*
*
* IDENTIFICATION
- * $PostgreSQL: pgsql/src/bin/pg_dump/pg_backup_archiver.c,v 1.140 2007/01/25 03:30:43 momjian Exp $
+ * src/bin/pg_dump/pg_backup_archiver.c
*
*-------------------------------------------------------------------------
*/
#include "dumputils.h"
#include <ctype.h>
-
#include <unistd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
#ifdef WIN32
#include <io.h>
#endif
#include "libpq/libpq-fs.h"
-#include "mb/pg_wchar.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
+
+/* Arguments needed for a worker child */
+typedef struct _restore_args
+{
+ ArchiveHandle *AH;
+ TocEntry *te;
+} RestoreArgs;
+
+/* State for each parallel activity slot */
+typedef struct _parallel_slot
+{
+ thandle child_id;
+ RestoreArgs *args;
+} ParallelSlot;
+
+#define NO_SLOT (-1)
const char *progname;
-static char *modulename = gettext_noop("archiver");
+static const char *modulename = gettext_noop("archiver");
+
+/* index array created by fix_dependencies -- only used in parallel restore */
+static TocEntry **tocsByDumpId; /* index by dumpId - 1 */
+static DumpId maxDumpId; /* length of above array */
static ArchiveHandle *_allocAH(const char *FileSpec, const ArchiveFormat fmt,
static void processEncodingEntry(ArchiveHandle *AH, TocEntry *te);
static void processStdStringsEntry(ArchiveHandle *AH, TocEntry *te);
static teReqs _tocEntryRequired(TocEntry *te, RestoreOptions *ropt, bool include_acls);
+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 _moveAfter(ArchiveHandle *AH, TocEntry *pos, TocEntry *te);
+static void _moveBefore(ArchiveHandle *AH, TocEntry *pos, TocEntry *te);
static int _discoverArchiveFormat(ArchiveHandle *AH);
static void dump_lo_buf(ArchiveHandle *AH);
static OutputContext SetOutput(ArchiveHandle *AH, char *filename, int compression);
static void ResetOutput(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,
+ DumpId tableId, DumpId tableDataId);
+static void identify_locking_dependencies(TocEntry *te);
+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);
+
/*
* Wrapper functions.
TocEntry *te;
teReqs reqs;
OutputContext sav;
- bool defnDumped;
AH->ropt = ropt;
AH->stage = STAGE_INITIALIZING;
/*
* Check for nonsensical option combinations.
*
- * NB: create+dropSchema is useless because if you're creating the DB,
+ * NB: createDB+dropSchema is useless because if you're creating the DB,
* there's no need to drop individual items in it. Moreover, if we tried
* to do that then we'd issue the drops in the database initially
* connected to, not the one we will create, which is very bad...
*/
- if (ropt->create && ropt->dropSchema)
+ if (ropt->createDB && ropt->dropSchema)
die_horribly(AH, modulename, "-C and -c are incompatible options\n");
+ /*
+ * -C is not compatible with -1, because we can't create a database inside
+ * a transaction block.
+ */
+ if (ropt->createDB && ropt->single_txn)
+ die_horribly(AH, modulename, "-C and -1 are incompatible options\n");
+
+ /*
+ * Make sure we won't need (de)compression we haven't got
+ */
+#ifndef HAVE_LIBZ
+ if (AH->compression != 0 && AH->PrintTocDataPtr !=NULL)
+ {
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ reqs = _tocEntryRequired(te, ropt, false);
+ if (te->hadDumper && (reqs & REQ_DATA) != 0)
+ die_horribly(AH, modulename, "cannot restore from compressed archive (compression not supported in this installation)\n");
+ }
+ }
+#endif
+
/*
* If we're using a DB connection, then connect it.
*/
ConnectDatabase(AHX, ropt->dbname,
ropt->pghost, ropt->pgport, ropt->username,
- ropt->requirePassword, ropt->ignoreVersion);
+ ropt->promptPassword);
/*
* If we're talking to the DB directly, don't send comments since they
/*
* Setup the output file if necessary.
- */
+ */
if (ropt->filename || ropt->compression)
sav = SetOutput(AH, ropt->filename, ropt->compression);
ahprintf(AH, "--\n-- PostgreSQL database dump\n--\n\n");
if (AH->public.verbose)
+ {
+ if (AH->archiveRemoteVersion)
+ ahprintf(AH, "-- Dumped from database version %s\n",
+ AH->archiveRemoteVersion);
+ if (AH->archiveDumpVersion)
+ ahprintf(AH, "-- Dumped by pg_dump version %s\n",
+ AH->archiveDumpVersion);
dumpTimestamp(AH, "Started on", AH->createDate);
+ }
if (ropt->single_txn)
{
AH->currentTE = te;
reqs = _tocEntryRequired(te, ropt, false /* needn't drop ACLs */ );
- if (((reqs & REQ_SCHEMA) != 0) && te->dropStmt)
+ /* We want anything that's selected and has a dropStmt */
+ if (((reqs & (REQ_SCHEMA | REQ_DATA)) != 0) && te->dropStmt)
{
- /* We want the schema */
ahlog(AH, 1, "dropping %s %s\n", te->desc, te->tag);
/* Select owner and schema as necessary */
_becomeOwner(AH, te);
ahprintf(AH, "%s", te->dropStmt);
}
}
+
+ /*
+ * _selectOutputSchema may have set currSchema to reflect the effect
+ * of a "SET search_path" command it emitted. However, by now we may
+ * have dropped that schema; or it might not have existed in the first
+ * place. In either case the effective value of search_path will not
+ * be what we think. Forcibly reset currSchema so that we will
+ * re-establish the search_path setting when needed (after creating
+ * the schema).
+ *
+ * If we treated users as pg_dump'able objects then we'd need to reset
+ * currUser here too.
+ */
+ if (AH->currSchema)
+ free(AH->currSchema);
+ AH->currSchema = NULL;
}
/*
- * Now process each non-ACL TOC entry
+ * In serial mode, we now process each non-ACL TOC entry.
+ *
+ * In parallel mode, turn control over to the parallel-restore logic.
*/
- for (te = AH->toc->next; te != AH->toc; te = te->next)
+ if (ropt->number_of_jobs > 1 && ropt->useDB)
+ restore_toc_entries_parallel(AH);
+ else
{
- AH->currentTE = te;
-
- /* Work out what, if anything, we want from this entry */
- reqs = _tocEntryRequired(te, ropt, false);
-
- /* Dump any relevant dump warnings to stderr */
- if (!ropt->suppressDumpWarnings && strcmp(te->desc, "WARNING") == 0)
- {
- if (!ropt->dataOnly && te->defn != NULL && strlen(te->defn) != 0)
- write_msg(modulename, "warning from original dump file: %s\n", te->defn);
- else if (te->copyStmt != NULL && strlen(te->copyStmt) != 0)
- write_msg(modulename, "warning from original dump file: %s\n", te->copyStmt);
- }
-
- defnDumped = false;
-
- if ((reqs & REQ_SCHEMA) != 0) /* We want the schema */
- {
- ahlog(AH, 1, "creating %s %s\n", te->desc, te->tag);
-
- _printTocEntry(AH, te, ropt, false, false);
- defnDumped = true;
-
- /*
- * If we could not create a table and --no-data-for-failed-tables
- * was given, ignore the corresponding TABLE DATA
- */
- if (ropt->noDataForFailedTables &&
- AH->lastErrorTE == te &&
- strcmp(te->desc, "TABLE") == 0)
- {
- TocEntry *tes;
-
- ahlog(AH, 1, "table \"%s\" could not be created, will not restore its data\n",
- te->tag);
-
- for (tes = te->next; tes != AH->toc; tes = tes->next)
- {
- if (strcmp(tes->desc, "TABLE DATA") == 0 &&
- strcmp(tes->tag, te->tag) == 0 &&
- strcmp(tes->namespace ? tes->namespace : "",
- te->namespace ? te->namespace : "") == 0)
- {
- /* mark it unwanted */
- ropt->idWanted[tes->dumpId - 1] = false;
- break;
- }
- }
- }
-
- /* If we created a DB, connect to it... */
- if (strcmp(te->desc, "DATABASE") == 0)
- {
- ahlog(AH, 1, "connecting to new database \"%s\"\n", te->tag);
- _reconnectToDB(AH, te->tag);
- }
- }
-
- /*
- * If we have a data component, then process it
- */
- if ((reqs & REQ_DATA) != 0)
- {
- /*
- * hadDumper will be set if there is genuine data component for
- * this node. Otherwise, we need to check the defn field for
- * statements that need to be executed in data-only restores.
- */
- if (te->hadDumper)
- {
- /*
- * If we can output the data, then restore it.
- */
- if (AH->PrintTocDataPtr !=NULL && (reqs & REQ_DATA) != 0)
- {
-#ifndef HAVE_LIBZ
- if (AH->compression != 0)
- die_horribly(AH, modulename, "cannot restore from compressed archive (compression not supported in this installation)\n");
-#endif
-
- _printTocEntry(AH, te, ropt, true, false);
-
- if (strcmp(te->desc, "BLOBS") == 0 ||
- strcmp(te->desc, "BLOB COMMENTS") == 0)
- {
- ahlog(AH, 1, "restoring %s\n", te->desc);
-
- _selectOutputSchema(AH, "pg_catalog");
-
- (*AH->PrintTocDataPtr) (AH, te, ropt);
- }
- else
- {
- _disableTriggersIfNecessary(AH, te, ropt);
-
- /* Select owner and schema as necessary */
- _becomeOwner(AH, te);
- _selectOutputSchema(AH, te->namespace);
-
- ahlog(AH, 1, "restoring data for table \"%s\"\n",
- te->tag);
-
- /*
- * If we have a copy statement, use it. As of V1.3,
- * these are separate to allow easy import from
- * withing a database connection. Pre 1.3 archives can
- * not use DB connections and are sent to output only.
- *
- * For V1.3+, the table data MUST have a copy
- * statement so that we can go into appropriate mode
- * with libpq.
- */
- if (te->copyStmt && strlen(te->copyStmt) > 0)
- {
- ahprintf(AH, "%s", te->copyStmt);
- AH->writingCopyData = true;
- }
-
- (*AH->PrintTocDataPtr) (AH, te, ropt);
-
- AH->writingCopyData = false;
-
- _enableTriggersIfNecessary(AH, te, ropt);
- }
- }
- }
- else if (!defnDumped)
- {
- /* If we haven't already dumped the defn part, do so now */
- ahlog(AH, 1, "executing %s %s\n", te->desc, te->tag);
- _printTocEntry(AH, te, ropt, false, false);
- }
- }
- } /* end loop over TOC entries */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ (void) restore_toc_entry(AH, te, ropt, false);
+ }
/*
* Scan TOC again to output ownership commands and ACLs
/* Work out what, if anything, we want from this entry */
reqs = _tocEntryRequired(te, ropt, true);
- if ((reqs & REQ_SCHEMA) != 0) /* We want the schema */
+ /* Both schema and data objects might now have ownership/ACLs */
+ if ((reqs & (REQ_SCHEMA | REQ_DATA)) != 0)
{
ahlog(AH, 1, "setting owner and privileges for %s %s\n",
te->desc, te->tag);
}
}
+/*
+ * Restore a single TOC item. Used in both parallel and non-parallel restore;
+ * is_parallel is true if we are in a worker child process.
+ *
+ * Returns 0 normally, but WORKER_CREATE_DONE or WORKER_INHIBIT_DATA if
+ * the parallel parent has to make the corresponding status update.
+ */
+static int
+restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
+ RestoreOptions *ropt, bool is_parallel)
+{
+ int retval = 0;
+ teReqs reqs;
+ bool defnDumped;
+
+ AH->currentTE = te;
+
+ /* Work out what, if anything, we want from this entry */
+ reqs = _tocEntryRequired(te, ropt, false);
+
+ /* Dump any relevant dump warnings to stderr */
+ if (!ropt->suppressDumpWarnings && strcmp(te->desc, "WARNING") == 0)
+ {
+ if (!ropt->dataOnly && te->defn != NULL && strlen(te->defn) != 0)
+ write_msg(modulename, "warning from original dump file: %s\n", te->defn);
+ else if (te->copyStmt != NULL && strlen(te->copyStmt) != 0)
+ write_msg(modulename, "warning from original dump file: %s\n", te->copyStmt);
+ }
+
+ defnDumped = false;
+
+ if ((reqs & REQ_SCHEMA) != 0) /* We want the schema */
+ {
+ ahlog(AH, 1, "creating %s %s\n", te->desc, te->tag);
+
+ _printTocEntry(AH, te, ropt, false, false);
+ defnDumped = true;
+
+ if (strcmp(te->desc, "TABLE") == 0)
+ {
+ if (AH->lastErrorTE == te)
+ {
+ /*
+ * We failed to create the table. If
+ * --no-data-for-failed-tables was given, mark the
+ * corresponding TABLE DATA to be ignored.
+ *
+ * In the parallel case this must be done in the parent, so we
+ * just set the return value.
+ */
+ if (ropt->noDataForFailedTables)
+ {
+ if (is_parallel)
+ retval = WORKER_INHIBIT_DATA;
+ else
+ inhibit_data_for_failed_table(AH, te);
+ }
+ }
+ else
+ {
+ /*
+ * We created the table successfully. Mark the corresponding
+ * TABLE DATA for possible truncation.
+ *
+ * In the parallel case this must be done in the parent, so we
+ * just set the return value.
+ */
+ if (is_parallel)
+ retval = WORKER_CREATE_DONE;
+ else
+ mark_create_done(AH, te);
+ }
+ }
+
+ /* If we created a DB, connect to it... */
+ if (strcmp(te->desc, "DATABASE") == 0)
+ {
+ ahlog(AH, 1, "connecting to new database \"%s\"\n", te->tag);
+ _reconnectToDB(AH, te->tag);
+ ropt->dbname = strdup(te->tag);
+ }
+ }
+
+ /*
+ * If we have a data component, then process it
+ */
+ if ((reqs & REQ_DATA) != 0)
+ {
+ /*
+ * hadDumper will be set if there is genuine data component for this
+ * node. Otherwise, we need to check the defn field for statements
+ * that need to be executed in data-only restores.
+ */
+ if (te->hadDumper)
+ {
+ /*
+ * If we can output the data, then restore it.
+ */
+ if (AH->PrintTocDataPtr !=NULL && (reqs & REQ_DATA) != 0)
+ {
+ _printTocEntry(AH, te, ropt, true, false);
+
+ if (strcmp(te->desc, "BLOBS") == 0 ||
+ strcmp(te->desc, "BLOB COMMENTS") == 0)
+ {
+ ahlog(AH, 1, "restoring %s\n", te->desc);
+
+ _selectOutputSchema(AH, "pg_catalog");
+
+ (*AH->PrintTocDataPtr) (AH, te, ropt);
+ }
+ else
+ {
+ _disableTriggersIfNecessary(AH, te, ropt);
+
+ /* Select owner and schema as necessary */
+ _becomeOwner(AH, te);
+ _selectOutputSchema(AH, te->namespace);
+
+ ahlog(AH, 1, "restoring data for table \"%s\"\n",
+ te->tag);
+
+ /*
+ * In parallel restore, if we created the table earlier in
+ * the run then we wrap the COPY in a transaction and
+ * precede it with a TRUNCATE. If archiving is not on
+ * this prevents WAL-logging the COPY. This obtains a
+ * speedup similar to that from using single_txn mode in
+ * non-parallel restores.
+ */
+ if (is_parallel && te->created)
+ {
+ /*
+ * Parallel restore is always talking directly to a
+ * server, so no need to see if we should issue BEGIN.
+ */
+ StartTransaction(AH);
+
+ /*
+ * If the server version is >= 8.4, make sure we issue
+ * TRUNCATE with ONLY so that child tables are not
+ * wiped.
+ */
+ ahprintf(AH, "TRUNCATE TABLE %s%s;\n\n",
+ (PQserverVersion(AH->connection) >= 80400 ?
+ "ONLY " : ""),
+ fmtId(te->tag));
+ }
+
+ /*
+ * If we have a copy statement, use it. As of V1.3, these
+ * are separate to allow easy import from withing a
+ * database connection. Pre 1.3 archives can not use DB
+ * connections and are sent to output only.
+ *
+ * For V1.3+, the table data MUST have a copy statement so
+ * that we can go into appropriate mode with libpq.
+ */
+ if (te->copyStmt && strlen(te->copyStmt) > 0)
+ {
+ ahprintf(AH, "%s", te->copyStmt);
+ AH->writingCopyData = true;
+ }
+
+ (*AH->PrintTocDataPtr) (AH, te, ropt);
+
+ AH->writingCopyData = false;
+
+ /* close out the transaction started above */
+ if (is_parallel && te->created)
+ CommitTransaction(AH);
+
+ _enableTriggersIfNecessary(AH, te, ropt);
+ }
+ }
+ }
+ else if (!defnDumped)
+ {
+ /* If we haven't already dumped the defn part, do so now */
+ ahlog(AH, 1, "executing %s %s\n", te->desc, te->tag);
+ _printTocEntry(AH, te, ropt, false, false);
+ }
+ }
+
+ return retval;
+}
+
/*
* Allocate a new RestoreOptions block.
* This is mainly so we can initialize it, but also for future expansion,
opts = (RestoreOptions *) calloc(1, sizeof(RestoreOptions));
+ /* set any fields that shouldn't default to zeroes */
opts->format = archUnknown;
- opts->suppressDumpWarnings = false;
- opts->exit_on_error = false;
+ opts->promptPassword = TRI_DEFAULT;
return opts;
}
const char *namespace,
const char *tablespace,
const char *owner, bool withOids,
- const char *desc, const char *defn,
+ const char *desc, teSection section,
+ const char *defn,
const char *dropStmt, const char *copyStmt,
const DumpId *deps, int nDeps,
DataDumperPtr dumpFn, void *dumpArg)
newToc->catalogId = catalogId;
newToc->dumpId = dumpId;
+ newToc->section = section;
newToc->tag = strdup(tag);
newToc->namespace = namespace ? strdup(namespace) : NULL;
PrintTOCSummary(Archive *AHX, RestoreOptions *ropt)
{
ArchiveHandle *AH = (ArchiveHandle *) AHX;
- TocEntry *te = AH->toc->next;
+ TocEntry *te;
OutputContext sav;
char *fmtName;
ahprintf(AH, ";\n;\n; Selected TOC Entries:\n;\n");
- while (te != AH->toc)
+ /* We should print DATABASE entries whether or not -C was specified */
+ ropt->createDB = 1;
+
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
{
- if (_tocEntryRequired(te, ropt, true) != 0)
+ if (ropt->verbose || _tocEntryRequired(te, ropt, true) != 0)
ahprintf(AH, "%d; %u %u %s %s %s %s\n", te->dumpId,
te->catalogId.tableoid, te->catalogId.oid,
te->desc, te->namespace ? te->namespace : "-",
te->tag, te->owner);
- te = te->next;
+ if (ropt->verbose && te->nDeps > 0)
+ {
+ int i;
+
+ ahprintf(AH, ";\tdepends on:");
+ for (i = 0; i < te->nDeps; i++)
+ ahprintf(AH, " %d", te->dependencies[i]);
+ ahprintf(AH, "\n");
+ }
}
if (ropt->filename)
ahprintf(AH, "COMMIT;\n\n");
}
- ahlog(AH, 1, "restored %d large objects\n", AH->blobCount);
+ ahlog(AH, 1, ngettext("restored %d large object\n",
+ "restored %d large objects\n",
+ AH->blobCount),
+ AH->blobCount);
}
* Called by a format handler to initiate restoration of a blob
*/
void
-StartRestoreBlob(ArchiveHandle *AH, Oid oid)
+StartRestoreBlob(ArchiveHandle *AH, Oid oid, bool drop)
{
+ bool old_blob_style = (AH->version < K_VERS_1_12);
Oid loOid;
AH->blobCount++;
ahlog(AH, 2, "restoring large object with OID %u\n", oid);
+ /* With an old archive we must do drop and create logic here */
+ if (old_blob_style && drop)
+ DropBlobIfExists(AH, oid);
+
if (AH->connection)
{
- loOid = lo_create(AH->connection, oid);
- if (loOid == 0 || loOid != oid)
- die_horribly(AH, modulename, "could not create large object %u\n",
- oid);
-
+ if (old_blob_style)
+ {
+ loOid = lo_create(AH->connection, oid);
+ if (loOid == 0 || loOid != oid)
+ die_horribly(AH, modulename, "could not create large object %u: %s",
+ oid, PQerrorMessage(AH->connection));
+ }
AH->loFd = lo_open(AH->connection, oid, INV_WRITE);
if (AH->loFd == -1)
- die_horribly(AH, modulename, "could not open large object\n");
+ die_horribly(AH, modulename, "could not open large object %u: %s",
+ oid, PQerrorMessage(AH->connection));
}
else
{
- ahprintf(AH, "SELECT lo_open(lo_create(%u), %d);\n", oid, INV_WRITE);
+ if (old_blob_style)
+ ahprintf(AH, "SELECT pg_catalog.lo_open(pg_catalog.lo_create('%u'), %d);\n",
+ oid, INV_WRITE);
+ else
+ ahprintf(AH, "SELECT pg_catalog.lo_open('%u', %d);\n",
+ oid, INV_WRITE);
}
AH->writingBlob = 1;
}
else
{
- ahprintf(AH, "SELECT lo_close(0);\n\n");
+ ahprintf(AH, "SELECT pg_catalog.lo_close(0);\n\n");
}
}
char *endptr;
DumpId id;
TocEntry *te;
- TocEntry *tePrev;
/* Allocate space for the 'wanted' array, and init it */
ropt->idWanted = (bool *) malloc(sizeof(bool) * AH->maxDumpId);
memset(ropt->idWanted, 0, sizeof(bool) * AH->maxDumpId);
- /* Set prev entry as head of list */
- tePrev = AH->toc;
-
/* Setup the file */
fh = fopen(ropt->tocFile, PG_BINARY_R);
if (!fh)
- die_horribly(AH, modulename, "could not open TOC file: %s\n",
- strerror(errno));
+ die_horribly(AH, modulename, "could not open TOC file \"%s\": %s\n",
+ ropt->tocFile, strerror(errno));
while (fgets(buf, sizeof(buf), fh) != NULL)
{
cmnt[0] = '\0';
/* Ignore if all blank */
- if (strspn(buf, " \t\r") == strlen(buf))
+ if (strspn(buf, " \t\r\n") == strlen(buf))
continue;
/* Get an ID, check it's valid and not already seen */
die_horribly(AH, modulename, "could not find entry for ID %d\n",
id);
+ /* Mark it wanted */
ropt->idWanted[id - 1] = true;
- _moveAfter(AH, tePrev, te);
- tePrev = te;
+ /*
+ * Move each item to the end of the list as it is selected, so that
+ * they are placed in the desired order. Any unwanted items will end
+ * up at the front of the list, which may seem unintuitive but it's
+ * what we need. In an ordinary serial restore that makes no
+ * difference, but in a parallel restore we need to mark unrestored
+ * items' dependencies as satisfied before we start examining
+ * restorable items. Otherwise they could have surprising
+ * side-effects on the order in which restorable items actually get
+ * restored.
+ */
+ _moveBefore(AH, AH->toc, te);
}
if (fclose(fh) != 0)
}
if (!AH->OF)
- die_horribly(AH, modulename, "could not open output file: %s\n", strerror(errno));
+ {
+ if (filename)
+ die_horribly(AH, modulename, "could not open output file \"%s\": %s\n",
+ filename, strerror(errno));
+ else
+ die_horribly(AH, modulename, "could not open output file: %s\n",
+ strerror(errno));
+ }
return sav;
}
size_t res;
res = lo_write(AH->connection, AH->loFd, AH->lo_buf, AH->lo_buf_used);
- ahlog(AH, 5, "wrote %lu bytes of large object data (result = %lu)\n",
+ ahlog(AH, 5, ngettext("wrote %lu byte of large object data (result = %lu)\n",
+ "wrote %lu bytes of large object data (result = %lu)\n",
+ AH->lo_buf_used),
(unsigned long) AH->lo_buf_used, (unsigned long) res);
if (res != AH->lo_buf_used)
die_horribly(AH, modulename,
}
else
{
- unsigned char *str;
- size_t len;
+ PQExpBuffer buf = createPQExpBuffer();
- str = PQescapeBytea((const unsigned char *) AH->lo_buf,
- AH->lo_buf_used, &len);
- if (!str)
- die_horribly(AH, modulename, "out of memory\n");
+ appendByteaLiteralAHX(buf,
+ (const unsigned char *) AH->lo_buf,
+ AH->lo_buf_used,
+ AH);
/* Hack: turn off writingBlob so ahwrite doesn't recurse to here */
AH->writingBlob = 0;
- ahprintf(AH, "SELECT lowrite(0, '%s');\n", str);
+ ahprintf(AH, "SELECT pg_catalog.lowrite(0, %s);\n", buf->data);
AH->writingBlob = 1;
- free(str);
+ destroyPQExpBuffer(buf);
}
AH->lo_buf_used = 0;
}
va_end(ap);
}
+#ifdef NOT_USED
+
static void
_moveAfter(ArchiveHandle *AH, TocEntry *pos, TocEntry *te)
{
+ /* Unlink te from list */
te->prev->next = te->next;
te->next->prev = te->prev;
+ /* and insert it after "pos" */
te->prev = pos;
te->next = pos->next;
-
pos->next->prev = te;
pos->next = te;
}
-#ifdef NOT_USED
+#endif
static void
_moveBefore(ArchiveHandle *AH, TocEntry *pos, TocEntry *te)
{
+ /* Unlink te from list */
te->prev->next = te->next;
te->next->prev = te->prev;
+ /* and insert it before "pos" */
te->prev = pos->prev;
te->next = pos;
pos->prev->next = te;
pos->prev = te;
}
-#endif
static TocEntry *
getTocEntryByDumpId(ArchiveHandle *AH, DumpId id)
{
TocEntry *te;
- te = AH->toc->next;
- while (te != AH->toc)
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if (te->dumpId == id)
return te;
- te = te->next;
}
return NULL;
}
}
size_t
-WriteOffset(ArchiveHandle *AH, off_t o, int wasSet)
+WriteOffset(ArchiveHandle *AH, pgoff_t o, int wasSet)
{
int off;
/* Save the flag */
(*AH->WriteBytePtr) (AH, wasSet);
- /* Write out off_t smallest byte first, prevents endian mismatch */
- for (off = 0; off < sizeof(off_t); off++)
+ /* Write out pgoff_t smallest byte first, prevents endian mismatch */
+ for (off = 0; off < sizeof(pgoff_t); off++)
{
(*AH->WriteBytePtr) (AH, o & 0xFF);
o >>= 8;
}
- return sizeof(off_t) + 1;
+ return sizeof(pgoff_t) + 1;
}
int
-ReadOffset(ArchiveHandle *AH, off_t *o)
+ReadOffset(ArchiveHandle *AH, pgoff_t * o)
{
int i;
int off;
else if (i == 0)
return K_OFFSET_NO_DATA;
- /* Cast to off_t because it was written as an int. */
- *o = (off_t) i;
+ /* Cast to pgoff_t because it was written as an int. */
+ *o = (pgoff_t) i;
return K_OFFSET_POS_SET;
}
*/
for (off = 0; off < AH->offSize; off++)
{
- if (off < sizeof(off_t))
- *o |= ((off_t) ((*AH->ReadBytePtr) (AH))) << (off * 8);
+ if (off < sizeof(pgoff_t))
+ *o |= ((pgoff_t) ((*AH->ReadBytePtr) (AH))) << (off * 8);
else
{
if ((*AH->ReadBytePtr) (AH) != 0)
int l;
l = ReadInt(AH);
- if (l == -1)
+ if (l < 0)
buf = NULL;
else
{
if (!buf)
die_horribly(AH, modulename, "out of memory\n");
- (*AH->ReadBufPtr) (AH, (void *) buf, l);
+ if ((*AH->ReadBufPtr) (AH, (void *) buf, l) != l)
+ die_horribly(AH, modulename, "unexpected end of file\n");
+
buf[l] = '\0';
}
{
wantClose = 1;
fh = fopen(AH->fSpec, PG_BINARY_R);
+ if (!fh)
+ die_horribly(AH, modulename, "could not open input file \"%s\": %s\n",
+ AH->fSpec, strerror(errno));
}
else
+ {
fh = stdin;
-
- if (!fh)
- die_horribly(AH, modulename, "could not open input file: %s\n", strerror(errno));
+ if (!fh)
+ die_horribly(AH, modulename, "could not open input file: %s\n",
+ strerror(errno));
+ }
cnt = fread(sig, 1, 5, fh);
if (strncmp(sig, "PGDMP", 5) == 0)
{
+ /*
+ * Finish reading (most of) a custom-format header.
+ *
+ * NB: this code must agree with ReadHead().
+ */
AH->vmaj = fgetc(fh);
AH->vmin = fgetc(fh);
else
AH->lookaheadLen = 0; /* Don't bother since we've reset the file */
-#if 0
- write_msg(modulename, "read %lu bytes into lookahead buffer\n",
- (unsigned long) AH->lookaheadLen);
-#endif
-
/* Close the file */
if (wantClose)
if (fclose(fh) != 0)
AH->vmin = K_VERS_MINOR;
AH->vrev = K_VERS_REV;
+ /* Make a convenient integer <maj><min><rev>00 */
+ AH->version = ((AH->vmaj * 256 + AH->vmin) * 256 + AH->vrev) * 256 + 0;
+
/* initialize for backwards compatible string processing */
- AH->public.encoding = PG_SQL_ASCII;
+ AH->public.encoding = 0; /* PG_SQL_ASCII */
AH->public.std_strings = false;
/* sql error handling */
AH->public.exit_on_error = true;
AH->public.n_errors = 0;
+ AH->archiveDumpVersion = PG_VERSION;
+
AH->createDate = time(NULL);
AH->intSize = sizeof(int);
- AH->offSize = sizeof(off_t);
+ AH->offSize = sizeof(pgoff_t);
if (FileSpec)
{
AH->fSpec = strdup(FileSpec);
else
AH->fSpec = NULL;
- AH->currUser = strdup(""); /* So it's valid, but we can free() it later
- * if necessary */
- AH->currSchema = strdup(""); /* ditto */
+ AH->currUser = NULL; /* unknown */
+ AH->currSchema = NULL; /* ditto */
+ AH->currTablespace = NULL; /* ditto */
AH->currWithOids = -1; /* force SET */
AH->toc = (TocEntry *) calloc(1, sizeof(TocEntry));
}
#endif
-#if 0
- write_msg(modulename, "archive format is %d\n", fmt);
-#endif
-
if (fmt == archUnknown)
AH->format = _discoverArchiveFormat(AH);
else
AH->format = fmt;
+ AH->promptPassword = TRI_DEFAULT;
+
switch (AH->format)
{
case archCustom:
void
WriteDataChunks(ArchiveHandle *AH)
{
- TocEntry *te = AH->toc->next;
+ TocEntry *te;
StartDataPtr startPtr;
EndDataPtr endPtr;
- while (te != AH->toc)
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
{
if (te->dataDumper != NULL)
{
(*endPtr) (AH, te);
AH->currToc = NULL;
}
- te = te->next;
}
}
WriteStr(AH, te->tag);
WriteStr(AH, te->desc);
+ WriteInt(AH, te->section);
WriteStr(AH, te->defn);
WriteStr(AH, te->dropStmt);
WriteStr(AH, te->copyStmt);
DumpId *deps;
int depIdx;
int depSize;
-
- TocEntry *te = AH->toc->next;
+ TocEntry *te;
AH->tocCount = ReadInt(AH);
AH->maxDumpId = 0;
te->tag = ReadStr(AH);
te->desc = ReadStr(AH);
+
+ if (AH->version >= K_VERS_1_11)
+ {
+ te->section = ReadInt(AH);
+ }
+ else
+ {
+ /*
+ * Rules for pre-8.4 archives wherein pg_dump hasn't classified
+ * the entries into sections. This list need not cover entry
+ * types added later than 8.4.
+ */
+ if (strcmp(te->desc, "COMMENT") == 0 ||
+ strcmp(te->desc, "ACL") == 0 ||
+ strcmp(te->desc, "ACL LANGUAGE") == 0)
+ te->section = SECTION_NONE;
+ else if (strcmp(te->desc, "TABLE DATA") == 0 ||
+ strcmp(te->desc, "BLOBS") == 0 ||
+ strcmp(te->desc, "BLOB COMMENTS") == 0)
+ te->section = SECTION_DATA;
+ else if (strcmp(te->desc, "CONSTRAINT") == 0 ||
+ strcmp(te->desc, "CHECK CONSTRAINT") == 0 ||
+ strcmp(te->desc, "FK CONSTRAINT") == 0 ||
+ strcmp(te->desc, "INDEX") == 0 ||
+ strcmp(te->desc, "RULE") == 0 ||
+ strcmp(te->desc, "TRIGGER") == 0)
+ te->section = SECTION_POST_DATA;
+ else
+ te->section = SECTION_PRE_DATA;
+ }
+
te->defn = ReadStr(AH);
te->dropStmt = ReadStr(AH);
return 0;
/* If it's an ACL, maybe ignore it */
- if ((!include_acls || ropt->aclsSkip) && strcmp(te->desc, "ACL") == 0)
+ if ((!include_acls || ropt->aclsSkip) && _tocEntryIsACL(te))
+ return 0;
+
+ /* If it's security labels, maybe ignore it */
+ if (ropt->skip_seclabel && strcmp(te->desc, "SECURITY LABEL") == 0)
return 0;
- if (!ropt->create && strcmp(te->desc, "DATABASE") == 0)
+ /* Ignore DATABASE entry unless we should create it */
+ if (!ropt->createDB && strcmp(te->desc, "DATABASE") == 0)
return 0;
/* Check options for selective dump/restore */
if (!te->hadDumper)
{
/*
- * Special Case: If 'SEQUENCE SET' then it is considered a data entry
+ * Special Case: If 'SEQUENCE SET' or anything to do with BLOBs, then
+ * it is considered a data entry. We don't need to check for the
+ * BLOBS entry or old-style BLOB COMMENTS, because they will have
+ * hadDumper = true ... but we do need to check new-style BLOB
+ * comments.
*/
- if (strcmp(te->desc, "SEQUENCE SET") == 0)
+ if (strcmp(te->desc, "SEQUENCE SET") == 0 ||
+ strcmp(te->desc, "BLOB") == 0 ||
+ (strcmp(te->desc, "ACL") == 0 &&
+ strncmp(te->tag, "LARGE OBJECT ", 13) == 0) ||
+ (strcmp(te->desc, "COMMENT") == 0 &&
+ strncmp(te->tag, "LARGE OBJECT ", 13) == 0) ||
+ (strcmp(te->desc, "SECURITY LABEL") == 0 &&
+ strncmp(te->tag, "LARGE OBJECT ", 13) == 0))
res = res & REQ_DATA;
else
res = res & ~REQ_DATA;
return res;
}
+/*
+ * Identify TOC entries that are ACLs.
+ */
+static bool
+_tocEntryIsACL(TocEntry *te)
+{
+ /* "ACL LANGUAGE" was a crock emitted only in PG 7.4 */
+ if (strcmp(te->desc, "ACL") == 0 ||
+ strcmp(te->desc, "ACL LANGUAGE") == 0 ||
+ strcmp(te->desc, "DEFAULT ACL") == 0)
+ return true;
+ return false;
+}
+
/*
* Issue SET commands for parameters that we want to have set the same way
* at all times during execution of a restore script.
static void
_doSetFixedOutputState(ArchiveHandle *AH)
{
+ /* Disable statement_timeout in archive for pg_restore/psql */
+ ahprintf(AH, "SET statement_timeout = 0;\n");
+
/* Select the correct character set encoding */
ahprintf(AH, "SET client_encoding = '%s';\n",
pg_encoding_to_char(AH->public.encoding));
ahprintf(AH, "SET standard_conforming_strings = %s;\n",
AH->public.std_strings ? "on" : "off");
+ /* Select the role to be used during restore */
+ if (AH->ropt && AH->ropt->use_role)
+ ahprintf(AH, "SET ROLE %s;\n", fmtId(AH->ropt->use_role));
+
/* Make sure function checking is disabled */
ahprintf(AH, "SET check_function_bodies = false;\n");
*/
if (AH->currUser)
free(AH->currUser);
+ AH->currUser = NULL;
- AH->currUser = strdup("");
-
- /* don't assume we still know the output schema */
+ /* don't assume we still know the output schema, tablespace, etc either */
if (AH->currSchema)
free(AH->currSchema);
- AH->currSchema = strdup("");
+ AH->currSchema = NULL;
+ if (AH->currTablespace)
+ free(AH->currTablespace);
+ AH->currTablespace = NULL;
AH->currWithOids = -1;
/* re-establish fixed state */
*/
if (AH->currUser)
free(AH->currUser);
-
AH->currUser = strdup(user);
}
/*
- * Become the owner of the the given TOC entry object. If
+ * Become the owner of the given TOC entry object. If
* changes in ownership are not allowed, this doesn't do anything.
*/
static void
const char *want,
*have;
+ /* do nothing in --no-tablespaces mode */
+ if (AH->ropt->noTablespace)
+ return;
+
have = AH->currTablespace;
want = tablespace;
if (strcmp(type, "CONVERSION") == 0 ||
strcmp(type, "DOMAIN") == 0 ||
strcmp(type, "TABLE") == 0 ||
- strcmp(type, "TYPE") == 0)
+ strcmp(type, "TYPE") == 0 ||
+ strcmp(type, "FOREIGN TABLE") == 0 ||
+ strcmp(type, "TEXT SEARCH DICTIONARY") == 0 ||
+ strcmp(type, "TEXT SEARCH CONFIGURATION") == 0)
{
appendPQExpBuffer(buf, "%s ", type);
if (te->namespace && te->namespace[0]) /* is null pre-7.3 */
/* objects named by just a name */
if (strcmp(type, "DATABASE") == 0 ||
- strcmp(type, "SCHEMA") == 0)
+ strcmp(type, "PROCEDURAL LANGUAGE") == 0 ||
+ strcmp(type, "SCHEMA") == 0 ||
+ strcmp(type, "FOREIGN DATA WRAPPER") == 0 ||
+ strcmp(type, "SERVER") == 0 ||
+ strcmp(type, "USER MAPPING") == 0)
{
appendPQExpBuffer(buf, "%s %s", type, fmtId(te->tag));
return;
}
+ /* BLOBs just have a name, but it's numeric so must not use fmtId */
+ if (strcmp(type, "BLOB") == 0)
+ {
+ appendPQExpBuffer(buf, "LARGE OBJECT %s", te->tag);
+ return;
+ }
+
/*
* These object types require additional decoration. Fortunately, the
* information needed is exactly what's in the DROP command.
/* ACLs are dumped only during acl pass */
if (acl_pass)
{
- if (strcmp(te->desc, "ACL") != 0)
+ if (!_tocEntryIsACL(te))
return;
}
else
{
- if (strcmp(te->desc, "ACL") == 0)
+ if (_tocEntryIsACL(te))
return;
}
/*
* Avoid dumping the public schema, as it will already be created ...
* unless we are using --clean mode, in which case it's been deleted and
- * we'd better recreate it.
+ * we'd better recreate it. Likewise for its comment, if any.
*/
- if (!ropt->dropSchema &&
- strcmp(te->desc, "SCHEMA") == 0 && strcmp(te->tag, "public") == 0)
- return;
+ if (!ropt->dropSchema)
+ {
+ if (strcmp(te->desc, "SCHEMA") == 0 &&
+ strcmp(te->tag, "public") == 0)
+ return;
+ /* The comment restore would require super-user privs, so avoid it. */
+ if (strcmp(te->desc, "COMMENT") == 0 &&
+ strcmp(te->tag, "SCHEMA public") == 0)
+ return;
+ }
/* Select owner, schema, and tablespace as necessary */
_becomeOwner(AH, te);
pfx, te->tag, te->desc,
te->namespace ? te->namespace : "-",
ropt->noOwner ? "-" : te->owner);
- if (te->tablespace)
+ if (te->tablespace && !ropt->noTablespace)
ahprintf(AH, "; Tablespace: %s", te->tablespace);
ahprintf(AH, "\n");
strlen(te->owner) > 0 && strlen(te->dropStmt) > 0)
{
if (strcmp(te->desc, "AGGREGATE") == 0 ||
+ strcmp(te->desc, "BLOB") == 0 ||
strcmp(te->desc, "CONVERSION") == 0 ||
strcmp(te->desc, "DATABASE") == 0 ||
strcmp(te->desc, "DOMAIN") == 0 ||
strcmp(te->desc, "OPERATOR") == 0 ||
strcmp(te->desc, "OPERATOR CLASS") == 0 ||
strcmp(te->desc, "OPERATOR FAMILY") == 0 ||
+ strcmp(te->desc, "PROCEDURAL LANGUAGE") == 0 ||
strcmp(te->desc, "SCHEMA") == 0 ||
strcmp(te->desc, "TABLE") == 0 ||
strcmp(te->desc, "TYPE") == 0 ||
strcmp(te->desc, "VIEW") == 0 ||
- strcmp(te->desc, "SEQUENCE") == 0)
+ strcmp(te->desc, "SEQUENCE") == 0 ||
+ strcmp(te->desc, "FOREIGN TABLE") == 0 ||
+ strcmp(te->desc, "TEXT SEARCH DICTIONARY") == 0 ||
+ strcmp(te->desc, "TEXT SEARCH CONFIGURATION") == 0 ||
+ strcmp(te->desc, "FOREIGN DATA WRAPPER") == 0 ||
+ strcmp(te->desc, "SERVER") == 0)
{
PQExpBuffer temp = createPQExpBuffer();
strcmp(te->desc, "DEFAULT") == 0 ||
strcmp(te->desc, "FK CONSTRAINT") == 0 ||
strcmp(te->desc, "INDEX") == 0 ||
- strcmp(te->desc, "PROCEDURAL LANGUAGE") == 0 ||
strcmp(te->desc, "RULE") == 0 ||
- strcmp(te->desc, "TRIGGER") == 0)
+ strcmp(te->desc, "TRIGGER") == 0 ||
+ strcmp(te->desc, "USER MAPPING") == 0)
{
/* these object types don't have separate owners */
}
* If it's an ACL entry, it might contain SET SESSION AUTHORIZATION
* commands, so we can no longer assume we know the current auth setting.
*/
- if (strncmp(te->desc, "ACL", 3) == 0)
+ if (acl_pass)
{
if (AH->currUser)
free(AH->currUser);
int fmt;
struct tm crtm;
- /* If we haven't already read the header... */
+ /*
+ * If we haven't already read the header, do so.
+ *
+ * NB: this code must agree with _discoverArchiveFormat(). Maybe find a
+ * way to unify the cases?
+ */
if (!AH->readHeader)
{
-
- (*AH->ReadBufPtr) (AH, tmpMag, 5);
+ if ((*AH->ReadBufPtr) (AH, tmpMag, 5) != 5)
+ die_horribly(AH, modulename, "unexpected end of file\n");
if (strncmp(tmpMag, "PGDMP", 5) != 0)
die_horribly(AH, modulename, "did not find magic string in file header\n");
AH->version = ((AH->vmaj * 256 + AH->vmin) * 256 + AH->vrev) * 256 + 0;
-
if (AH->version < K_VERS_1_0 || AH->version > K_VERS_MAX)
die_horribly(AH, modulename, "unsupported version (%d.%d) in file header\n",
AH->vmaj, AH->vmin);
(unsigned long) AH->intSize);
if (AH->intSize > sizeof(int))
- write_msg(modulename, "WARNING: archive was made on a machine with larger integers, some operations may fail\n");
+ write_msg(modulename, "WARNING: archive was made on a machine with larger integers, some operations might fail\n");
if (AH->version >= K_VERS_1_7)
AH->offSize = (*AH->ReadBytePtr) (AH);
AH->archiveRemoteVersion = ReadStr(AH);
AH->archiveDumpVersion = ReadStr(AH);
}
-
}
/*
* checkSeek
- * check to see if fseek can be performed.
+ * check to see if ftell/fseek can be performed.
*/
-
bool
checkSeek(FILE *fp)
{
+ pgoff_t tpos;
- if (fseeko(fp, 0, SEEK_CUR) != 0)
+ /*
+ * If pgoff_t is wider than long, we must have "real" fseeko and not an
+ * emulation using fseek. Otherwise report no seek capability.
+ */
+#ifndef HAVE_FSEEKO
+ if (sizeof(pgoff_t) > sizeof(long))
return false;
- else if (sizeof(off_t) > sizeof(long))
+#endif
- /*
- * At this point, off_t is too large for long, so we return based on
- * whether an off_t version of fseek is available.
- */
-#ifdef HAVE_FSEEKO
- return true;
-#else
+ /* Check that ftello works on this file */
+ errno = 0;
+ tpos = ftello(fp);
+ if (errno)
return false;
-#endif
- else
- return true;
+
+ /*
+ * Check that fseeko(SEEK_SET) works, too. NB: we used to try to test
+ * this with fseeko(fp, 0, SEEK_CUR). But some platforms treat that as a
+ * successful no-op even on files that are otherwise unseekable.
+ */
+ if (fseeko(fp, tpos, SEEK_SET) != 0)
+ return false;
+
+ return true;
}
/*
* We don't print the timezone on Win32, because the names are long and
* localized, which means they may contain characters in various random
- * encodings; this has been seen to cause encoding errors when reading
- * the dump script.
+ * encodings; this has been seen to cause encoding errors when reading the
+ * dump script.
*/
if (strftime(buf, sizeof(buf),
#ifndef WIN32
localtime(&tim)) != 0)
ahprintf(AH, "-- %s %s\n\n", msg, buf);
}
+
+
+/*
+ * Main engine for parallel restore.
+ *
+ * Work is done in three phases.
+ * First we process tocEntries until we come to one that is marked
+ * SECTION_DATA or SECTION_POST_DATA, in a single connection, just as for a
+ * standard restore. Second we process the remaining non-ACL steps in
+ * parallel worker children (threads on Windows, processes on Unix), each of
+ * which connects separately to the database. Finally we process all the ACL
+ * entries in a single connection (that happens back in 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;
+ TocEntry pending_list;
+ TocEntry ready_list;
+ TocEntry *next_work_item;
+ thandle ret_child;
+ TocEntry *te;
+
+ ahlog(AH, 2, "entering restore_toc_entries_parallel\n");
+
+ /* we haven't got round to making this work for all archive formats */
+ if (AH->ClonePtr == NULL || AH->ReopenPtr == NULL)
+ die_horribly(AH, 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)
+ die_horribly(AH, modulename, "parallel restore is not supported with archives made by pre-8.0 pg_dump\n");
+
+ slots = (ParallelSlot *) calloc(sizeof(ParallelSlot), n_slots);
+
+ /* Adjust dependency information */
+ fix_dependencies(AH);
+
+ /*
+ * Do all the early stuff in a single connection in the parent. There's no
+ * great point in running it in parallel, in fact it will actually run
+ * faster in a single connection because we avoid all the connection and
+ * setup overhead. Also, pg_dump is not currently very good about
+ * showing all the dependencies of SECTION_PRE_DATA items, so we do not
+ * risk trying to process them out-of-order.
+ */
+ for (next_work_item = AH->toc->next; next_work_item != AH->toc; next_work_item = next_work_item->next)
+ {
+ /* Non-PRE_DATA items are just ignored for now */
+ if (next_work_item->section == SECTION_DATA ||
+ next_work_item->section == SECTION_POST_DATA)
+ continue;
+
+ ahlog(AH, 1, "processing item %d %s %s\n",
+ next_work_item->dumpId,
+ next_work_item->desc, next_work_item->tag);
+
+ (void) restore_toc_entry(AH, next_work_item, ropt, false);
+
+ /* there should be no touch of ready_list here, so pass NULL */
+ reduce_dependencies(AH, next_work_item, NULL);
+ }
+
+ /*
+ * Now close parent connection in prep for parallel steps. We do this
+ * mainly to ensure that we don't exceed the specified number of parallel
+ * connections.
+ */
+ PQfinish(AH->connection);
+ AH->connection = NULL;
+
+ /* blow away any transient state from the old connection */
+ if (AH->currUser)
+ free(AH->currUser);
+ AH->currUser = NULL;
+ if (AH->currSchema)
+ free(AH->currSchema);
+ AH->currSchema = NULL;
+ if (AH->currTablespace)
+ 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);
+ for (next_work_item = AH->toc->next; next_work_item != AH->toc; next_work_item = next_work_item->next)
+ {
+ /* All PRE_DATA items were dealt with above */
+ if (next_work_item->section == SECTION_DATA ||
+ next_work_item->section == SECTION_POST_DATA)
+ {
+ if (next_work_item->depCount > 0)
+ par_list_append(&pending_list, next_work_item);
+ else
+ par_list_append(&ready_list, next_work_item);
+ }
+ }
+
+ /*
+ * main parent loop
+ *
+ * Keep going until there is no worker still running AND there is no work
+ * left to be done.
+ */
+
+ 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)
+ {
+ teReqs reqs;
+
+ /* If not to be dumped, don't waste time launching a worker */
+ reqs = _tocEntryRequired(next_work_item, AH->ropt, false);
+ if ((reqs & (REQ_SCHEMA | REQ_DATA)) == 0)
+ {
+ ahlog(AH, 1, "skipping item %d %s %s\n",
+ next_work_item->dumpId,
+ next_work_item->desc, next_work_item->tag);
+
+ par_list_remove(next_work_item);
+ reduce_dependencies(AH, next_work_item, &ready_list);
+
+ 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 = malloc(sizeof(RestoreArgs));
+ args->AH = CloneArchive(AH);
+ args->te = next_work_item;
+
+ /* 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
+ {
+ die_horribly(AH, modulename, "worker process crashed: status %d\n",
+ work_status);
+ }
+ }
+
+ ahlog(AH, 1, "finished main parallel loop\n");
+
+ /*
+ * Now reconnect the single parent connection.
+ */
+ ConnectDatabase((Archive *) AH, ropt->dbname,
+ ropt->pghost, ropt->pgport, ropt->username,
+ ropt->promptPassword);
+
+ _doSetFixedOutputState(AH);
+
+ /*
+ * Make sure there is no non-ACL work left due to, say, circular
+ * 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);
+ (void) restore_toc_entry(AH, te, ropt, false);
+ }
+
+ /* The ACLs will be handled back in RestoreArchive. */
+}
+
+/*
+ * 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);
+ die_horribly(args->AH, modulename,
+ "parallel_restore should not return\n");
+ }
+ else if (child < 0)
+ {
+ /* fork failed */
+ die_horribly(args->AH, 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)
+ die_horribly(args->AH, 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 *) 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.
+ */
+static bool
+has_lock_conflicts(TocEntry *te1, TocEntry *te2)
+{
+ int j,
+ k;
+
+ for (j = 0; j < te1->nLockDeps; j++)
+ {
+ for (k = 0; k < te2->nDeps; k++)
+ {
+ if (te1->lockDeps[j] == te2->dependencies[k])
+ return true;
+ }
+ }
+ return false;
+}
+
+
+/*
+ * Initialize the header of a parallel-processing list.
+ *
+ * These are circular lists with a dummy TocEntry as header, just like the
+ * main TOC list; but we use separate list links so that an entry can be in
+ * the main TOC list as well as in a parallel-processing list.
+ */
+static void
+par_list_header_init(TocEntry *l)
+{
+ l->par_prev = l->par_next = l;
+}
+
+/* Append te to the end of the parallel-processing list headed by l */
+static void
+par_list_append(TocEntry *l, TocEntry *te)
+{
+ te->par_prev = l->par_prev;
+ l->par_prev->par_next = te;
+ l->par_prev = te;
+ te->par_next = l;
+}
+
+/* Remove te from whatever parallel-processing list it's in */
+static void
+par_list_remove(TocEntry *te)
+{
+ te->par_prev->par_next = te->par_next;
+ te->par_next->par_prev = te->par_prev;
+ te->par_prev = NULL;
+ te->par_next = NULL;
+}
+
+
+/*
+ * Find the next work item (if any) that is capable of being run now.
+ *
+ * To qualify, the item must have no remaining dependencies
+ * and no requirements for locks that are incompatible with
+ * items currently running. Items in the ready_list are known to have
+ * no remaining dependencies, but we have to check for lock conflicts.
+ *
+ * Note that the returned item has *not* been removed from ready_list.
+ * The caller must do that after successfully dispatching the item.
+ *
+ * pref_non_data is for an alternative selection algorithm that gives
+ * preference to non-data items if there is already a data load running.
+ * It is currently disabled.
+ */
+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;
+ TocEntry *te;
+ int i,
+ k;
+
+ /*
+ * Bogus heuristics for pref_non_data
+ */
+ if (pref_non_data)
+ {
+ 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;
+ }
+
+ /*
+ * Search the ready_list until we find a suitable item.
+ */
+ for (te = ready_list->par_next; te != ready_list; te = te->par_next)
+ {
+ bool conflicts = false;
+
+ /*
+ * Check to see if the item would need exclusive lock on something
+ * 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))
+ {
+ conflicts = true;
+ break;
+ }
+ }
+
+ if (conflicts)
+ continue;
+
+ if (pref_non_data && te->section == SECTION_DATA)
+ {
+ if (data_te == NULL)
+ data_te = te;
+ continue;
+ }
+
+ /* passed all tests, so this item can run */
+ return te;
+ }
+
+ if (data_te != NULL)
+ return data_te;
+
+ ahlog(AH, 2, "no item ready\n");
+ return NULL;
+}
+
+
+/*
+ * 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;
+
+ /*
+ * 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 */
+ PQfinish(AH->connection);
+ AH->connection = NULL;
+
+ /* 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
+}
+
+
+/*
+ * Housekeeping to be done after a step has been parallel restored.
+ *
+ * Clear the appropriate slot, free all the extra memory we allocated,
+ * update status, and reduce the dependency count of any dependent items.
+ */
+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)
+ die_horribly(AH, modulename, "could not find slot of finished worker\n");
+
+ ahlog(AH, 1, "finished item %d %s %s\n",
+ te->dumpId, te->desc, te->tag);
+
+ if (status == WORKER_CREATE_DONE)
+ mark_create_done(AH, te);
+ else if (status == WORKER_INHIBIT_DATA)
+ {
+ inhibit_data_for_failed_table(AH, te);
+ AH->public.n_errors++;
+ }
+ else if (status == WORKER_IGNORED_ERRORS)
+ AH->public.n_errors++;
+ else if (status != 0)
+ die_horribly(AH, modulename, "worker process failed: exit code %d\n",
+ status);
+
+ reduce_dependencies(AH, te, ready_list);
+}
+
+
+/*
+ * Process the dependency information into a form useful for parallel restore.
+ *
+ * This function takes care of fixing up some missing or badly designed
+ * dependencies, and then prepares subsidiary data structures that will be
+ * used in the main parallel-restore logic, including:
+ * 1. We build the tocsByDumpId[] index array.
+ * 2. We build the revDeps[] arrays of incoming dependency dumpIds.
+ * 3. We set up depCount fields that are the number of as-yet-unprocessed
+ * dependencies for each TOC entry.
+ *
+ * We also identify locking dependencies so that we can avoid trying to
+ * schedule conflicting items at the same time.
+ */
+static void
+fix_dependencies(ArchiveHandle *AH)
+{
+ TocEntry *te;
+ int i;
+
+ /*
+ * It is convenient to have an array that indexes the TOC entries by dump
+ * ID, rather than searching the TOC list repeatedly. Entries for dump
+ * IDs not present in the TOC will be NULL.
+ *
+ * NOTE: because maxDumpId is just the highest dump ID defined in the
+ * archive, there might be dependencies for IDs > maxDumpId. All uses of
+ * this array must guard against out-of-range dependency numbers.
+ *
+ * Also, initialize the depCount/revDeps/nRevDeps fields, and make sure
+ * the TOC items are marked as not being in any parallel-processing list.
+ */
+ maxDumpId = AH->maxDumpId;
+ tocsByDumpId = (TocEntry **) calloc(maxDumpId, sizeof(TocEntry *));
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ tocsByDumpId[te->dumpId - 1] = te;
+ te->depCount = te->nDeps;
+ te->revDeps = NULL;
+ te->nRevDeps = 0;
+ te->par_prev = NULL;
+ te->par_next = NULL;
+ }
+
+ /*
+ * POST_DATA items that are shown as depending on a table need to be
+ * re-pointed to depend on that table's data, instead. This ensures they
+ * won't get scheduled until the data has been loaded. We handle this by
+ * first finding TABLE/TABLE DATA pairs and then scanning all the
+ * dependencies.
+ *
+ * Note: currently, a TABLE DATA should always have exactly one
+ * dependency, on its TABLE item. So we don't bother to search, but look
+ * just at the first dependency. We do trouble to make sure that it's a
+ * TABLE, if possible. However, if the dependency isn't in the archive
+ * then just assume it was a TABLE; this is to cover cases where the table
+ * was suppressed but we have the data and some dependent post-data items.
+ *
+ * XXX this is O(N^2) if there are a lot of tables. We ought to fix
+ * pg_dump to produce correctly-linked dependencies in the first place.
+ */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ if (strcmp(te->desc, "TABLE DATA") == 0 && te->nDeps > 0)
+ {
+ DumpId tableId = te->dependencies[0];
+
+ if (tableId > maxDumpId ||
+ tocsByDumpId[tableId - 1] == NULL ||
+ strcmp(tocsByDumpId[tableId - 1]->desc, "TABLE") == 0)
+ {
+ repoint_table_dependencies(AH, tableId, te->dumpId);
+ }
+ }
+ }
+
+ /*
+ * Pre-8.4 versions of pg_dump neglected to set up a dependency from BLOB
+ * COMMENTS to BLOBS. Cope. (We assume there's only one BLOBS and only
+ * one BLOB COMMENTS in such files.)
+ */
+ if (AH->version < K_VERS_1_11)
+ {
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ if (strcmp(te->desc, "BLOB COMMENTS") == 0 && te->nDeps == 0)
+ {
+ TocEntry *te2;
+
+ for (te2 = AH->toc->next; te2 != AH->toc; te2 = te2->next)
+ {
+ if (strcmp(te2->desc, "BLOBS") == 0)
+ {
+ te->dependencies = (DumpId *) malloc(sizeof(DumpId));
+ te->dependencies[0] = te2->dumpId;
+ te->nDeps++;
+ te->depCount++;
+ break;
+ }
+ }
+ break;
+ }
+ }
+ }
+
+ /*
+ * At this point we start to build the revDeps reverse-dependency arrays,
+ * so all changes of dependencies must be complete.
+ */
+
+ /*
+ * Count the incoming dependencies for each item. Also, it is possible
+ * that the dependencies list items that are not in the archive at
+ * all. Subtract such items from the depCounts.
+ */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ for (i = 0; i < te->nDeps; i++)
+ {
+ DumpId depid = te->dependencies[i];
+
+ if (depid <= maxDumpId && tocsByDumpId[depid - 1] != NULL)
+ tocsByDumpId[depid - 1]->nRevDeps++;
+ else
+ te->depCount--;
+ }
+ }
+
+ /*
+ * Allocate space for revDeps[] arrays, and reset nRevDeps so we can
+ * use it as a counter below.
+ */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ if (te->nRevDeps > 0)
+ te->revDeps = (DumpId *) malloc(te->nRevDeps * sizeof(DumpId));
+ te->nRevDeps = 0;
+ }
+
+ /*
+ * Build the revDeps[] arrays of incoming-dependency dumpIds. This
+ * had better agree with the loops above.
+ */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ for (i = 0; i < te->nDeps; i++)
+ {
+ DumpId depid = te->dependencies[i];
+
+ if (depid <= maxDumpId && tocsByDumpId[depid - 1] != NULL)
+ {
+ TocEntry *otherte = tocsByDumpId[depid - 1];
+
+ otherte->revDeps[otherte->nRevDeps++] = te->dumpId;
+ }
+ }
+ }
+
+ /*
+ * Lastly, work out the locking dependencies.
+ */
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ te->lockDeps = NULL;
+ te->nLockDeps = 0;
+ identify_locking_dependencies(te);
+ }
+}
+
+/*
+ * Change dependencies on tableId to depend on tableDataId instead,
+ * but only in POST_DATA items.
+ */
+static void
+repoint_table_dependencies(ArchiveHandle *AH,
+ DumpId tableId, DumpId tableDataId)
+{
+ TocEntry *te;
+ int i;
+
+ for (te = AH->toc->next; te != AH->toc; te = te->next)
+ {
+ if (te->section != SECTION_POST_DATA)
+ continue;
+ for (i = 0; i < te->nDeps; i++)
+ {
+ if (te->dependencies[i] == tableId)
+ {
+ te->dependencies[i] = tableDataId;
+ ahlog(AH, 2, "transferring dependency %d -> %d to %d\n",
+ te->dumpId, tableId, tableDataId);
+ }
+ }
+ }
+}
+
+/*
+ * Identify which objects we'll need exclusive lock on in order to restore
+ * the given TOC entry (*other* than the one identified by the TOC entry
+ * itself). Record their dump IDs in the entry's lockDeps[] array.
+ */
+static void
+identify_locking_dependencies(TocEntry *te)
+{
+ DumpId *lockids;
+ int nlockids;
+ int i;
+
+ /* Quick exit if no dependencies at all */
+ if (te->nDeps == 0)
+ return;
+
+ /* Exit if this entry doesn't need exclusive lock on other objects */
+ if (!(strcmp(te->desc, "CONSTRAINT") == 0 ||
+ strcmp(te->desc, "CHECK CONSTRAINT") == 0 ||
+ strcmp(te->desc, "FK CONSTRAINT") == 0 ||
+ strcmp(te->desc, "RULE") == 0 ||
+ strcmp(te->desc, "TRIGGER") == 0))
+ return;
+
+ /*
+ * We assume the item requires exclusive lock on each TABLE DATA item
+ * listed among its dependencies. (This was originally a dependency on
+ * the TABLE, but fix_dependencies repointed it to the data item. Note
+ * that all the entry types we are interested in here are POST_DATA, so
+ * they will all have been changed this way.)
+ */
+ lockids = (DumpId *) malloc(te->nDeps * sizeof(DumpId));
+ nlockids = 0;
+ for (i = 0; i < te->nDeps; i++)
+ {
+ DumpId depid = te->dependencies[i];
+
+ if (depid <= maxDumpId && tocsByDumpId[depid - 1] &&
+ strcmp(tocsByDumpId[depid - 1]->desc, "TABLE DATA") == 0)
+ lockids[nlockids++] = depid;
+ }
+
+ if (nlockids == 0)
+ {
+ free(lockids);
+ return;
+ }
+
+ te->lockDeps = realloc(lockids, nlockids * sizeof(DumpId));
+ te->nLockDeps = nlockids;
+}
+
+/*
+ * Remove the specified TOC entry from the depCounts of items that depend on
+ * it, thereby possibly making them ready-to-run. Any pending item that
+ * becomes ready should be moved to the ready list.
+ */
+static void
+reduce_dependencies(ArchiveHandle *AH, TocEntry *te, TocEntry *ready_list)
+{
+ int i;
+
+ ahlog(AH, 2, "reducing dependencies for %d\n", te->dumpId);
+
+ for (i = 0; i < te->nRevDeps; i++)
+ {
+ TocEntry *otherte = tocsByDumpId[te->revDeps[i] - 1];
+
+ otherte->depCount--;
+ if (otherte->depCount == 0 && otherte->par_prev != NULL)
+ {
+ /* It must be in the pending list, so remove it ... */
+ par_list_remove(otherte);
+ /* ... and add to ready_list */
+ par_list_append(ready_list, otherte);
+ }
+ }
+}
+
+/*
+ * Set the created flag on the DATA member corresponding to the given
+ * TABLE member
+ */
+static void
+mark_create_done(ArchiveHandle *AH, TocEntry *te)
+{
+ TocEntry *tes;
+
+ for (tes = AH->toc->next; tes != AH->toc; tes = tes->next)
+ {
+ if (strcmp(tes->desc, "TABLE DATA") == 0 &&
+ strcmp(tes->tag, te->tag) == 0 &&
+ strcmp(tes->namespace ? tes->namespace : "",
+ te->namespace ? te->namespace : "") == 0)
+ {
+ tes->created = true;
+ break;
+ }
+ }
+}
+
+/*
+ * Mark the DATA member corresponding to the given TABLE member
+ * as not wanted
+ */
+static void
+inhibit_data_for_failed_table(ArchiveHandle *AH, TocEntry *te)
+{
+ RestoreOptions *ropt = AH->ropt;
+ TocEntry *tes;
+
+ ahlog(AH, 1, "table \"%s\" could not be created, will not restore its data\n",
+ te->tag);
+
+ for (tes = AH->toc->next; tes != AH->toc; tes = tes->next)
+ {
+ if (strcmp(tes->desc, "TABLE DATA") == 0 &&
+ strcmp(tes->tag, te->tag) == 0 &&
+ strcmp(tes->namespace ? tes->namespace : "",
+ te->namespace ? te->namespace : "") == 0)
+ {
+ /* mark it unwanted; we assume idWanted array already exists */
+ ropt->idWanted[tes->dumpId - 1] = false;
+ break;
+ }
+ }
+}
+
+
+/*
+ * Clone and de-clone routines used in parallel restoration.
+ *
+ * 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;
+
+ /* Make a "flat" copy */
+ clone = (ArchiveHandle *) malloc(sizeof(ArchiveHandle));
+ if (clone == NULL)
+ die_horribly(AH, modulename, "out of memory\n");
+ memcpy(clone, AH, sizeof(ArchiveHandle));
+
+ /* Handle format-independent fields */
+ clone->pgCopyBuf = createPQExpBuffer();
+ clone->sqlBuf = createPQExpBuffer();
+ clone->sqlparse.tagBuf = NULL;
+
+ /* The clone will have its own connection, so disregard connection state */
+ clone->connection = NULL;
+ clone->currUser = NULL;
+ clone->currSchema = NULL;
+ clone->currTablespace = NULL;
+ clone->currWithOids = -1;
+
+ /* savedPassword must be local in case we change it while connecting */
+ if (clone->savedPassword)
+ clone->savedPassword = strdup(clone->savedPassword);
+
+ /* clone has its own error count, too */
+ clone->public.n_errors = 0;
+
+ /* Let the format-specific code have a chance too */
+ (clone->ClonePtr) (clone);
+
+ return clone;
+}
+
+/*
+ * Release clone-local storage.
+ *
+ * Note: we assume any clone-local connection was already closed.
+ */
+static void
+DeCloneArchive(ArchiveHandle *AH)
+{
+ /* Clear format-specific state */
+ (AH->DeClonePtr) (AH);
+
+ /* Clear state allocated by CloneArchive */
+ destroyPQExpBuffer(AH->pgCopyBuf);
+ destroyPQExpBuffer(AH->sqlBuf);
+ if (AH->sqlparse.tagBuf)
+ destroyPQExpBuffer(AH->sqlparse.tagBuf);
+
+ /* Clear any connection-local state */
+ if (AH->currUser)
+ free(AH->currUser);
+ if (AH->currSchema)
+ free(AH->currSchema);
+ if (AH->currTablespace)
+ free(AH->currTablespace);
+ if (AH->savedPassword)
+ free(AH->savedPassword);
+
+ free(AH);
+}
projects / postgresql / blobdiff