/*
* ExecQueryUsingCursor: run a SELECT-like query using a cursor
*
* This feature allows result sets larger than RAM to be dealt with.
*
* Returns true if the query executed successfully, false otherwise.
*
* If pset.timing is on, total query time (exclusive of result-printing) is
* stored into *elapsed_msec.
*/
static bool
ExecQueryUsingCursor(const char *query, double *elapsed_msec)
{
bool OK = true;
PGresult *results;
PQExpBufferData buf;
printQueryOpt my_popt = pset.popt;
FILE *queryFout_copy = pset.queryFout;
bool queryFoutPipe_copy = pset.queryFoutPipe;
bool started_txn = false;
bool did_pager = false;
int ntuples;
char fetch_cmd[64];
instr_time before,
after;
int flush_error;
*elapsed_msec = 0;
/* initialize print options for partial table output */
my_popt.topt.start_table = true;
my_popt.topt.stop_table = false;
my_popt.topt.prior_records = 0;
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/* if we're not in a transaction, start one */
if (PQtransactionStatus(pset.db) == PQTRANS_IDLE)
{
results = PQexec(pset.db, "BEGIN");
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
PQclear(results);
if (!OK)
return false;
started_txn = true;
}
/* Send DECLARE CURSOR */
initPQExpBuffer(&buf);
appendPQExpBuffer(&buf, "DECLARE _psql_cursor NO SCROLL CURSOR FOR\n%s",
query);
results = PQexec(pset.db, buf.data);
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
PQclear(results);
termPQExpBuffer(&buf);
if (!OK)
goto cleanup;
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
snprintf(fetch_cmd, sizeof(fetch_cmd),
"FETCH FORWARD %d FROM _psql_cursor",
pset.fetch_count);
/* prepare to write output to \g argument, if any */
if (pset.gfname)
{
/* keep this code in sync with PrintQueryTuples */
pset.queryFout = stdout; /* so it doesn't get closed */
/* open file/pipe */
if (!setQFout(pset.gfname))
{
pset.queryFout = queryFout_copy;
pset.queryFoutPipe = queryFoutPipe_copy;
OK = false;
goto cleanup;
}
}
/* clear any pre-existing error indication on the output stream */
clearerr(pset.queryFout);
for (;;)
{
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/* get FETCH_COUNT tuples at a time */
results = PQexec(pset.db, fetch_cmd);
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
if (PQresultStatus(results) != PGRES_TUPLES_OK)
{
/* shut down pager before printing error message */
if (did_pager)
{
ClosePager(pset.queryFout);
pset.queryFout = queryFout_copy;
pset.queryFoutPipe = queryFoutPipe_copy;
did_pager = false;
}
OK = AcceptResult(results);
psql_assert(!OK);
PQclear(results);
break;
}
ntuples = PQntuples(results);
if (ntuples < pset.fetch_count)
{
/* this is the last result set, so allow footer decoration */
my_popt.topt.stop_table = true;
}
else if (pset.queryFout == stdout && !did_pager)
{
/*
* If query requires multiple result sets, hack to ensure that
* only one pager instance is used for the whole mess
*/
pset.queryFout = PageOutput(100000, my_popt.topt.pager);
did_pager = true;
}
printQuery(results, &my_popt, pset.queryFout, pset.logfile);
PQclear(results);
/* after the first result set, disallow header decoration */
my_popt.topt.start_table = false;
my_popt.topt.prior_records += ntuples;
/*
* Make sure to flush the output stream, so intermediate results are
* visible to the client immediately. We check the results because if
* the pager dies/exits/etc, there's no sense throwing more data at
* it.
*/
flush_error = fflush(pset.queryFout);
/*
* Check if we are at the end, if a cancel was pressed, or if there
* were any errors either trying to flush out the results, or more
* generally on the output stream at all. If we hit any errors
* writing things to the stream, we presume $PAGER has disappeared and
* stop bothering to pull down more data.
*/
if (ntuples < pset.fetch_count || cancel_pressed || flush_error ||
ferror(pset.queryFout))
break;
}
/* close \g argument file/pipe, restore old setting */
if (pset.gfname)
{
/* keep this code in sync with PrintQueryTuples */
setQFout(NULL);
pset.queryFout = queryFout_copy;
pset.queryFoutPipe = queryFoutPipe_copy;
free(pset.gfname);
pset.gfname = NULL;
}
else if (did_pager)
{
ClosePager(pset.queryFout);
pset.queryFout = queryFout_copy;
pset.queryFoutPipe = queryFoutPipe_copy;
}
cleanup:
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/*
* We try to close the cursor on either success or failure, but on failure
* ignore the result (it's probably just a bleat about being in an aborted
* transaction)
*/
results = PQexec(pset.db, "CLOSE _psql_cursor");
if (OK)
{
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
}
PQclear(results);
if (started_txn)
{
results = PQexec(pset.db, OK ? "COMMIT" : "ROLLBACK");
OK &= AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
PQclear(results);
}
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
return OK;
}
static void powa_main(Datum main_arg)
{
char *q1 = "SELECT powa_take_snapshot()";
static char *q2 = "SET application_name = 'POWA collector'";
instr_time begin;
instr_time end;
long time_to_wait;
die_on_too_small_frequency();
/*
Set up signal handlers, then unblock signalsl
*/
pqsignal(SIGHUP, powa_sighup);
pqsignal(SIGTERM, powa_sigterm);
BackgroundWorkerUnblockSignals();
/*
We only connect when powa_frequency >0. If not, powa has been deactivated
*/
if (powa_frequency < 0)
{
elog(LOG, "POWA is deactivated (powa.frequency = %i), exiting",
powa_frequency);
exit(1);
}
// We got here: it means powa_frequency > 0. Let's connect
/*
Connect to POWA database
*/
BackgroundWorkerInitializeConnection(powa_database, NULL);
elog(LOG, "POWA connected to %s", powa_database);
StartTransactionCommand();
SetCurrentStatementStartTimestamp();
SPI_connect();
PushActiveSnapshot(GetTransactionSnapshot());
SPI_execute(q2, false, 0);
SPI_finish();
PopActiveSnapshot();
CommitTransactionCommand();
/*
let's store the current time. It will be used to
calculate a quite stable interval between each measure
*/
while (!got_sigterm)
{
/*
We can get here with a new value of powa_frequency
because of a reload. Let's suicide to disconnect
if this value is <0
*/
if (powa_frequency < 0)
{
elog(LOG, "POWA exits to disconnect from the database now");
exit(1);
}
INSTR_TIME_SET_CURRENT(begin);
ResetLatch(&MyProc->procLatch);
StartTransactionCommand();
SetCurrentStatementStartTimestamp();
SPI_connect();
PushActiveSnapshot(GetTransactionSnapshot());
SPI_execute(q1, false, 0);
SPI_finish();
PopActiveSnapshot();
CommitTransactionCommand();
INSTR_TIME_SET_CURRENT(end);
INSTR_TIME_SUBTRACT(end, begin);
/*
Wait powa.frequency, compensate for work time of last snapshot
*/
/*
If we got off schedule (because of a compact or delete,
just do another operation right now
*/
time_to_wait = powa_frequency - INSTR_TIME_GET_MILLISEC(end);
if (time_to_wait > 0)
{
WaitLatch(&MyProc->procLatch,
WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
time_to_wait);
}
}
proc_exit(0);
}
/*
* ProcessUtility hook
*/
static void
pgss_ProcessUtility(Node *parsetree, const char *queryString,
ParamListInfo params, bool isTopLevel,
DestReceiver *dest, char *completionTag)
{
if (pgss_track_utility && pgss_enabled())
{
instr_time start;
instr_time duration;
uint64 rows = 0;
BufferUsage bufusage;
bufusage = pgBufferUsage;
INSTR_TIME_SET_CURRENT(start);
nested_level++;
PG_TRY();
{
if (prev_ProcessUtility)
prev_ProcessUtility(parsetree, queryString, params,
isTopLevel, dest, completionTag);
else
standard_ProcessUtility(parsetree, queryString, params,
isTopLevel, dest, completionTag);
nested_level--;
}
PG_CATCH();
{
nested_level--;
PG_RE_THROW();
}
PG_END_TRY();
INSTR_TIME_SET_CURRENT(duration);
INSTR_TIME_SUBTRACT(duration, start);
/* parse command tag to retrieve the number of affected rows. */
if (completionTag &&
sscanf(completionTag, "COPY " UINT64_FORMAT, &rows) != 1)
rows = 0;
/* calc differences of buffer counters. */
bufusage.shared_blks_hit =
pgBufferUsage.shared_blks_hit - bufusage.shared_blks_hit;
bufusage.shared_blks_read =
pgBufferUsage.shared_blks_read - bufusage.shared_blks_read;
bufusage.shared_blks_written =
pgBufferUsage.shared_blks_written - bufusage.shared_blks_written;
bufusage.local_blks_hit =
pgBufferUsage.local_blks_hit - bufusage.local_blks_hit;
bufusage.local_blks_read =
pgBufferUsage.local_blks_read - bufusage.local_blks_read;
bufusage.local_blks_written =
pgBufferUsage.local_blks_written - bufusage.local_blks_written;
bufusage.temp_blks_read =
pgBufferUsage.temp_blks_read - bufusage.temp_blks_read;
bufusage.temp_blks_written =
pgBufferUsage.temp_blks_written - bufusage.temp_blks_written;
pgss_store(queryString, INSTR_TIME_GET_DOUBLE(duration), rows,
&bufusage);
}
else
{
if (prev_ProcessUtility)
prev_ProcessUtility(parsetree, queryString, params,
isTopLevel, dest, completionTag);
else
standard_ProcessUtility(parsetree, queryString, params,
isTopLevel, dest, completionTag);
}
}
/*
* SendQuery: send the query string to the backend
* (and print out results)
*
* Note: This is the "front door" way to send a query. That is, use it to
* send queries actually entered by the user. These queries will be subject to
* single step mode.
* To send "back door" queries (generated by slash commands, etc.) in a
* controlled way, use PSQLexec().
*
* Returns true if the query executed successfully, false otherwise.
*/
bool
SendQuery(const char *query)
{
PGresult *results;
PGTransactionStatusType transaction_status;
double elapsed_msec = 0;
bool OK,
on_error_rollback_savepoint = false;
static bool on_error_rollback_warning = false;
if (!pset.db)
{
psql_error("You are currently not connected to a database.\n");
return false;
}
if (pset.singlestep)
{
char buf[3];
printf(_("***(Single step mode: verify command)*******************************************\n"
"%s\n"
"***(press return to proceed or enter x and return to cancel)********************\n"),
query);
fflush(stdout);
if (fgets(buf, sizeof(buf), stdin) != NULL)
if (buf[0] == 'x')
return false;
}
else if (pset.echo == PSQL_ECHO_QUERIES)
{
puts(query);
fflush(stdout);
}
if (pset.logfile)
{
fprintf(pset.logfile,
_("********* QUERY **********\n"
"%s\n"
"**************************\n\n"), query);
fflush(pset.logfile);
}
SetCancelConn();
transaction_status = PQtransactionStatus(pset.db);
if (transaction_status == PQTRANS_IDLE &&
!pset.autocommit &&
!command_no_begin(query))
{
results = PQexec(pset.db, "BEGIN");
if (PQresultStatus(results) != PGRES_COMMAND_OK)
{
psql_error("%s", PQerrorMessage(pset.db));
PQclear(results);
ResetCancelConn();
return false;
}
PQclear(results);
transaction_status = PQtransactionStatus(pset.db);
}
if (transaction_status == PQTRANS_INTRANS &&
pset.on_error_rollback != PSQL_ERROR_ROLLBACK_OFF &&
(pset.cur_cmd_interactive ||
pset.on_error_rollback == PSQL_ERROR_ROLLBACK_ON))
{
if (on_error_rollback_warning == false && pset.sversion < 80000)
{
fprintf(stderr, _("The server (version %d.%d) does not support savepoints for ON_ERROR_ROLLBACK.\n"),
pset.sversion / 10000, (pset.sversion / 100) % 100);
on_error_rollback_warning = true;
}
else
{
results = PQexec(pset.db, "SAVEPOINT pg_psql_temporary_savepoint");
if (PQresultStatus(results) != PGRES_COMMAND_OK)
{
psql_error("%s", PQerrorMessage(pset.db));
PQclear(results);
ResetCancelConn();
return false;
}
PQclear(results);
on_error_rollback_savepoint = true;
}
}
if (pset.fetch_count <= 0 || !is_select_command(query))
{
/* Default fetch-it-all-and-print mode */
instr_time before,
after;
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
results = PQexec(pset.db, query);
/* these operations are included in the timing result: */
ResetCancelConn();
OK = (AcceptResult(results) && ProcessCopyResult(results));
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
elapsed_msec = INSTR_TIME_GET_MILLISEC(after);
}
/* but printing results isn't: */
if (OK)
OK = PrintQueryResults(results);
}
else
{
/* Fetch-in-segments mode */
OK = ExecQueryUsingCursor(query, &elapsed_msec);
ResetCancelConn();
results = NULL; /* PQclear(NULL) does nothing */
}
/* If we made a temporary savepoint, possibly release/rollback */
if (on_error_rollback_savepoint)
{
const char *svptcmd;
transaction_status = PQtransactionStatus(pset.db);
if (transaction_status == PQTRANS_INERROR)
{
/* We always rollback on an error */
svptcmd = "ROLLBACK TO pg_psql_temporary_savepoint";
}
else if (transaction_status != PQTRANS_INTRANS)
{
/* If they are no longer in a transaction, then do nothing */
svptcmd = NULL;
}
else
{
/*
* Do nothing if they are messing with savepoints themselves: If
* the user did RELEASE or ROLLBACK, our savepoint is gone. If
* they issued a SAVEPOINT, releasing ours would remove theirs.
*/
if (results &&
(strcmp(PQcmdStatus(results), "SAVEPOINT") == 0 ||
strcmp(PQcmdStatus(results), "RELEASE") == 0 ||
strcmp(PQcmdStatus(results), "ROLLBACK") == 0))
svptcmd = NULL;
else
svptcmd = "RELEASE pg_psql_temporary_savepoint";
}
if (svptcmd)
{
PGresult *svptres;
svptres = PQexec(pset.db, svptcmd);
if (PQresultStatus(svptres) != PGRES_COMMAND_OK)
{
psql_error("%s", PQerrorMessage(pset.db));
PQclear(svptres);
PQclear(results);
ResetCancelConn();
return false;
}
PQclear(svptres);
}
}
PQclear(results);
/* Possible microtiming output */
if (OK && pset.timing)
printf(_("Time: %.3f ms\n"), elapsed_msec);
/* check for events that may occur during query execution */
if (pset.encoding != PQclientEncoding(pset.db) &&
PQclientEncoding(pset.db) >= 0)
{
/* track effects of SET CLIENT_ENCODING */
pset.encoding = PQclientEncoding(pset.db);
pset.popt.topt.encoding = pset.encoding;
SetVariable(pset.vars, "ENCODING",
pg_encoding_to_char(pset.encoding));
}
PrintNotifications();
return OK;
}
/*
* PSQLexecWatch
*
* This function is used for \watch command to send the query to
* the server and print out the results.
*
* Returns 1 if the query executed successfully, 0 if it cannot be repeated,
* e.g., because of the interrupt, -1 on error.
*/
int
PSQLexecWatch(const char *query, const printQueryOpt *opt)
{
PGresult *res;
double elapsed_msec = 0;
instr_time before;
instr_time after;
if (!pset.db)
{
psql_error("You are currently not connected to a database.\n");
return 0;
}
SetCancelConn();
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
res = PQexec(pset.db, query);
ResetCancelConn();
if (!AcceptResult(res))
{
PQclear(res);
return 0;
}
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
elapsed_msec = INSTR_TIME_GET_MILLISEC(after);
}
/*
* If SIGINT is sent while the query is processing, the interrupt
* will be consumed. The user's intention, though, is to cancel
* the entire watch process, so detect a sent cancellation request and
* exit in this case.
*/
if (cancel_pressed)
{
PQclear(res);
return 0;
}
switch (PQresultStatus(res))
{
case PGRES_TUPLES_OK:
printQuery(res, opt, pset.queryFout, pset.logfile);
break;
case PGRES_COMMAND_OK:
fprintf(pset.queryFout, "%s\n%s\n\n", opt->title, PQcmdStatus(res));
break;
case PGRES_EMPTY_QUERY:
psql_error(_("\\watch cannot be used with an empty query\n"));
PQclear(res);
return -1;
case PGRES_COPY_OUT:
case PGRES_COPY_IN:
case PGRES_COPY_BOTH:
psql_error(_("\\watch cannot be used with COPY\n"));
PQclear(res);
return -1;
default:
psql_error(_("unexpected result status for \\watch\n"));
PQclear(res);
return -1;
}
PQclear(res);
fflush(pset.queryFout);
/* Possible microtiming output */
if (pset.timing)
printf(_("Time: %.3f ms\n"), elapsed_msec);
return 1;
}
/*
* Rescan end pages to verify that they are (still) empty of tuples.
*
* Returns number of nondeletable pages (last nonempty page + 1).
*/
static BlockNumber
count_nondeletable_pages(Relation onerel, LVRelStats *vacrelstats)
{
BlockNumber blkno;
instr_time starttime;
/* Initialize the starttime if we check for conflicting lock requests */
INSTR_TIME_SET_CURRENT(starttime);
/* Strange coding of loop control is needed because blkno is unsigned */
blkno = vacrelstats->rel_pages;
while (blkno > vacrelstats->nonempty_pages)
{
Buffer buf;
Page page;
OffsetNumber offnum,
maxoff;
bool hastup;
/*
* Check if another process requests a lock on our relation. We are
* holding an AccessExclusiveLock here, so they will be waiting. We
* only do this once per VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL, and we
* only check if that interval has elapsed once every 32 blocks to
* keep the number of system calls and actual shared lock table
* lookups to a minimum.
*/
if ((blkno % 32) == 0)
{
instr_time currenttime;
instr_time elapsed;
INSTR_TIME_SET_CURRENT(currenttime);
elapsed = currenttime;
INSTR_TIME_SUBTRACT(elapsed, starttime);
if ((INSTR_TIME_GET_MICROSEC(elapsed) / 1000)
>= VACUUM_TRUNCATE_LOCK_CHECK_INTERVAL)
{
if (LockHasWaitersRelation(onerel, AccessExclusiveLock))
{
ereport(elevel,
(errmsg("\"%s\": suspending truncate due to conflicting lock request",
RelationGetRelationName(onerel))));
vacrelstats->lock_waiter_detected = true;
return blkno;
}
starttime = currenttime;
}
}
/*
* We don't insert a vacuum delay point here, because we have an
* exclusive lock on the table which we want to hold for as short a
* time as possible. We still need to check for interrupts however.
*/
CHECK_FOR_INTERRUPTS();
blkno--;
buf = ReadBufferExtended(onerel, MAIN_FORKNUM, blkno,
RBM_NORMAL, vac_strategy);
/* In this phase we only need shared access to the buffer */
LockBuffer(buf, BUFFER_LOCK_SHARE);
page = BufferGetPage(buf);
if (PageIsNew(page) || PageIsEmpty(page))
{
/* PageIsNew probably shouldn't happen... */
UnlockReleaseBuffer(buf);
continue;
}
hastup = false;
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/*
* Note: any non-unused item should be taken as a reason to keep
* this page. We formerly thought that DEAD tuples could be
* thrown away, but that's not so, because we'd not have cleaned
* out their index entries.
*/
if (ItemIdIsUsed(itemid))
{
hastup = true;
break; /* can stop scanning */
}
} /* scan along page */
UnlockReleaseBuffer(buf);
/* Done scanning if we found a tuple here */
if (hastup)
return blkno + 1;
}
/*
* If we fall out of the loop, all the previously-thought-to-be-empty
* pages still are; we need not bother to look at the last known-nonempty
* page.
*/
return vacrelstats->nonempty_pages;
}
/*
* Select next block to sample.
*
* Uses linear probing algorithm for picking next block.
*/
static BlockNumber
system_time_nextsampleblock(SampleScanState *node)
{
SystemTimeSamplerData *sampler = (SystemTimeSamplerData *) node->tsm_state;
HeapScanDesc scan = node->ss.ss_currentScanDesc;
instr_time cur_time;
/* First call within scan? */
if (sampler->doneblocks == 0)
{
/* First scan within query? */
if (sampler->step == 0)
{
/* Initialize now that we have scan descriptor */
SamplerRandomState randstate;
/* If relation is empty, there's nothing to scan */
if (scan->rs_nblocks == 0)
return InvalidBlockNumber;
/* We only need an RNG during this setup step */
sampler_random_init_state(sampler->seed, randstate);
/* Compute nblocks/firstblock/step only once per query */
sampler->nblocks = scan->rs_nblocks;
/* Choose random starting block within the relation */
/* (Actually this is the predecessor of the first block visited) */
sampler->firstblock = sampler_random_fract(randstate) *
sampler->nblocks;
/* Find relative prime as step size for linear probing */
sampler->step = random_relative_prime(sampler->nblocks, randstate);
}
/* Reinitialize lb and start_time */
sampler->lb = sampler->firstblock;
INSTR_TIME_SET_CURRENT(sampler->start_time);
}
/* If we've read all blocks in relation, we're done */
if (++sampler->doneblocks > sampler->nblocks)
return InvalidBlockNumber;
/* If we've used up all the allotted time, we're done */
INSTR_TIME_SET_CURRENT(cur_time);
INSTR_TIME_SUBTRACT(cur_time, sampler->start_time);
if (INSTR_TIME_GET_MILLISEC(cur_time) >= sampler->millis)
return InvalidBlockNumber;
/*
* It's probably impossible for scan->rs_nblocks to decrease between scans
* within a query; but just in case, loop until we select a block number
* less than scan->rs_nblocks. We don't care if scan->rs_nblocks has
* increased since the first scan.
*/
do
{
/* Advance lb, using uint64 arithmetic to forestall overflow */
sampler->lb = ((uint64) sampler->lb + sampler->step) % sampler->nblocks;
} while (sampler->lb >= scan->rs_nblocks);
return sampler->lb;
}
/*
* Like WaitLatch, but with an extra socket argument for WL_SOCKET_*
* conditions.
*
* When waiting on a socket, WL_SOCKET_READABLE *must* be included in
* 'wakeEvents'; WL_SOCKET_WRITEABLE is optional. The reason for this is
* that EOF and error conditions are reported only via WL_SOCKET_READABLE.
*/
int
WaitLatchOrSocket(volatile Latch *latch, int wakeEvents, pgsocket sock,
long timeout)
{
int result = 0;
int rc;
instr_time start_time,
cur_time;
long cur_timeout;
#ifdef HAVE_POLL
struct pollfd pfds[3];
int nfds;
#else
struct timeval tv,
*tvp;
fd_set input_mask;
fd_set output_mask;
int hifd;
#endif
/* Ignore WL_SOCKET_* events if no valid socket is given */
if (sock == PGINVALID_SOCKET)
wakeEvents &= ~(WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE);
Assert(wakeEvents != 0); /* must have at least one wake event */
/* Cannot specify WL_SOCKET_WRITEABLE without WL_SOCKET_READABLE */
Assert((wakeEvents & (WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE)) != WL_SOCKET_WRITEABLE);
if ((wakeEvents & WL_LATCH_SET) && latch->owner_pid != MyProcPid)
elog(ERROR, "cannot wait on a latch owned by another process");
/*
* Initialize timeout if requested. We must record the current time so
* that we can determine the remaining timeout if the poll() or select()
* is interrupted. (On some platforms, select() will update the contents
* of "tv" for us, but unfortunately we can't rely on that.)
*/
if (wakeEvents & WL_TIMEOUT)
{
INSTR_TIME_SET_CURRENT(start_time);
Assert(timeout >= 0);
cur_timeout = timeout;
#ifndef HAVE_POLL
tv.tv_sec = cur_timeout / 1000L;
tv.tv_usec = (cur_timeout % 1000L) * 1000L;
tvp = &tv;
#endif
}
else
{
cur_timeout = -1;
#ifndef HAVE_POLL
tvp = NULL;
#endif
}
waiting = true;
do
{
/*
* Clear the pipe, then check if the latch is set already. If someone
* sets the latch between this and the poll()/select() below, the
* setter will write a byte to the pipe (or signal us and the signal
* handler will do that), and the poll()/select() will return
* immediately.
*
* Note: we assume that the kernel calls involved in drainSelfPipe()
* and SetLatch() will provide adequate synchronization on machines
* with weak memory ordering, so that we cannot miss seeing is_set if
* the signal byte is already in the pipe when we drain it.
*/
drainSelfPipe();
if ((wakeEvents & WL_LATCH_SET) && latch->is_set)
{
result |= WL_LATCH_SET;
/*
* Leave loop immediately, avoid blocking again. We don't attempt
* to report any other events that might also be satisfied.
*/
break;
}
/* Must wait ... we use poll(2) if available, otherwise select(2) */
#ifdef HAVE_POLL
nfds = 0;
if (wakeEvents & (WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE))
{
/* socket, if used, is always in pfds[0] */
pfds[0].fd = sock;
pfds[0].events = 0;
if (wakeEvents & WL_SOCKET_READABLE)
pfds[0].events |= POLLIN;
if (wakeEvents & WL_SOCKET_WRITEABLE)
pfds[0].events |= POLLOUT;
pfds[0].revents = 0;
nfds++;
}
pfds[nfds].fd = selfpipe_readfd;
pfds[nfds].events = POLLIN;
pfds[nfds].revents = 0;
nfds++;
if (wakeEvents & WL_POSTMASTER_DEATH)
{
/* postmaster fd, if used, is always in pfds[nfds - 1] */
pfds[nfds].fd = postmaster_alive_fds[POSTMASTER_FD_WATCH];
pfds[nfds].events = POLLIN;
pfds[nfds].revents = 0;
nfds++;
}
/* Sleep */
rc = poll(pfds, nfds, (int) cur_timeout);
/* Check return code */
if (rc < 0)
{
/* EINTR is okay, otherwise complain */
if (errno != EINTR)
{
waiting = false;
ereport(ERROR,
(errcode_for_socket_access(),
errmsg("poll() failed: %m")));
}
}
else if (rc == 0)
{
/* timeout exceeded */
if (wakeEvents & WL_TIMEOUT)
result |= WL_TIMEOUT;
}
else
{
/* at least one event occurred, so check revents values */
if ((wakeEvents & WL_SOCKET_READABLE) &&
(pfds[0].revents & (POLLIN | POLLHUP | POLLERR | POLLNVAL)))
{
/* data available in socket, or EOF/error condition */
result |= WL_SOCKET_READABLE;
}
if ((wakeEvents & WL_SOCKET_WRITEABLE) &&
(pfds[0].revents & POLLOUT))
{
result |= WL_SOCKET_WRITEABLE;
}
/*
* We expect a POLLHUP when the remote end is closed, but because
* we don't expect the pipe to become readable or to have any
* errors either, treat those cases as postmaster death, too.
*/
if ((wakeEvents & WL_POSTMASTER_DEATH) &&
(pfds[nfds - 1].revents & (POLLHUP | POLLIN | POLLERR | POLLNVAL)))
{
/*
* According to the select(2) man page on Linux, select(2) may
* spuriously return and report a file descriptor as readable,
* when it's not; and presumably so can poll(2). It's not
* clear that the relevant cases would ever apply to the
* postmaster pipe, but since the consequences of falsely
* returning WL_POSTMASTER_DEATH could be pretty unpleasant,
* we take the trouble to positively verify EOF with
* PostmasterIsAlive().
*/
if (!PostmasterIsAlive())
result |= WL_POSTMASTER_DEATH;
}
}
#else /* !HAVE_POLL */
FD_ZERO(&input_mask);
FD_ZERO(&output_mask);
FD_SET(selfpipe_readfd, &input_mask);
hifd = selfpipe_readfd;
if (wakeEvents & WL_POSTMASTER_DEATH)
{
FD_SET(postmaster_alive_fds[POSTMASTER_FD_WATCH], &input_mask);
if (postmaster_alive_fds[POSTMASTER_FD_WATCH] > hifd)
hifd = postmaster_alive_fds[POSTMASTER_FD_WATCH];
}
if (wakeEvents & WL_SOCKET_READABLE)
{
FD_SET(sock, &input_mask);
if (sock > hifd)
hifd = sock;
}
if (wakeEvents & WL_SOCKET_WRITEABLE)
{
FD_SET(sock, &output_mask);
if (sock > hifd)
hifd = sock;
}
/* Sleep */
rc = select(hifd + 1, &input_mask, &output_mask, NULL, tvp);
/* Check return code */
if (rc < 0)
{
/* EINTR is okay, otherwise complain */
if (errno != EINTR)
{
waiting = false;
ereport(ERROR,
(errcode_for_socket_access(),
errmsg("select() failed: %m")));
}
}
else if (rc == 0)
{
/* timeout exceeded */
if (wakeEvents & WL_TIMEOUT)
result |= WL_TIMEOUT;
}
else
{
/* at least one event occurred, so check masks */
if ((wakeEvents & WL_SOCKET_READABLE) && FD_ISSET(sock, &input_mask))
{
/* data available in socket, or EOF */
result |= WL_SOCKET_READABLE;
}
if ((wakeEvents & WL_SOCKET_WRITEABLE) && FD_ISSET(sock, &output_mask))
{
result |= WL_SOCKET_WRITEABLE;
}
if ((wakeEvents & WL_POSTMASTER_DEATH) &&
FD_ISSET(postmaster_alive_fds[POSTMASTER_FD_WATCH], &input_mask))
{
/*
* According to the select(2) man page on Linux, select(2) may
* spuriously return and report a file descriptor as readable,
* when it's not; and presumably so can poll(2). It's not
* clear that the relevant cases would ever apply to the
* postmaster pipe, but since the consequences of falsely
* returning WL_POSTMASTER_DEATH could be pretty unpleasant,
* we take the trouble to positively verify EOF with
* PostmasterIsAlive().
*/
if (!PostmasterIsAlive())
result |= WL_POSTMASTER_DEATH;
}
}
#endif /* HAVE_POLL */
/* If we're not done, update cur_timeout for next iteration */
if (result == 0 && cur_timeout >= 0)
{
INSTR_TIME_SET_CURRENT(cur_time);
INSTR_TIME_SUBTRACT(cur_time, start_time);
cur_timeout = timeout - (long) INSTR_TIME_GET_MILLISEC(cur_time);
if (cur_timeout < 0)
cur_timeout = 0;
#ifndef HAVE_POLL
tv.tv_sec = cur_timeout / 1000L;
tv.tv_usec = (cur_timeout % 1000L) * 1000L;
#endif
}
} while (result == 0);
waiting = false;
return result;
}
/*
* ExecQueryUsingCursor: run a SELECT-like query using a cursor
*
* This feature allows result sets larger than RAM to be dealt with.
*
* Returns true if the query executed successfully, false otherwise.
*
* If pset.timing is on, total query time (exclusive of result-printing) is
* stored into *elapsed_msec.
*/
static bool
ExecQueryUsingCursor(const char *query, double *elapsed_msec)
{
bool OK = true;
PGresult *results;
PQExpBufferData buf;
printQueryOpt my_popt = pset.popt;
FILE *fout;
bool is_pipe;
bool is_pager = false;
bool started_txn = false;
int ntuples;
int fetch_count;
char fetch_cmd[64];
instr_time before,
after;
int flush_error;
*elapsed_msec = 0;
/* initialize print options for partial table output */
my_popt.topt.start_table = true;
my_popt.topt.stop_table = false;
my_popt.topt.prior_records = 0;
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/* if we're not in a transaction, start one */
if (PQtransactionStatus(pset.db) == PQTRANS_IDLE)
{
results = PQexec(pset.db, "BEGIN");
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
ClearOrSaveResult(results);
if (!OK)
return false;
started_txn = true;
}
/* Send DECLARE CURSOR */
initPQExpBuffer(&buf);
appendPQExpBuffer(&buf, "DECLARE _psql_cursor NO SCROLL CURSOR FOR\n%s",
query);
results = PQexec(pset.db, buf.data);
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
ClearOrSaveResult(results);
termPQExpBuffer(&buf);
if (!OK)
goto cleanup;
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
/*
* In \gset mode, we force the fetch count to be 2, so that we will throw
* the appropriate error if the query returns more than one row.
*/
if (pset.gset_prefix)
fetch_count = 2;
else
fetch_count = pset.fetch_count;
snprintf(fetch_cmd, sizeof(fetch_cmd),
"FETCH FORWARD %d FROM _psql_cursor",
fetch_count);
/* prepare to write output to \g argument, if any */
if (pset.gfname)
{
if (!openQueryOutputFile(pset.gfname, &fout, &is_pipe))
{
OK = false;
goto cleanup;
}
if (is_pipe)
disable_sigpipe_trap();
}
else
{
fout = pset.queryFout;
is_pipe = false; /* doesn't matter */
}
/* clear any pre-existing error indication on the output stream */
clearerr(fout);
for (;;)
{
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/* get fetch_count tuples at a time */
results = PQexec(pset.db, fetch_cmd);
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
if (PQresultStatus(results) != PGRES_TUPLES_OK)
{
/* shut down pager before printing error message */
if (is_pager)
{
ClosePager(fout);
is_pager = false;
}
OK = AcceptResult(results);
Assert(!OK);
ClearOrSaveResult(results);
break;
}
if (pset.gset_prefix)
{
/* StoreQueryTuple will complain if not exactly one row */
OK = StoreQueryTuple(results);
ClearOrSaveResult(results);
break;
}
/* Note we do not deal with \gexec or \crosstabview modes here */
ntuples = PQntuples(results);
if (ntuples < fetch_count)
{
/* this is the last result set, so allow footer decoration */
my_popt.topt.stop_table = true;
}
else if (fout == stdout && !is_pager)
{
/*
* If query requires multiple result sets, hack to ensure that
* only one pager instance is used for the whole mess
*/
fout = PageOutput(INT_MAX, &(my_popt.topt));
is_pager = true;
}
printQuery(results, &my_popt, fout, is_pager, pset.logfile);
ClearOrSaveResult(results);
/* after the first result set, disallow header decoration */
my_popt.topt.start_table = false;
my_popt.topt.prior_records += ntuples;
/*
* Make sure to flush the output stream, so intermediate results are
* visible to the client immediately. We check the results because if
* the pager dies/exits/etc, there's no sense throwing more data at
* it.
*/
flush_error = fflush(fout);
/*
* Check if we are at the end, if a cancel was pressed, or if there
* were any errors either trying to flush out the results, or more
* generally on the output stream at all. If we hit any errors
* writing things to the stream, we presume $PAGER has disappeared and
* stop bothering to pull down more data.
*/
if (ntuples < fetch_count || cancel_pressed || flush_error ||
ferror(fout))
break;
}
if (pset.gfname)
{
/* close \g argument file/pipe */
if (is_pipe)
{
pclose(fout);
restore_sigpipe_trap();
}
else
fclose(fout);
}
else if (is_pager)
{
/* close transient pager */
ClosePager(fout);
}
cleanup:
if (pset.timing)
INSTR_TIME_SET_CURRENT(before);
/*
* We try to close the cursor on either success or failure, but on failure
* ignore the result (it's probably just a bleat about being in an aborted
* transaction)
*/
results = PQexec(pset.db, "CLOSE _psql_cursor");
if (OK)
{
OK = AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
ClearOrSaveResult(results);
}
else
PQclear(results);
if (started_txn)
{
results = PQexec(pset.db, OK ? "COMMIT" : "ROLLBACK");
OK &= AcceptResult(results) &&
(PQresultStatus(results) == PGRES_COMMAND_OK);
ClearOrSaveResult(results);
}
if (pset.timing)
{
INSTR_TIME_SET_CURRENT(after);
INSTR_TIME_SUBTRACT(after, before);
*elapsed_msec += INSTR_TIME_GET_MILLISEC(after);
}
return OK;
}