERRORS;
! #ifndef WIN32
! exit(retval);
! #else
! return retval;
! #endif
}
--- 3664,3692 ----
/*
* Restore a single TOC item in parallel with others
*
! * this is run in the worker, i.e. in a thread (Windows) or a separate process
! * (everything else). A worker process executes several such work items during
! * a parallel backup or restore. Once we terminate here and report back that
! * our work is finished, the master process will assign us a new work item.
*/
! int
! parallel_restore(ParallelArgs *args)
{
ArchiveHandle *AH = args->AH;
TocEntry *te = args->te;
RestoreOptions *ropt = AH->ropt;
! int status;
_doSetFixedOutputState(AH);
! Assert(AH->connection != NULL);
! AH->public.n_errors = 0;
! /* Restore the TOC item */
! status = restore_toc_entry(AH, te, ropt, true);
! return status;
}
***************
*** 3929,3953 **** parallel_restore(RestoreArgs *args)
*/
static void
mark_work_done(ArchiveHandle *AH, TocEntry *ready_list,
! thandle worker, int status,
! ParallelSlot *slots, int n_slots)
{
TocEntry *te = NULL;
- int i;
! for (i = 0; i < n_slots; i++)
! {
! if (slots[i].child_id == worker)
! {
! slots[i].child_id = 0;
! te = slots[i].args->te;
! DeCloneArchive(slots[i].args->AH);
! free(slots[i].args);
! slots[i].args = NULL;
!
! break;
! }
! }
if (te == NULL)
exit_horribly(modulename, "could not find slot of finished worker\n");
--- 3698,3709 ----
*/
static void
mark_work_done(ArchiveHandle *AH, TocEntry *ready_list,
! int worker, int status,
! ParallelState *pstate)
{
TocEntry *te = NULL;
! te = pstate->parallelSlot[worker].args->te;
if (te == NULL)
exit_horribly(modulename, "could not find slot of finished worker\n");
***************
*** 4302,4311 **** inhibit_data_for_failed_table(ArchiveHandle *AH, TocEntry *te)
*
* Enough of the structure is cloned to ensure that there is no
* conflict between different threads each with their own clone.
- *
- * These could be public, but no need at present.
*/
! static ArchiveHandle *
CloneArchive(ArchiveHandle *AH)
{
ArchiveHandle *clone;
--- 4058,4065 ----
*
* Enough of the structure is cloned to ensure that there is no
* conflict between different threads each with their own clone.
*/
! ArchiveHandle *
CloneArchive(ArchiveHandle *AH)
{
ArchiveHandle *clone;
***************
*** 4331,4339 **** CloneArchive(ArchiveHandle *AH)
--- 4085,4141 ----
/* clone has its own error count, too */
clone->public.n_errors = 0;
+ /*
+ * Connect our new clone object to the database:
+ * In parallel restore the parent is already disconnected.
+ * In parallel backup we clone the parent's existing connection.
+ */
+ if (AH->ropt)
+ {
+ RestoreOptions *ropt = AH->ropt;
+ Assert(AH->connection == NULL);
+ /* this also sets clone->connection */
+ ConnectDatabase((Archive *) clone, ropt->dbname,
+ ropt->pghost, ropt->pgport, ropt->username,
+ ropt->promptPassword);
+ }
+ else
+ {
+ char *dbname;
+ char *pghost;
+ char *pgport;
+ char *username;
+ const char *encname;
+
+ Assert(AH->connection != NULL);
+
+ /*
+ * Even though we are technically accessing the parent's database object
+ * here, these functions are fine to be called like that because all just
+ * return a pointer and do not actually send/receive any data to/from the
+ * database.
+ */
+ dbname = PQdb(AH->connection);
+ pghost = PQhost(AH->connection);
+ pgport = PQport(AH->connection);
+ username = PQuser(AH->connection);
+ encname = pg_encoding_to_char(AH->public.encoding);
+
+ /* this also sets clone->connection */
+ ConnectDatabase((Archive *) clone, dbname, pghost, pgport, username, TRI_NO);
+
+ /*
+ * Set the same encoding, whatever we set here is what we got from
+ * pg_encoding_to_char(), so we really shouldn't run into an error setting that
+ * very same value. Also see the comment in SetupConnection().
+ */
+ PQsetClientEncoding(clone->connection, encname);
+ }
+
/* Let the format-specific code have a chance too */
(clone->ClonePtr) (clone);
+ Assert(clone->connection != NULL);
return clone;
}
***************
*** 4342,4348 **** CloneArchive(ArchiveHandle *AH)
*
* Note: we assume any clone-local connection was already closed.
*/
! static void
DeCloneArchive(ArchiveHandle *AH)
{
/* Clear format-specific state */
--- 4144,4150 ----
*
* Note: we assume any clone-local connection was already closed.
*/
! void
DeCloneArchive(ArchiveHandle *AH)
{
/* Clear format-specific state */
*** a/src/bin/pg_dump/pg_backup_archiver.h
--- b/src/bin/pg_dump/pg_backup_archiver.h
***************
*** 100,107 **** typedef z_stream *z_streamp;
--- 100,120 ----
#define K_OFFSET_POS_SET 2
#define K_OFFSET_NO_DATA 3
+ /*
+ * Special exit values from worker children. We reserve 0 for normal
+ * success; 1 and other small values should be interpreted as crashes.
+ */
+ #define WORKER_OK 0
+ #define WORKER_CREATE_DONE 10
+ #define WORKER_INHIBIT_DATA 11
+ #define WORKER_IGNORED_ERRORS 12
+
struct _archiveHandle;
struct _tocEntry;
+ struct _restoreList;
+ struct _parallel_args;
+ struct _parallel_state;
+ enum _action;
typedef void (*ClosePtr) (struct _archiveHandle * AH);
typedef void (*ReopenPtr) (struct _archiveHandle * AH);
***************
*** 129,134 **** typedef void (*PrintTocDataPtr) (struct _archiveHandle * AH, struct _tocEntry *
--- 142,154 ----
typedef void (*ClonePtr) (struct _archiveHandle * AH);
typedef void (*DeClonePtr) (struct _archiveHandle * AH);
+ typedef char *(*WorkerJobRestorePtr)(struct _archiveHandle * AH, struct _tocEntry * te);
+ typedef char *(*WorkerJobDumpPtr)(struct _archiveHandle * AH, struct _tocEntry * te);
+ typedef char *(*MasterStartParallelItemPtr)(struct _archiveHandle * AH, struct _tocEntry * te,
+ enum _action act);
+ typedef int (*MasterEndParallelItemPtr)(struct _archiveHandle * AH, struct _tocEntry * te,
+ const char *str, enum _action act);
+
typedef size_t (*CustomOutPtr) (struct _archiveHandle * AH, const void *buf, size_t len);
typedef enum
***************
*** 227,232 **** typedef struct _archiveHandle
--- 247,258 ----
StartBlobPtr StartBlobPtr;
EndBlobPtr EndBlobPtr;
+ MasterStartParallelItemPtr MasterStartParallelItemPtr;
+ MasterEndParallelItemPtr MasterEndParallelItemPtr;
+
+ WorkerJobDumpPtr WorkerJobDumpPtr;
+ WorkerJobRestorePtr WorkerJobRestorePtr;
+
ClonePtr ClonePtr; /* Clone format-specific fields */
DeClonePtr DeClonePtr; /* Clean up cloned fields */
***************
*** 236,241 **** typedef struct _archiveHandle
--- 262,268 ----
char *archdbname; /* DB name *read* from archive */
enum trivalue promptPassword;
char *savedPassword; /* password for ropt->username, if known */
+ char *use_role;
PGconn *connection;
int connectToDB; /* Flag to indicate if direct DB connection is
* required */
***************
*** 323,328 **** typedef struct _tocEntry
--- 350,356 ----
int nLockDeps; /* number of such dependencies */
} TocEntry;
+ extern int parallel_restore(struct _parallel_args *args);
extern void on_exit_close_archive(Archive *AHX);
extern void warn_or_exit_horribly(ArchiveHandle *AH, const char *modulename, const char *fmt,...) __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
***************
*** 333,341 **** extern void WriteHead(ArchiveHandle *AH);
extern void ReadHead(ArchiveHandle *AH);
extern void WriteToc(ArchiveHandle *AH);
extern void ReadToc(ArchiveHandle *AH);
! extern void WriteDataChunks(ArchiveHandle *AH);
extern teReqs TocIDRequired(ArchiveHandle *AH, DumpId id, RestoreOptions *ropt);
extern bool checkSeek(FILE *fp);
#define appendStringLiteralAHX(buf,str,AH) \
--- 361,374 ----
extern void ReadHead(ArchiveHandle *AH);
extern void WriteToc(ArchiveHandle *AH);
extern void ReadToc(ArchiveHandle *AH);
! extern void WriteDataChunks(ArchiveHandle *AH, struct _parallel_state *pstate);
! extern void WriteDataChunksForTocEntry(ArchiveHandle *AH, TocEntry *te);
!
! extern ArchiveHandle *CloneArchive(ArchiveHandle *AH);
! extern void DeCloneArchive(ArchiveHandle *AH);
extern teReqs TocIDRequired(ArchiveHandle *AH, DumpId id, RestoreOptions *ropt);
+ TocEntry *getTocEntryByDumpId(ArchiveHandle *AH, DumpId id);
extern bool checkSeek(FILE *fp);
#define appendStringLiteralAHX(buf,str,AH) \
***************
*** 376,379 **** int ahprintf(ArchiveHandle *AH, const char *fmt,...) __attribute__((format(PG_
--- 409,424 ----
void ahlog(ArchiveHandle *AH, int level, const char *fmt,...) __attribute__((format(PG_PRINTF_ATTRIBUTE, 3, 4)));
+ #ifdef USE_ASSERT_CHECKING
+ #define Assert(condition) \
+ if (!(condition)) \
+ { \
+ write_msg(NULL, "Failed assertion in %s, line %d\n", \
+ __FILE__, __LINE__); \
+ abort();\
+ }
+ #else
+ #define Assert(condition)
+ #endif
+
#endif
*** a/src/bin/pg_dump/pg_backup_custom.c
--- b/src/bin/pg_dump/pg_backup_custom.c
***************
*** 27,32 ****
--- 27,33 ----
#include "compress_io.h"
#include "dumputils.h"
#include "dumpmem.h"
+ #include "parallel.h"
/*--------
* Routines in the format interface
***************
*** 60,65 **** static void _LoadBlobs(ArchiveHandle *AH, bool drop);
--- 61,70 ----
static void _Clone(ArchiveHandle *AH);
static void _DeClone(ArchiveHandle *AH);
+ static char *_MasterStartParallelItem(ArchiveHandle *AH, TocEntry *te, T_Action act);
+ static int _MasterEndParallelItem(ArchiveHandle *AH, TocEntry *te, const char *str, T_Action act);
+ char *_WorkerJobRestoreCustom(ArchiveHandle *AH, TocEntry *te);
+
typedef struct
{
CompressorState *cs;
***************
*** 127,132 **** InitArchiveFmt_Custom(ArchiveHandle *AH)
--- 132,144 ----
AH->ClonePtr = _Clone;
AH->DeClonePtr = _DeClone;
+ AH->MasterStartParallelItemPtr = _MasterStartParallelItem;
+ AH->MasterEndParallelItemPtr = _MasterEndParallelItem;
+
+ /* no parallel dump in the custom archive, only parallel restore */
+ AH->WorkerJobDumpPtr = NULL;
+ AH->WorkerJobRestorePtr = _WorkerJobRestoreCustom;
+
/* Set up a private area. */
ctx = (lclContext *) pg_calloc(1, sizeof(lclContext));
AH->formatData = (void *) ctx;
***************
*** 698,704 **** _CloseArchive(ArchiveHandle *AH)
tpos = ftello(AH->FH);
WriteToc(AH);
ctx->dataStart = _getFilePos(AH, ctx);
! WriteDataChunks(AH);
/*
* If possible, re-write the TOC in order to update the data offset
--- 710,716 ----
tpos = ftello(AH->FH);
WriteToc(AH);
ctx->dataStart = _getFilePos(AH, ctx);
! WriteDataChunks(AH, NULL);
/*
* If possible, re-write the TOC in order to update the data offset
***************
*** 796,801 **** _DeClone(ArchiveHandle *AH)
--- 808,888 ----
free(ctx);
}
+ /*
+ * This function is executed in the child of a parallel backup for the
+ * custom format archive and dumps the actual data.
+ */
+ char *
+ _WorkerJobRestoreCustom(ArchiveHandle *AH, TocEntry *te)
+ {
+ /* short fixed-size string + some ID so far, this needs to be malloc'ed
+ * instead of static because we work with threads on windows */
+ const int buflen = 64;
+ char *buf = (char*) pg_malloc(buflen);
+ ParallelArgs pargs;
+ int status;
+ lclTocEntry *tctx;
+
+ tctx = (lclTocEntry *) te->formatData;
+
+ pargs.AH = AH;
+ pargs.te = te;
+
+ status = parallel_restore(&pargs);
+
+ snprintf(buf, buflen, "OK RESTORE %d %d %d", te->dumpId, status,
+ status == WORKER_IGNORED_ERRORS ? AH->public.n_errors : 0);
+
+ return buf;
+ }
+
+ /*
+ * This function is executed in the parent process. Depending on the desired
+ * action (dump or restore) it creates a string that is understood by the
+ * _WorkerJobDumpDirectory/_WorkerJobRestoreDirectory functions of the
+ * respective dump format.
+ */
+ static char *
+ _MasterStartParallelItem(ArchiveHandle *AH, TocEntry *te, T_Action act)
+ {
+ /*
+ * A static char is okay here, even on Windows because we call this
+ * function only from one process (the master).
+ */
+ static char buf[64]; /* short fixed-size string + number */
+
+ /* no parallel dump in the custom archive format */
+ Assert(act == ACT_RESTORE);
+
+ snprintf(buf, sizeof(buf), "RESTORE %d", te->dumpId);
+
+ return buf;
+ }
+
+ /*
+ * This function is executed in the parent process. It analyzes the response of
+ * the _WorkerJobDumpDirectory/_WorkerJobRestoreDirectory functions of the
+ * respective dump format.
+ */
+ static int
+ _MasterEndParallelItem(ArchiveHandle *AH, TocEntry *te, const char *str, T_Action act)
+ {
+ DumpId dumpId;
+ int nBytes, status, n_errors;
+
+ /* no parallel dump in the custom archive */
+ Assert(act == ACT_RESTORE);
+
+ sscanf(str, "%u %u %u%n", &dumpId, &status, &n_errors, &nBytes);
+
+ Assert(nBytes == strlen(str));
+ Assert(dumpId == te->dumpId);
+
+ AH->public.n_errors += n_errors;
+
+ return status;
+ }
+
/*--------------------------------------------------
* END OF FORMAT CALLBACKS
*--------------------------------------------------
*** a/src/bin/pg_dump/pg_backup_db.c
--- b/src/bin/pg_dump/pg_backup_db.c
***************
*** 308,319 **** ConnectDatabase(Archive *AHX,
PQsetNoticeProcessor(AH->connection, notice_processor, NULL);
}
void
DisconnectDatabase(Archive *AHX)
{
ArchiveHandle *AH = (ArchiveHandle *) AHX;
! PQfinish(AH->connection); /* noop if AH->connection is NULL */
AH->connection = NULL;
}
--- 308,337 ----
PQsetNoticeProcessor(AH->connection, notice_processor, NULL);
}
+ /*
+ * Close the connection to the database and also cancel off the query if we
+ * have one running.
+ */
void
DisconnectDatabase(Archive *AHX)
{
ArchiveHandle *AH = (ArchiveHandle *) AHX;
+ PGcancel *cancel;
+ char errbuf[1];
+
+ if (!AH->connection)
+ return;
! if (PQtransactionStatus(AH->connection) == PQTRANS_ACTIVE)
! {
! if ((cancel = PQgetCancel(AH->connection)))
! {
! PQcancel(cancel, errbuf, sizeof(errbuf));
! PQfreeCancel(cancel);
! }
! }
!
! PQfinish(AH->connection);
AH->connection = NULL;
}
*** a/src/bin/pg_dump/pg_backup_directory.c
--- b/src/bin/pg_dump/pg_backup_directory.c
***************
*** 36,41 ****
--- 36,42 ----
#include "compress_io.h"
#include "dumpmem.h"
#include "dumputils.h"
+ #include "parallel.h"
#include <dirent.h>
#include <sys/stat.h>
***************
*** 51,56 **** typedef struct
--- 52,58 ----
cfp *dataFH; /* currently open data file */
cfp *blobsTocFH; /* file handle for blobs.toc */
+ ParallelState *pstate; /* for parallel backup / restore */
} lclContext;
typedef struct
***************
*** 70,75 **** static int _ReadByte(ArchiveHandle *);
--- 72,78 ----
static size_t _WriteBuf(ArchiveHandle *AH, const void *buf, size_t len);
static size_t _ReadBuf(ArchiveHandle *AH, void *buf, size_t len);
static void _CloseArchive(ArchiveHandle *AH);
+ static void _ReopenArchive(ArchiveHandle *AH);
static void _PrintTocData(ArchiveHandle *AH, TocEntry *te, RestoreOptions *ropt);
static void _WriteExtraToc(ArchiveHandle *AH, TocEntry *te);
***************
*** 81,91 **** static void _StartBlob(ArchiveHandle *AH, TocEntry *te, Oid oid);
static void _EndBlob(ArchiveHandle *AH, TocEntry *te, Oid oid);
static void _EndBlobs(ArchiveHandle *AH, TocEntry *te);
static void _LoadBlobs(ArchiveHandle *AH, RestoreOptions *ropt);
! static char *prependDirectory(ArchiveHandle *AH, const char *relativeFilename);
static void createDirectory(const char *dir);
!
/*
* Init routine required by ALL formats. This is a global routine
--- 84,99 ----
static void _EndBlob(ArchiveHandle *AH, TocEntry *te, Oid oid);
static void _EndBlobs(ArchiveHandle *AH, TocEntry *te);
static void _LoadBlobs(ArchiveHandle *AH, RestoreOptions *ropt);
+ static void _Clone(ArchiveHandle *AH);
+ static void _DeClone(ArchiveHandle *AH);
! static char *_MasterStartParallelItem(ArchiveHandle *AH, TocEntry *te, T_Action act);
! static int _MasterEndParallelItem(ArchiveHandle *AH, TocEntry *te, const char *str, T_Action act);
! static char *_WorkerJobRestoreDirectory(ArchiveHandle *AH, TocEntry *te);
! static char *_WorkerJobDumpDirectory(ArchiveHandle *AH, TocEntry *te);
static void createDirectory(const char *dir);
! static char *prependDirectory(ArchiveHandle *AH, char *buf, const char *relativeFilename);
/*
* Init routine required by ALL formats. This is a global routine
***************
*** 112,118 **** InitArchiveFmt_Directory(ArchiveHandle *AH)
AH->WriteBufPtr = _WriteBuf;
AH->ReadBufPtr = _ReadBuf;
AH->ClosePtr = _CloseArchive;
! AH->ReopenPtr = NULL;
AH->PrintTocDataPtr = _PrintTocData;
AH->ReadExtraTocPtr = _ReadExtraToc;
AH->WriteExtraTocPtr = _WriteExtraToc;
--- 120,126 ----
AH->WriteBufPtr = _WriteBuf;
AH->ReadBufPtr = _ReadBuf;
AH->ClosePtr = _CloseArchive;
! AH->ReopenPtr = _ReopenArchive;
AH->PrintTocDataPtr = _PrintTocData;
AH->ReadExtraTocPtr = _ReadExtraToc;
AH->WriteExtraTocPtr = _WriteExtraToc;
***************
*** 123,130 **** InitArchiveFmt_Directory(ArchiveHandle *AH)
AH->EndBlobPtr = _EndBlob;
AH->EndBlobsPtr = _EndBlobs;
! AH->ClonePtr = NULL;
! AH->DeClonePtr = NULL;
/* Set up our private context */
ctx = (lclContext *) pg_calloc(1, sizeof(lclContext));
--- 131,144 ----
AH->EndBlobPtr = _EndBlob;
AH->EndBlobsPtr = _EndBlobs;
! AH->ClonePtr = _Clone;
! AH->DeClonePtr = _DeClone;
!
! AH->WorkerJobRestorePtr = _WorkerJobRestoreDirectory;
! AH->WorkerJobDumpPtr = _WorkerJobDumpDirectory;
!
! AH->MasterStartParallelItemPtr = _MasterStartParallelItem;
! AH->MasterEndParallelItemPtr = _MasterEndParallelItem;
/* Set up our private context */
ctx = (lclContext *) pg_calloc(1, sizeof(lclContext));
***************
*** 153,162 **** InitArchiveFmt_Directory(ArchiveHandle *AH)
}
else
{ /* Read Mode */
! char *fname;
cfp *tocFH;
! fname = prependDirectory(AH, "toc.dat");
tocFH = cfopen_read(fname, PG_BINARY_R);
if (tocFH == NULL)
--- 167,176 ----
}
else
{ /* Read Mode */
! char fname[MAXPGPATH];
cfp *tocFH;
! prependDirectory(AH, fname, "toc.dat");
tocFH = cfopen_read(fname, PG_BINARY_R);
if (tocFH == NULL)
***************
*** 282,290 **** _StartData(ArchiveHandle *AH, TocEntry *te)
{
lclTocEntry *tctx = (lclTocEntry *) te->formatData;
lclContext *ctx = (lclContext *) AH->formatData;
! char *fname;
! fname = prependDirectory(AH, tctx->filename);
ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression);
if (ctx->dataFH == NULL)
--- 296,304 ----
{
lclTocEntry *tctx = (lclTocEntry *) te->formatData;
lclContext *ctx = (lclContext *) AH->formatData;
! char fname[MAXPGPATH];
! prependDirectory(AH, fname, tctx->filename);
ctx->dataFH = cfopen_write(fname, PG_BINARY_W, AH->compression);
if (ctx->dataFH == NULL)
***************
*** 309,314 **** _WriteData(ArchiveHandle *AH, const void *data, size_t dLen)
--- 323,331 ----
if (dLen == 0)
return 0;
+ /* Are we aborting? */
+ checkAborting(AH);
+
return cfwrite(data, dLen, ctx->dataFH);
}
***************
*** 376,383 **** _PrintTocData(ArchiveHandle *AH, TocEntry *te, RestoreOptions *ropt)
_LoadBlobs(AH, ropt);
else
{
! char *fname = prependDirectory(AH, tctx->filename);
_PrintFileData(AH, fname, ropt);
}
}
--- 393,401 ----
_LoadBlobs(AH, ropt);
else
{
! char fname[MAXPGPATH];
+ prependDirectory(AH, fname, tctx->filename);
_PrintFileData(AH, fname, ropt);
}
}
***************
*** 387,398 **** _LoadBlobs(ArchiveHandle *AH, RestoreOptions *ropt)
{
Oid oid;
lclContext *ctx = (lclContext *) AH->formatData;
! char *fname;
char line[MAXPGPATH];
StartRestoreBlobs(AH);
! fname = prependDirectory(AH, "blobs.toc");
ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R);
--- 405,416 ----
{
Oid oid;
lclContext *ctx = (lclContext *) AH->formatData;
! char fname[MAXPGPATH];
char line[MAXPGPATH];
StartRestoreBlobs(AH);
! prependDirectory(AH, fname, "blobs.toc");
ctx->blobsTocFH = cfopen_read(fname, PG_BINARY_R);
***************
*** 475,480 **** _WriteBuf(ArchiveHandle *AH, const void *buf, size_t len)
--- 493,501 ----
lclContext *ctx = (lclContext *) AH->formatData;
size_t res;
+ /* Are we aborting? */
+ checkAborting(AH);
+
res = cfwrite(buf, len, ctx->dataFH);
if (res != len)
exit_horribly(modulename, "could not write to output file: %s\n",
***************
*** 519,525 **** _CloseArchive(ArchiveHandle *AH)
if (AH->mode == archModeWrite)
{
cfp *tocFH;
! char *fname = prependDirectory(AH, "toc.dat");
/* The TOC is always created uncompressed */
tocFH = cfopen_write(fname, PG_BINARY_W, 0);
--- 540,551 ----
if (AH->mode == archModeWrite)
{
cfp *tocFH;
! char fname[MAXPGPATH];
!
! prependDirectory(AH, fname, "toc.dat");
!
! /* this will actually fork the processes for a parallel backup */
! ctx->pstate = ParallelBackupStart(AH, NULL);
/* The TOC is always created uncompressed */
tocFH = cfopen_write(fname, PG_BINARY_W, 0);
***************
*** 540,550 **** _CloseArchive(ArchiveHandle *AH)
if (cfclose(tocFH) != 0)
exit_horribly(modulename, "could not close TOC file: %s\n",
strerror(errno));
! WriteDataChunks(AH);
}
AH->FH = NULL;
}
/*
* BLOB support
--- 566,589 ----
if (cfclose(tocFH) != 0)
exit_horribly(modulename, "could not close TOC file: %s\n",
strerror(errno));
! WriteDataChunks(AH, ctx->pstate);
!
! ParallelBackupEnd(AH, ctx->pstate);
}
AH->FH = NULL;
}
+ /*
+ * Reopen the archive's file handle.
+ */
+ static void
+ _ReopenArchive(ArchiveHandle *AH)
+ {
+ /*
+ * Our TOC is in memory, our data files are opened by each child anyway as
+ * they are separate. We support reopening the archive by just doing nothing.
+ */
+ }
/*
* BLOB support
***************
*** 561,569 **** static void
_StartBlobs(ArchiveHandle *AH, TocEntry *te)
{
lclContext *ctx = (lclContext *) AH->formatData;
! char *fname;
! fname = prependDirectory(AH, "blobs.toc");
/* The blob TOC file is never compressed */
ctx->blobsTocFH = cfopen_write(fname, "ab", 0);
--- 600,608 ----
_StartBlobs(ArchiveHandle *AH, TocEntry *te)
{
lclContext *ctx = (lclContext *) AH->formatData;
! char fname[MAXPGPATH];
! prependDirectory(AH, fname, "blobs.toc");
/* The blob TOC file is never compressed */
ctx->blobsTocFH = cfopen_write(fname, "ab", 0);
***************
*** 656,667 **** createDirectory(const char *dir)
dir, strerror(errno));
}
!
static char *
! prependDirectory(ArchiveHandle *AH, const char *relativeFilename)
{
lclContext *ctx = (lclContext *) AH->formatData;
- static char buf[MAXPGPATH];
char *dname;
dname = ctx->directory;
--- 695,710 ----
dir, strerror(errno));
}
! /*
! * Gets a relative file name and prepends the output directory, writing the
! * result to buf. The caller needs to make sure that buf is MAXPGPATH bytes
! * big. Can't use a static char[MAXPGPATH] inside the function because we run
! * multithreaded on Windows.
! */
static char *
! prependDirectory(ArchiveHandle *AH, char* buf, const char *relativeFilename)
{
lclContext *ctx = (lclContext *) AH->formatData;
char *dname;
dname = ctx->directory;
***************
*** 675,677 **** prependDirectory(ArchiveHandle *AH, const char *relativeFilename)
--- 718,869 ----
return buf;
}
+
+ /*
+ * Clone format-specific fields during parallel restoration.
+ */
+ static void
+ _Clone(ArchiveHandle *AH)
+ {
+ lclContext *ctx = (lclContext *) AH->formatData;
+
+ AH->formatData = (lclContext *) pg_malloc(sizeof(lclContext));
+ memcpy(AH->formatData, ctx, sizeof(lclContext));
+ ctx = (lclContext *) AH->formatData;
+
+ /*
+ * Note: we do not make a local lo_buf because we expect at most one BLOBS
+ * entry per archive, so no parallelism is possible. Likewise,
+ * TOC-entry-local state isn't an issue because any one TOC entry is
+ * touched by just one worker child.
+ */
+
+ /*
+ * We also don't copy the ParallelState pointer (pstate), only the master
+ * process ever writes to it.
+ */
+ }
+
+ static void
+ _DeClone(ArchiveHandle *AH)
+ {
+ lclContext *ctx = (lclContext *) AH->formatData;
+ free(ctx);
+ }
+
+ /*
+ * This function is executed in the parent process. Depending on the desired
+ * action (dump or restore) it creates a string that is understood by the
+ * _WorkerJobDumpDirectory/_WorkerJobRestoreDirectory functions of the
+ * respective dump format.
+ */
+ static char *
+ _MasterStartParallelItem(ArchiveHandle *AH, TocEntry *te, T_Action act)
+ {
+ /*
+ * A static char is okay here, even on Windows because we call this
+ * function only from one process (the master).
+ */
+ static char buf[64];
+
+ if (act == ACT_DUMP)
+ snprintf(buf, sizeof(buf), "DUMP %d", te->dumpId);
+ else if (act == ACT_RESTORE)
+ snprintf(buf, sizeof(buf), "RESTORE %d", te->dumpId);
+
+ return buf;
+ }
+
+ /*
+ * This function is executed in the child of a parallel backup for the
+ * directory archive and dumps the actual data.
+ *
+ * We are currently returning only the DumpId so theoretically we could
+ * make this function returning an int (or a DumpId). However, to
+ * facilitate further enhancements and because sooner or later we need to
+ * convert this to a string and send it via a message anyway, we stick with
+ * char *. It is parsed on the other side by the _EndMasterParallel()
+ * function of the respective dump format.
+ */
+ static char *
+ _WorkerJobDumpDirectory(ArchiveHandle *AH, TocEntry *te)
+ {
+ /* short fixed-size string + some ID so far, this needs to be malloc'ed
+ * instead of static because we work with threads on windows */
+ const int buflen = 64;
+ char *buf = (char*) pg_malloc(buflen);
+ lclTocEntry *tctx = (lclTocEntry *) te->formatData;
+
+ /* This should never happen */
+ if (!tctx)
+ exit_horribly(modulename, "Error during backup\n");
+
+ /*
+ * This function returns void. We either fail and die horribly or succeed...
+ * A failure will be detected by the parent when the child dies unexpectedly.
+ */
+ WriteDataChunksForTocEntry(AH, te);
+
+ snprintf(buf, buflen, "OK DUMP %d", te->dumpId);
+
+ return buf;
+ }
+
+ /*
+ * This function is executed in the child of a parallel backup for the
+ * directory archive and dumps the actual data.
+ */
+ static char *
+ _WorkerJobRestoreDirectory(ArchiveHandle *AH, TocEntry *te)
+ {
+ /* short fixed-size string + some ID so far, this needs to be malloc'ed
+ * instead of static because we work with threads on windows */
+ const int buflen = 64;
+ char *buf = (char*) pg_malloc(buflen);
+ ParallelArgs pargs;
+ int status;
+ lclTocEntry *tctx;
+
+ tctx = (lclTocEntry *) te->formatData;
+
+ pargs.AH = AH;
+ pargs.te = te;
+
+ status = parallel_restore(&pargs);
+
+ snprintf(buf, buflen, "OK RESTORE %d %d %d", te->dumpId, status,
+ status == WORKER_IGNORED_ERRORS ? AH->public.n_errors : 0);
+
+ return buf;
+ }
+ /*
+ * This function is executed in the parent process. It analyzes the response of
+ * the _WorkerJobDumpDirectory/_WorkerJobRestoreDirectory functions of the
+ * respective dump format.
+ */
+ static int
+ _MasterEndParallelItem(ArchiveHandle *AH, TocEntry *te, const char *str, T_Action act)
+ {
+ DumpId dumpId;
+ int nBytes, n_errors;
+ int status = 0;
+
+ if (act == ACT_DUMP)
+ {
+ sscanf(str, "%u%n", &dumpId, &nBytes);
+
+ Assert(dumpId == te->dumpId);
+ Assert(nBytes == strlen(str));
+ }
+ else if (act == ACT_RESTORE)
+ {
+ sscanf(str, "%u %u %u%n", &dumpId, &status, &n_errors, &nBytes);
+
+ Assert(dumpId == te->dumpId);
+ Assert(nBytes == strlen(str));
+
+ AH->public.n_errors += n_errors;
+ }
+
+ return status;
+ }
*** a/src/bin/pg_dump/pg_backup_tar.c
--- b/src/bin/pg_dump/pg_backup_tar.c
***************
*** 155,160 **** InitArchiveFmt_Tar(ArchiveHandle *AH)
--- 155,166 ----
AH->ClonePtr = NULL;
AH->DeClonePtr = NULL;
+ AH->MasterStartParallelItemPtr = NULL;
+ AH->MasterEndParallelItemPtr = NULL;
+
+ AH->WorkerJobDumpPtr = NULL;
+ AH->WorkerJobRestorePtr = NULL;
+
/*
* Set up some special context used in compressing data.
*/
***************
*** 834,840 **** _CloseArchive(ArchiveHandle *AH)
/*
* Now send the data (tables & blobs)
*/
! WriteDataChunks(AH);
/*
* Now this format wants to append a script which does a full restore
--- 840,846 ----
/*
* Now send the data (tables & blobs)
*/
! WriteDataChunks(AH, NULL);
/*
* Now this format wants to append a script which does a full restore
*** a/src/bin/pg_dump/pg_dump.c
--- b/src/bin/pg_dump/pg_dump.c
***************
*** 139,144 **** static int disable_dollar_quoting = 0;
--- 139,145 ----
static int dump_inserts = 0;
static int column_inserts = 0;
static int no_security_labels = 0;
+ static int no_synchronized_snapshots = 0;
static int no_unlogged_table_data = 0;
static int serializable_deferrable = 0;
***************
*** 235,242 **** static Oid findLastBuiltinOid_V70(Archive *fout);
static void selectSourceSchema(Archive *fout, const char *schemaName);
static char *getFormattedTypeName(Archive *fout, Oid oid, OidOptions opts);
static char *myFormatType(const char *typname, int32 typmod);
- static const char *fmtQualifiedId(Archive *fout,
- const char *schema, const char *id);
static void getBlobs(Archive *fout);
static void dumpBlob(Archive *fout, BlobInfo *binfo);
static int dumpBlobs(Archive *fout, void *arg);
--- 236,241 ----
***************
*** 254,261 **** static void binary_upgrade_extension_member(PQExpBuffer upgrade_buffer,
DumpableObject *dobj,
const char *objlabel);
static const char *getAttrName(int attrnum, TableInfo *tblInfo);
! static const char *fmtCopyColumnList(const TableInfo *ti);
! static PGresult *ExecuteSqlQueryForSingleRow(Archive *fout, char *query);
int
main(int argc, char **argv)
--- 253,261 ----
DumpableObject *dobj,
const char *objlabel);
static const char *getAttrName(int attrnum, TableInfo *tblInfo);
! static const char *fmtCopyColumnList(const TableInfo *ti, PQExpBuffer buffer);
! static char *get_synchronized_snapshot(Archive *fout);
! static PGresult *ExecuteSqlQueryForSingleRow(Archive *fout, const char *query);
int
main(int argc, char **argv)
***************
*** 274,279 **** main(int argc, char **argv)
--- 274,280 ----
DumpableObject **dobjs;
int numObjs;
int i;
+ int numWorkers = 1;
enum trivalue prompt_password = TRI_DEFAULT;
int compressLevel = -1;
int plainText = 0;
***************
*** 303,308 **** main(int argc, char **argv)
--- 304,310 ----
{"format", required_argument, NULL, 'F'},
{"host", required_argument, NULL, 'h'},
{"ignore-version", no_argument, NULL, 'i'},
+ {"jobs", 1, NULL, 'j'},
{"no-reconnect", no_argument, NULL, 'R'},
{"oids", no_argument, NULL, 'o'},
{"no-owner", no_argument, NULL, 'O'},
***************
*** 342,347 **** main(int argc, char **argv)
--- 344,350 ----
{"serializable-deferrable", no_argument, &serializable_deferrable, 1},
{"use-set-session-authorization", no_argument, &use_setsessauth, 1},
{"no-security-labels", no_argument, &no_security_labels, 1},
+ {"no-synchronized-snapshots", no_argument, &no_synchronized_snapshots, 1},
{"no-unlogged-table-data", no_argument, &no_unlogged_table_data, 1},
{NULL, 0, NULL, 0}
***************
*** 349,354 **** main(int argc, char **argv)
--- 352,359 ----
set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pg_dump"));
+ init_parallel_dump_utils();
+
g_verbose = false;
strcpy(g_comment_start, "-- ");
***************
*** 379,385 **** main(int argc, char **argv)
}
}
! while ((c = getopt_long(argc, argv, "abcCE:f:F:h:in:N:oOp:RsS:t:T:U:vwWxZ:",
long_options, &optindex)) != -1)
{
switch (c)
--- 384,390 ----
}
}
! while ((c = getopt_long(argc, argv, "abcCE:f:F:h:ij:n:N:oOp:RsS:t:T:U:vwWxZ:",
long_options, &optindex)) != -1)
{
switch (c)
***************
*** 420,425 **** main(int argc, char **argv)
--- 425,434 ----
/* ignored, deprecated option */
break;
+ case 'j': /* number of dump jobs */
+ numWorkers = atoi(optarg);
+ break;
+
case 'n': /* include schema(s) */
simple_string_list_append(&schema_include_patterns, optarg);
include_everything = false;
***************
*** 572,577 **** main(int argc, char **argv)
--- 581,602 ----
compressLevel = 0;
}
+ /*
+ * On Windows we can only have at most MAXIMUM_WAIT_OBJECTS (= 64 usually)
+ * parallel jobs because that's the maximum limit for the
+ * WaitForMultipleObjects() call.
+ */
+ if (numWorkers <= 0
+ #ifdef WIN32
+ || numWorkers > MAXIMUM_WAIT_OBJECTS
+ #endif
+ )
+ exit_horribly(NULL, "%s: invalid number of parallel jobs\n", progname);
+
+ /* Parallel backup only in the directory archive format so far */
+ if (archiveFormat != archDirectory && numWorkers > 1)
+ exit_horribly(NULL, "parallel backup only supported by the directory format\n");
+
/* Open the output file */
fout = CreateArchive(filename, archiveFormat, compressLevel, archiveMode);
***************
*** 595,600 **** main(int argc, char **argv)
--- 620,627 ----
fout->minRemoteVersion = 70000;
fout->maxRemoteVersion = (my_version / 100) * 100 + 99;
+ fout->numWorkers = numWorkers;
+
/*
* Open the database using the Archiver, so it knows about it. Errors mean
* death.
***************
*** 609,633 **** main(int argc, char **argv)
if (fout->remoteVersion < 90100)
no_security_labels = 1;
- /*
- * Start transaction-snapshot mode transaction to dump consistent data.
- */
- ExecuteSqlStatement(fout, "BEGIN");
- if (fout->remoteVersion >= 90100)
- {
- if (serializable_deferrable)
- ExecuteSqlStatement(fout,
- "SET TRANSACTION ISOLATION LEVEL "
- "SERIALIZABLE, READ ONLY, DEFERRABLE");
- else
- ExecuteSqlStatement(fout,
- "SET TRANSACTION ISOLATION LEVEL "
- "REPEATABLE READ");
- }
- else
- ExecuteSqlStatement(fout,
- "SET TRANSACTION ISOLATION LEVEL SERIALIZABLE");
-
/* Select the appropriate subquery to convert user IDs to names */
if (fout->remoteVersion >= 80100)
username_subquery = "SELECT rolname FROM pg_catalog.pg_roles WHERE oid =";
--- 636,641 ----
***************
*** 636,641 **** main(int argc, char **argv)
--- 644,657 ----
else
username_subquery = "SELECT usename FROM pg_user WHERE usesysid =";
+ /* check the version for the synchronized snapshots feature */
+ if (numWorkers > 1 && fout->remoteVersion < 90200
+ && !no_synchronized_snapshots)
+ exit_horribly(NULL,
+ "No synchronized snapshots available in this server version. "
+ "Run with --no-synchronized-snapshots instead if you do not "
+ "need synchronized snapshots.\n");
+
/* Find the last built-in OID, if needed */
if (fout->remoteVersion < 70300)
{
***************
*** 723,728 **** main(int argc, char **argv)
--- 739,748 ----
else
sortDumpableObjectsByTypeOid(dobjs, numObjs);
+ /* If we do a parallel dump, we want the largest tables to go first */
+ if (archiveFormat == archDirectory && numWorkers > 1)
+ sortDataAndIndexObjectsBySize(dobjs, numObjs);
+
sortDumpableObjects(dobjs, numObjs);
/*
***************
*** 786,791 **** help(const char *progname)
--- 806,812 ----
printf(_(" -f, --file=FILENAME output file or directory name\n"));
printf(_(" -F, --format=c|d|t|p output file format (custom, directory, tar,\n"
" plain text (default))\n"));
+ printf(_(" -j, --jobs=NUM use this many parallel jobs to dump\n"));
printf(_(" -v, --verbose verbose mode\n"));
printf(_(" -Z, --compress=0-9 compression level for compressed formats\n"));
printf(_(" --lock-wait-timeout=TIMEOUT fail after waiting TIMEOUT for a table lock\n"));
***************
*** 815,820 **** help(const char *progname)
--- 836,842 ----
printf(_(" --exclude-table-data=TABLE do NOT dump data for the named table(s)\n"));
printf(_(" --inserts dump data as INSERT commands, rather than COPY\n"));
printf(_(" --no-security-labels do not dump security label assignments\n"));
+ printf(_(" --no-synchronized-snapshots parallel processes should not use synchronized snapshots\n"));
printf(_(" --no-tablespaces do not dump tablespace assignments\n"));
printf(_(" --no-unlogged-table-data do not dump unlogged table data\n"));
printf(_(" --quote-all-identifiers quote all identifiers, even if not key words\n"));
***************
*** 843,849 **** setup_connection(Archive *AH, const char *dumpencoding, char *use_role)
PGconn *conn = GetConnection(AH);
const char *std_strings;
! /* Set the client encoding if requested */
if (dumpencoding)
{
if (PQsetClientEncoding(conn, dumpencoding) < 0)
--- 865,876 ----
PGconn *conn = GetConnection(AH);
const char *std_strings;
! /*
! * Set the client encoding if requested. If dumpencoding == NULL then
! * either it hasn't been requested or we're a cloned connection and then this
! * has already been set in CloneArchive according to the original
! * connection encoding.
! */
if (dumpencoding)
{
if (PQsetClientEncoding(conn, dumpencoding) < 0)
***************
*** 861,866 **** setup_connection(Archive *AH, const char *dumpencoding, char *use_role)
--- 888,897 ----
AH->std_strings = (std_strings && strcmp(std_strings, "on") == 0);
/* Set the role if requested */
+ if (!use_role && AH->use_role)
+ use_role = AH->use_role;
+
+ /* Set the role if requested */
if (use_role && AH->remoteVersion >= 80100)
{
PQExpBuffer query = createPQExpBuffer();
***************
*** 868,873 **** setup_connection(Archive *AH, const char *dumpencoding, char *use_role)
--- 899,908 ----
appendPQExpBuffer(query, "SET ROLE %s", fmtId(use_role));
ExecuteSqlStatement(AH, query->data);
destroyPQExpBuffer(query);
+
+ /* save this for later use on parallel connections */
+ if (!AH->use_role)
+ AH->use_role = strdup(use_role);
}
/* Set the datestyle to ISO to ensure the dump's portability */
***************
*** 904,909 **** setup_connection(Archive *AH, const char *dumpencoding, char *use_role)
--- 939,997 ----
*/
if (quote_all_identifiers && AH->remoteVersion >= 90100)
ExecuteSqlStatement(AH, "SET quote_all_identifiers = true");
+
+ /*
+ * Start transaction-snapshot mode transaction to dump consistent data.
+ */
+ ExecuteSqlStatement(AH, "BEGIN");
+ if (AH->remoteVersion >= 90100)
+ {
+ if (serializable_deferrable)
+ ExecuteSqlStatement(AH,
+ "SET TRANSACTION ISOLATION LEVEL SERIALIZABLE, "
+ "READ ONLY, DEFERRABLE");
+ else
+ ExecuteSqlStatement(AH,
+ "SET TRANSACTION ISOLATION LEVEL REPEATABLE READ");
+ }
+ else
+ ExecuteSqlStatement(AH, "SET TRANSACTION ISOLATION LEVEL SERIALIZABLE");
+
+ if (AH->numWorkers > 1 && AH->remoteVersion >= 90200 && !no_synchronized_snapshots)
+ {
+ if (AH->sync_snapshot_id)
+ {
+ PQExpBuffer query = createPQExpBuffer();
+ appendPQExpBuffer(query, "SET TRANSACTION SNAPSHOT ");
+ appendStringLiteralConn(query, AH->sync_snapshot_id, conn);
+ destroyPQExpBuffer(query);
+ }
+ else
+ AH->sync_snapshot_id = get_synchronized_snapshot(AH);
+ }
+ }
+
+ /*
+ * Initialize the connection for a new worker process.
+ */
+ void
+ _SetupWorker(Archive *AHX, RestoreOptions *ropt)
+ {
+ setup_connection(AHX, NULL, NULL);
+ }
+
+ static char*
+ get_synchronized_snapshot(Archive *fout)
+ {
+ const char *query = "select pg_export_snapshot()";
+ char *result;
+ PGresult *res;
+
+ res = ExecuteSqlQueryForSingleRow(fout, query);
+ result = strdup(PQgetvalue(res, 0, 0));
+ PQclear(res);
+
+ return result;
}
static ArchiveFormat
***************
*** 1220,1225 **** dumpTableData_copy(Archive *fout, void *dcontext)
--- 1308,1318 ----
const bool hasoids = tbinfo->hasoids;
const bool oids = tdinfo->oids;
PQExpBuffer q = createPQExpBuffer();
+ /*
+ * Note: can't use getThreadLocalPQExpBuffer() here, we're calling fmtId which
+ * uses it already.
+ */
+ PQExpBuffer clistBuf = createPQExpBuffer();
PGconn *conn = GetConnection(fout);
PGresult *res;
int ret;
***************
*** 1244,1257 **** dumpTableData_copy(Archive *fout, void *dcontext)
* cases involving ADD COLUMN and inheritance.)
*/
if (fout->remoteVersion >= 70300)
! column_list = fmtCopyColumnList(tbinfo);
else
column_list = ""; /* can't select columns in COPY */
if (oids && hasoids)
{
appendPQExpBuffer(q, "COPY %s %s WITH OIDS TO stdout;",
! fmtQualifiedId(fout,
tbinfo->dobj.namespace->dobj.name,
classname),
column_list);
--- 1337,1350 ----
* cases involving ADD COLUMN and inheritance.)
*/
if (fout->remoteVersion >= 70300)
! column_list = fmtCopyColumnList(tbinfo, clistBuf);
else
column_list = ""; /* can't select columns in COPY */
if (oids && hasoids)
{
appendPQExpBuffer(q, "COPY %s %s WITH OIDS TO stdout;",
! fmtQualifiedId(fout->remoteVersion,
tbinfo->dobj.namespace->dobj.name,
classname),
column_list);
***************
*** 1269,1275 **** dumpTableData_copy(Archive *fout, void *dcontext)
else
appendPQExpBufferStr(q, "* ");
appendPQExpBuffer(q, "FROM %s %s) TO stdout;",
! fmtQualifiedId(fout,
tbinfo->dobj.namespace->dobj.name,
classname),
tdinfo->filtercond);
--- 1362,1368 ----
else
appendPQExpBufferStr(q, "* ");
appendPQExpBuffer(q, "FROM %s %s) TO stdout;",
! fmtQualifiedId(fout->remoteVersion,
tbinfo->dobj.namespace->dobj.name,
classname),
tdinfo->filtercond);
***************
*** 1277,1289 **** dumpTableData_copy(Archive *fout, void *dcontext)
else
{
appendPQExpBuffer(q, "COPY %s %s TO stdout;",
! fmtQualifiedId(fout,
tbinfo->dobj.namespace->dobj.name,
classname),
column_list);
}
res = ExecuteSqlQuery(fout, q->data, PGRES_COPY_OUT);
PQclear(res);
for (;;)
{
--- 1370,1383 ----
else
{
appendPQExpBuffer(q, "COPY %s %s TO stdout;",
! fmtQualifiedId(fout->remoteVersion,
tbinfo->dobj.namespace->dobj.name,
classname),
column_list);
}
res = ExecuteSqlQuery(fout, q->data, PGRES_COPY_OUT);
PQclear(res);
+ destroyPQExpBuffer(clistBuf);
for (;;)
{
***************
*** 1402,1408 **** dumpTableData_insert(Archive *fout, void *dcontext)
{
appendPQExpBuffer(q, "DECLARE _pg_dump_cursor CURSOR FOR "
"SELECT * FROM ONLY %s",
! fmtQualifiedId(fout,
tbinfo->dobj.namespace->dobj.name,
classname));
}
--- 1496,1502 ----
{
appendPQExpBuffer(q, "DECLARE _pg_dump_cursor CURSOR FOR "
"SELECT * FROM ONLY %s",
! fmtQualifiedId(fout->remoteVersion,
tbinfo->dobj.namespace->dobj.name,
classname));
}
***************
*** 1410,1416 **** dumpTableData_insert(Archive *fout, void *dcontext)
{
appendPQExpBuffer(q, "DECLARE _pg_dump_cursor CURSOR FOR "
"SELECT * FROM %s",
! fmtQualifiedId(fout,
tbinfo->dobj.namespace->dobj.name,
classname));
}
--- 1504,1510 ----
{
appendPQExpBuffer(q, "DECLARE _pg_dump_cursor CURSOR FOR "
"SELECT * FROM %s",
! fmtQualifiedId(fout->remoteVersion,
tbinfo->dobj.namespace->dobj.name,
classname));
}
***************
*** 1542,1547 **** dumpTableData(Archive *fout, TableDataInfo *tdinfo)
--- 1636,1642 ----
{
TableInfo *tbinfo = tdinfo->tdtable;
PQExpBuffer copyBuf = createPQExpBuffer();
+ PQExpBuffer clistBuf = createPQExpBuffer();
DataDumperPtr dumpFn;
char *copyStmt;
***************
*** 1553,1559 **** dumpTableData(Archive *fout, TableDataInfo *tdinfo)
appendPQExpBuffer(copyBuf, "COPY %s ",
fmtId(tbinfo->dobj.name));
appendPQExpBuffer(copyBuf, "%s %sFROM stdin;\n",
! fmtCopyColumnList(tbinfo),
(tdinfo->oids && tbinfo->hasoids) ? "WITH OIDS " : "");
copyStmt = copyBuf->data;
}
--- 1648,1654 ----
appendPQExpBuffer(copyBuf, "COPY %s ",
fmtId(tbinfo->dobj.name));
appendPQExpBuffer(copyBuf, "%s %sFROM stdin;\n",
! fmtCopyColumnList(tbinfo, clistBuf),
(tdinfo->oids && tbinfo->hasoids) ? "WITH OIDS " : "");
copyStmt = copyBuf->data;
}
***************
*** 1573,1578 **** dumpTableData(Archive *fout, TableDataInfo *tdinfo)
--- 1668,1674 ----
dumpFn, tdinfo);
destroyPQExpBuffer(copyBuf);
+ destroyPQExpBuffer(clistBuf);
}
/*
***************
*** 3842,3847 **** getTables(Archive *fout, int *numTables)
--- 3938,3944 ----
int i_reloptions;
int i_toastreloptions;
int i_reloftype;
+ int i_relpages;
/* Make sure we are in proper schema */
selectSourceSchema(fout, "pg_catalog");
***************
*** 3881,3886 **** getTables(Archive *fout, int *numTables)
--- 3978,3984 ----
"c.relfrozenxid, tc.oid AS toid, "
"tc.relfrozenxid AS tfrozenxid, "
"c.relpersistence, "
+ "c.relpages, "
"CASE WHEN c.reloftype <> 0 THEN c.reloftype::pg_catalog.regtype ELSE NULL END AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 3917,3922 **** getTables(Archive *fout, int *numTables)
--- 4015,4021 ----
"c.relfrozenxid, tc.oid AS toid, "
"tc.relfrozenxid AS tfrozenxid, "
"'p' AS relpersistence, "
+ "c.relpages, "
"CASE WHEN c.reloftype <> 0 THEN c.reloftype::pg_catalog.regtype ELSE NULL END AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 3952,3957 **** getTables(Archive *fout, int *numTables)
--- 4051,4057 ----
"c.relfrozenxid, tc.oid AS toid, "
"tc.relfrozenxid AS tfrozenxid, "
"'p' AS relpersistence, "
+ "c.relpages, "
"NULL AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 3987,3992 **** getTables(Archive *fout, int *numTables)
--- 4087,4093 ----
"c.relfrozenxid, tc.oid AS toid, "
"tc.relfrozenxid AS tfrozenxid, "
"'p' AS relpersistence, "
+ "c.relpages, "
"NULL AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 4023,4028 **** getTables(Archive *fout, int *numTables)
--- 4124,4130 ----
"0 AS toid, "
"0 AS tfrozenxid, "
"'p' AS relpersistence, "
+ "relpages, "
"NULL AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 4058,4063 **** getTables(Archive *fout, int *numTables)
--- 4160,4166 ----
"0 AS toid, "
"0 AS tfrozenxid, "
"'p' AS relpersistence, "
+ "relpages, "
"NULL AS reloftype, "
"d.refobjid AS owning_tab, "
"d.refobjsubid AS owning_col, "
***************
*** 4089,4094 **** getTables(Archive *fout, int *numTables)
--- 4192,4198 ----
"0 AS toid, "
"0 AS tfrozenxid, "
"'p' AS relpersistence, "
+ "relpages, "
"NULL AS reloftype, "
"NULL::oid AS owning_tab, "
"NULL::int4 AS owning_col, "
***************
*** 4115,4120 **** getTables(Archive *fout, int *numTables)
--- 4219,4225 ----
"0 AS toid, "
"0 AS tfrozenxid, "
"'p' AS relpersistence, "
+ "relpages, "
"NULL AS reloftype, "
"NULL::oid AS owning_tab, "
"NULL::int4 AS owning_col, "
***************
*** 4151,4156 **** getTables(Archive *fout, int *numTables)
--- 4256,4262 ----
"0 AS toid, "
"0 AS tfrozenxid, "
"'p' AS relpersistence, "
+ "0 AS relpages, "
"NULL AS reloftype, "
"NULL::oid AS owning_tab, "
"NULL::int4 AS owning_col, "
***************
*** 4204,4209 **** getTables(Archive *fout, int *numTables)
--- 4310,4316 ----
i_reloptions = PQfnumber(res, "reloptions");
i_toastreloptions = PQfnumber(res, "toast_reloptions");
i_reloftype = PQfnumber(res, "reloftype");
+ i_relpages = PQfnumber(res, "relpages");
if (lockWaitTimeout && fout->remoteVersion >= 70300)
{
***************
*** 4260,4265 **** getTables(Archive *fout, int *numTables)
--- 4367,4373 ----
tblinfo[i].reltablespace = pg_strdup(PQgetvalue(res, i, i_reltablespace));
tblinfo[i].reloptions = pg_strdup(PQgetvalue(res, i, i_reloptions));
tblinfo[i].toast_reloptions = pg_strdup(PQgetvalue(res, i, i_toastreloptions));
+ tblinfo[i].relpages = atoi(PQgetvalue(res, i, i_relpages));
/* other fields were zeroed above */
***************
*** 4288,4294 **** getTables(Archive *fout, int *numTables)
resetPQExpBuffer(query);
appendPQExpBuffer(query,
"LOCK TABLE %s IN ACCESS SHARE MODE",
! fmtQualifiedId(fout,
tblinfo[i].dobj.namespace->dobj.name,
tblinfo[i].dobj.name));
ExecuteSqlStatement(fout, query->data);
--- 4396,4402 ----
resetPQExpBuffer(query);
appendPQExpBuffer(query,
"LOCK TABLE %s IN ACCESS SHARE MODE",
! fmtQualifiedId(fout->remoteVersion,
tblinfo[i].dobj.namespace->dobj.name,
tblinfo[i].dobj.name));
ExecuteSqlStatement(fout, query->data);
***************
*** 4422,4428 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
i_conoid,
i_condef,
i_tablespace,
! i_options;
int ntups;
for (i = 0; i < numTables; i++)
--- 4530,4537 ----
i_conoid,
i_condef,
i_tablespace,
! i_options,
! i_relpages;
int ntups;
for (i = 0; i < numTables; i++)
***************
*** 4464,4469 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4573,4579 ----
"pg_catalog.pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, i.indisclustered, "
+ "t.relpages, "
"c.contype, c.conname, "
"c.condeferrable, c.condeferred, "
"c.tableoid AS contableoid, "
***************
*** 4489,4494 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4599,4605 ----
"pg_catalog.pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, i.indisclustered, "
+ "t.relpages, "
"c.contype, c.conname, "
"c.condeferrable, c.condeferred, "
"c.tableoid AS contableoid, "
***************
*** 4517,4522 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4628,4634 ----
"pg_catalog.pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, i.indisclustered, "
+ "t.relpages, "
"c.contype, c.conname, "
"c.condeferrable, c.condeferred, "
"c.tableoid AS contableoid, "
***************
*** 4545,4550 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4657,4663 ----
"pg_catalog.pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, i.indisclustered, "
+ "t.relpages, "
"c.contype, c.conname, "
"c.condeferrable, c.condeferred, "
"c.tableoid AS contableoid, "
***************
*** 4573,4578 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4686,4692 ----
"pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, false AS indisclustered, "
+ "t.relpages, "
"CASE WHEN i.indisprimary THEN 'p'::char "
"ELSE '0'::char END AS contype, "
"t.relname AS conname, "
***************
*** 4599,4604 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4713,4719 ----
"pg_get_indexdef(i.indexrelid) AS indexdef, "
"t.relnatts AS indnkeys, "
"i.indkey, false AS indisclustered, "
+ "t.relpages, "
"CASE WHEN i.indisprimary THEN 'p'::char "
"ELSE '0'::char END AS contype, "
"t.relname AS conname, "
***************
*** 4627,4632 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4742,4748 ----
i_indnkeys = PQfnumber(res, "indnkeys");
i_indkey = PQfnumber(res, "indkey");
i_indisclustered = PQfnumber(res, "indisclustered");
+ i_relpages = PQfnumber(res, "relpages");
i_contype = PQfnumber(res, "contype");
i_conname = PQfnumber(res, "conname");
i_condeferrable = PQfnumber(res, "condeferrable");
***************
*** 4669,4674 **** getIndexes(Archive *fout, TableInfo tblinfo[], int numTables)
--- 4785,4791 ----
parseOidArray(PQgetvalue(res, j, i_indkey),
indxinfo[j].indkeys, INDEX_MAX_KEYS);
indxinfo[j].indisclustered = (PQgetvalue(res, j, i_indisclustered)[0] == 't');
+ indxinfo[j].relpages = atoi(PQgetvalue(res, j, i_relpages));
contype = *(PQgetvalue(res, j, i_contype));
if (contype == 'p' || contype == 'u' || contype == 'x')
***************
*** 14070,14091 **** getDependencies(Archive *fout)
*
* Whenever the selected schema is not pg_catalog, be careful to qualify
* references to system catalogs and types in our emitted commands!
*/
static void
selectSourceSchema(Archive *fout, const char *schemaName)
{
- static char *curSchemaName = NULL;
PQExpBuffer query;
/* Not relevant if fetching from pre-7.3 DB */
if (fout->remoteVersion < 70300)
return;
- /* Ignore null schema names */
- if (schemaName == NULL || *schemaName == '\0')
- return;
- /* Optimize away repeated selection of same schema */
- if (curSchemaName && strcmp(curSchemaName, schemaName) == 0)
- return;
query = createPQExpBuffer();
appendPQExpBuffer(query, "SET search_path = %s",
--- 14187,14207 ----
*
* Whenever the selected schema is not pg_catalog, be careful to qualify
* references to system catalogs and types in our emitted commands!
+ *
+ * This function is called only from selectSourceSchemaOnAH and
+ * selectSourceSchema.
*/
static void
selectSourceSchema(Archive *fout, const char *schemaName)
{
PQExpBuffer query;
+ /* This is checked by the callers already */
+ Assert(schemaName != NULL && *schemaName != '\0');
+
/* Not relevant if fetching from pre-7.3 DB */
if (fout->remoteVersion < 70300)
return;
query = createPQExpBuffer();
appendPQExpBuffer(query, "SET search_path = %s",
***************
*** 14096,14104 **** selectSourceSchema(Archive *fout, const char *schemaName)
ExecuteSqlStatement(fout, query->data);
destroyPQExpBuffer(query);
- if (curSchemaName)
- free(curSchemaName);
- curSchemaName = pg_strdup(schemaName);
}
/*
--- 14212,14217 ----
***************
*** 14236,14313 **** myFormatType(const char *typname, int32 typmod)
}
/*
- * fmtQualifiedId - convert a qualified name to the proper format for
- * the source database.
- *
- * Like fmtId, use the result before calling again.
- */
- static const char *
- fmtQualifiedId(Archive *fout, const char *schema, const char *id)
- {
- static PQExpBuffer id_return = NULL;
-
- if (id_return) /* first time through? */
- resetPQExpBuffer(id_return);
- else
- id_return = createPQExpBuffer();
-
- /* Suppress schema name if fetching from pre-7.3 DB */
- if (fout->remoteVersion >= 70300 && schema && *schema)
- {
- appendPQExpBuffer(id_return, "%s.",
- fmtId(schema));
- }
- appendPQExpBuffer(id_return, "%s",
- fmtId(id));
-
- return id_return->data;
- }
-
- /*
* Return a column list clause for the given relation.
*
* Special case: if there are no undropped columns in the relation, return
* "", not an invalid "()" column list.
*/
static const char *
! fmtCopyColumnList(const TableInfo *ti)
{
- static PQExpBuffer q = NULL;
int numatts = ti->numatts;
char **attnames = ti->attnames;
bool *attisdropped = ti->attisdropped;
bool needComma;
int i;
! if (q) /* first time through? */
! resetPQExpBuffer(q);
! else
! q = createPQExpBuffer();
!
! appendPQExpBuffer(q, "(");
needComma = false;
for (i = 0; i < numatts; i++)
{
if (attisdropped[i])
continue;
if (needComma)
! appendPQExpBuffer(q, ", ");
! appendPQExpBuffer(q, "%s", fmtId(attnames[i]));
needComma = true;
}
if (!needComma)
return ""; /* no undropped columns */
! appendPQExpBuffer(q, ")");
! return q->data;
}
/*
* Execute an SQL query and verify that we got exactly one row back.
*/
static PGresult *
! ExecuteSqlQueryForSingleRow(Archive *fout, char *query)
{
PGresult *res;
int ntups;
--- 14349,14392 ----
}
/*
* Return a column list clause for the given relation.
*
* Special case: if there are no undropped columns in the relation, return
* "", not an invalid "()" column list.
*/
static const char *
! fmtCopyColumnList(const TableInfo *ti, PQExpBuffer buffer)
{
int numatts = ti->numatts;
char **attnames = ti->attnames;
bool *attisdropped = ti->attisdropped;
bool needComma;
int i;
! appendPQExpBuffer(buffer, "(");
needComma = false;
for (i = 0; i < numatts; i++)
{
if (attisdropped[i])
continue;
if (needComma)
! appendPQExpBuffer(buffer, ", ");
! appendPQExpBuffer(buffer, "%s", fmtId(attnames[i]));
needComma = true;
}
if (!needComma)
return ""; /* no undropped columns */
! appendPQExpBuffer(buffer, ")");
! return buffer->data;
}
/*
* Execute an SQL query and verify that we got exactly one row back.
*/
static PGresult *
! ExecuteSqlQueryForSingleRow(Archive *fout, const char *query)
{
PGresult *res;
int ntups;
*** a/src/bin/pg_dump/pg_dump.h
--- b/src/bin/pg_dump/pg_dump.h
***************
*** 256,261 **** typedef struct _tableInfo
--- 256,262 ----
/* these two are set only if table is a sequence owned by a column: */
Oid owning_tab; /* OID of table owning sequence */
int owning_col; /* attr # of column owning sequence */
+ int relpages;
bool interesting; /* true if need to collect more data */
***************
*** 319,324 **** typedef struct _indxInfo
--- 320,326 ----
bool indisclustered;
/* if there is an associated constraint object, its dumpId: */
DumpId indexconstraint;
+ int relpages; /* relpages of the underlying table */
} IndxInfo;
typedef struct _ruleInfo
***************
*** 523,528 **** extern void parseOidArray(const char *str, Oid *array, int arraysize);
--- 525,531 ----
extern void sortDumpableObjects(DumpableObject **objs, int numObjs);
extern void sortDumpableObjectsByTypeName(DumpableObject **objs, int numObjs);
extern void sortDumpableObjectsByTypeOid(DumpableObject **objs, int numObjs);
+ extern void sortDataAndIndexObjectsBySize(DumpableObject **objs, int numObjs);
/*
* version specific routines
*** a/src/bin/pg_dump/pg_dump_sort.c
--- b/src/bin/pg_dump/pg_dump_sort.c
***************
*** 121,126 **** static void repairDependencyLoop(DumpableObject **loop,
--- 121,213 ----
static void describeDumpableObject(DumpableObject *obj,
char *buf, int bufsize);
+ static int DOSizeCompare(const void *p1, const void *p2);
+
+ static int
+ findFirstEqualType(DumpableObjectType type, DumpableObject **objs, int numObjs)
+ {
+ int i;
+ for (i = 0; i < numObjs; i++)
+ if (objs[i]->objType == type)
+ return i;
+ return -1;
+ }
+
+ static int
+ findFirstDifferentType(DumpableObjectType type, DumpableObject **objs, int numObjs, int start)
+ {
+ int i;
+ for (i = start; i < numObjs; i++)
+ if (objs[i]->objType != type)
+ return i;
+ return numObjs - 1;
+ }
+
+ /*
+ * When we do a parallel dump, we want to start with the largest items first.
+ *
+ * Say we have the objects in this order:
+ * ....DDDDD....III....
+ *
+ * with D = Table data, I = Index, . = other object
+ *
+ * This sorting function now takes each of the D or I blocks and sorts them
+ * according to their size.
+ */
+ void
+ sortDataAndIndexObjectsBySize(DumpableObject **objs, int numObjs)
+ {
+ int startIdx, endIdx;
+ void *startPtr;
+
+ if (numObjs <= 1)
+ return;
+
+ startIdx = findFirstEqualType(DO_TABLE_DATA, objs, numObjs);
+ if (startIdx >= 0)
+ {
+ endIdx = findFirstDifferentType(DO_TABLE_DATA, objs, numObjs, startIdx);
+ startPtr = objs + startIdx;
+ qsort(startPtr, endIdx - startIdx, sizeof(DumpableObject *),
+ DOSizeCompare);
+ }
+
+ startIdx = findFirstEqualType(DO_INDEX, objs, numObjs);
+ if (startIdx >= 0)
+ {
+ endIdx = findFirstDifferentType(DO_INDEX, objs, numObjs, startIdx);
+ startPtr = objs + startIdx;
+ qsort(startPtr, endIdx - startIdx, sizeof(DumpableObject *),
+ DOSizeCompare);
+ }
+ }
+
+ static int
+ DOSizeCompare(const void *p1, const void *p2)
+ {
+ DumpableObject *obj1 = *(DumpableObject **) p1;
+ DumpableObject *obj2 = *(DumpableObject **) p2;
+ int obj1_size = 0;
+ int obj2_size = 0;
+
+ if (obj1->objType == DO_TABLE_DATA)
+ obj1_size = ((TableDataInfo *) obj1)->tdtable->relpages;
+ if (obj1->objType == DO_INDEX)
+ obj1_size = ((IndxInfo *) obj1)->relpages;
+
+ if (obj2->objType == DO_TABLE_DATA)
+ obj2_size = ((TableDataInfo *) obj2)->tdtable->relpages;
+ if (obj2->objType == DO_INDEX)
+ obj2_size = ((IndxInfo *) obj2)->relpages;
+
+ /* we want to see the biggest item go first */
+ if (obj1_size > obj2_size)
+ return -1;
+ if (obj2_size > obj1_size)
+ return 1;
+
+ return 0;
+ }
/*
* Sort the given objects into a type/name-based ordering
*** a/src/bin/pg_dump/pg_dumpall.c
--- b/src/bin/pg_dump/pg_dumpall.c
***************
*** 1918,1920 **** doShellQuoting(PQExpBuffer buf, const char *str)
--- 1918,1923 ----
appendPQExpBufferChar(buf, '"');
#endif /* WIN32 */
}
+
+ /* dummy, no parallel dump/restore for pg_dumpall yet */
+ void _SetupWorker(Archive *AHX, RestoreOptions *ropt) {}
*** a/src/bin/pg_dump/pg_restore.c
--- b/src/bin/pg_dump/pg_restore.c
***************
*** 72,77 **** main(int argc, char **argv)
--- 72,78 ----
RestoreOptions *opts;
int c;
int exit_code;
+ int numWorkers = 1;
Archive *AH;
char *inputFileSpec;
static int disable_triggers = 0;
***************
*** 183,189 **** main(int argc, char **argv)
break;
case 'j': /* number of restore jobs */
! opts->number_of_jobs = atoi(optarg);
break;
case 'l': /* Dump the TOC summary */
--- 184,190 ----
break;
case 'j': /* number of restore jobs */
! numWorkers = atoi(optarg);
break;
case 'l': /* Dump the TOC summary */
***************
*** 338,344 **** main(int argc, char **argv)
}
/* Can't do single-txn mode with multiple connections */
! if (opts->single_txn && opts->number_of_jobs > 1)
{
fprintf(stderr, _("%s: cannot specify both --single-transaction and multiple jobs\n"),
progname);
--- 339,345 ----
}
/* Can't do single-txn mode with multiple connections */
! if (opts->single_txn && numWorkers > 1)
{
fprintf(stderr, _("%s: cannot specify both --single-transaction and multiple jobs\n"),
progname);
***************
*** 405,410 **** main(int argc, char **argv)
--- 406,422 ----
InitDummyWantedList(AH, opts);
}
+ /* See comments in pg_dump.c */
+ #ifdef WIN32
+ if (numWorkers > MAXIMUM_WAIT_OBJECTS)
+ {
+ fprintf(stderr, _("%s: invalid number of parallel jobs\n"), progname);
+ exit(1);
+ }
+ #endif
+
+ AH->numWorkers = numWorkers;
+
if (opts->tocSummary)
PrintTOCSummary(AH, opts);
else
***************
*** 423,428 **** main(int argc, char **argv)
--- 435,447 ----
return exit_code;
}
+ void
+ _SetupWorker(Archive *AHX, RestoreOptions *ropt)
+ {
+ ArchiveHandle *AH = (ArchiveHandle *) AHX;
+ (AH->ReopenPtr) (AH);
+ }
+
static void
usage(const char *progname)
{
*** a/src/tools/msvc/Mkvcbuild.pm
--- b/src/tools/msvc/Mkvcbuild.pm
***************
*** 344,349 **** sub mkvcbuild
--- 344,351 ----
$pgdump->AddFile('src\bin\pg_dump\pg_dump_sort.c');
$pgdump->AddFile('src\bin\pg_dump\keywords.c');
$pgdump->AddFile('src\backend\parser\kwlookup.c');
+ $pgdump->AddLibrary('wsock32.lib');
+ $pgdump->AddLibrary('ws2_32.lib');
my $pgdumpall = AddSimpleFrontend('pg_dump', 1);
***************
*** 368,373 **** sub mkvcbuild
--- 370,377 ----
$pgrestore->AddFile('src\bin\pg_dump\pg_restore.c');
$pgrestore->AddFile('src\bin\pg_dump\keywords.c');
$pgrestore->AddFile('src\backend\parser\kwlookup.c');
+ $pgrestore->AddLibrary('wsock32.lib');
+ $pgrestore->AddLibrary('ws2_32.lib');
my $zic = $solution->AddProject('zic','exe','utils');
$zic->AddFiles('src\timezone','zic.c','ialloc.c','scheck.c','localtime.c');