On 30.06.2011 09:36, Fujii Masao wrote:
On Sat, Jun 25, 2011 at 10:41 AM, Peter Geoghegan<pe...@2ndquadrant.com> wrote:
Attached is patch that addresses Fujii's third and most recent set of concerns.
Thanks for updating the patch!
I think that Heikki is currently taking another look at my work,
because he indicates in a new message to the list a short time ago
that while reviewing my patch, he realised that there may be an
independent problem with silent_mode. I will wait for his remarks
before producing another version of the patch that incorporates those
two small changes.
Yes, we should wait for the comments from Heikki. But, I have another
comments;
Here's a WIP patch with some mostly cosmetic changes I've done this far.
I haven't tested the Windows code at all yet. It seems that no-one is
objecting to removing silent_mode altogether, so I'm going to do that
before committing this patch.
--
Heikki Linnakangas
EnterpriseDB http://www.enterprisedb.com
diff --git a/src/backend/access/transam/xlog.c b/src/backend/access/transam/xlog.c
index a7f5373..155acea 100644
--- a/src/backend/access/transam/xlog.c
+++ b/src/backend/access/transam/xlog.c
@@ -10165,7 +10165,7 @@ retry:
/*
* Wait for more WAL to arrive, or timeout to be reached
*/
- WaitLatch(&XLogCtl->recoveryWakeupLatch, 5000000L);
+ WaitLatch(&XLogCtl->recoveryWakeupLatch, WL_LATCH_SET | WL_TIMEOUT, 5000000L);
ResetLatch(&XLogCtl->recoveryWakeupLatch);
}
else
diff --git a/src/backend/port/unix_latch.c b/src/backend/port/unix_latch.c
index 6dae7c9..1a2e141 100644
--- a/src/backend/port/unix_latch.c
+++ b/src/backend/port/unix_latch.c
@@ -93,6 +93,7 @@
#endif
#include "miscadmin.h"
+#include "postmaster/postmaster.h"
#include "storage/latch.h"
#include "storage/shmem.h"
@@ -179,31 +180,32 @@ DisownLatch(volatile Latch *latch)
* Wait for given latch to be set or until timeout is exceeded.
* If the latch is already set, the function returns immediately.
*
- * The 'timeout' is given in microseconds, and -1 means wait forever.
- * On some platforms, signals cause the timeout to be restarted, so beware
- * that the function can sleep for several times longer than the specified
- * timeout.
+ * The 'timeout' is given in microseconds. It must be >= 0 if WL_TIMEOUT
+ * event is given, otherwise it is ignored. On some platforms, signals cause
+ * the timeout to be restarted, so beware that the function can sleep for
+ * several times longer than the specified timeout.
*
* The latch must be owned by the current process, ie. it must be a
* backend-local latch initialized with InitLatch, or a shared latch
* associated with the current process by calling OwnLatch.
*
- * Returns 'true' if the latch was set, or 'false' if timeout was reached.
+ * Returns bit field indicating which condition(s) caused the wake-up. Note
+ * that if multiple wake-up conditions are true, there is no guarantee that
+ * we return all of them in one call, but we will return at least one.
*/
-bool
-WaitLatch(volatile Latch *latch, long timeout)
+int
+WaitLatch(volatile Latch *latch, int wakeEvents, long timeout)
{
- return WaitLatchOrSocket(latch, PGINVALID_SOCKET, false, false, timeout) > 0;
+ return WaitLatchOrSocket(latch, wakeEvents, PGINVALID_SOCKET, timeout);
}
/*
- * Like WaitLatch, but will also return when there's data available in
- * 'sock' for reading or writing. Returns 0 if timeout was reached,
- * 1 if the latch was set, 2 if the socket became readable or writable.
+ * Like WaitLatch, but with an extra socket argument for WL_SOCKET_*
+ * conditions.
*/
int
-WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
- bool forWrite, long timeout)
+WaitLatchOrSocket(volatile Latch *latch, int wakeEvents, pgsocket sock,
+ long timeout)
{
struct timeval tv,
*tvp = NULL;
@@ -212,19 +214,26 @@ WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
int rc;
int result = 0;
+ Assert(wakeEvents != 0);
+
+ /* Ignore WL_SOCKET_* events if no valid socket is given */
+ if (sock == PGINVALID_SOCKET)
+ wakeEvents &= ~(WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE);
+
if (latch->owner_pid != MyProcPid)
elog(ERROR, "cannot wait on a latch owned by another process");
/* Initialize timeout */
- if (timeout >= 0)
+ if (wakeEvents & WL_TIMEOUT)
{
+ Assert(timeout >= 0);
tv.tv_sec = timeout / 1000000L;
tv.tv_usec = timeout % 1000000L;
tvp = &tv;
}
waiting = true;
- for (;;)
+ do
{
int hifd;
@@ -235,16 +244,28 @@ WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
* do that), and the select() will return immediately.
*/
drainSelfPipe();
- if (latch->is_set)
+ if (latch->is_set && (wakeEvents & WL_LATCH_SET))
{
- result = 1;
+ 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;
}
FD_ZERO(&input_mask);
FD_SET(selfpipe_readfd, &input_mask);
hifd = selfpipe_readfd;
- if (sock != PGINVALID_SOCKET && forRead)
+
+ 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)
@@ -252,7 +273,7 @@ WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
}
FD_ZERO(&output_mask);
- if (sock != PGINVALID_SOCKET && forWrite)
+ if (wakeEvents & WL_SOCKET_WRITEABLE)
{
FD_SET(sock, &output_mask);
if (sock > hifd)
@@ -268,20 +289,26 @@ WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
(errcode_for_socket_access(),
errmsg("select() failed: %m")));
}
- if (rc == 0)
+ if (rc == 0 && (wakeEvents & WL_TIMEOUT))
{
/* timeout exceeded */
- result = 0;
- break;
+ result |= WL_TIMEOUT;
}
- if (sock != PGINVALID_SOCKET &&
- ((forRead && FD_ISSET(sock, &input_mask)) ||
- (forWrite && FD_ISSET(sock, &output_mask))))
+ if ((wakeEvents & WL_SOCKET_READABLE) && FD_ISSET(sock, &input_mask))
{
- result = 2;
- break; /* data available in socket */
+ /* data available in socket */
+ 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))
+ {
+ result |= WL_POSTMASTER_DEATH;
+ }
+ } while(result == 0);
waiting = false;
return result;
diff --git a/src/backend/port/win32_latch.c b/src/backend/port/win32_latch.c
index 4bcf7b7..fc97323 100644
--- a/src/backend/port/win32_latch.c
+++ b/src/backend/port/win32_latch.c
@@ -23,6 +23,7 @@
#include <unistd.h>
#include "miscadmin.h"
+#include "postmaster/postmaster.h"
#include "replication/walsender.h"
#include "storage/latch.h"
#include "storage/shmem.h"
@@ -81,43 +82,66 @@ DisownLatch(volatile Latch *latch)
latch->owner_pid = 0;
}
-bool
-WaitLatch(volatile Latch *latch, long timeout)
+int
+WaitLatch(volatile Latch *latch, int wakeEvents, long timeout)
{
- return WaitLatchOrSocket(latch, PGINVALID_SOCKET, false, false, timeout) > 0;
+ return WaitLatchOrSocket(latch, wakeEvents, PGINVALID_SOCKET, timeout);
}
int
-WaitLatchOrSocket(volatile Latch *latch, SOCKET sock, bool forRead,
- bool forWrite, long timeout)
+WaitLatchOrSocket(volatile Latch *latch, int wakeEvents, SOCKET sock, long timeout)
{
DWORD rc;
- HANDLE events[3];
+ HANDLE events[4];
HANDLE latchevent;
- HANDLE sockevent = WSA_INVALID_EVENT; /* silence compiler */
+ HANDLE sockevent = WSA_INVALID_EVENT;
int numevents;
int result = 0;
+ int pmdeath_eventno;
+ long timeout_ms;
+
+ Assert(wakeEvents != 0);
+
+ /* Ignore WL_SOCKET_* events if no valid socket is given */
+ if (sock == PGINVALID_SOCKET)
+ wakeEvents &= ~(WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE);
+
+ /* Convert timeout to milliseconds for WaitForMultipleObjects() */
+ if ((wakeEvents & WL_TIMEOUT) != 0)
+ {
+ Assert(timeout >= 0);
+ timeout_ms = timeout / 1000;
+ }
+ else
+ timeout_ms = INFINITE;
+ /* Construct an array of event handles for WaitforMultipleObjects() */
latchevent = latch->event;
events[0] = latchevent;
events[1] = pgwin32_signal_event;
numevents = 2;
- if (sock != PGINVALID_SOCKET && (forRead || forWrite))
+ if (((wakeEvents & WL_SOCKET_READABLE) ||
+ (wakeEvents & WL_SOCKET_WRITEABLE)))
{
int flags = 0;
- if (forRead)
+ if (wakeEvents & WL_SOCKET_READABLE)
flags |= FD_READ;
- if (forWrite)
+ if (wakeEvents & WL_SOCKET_WRITEABLE)
flags |= FD_WRITE;
sockevent = WSACreateEvent();
WSAEventSelect(sock, sockevent, flags);
events[numevents++] = sockevent;
}
+ if (wakeEvents & WL_POSTMASTER_DEATH)
+ {
+ pmdeath_eventno = numevents;
+ events[numevents++] = PostmasterHandle;
+ }
- for (;;)
+ do
{
/*
* Reset the event, and check if the latch is set already. If someone
@@ -127,45 +151,64 @@ WaitLatchOrSocket(volatile Latch *latch, SOCKET sock, bool forRead,
*/
if (!ResetEvent(latchevent))
elog(ERROR, "ResetEvent failed: error code %d", (int) GetLastError());
- if (latch->is_set)
+ if (latch->is_set && (wakeEvents & WL_LATCH_SET))
{
- result = 1;
+ 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;
}
- rc = WaitForMultipleObjects(numevents, events, FALSE,
- (timeout >= 0) ? (timeout / 1000) : INFINITE);
+ rc = WaitForMultipleObjects(numevents, events, FALSE, timeout_ms);
+
if (rc == WAIT_FAILED)
elog(ERROR, "WaitForMultipleObjects() failed: error code %d", (int) GetLastError());
+
+ /* Participate in the Windows signal emulation */
+ else if (rc == WAIT_OBJECT_0 + 1)
+ pgwin32_dispatch_queued_signals();
+
+ else if ((wakeEvents & WL_POSTMASTER_DEATH) &&
+ rc == WAIT_OBJECT_0 + pmdeath_eventno)
+ {
+ /* Postmaster died */
+ result |= WL_POSTMASTER_DEATH;
+ }
else if (rc == WAIT_TIMEOUT)
{
- result = 0;
- break;
+ result |= WL_TIMEOUT;
}
- else if (rc == WAIT_OBJECT_0 + 1)
- pgwin32_dispatch_queued_signals();
- else if (rc == WAIT_OBJECT_0 + 2)
+ else if (wakeEvents & (WL_SOCKET_READABLE | WL_SOCKET_WRITEABLE) != 0 &&
+ rc == WAIT_OBJECT_0 + 2) /* socket is at event slot 2 */
{
WSANETWORKEVENTS resEvents;
- Assert(sock != PGINVALID_SOCKET);
-
ZeroMemory(&resEvents, sizeof(resEvents));
if (WSAEnumNetworkEvents(sock, sockevent, &resEvents) == SOCKET_ERROR)
ereport(FATAL,
(errmsg_internal("failed to enumerate network events: %i", (int) GetLastError())));
- if ((forRead && resEvents.lNetworkEvents & FD_READ) ||
- (forWrite && resEvents.lNetworkEvents & FD_WRITE))
- result = 2;
- break;
+ if ((wakeEvents & WL_SOCKET_READABLE) &&
+ (resEvents.lNetworkEvents & FD_READ))
+ {
+ result |= WL_SOCKET_READABLE;
+ }
+ if ((wakeEvents & WL_SOCKET_WRITEABLE) &&
+ (resEvents.lNetworkEvents & FD_WRITE))
+ {
+ result |= WL_SOCKET_WRITEABLE;
+ }
}
+ /* Otherwise it must be the latch event */
else if (rc != WAIT_OBJECT_0)
elog(ERROR, "unexpected return code from WaitForMultipleObjects(): %d", (int) rc);
}
+ while(result == 0);
/* Clean up the handle we created for the socket */
- if (sock != PGINVALID_SOCKET && (forRead || forWrite))
+ if (sockevent != WSA_INVALID_EVENT)
{
WSAEventSelect(sock, sockevent, 0);
WSACloseEvent(sockevent);
diff --git a/src/backend/postmaster/fork_process.c b/src/backend/postmaster/fork_process.c
index b2fe9a1..db9401a 100644
--- a/src/backend/postmaster/fork_process.c
+++ b/src/backend/postmaster/fork_process.c
@@ -11,6 +11,8 @@
*/
#include "postgres.h"
#include "postmaster/fork_process.h"
+#include "postmaster/postmaster.h"
+
#include <fcntl.h>
#include <time.h>
@@ -19,13 +21,14 @@
#include <unistd.h>
#ifndef WIN32
+
/*
* Wrapper for fork(). Return values are the same as those for fork():
* -1 if the fork failed, 0 in the child process, and the PID of the
* child in the parent process.
*/
pid_t
-fork_process(void)
+do_fork_process(bool remain_postmaster)
{
pid_t result;
@@ -61,6 +64,17 @@ fork_process(void)
#ifdef LINUX_PROFILE
setitimer(ITIMER_PROF, &prof_itimer, NULL);
#endif
+ /*
+ * Usually, we're forking to create a new, distinct process. That process
+ * should release the postmaster death watch handle, which is required by
+ * the implementation, as described in unix_latch.c.
+ *
+ * Less frequently, we want to fork for some other reason (such as for
+ * silent_mode), and the child process is intended to become the new
+ * postmaster. It should therefore retain the death watch handle.
+ */
+ if (!remain_postmaster)
+ ReleasePostmasterDeathWatchHandle();
/*
* By default, Linux tends to kill the postmaster in out-of-memory
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index b40375a..a56fe92 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -40,6 +40,7 @@
#include "postmaster/postmaster.h"
#include "storage/fd.h"
#include "storage/ipc.h"
+#include "storage/latch.h"
#include "storage/pg_shmem.h"
#include "storage/pmsignal.h"
#include "utils/guc.h"
@@ -87,6 +88,12 @@ static volatile sig_atomic_t got_SIGTERM = false;
static volatile sig_atomic_t wakened = false;
static volatile sig_atomic_t ready_to_stop = false;
+/*
+ * Latch that archiver loop waits on until it is awakened by
+ * signals, each of which there is a handler for
+ */
+static volatile Latch mainloop_latch;
+
/* ----------
* Local function forward declarations
* ----------
@@ -228,6 +235,8 @@ PgArchiverMain(int argc, char *argv[])
MyProcPid = getpid(); /* reset MyProcPid */
+ InitLatch(&mainloop_latch); /* initialise latch used in main loop, now that we are a subprocess */
+
MyStartTime = time(NULL); /* record Start Time for logging */
/*
@@ -282,6 +291,8 @@ ArchSigHupHandler(SIGNAL_ARGS)
{
/* set flag to re-read config file at next convenient time */
got_SIGHUP = true;
+ /* Let the waiting loop iterate */
+ SetLatch(&mainloop_latch);
}
/* SIGTERM signal handler for archiver process */
@@ -295,6 +306,8 @@ ArchSigTermHandler(SIGNAL_ARGS)
* archive commands.
*/
got_SIGTERM = true;
+ /* Let the waiting loop iterate */
+ SetLatch(&mainloop_latch);
}
/* SIGUSR1 signal handler for archiver process */
@@ -303,6 +316,8 @@ pgarch_waken(SIGNAL_ARGS)
{
/* set flag that there is work to be done */
wakened = true;
+ /* Let the waiting loop iterate */
+ SetLatch(&mainloop_latch);
}
/* SIGUSR2 signal handler for archiver process */
@@ -311,6 +326,8 @@ pgarch_waken_stop(SIGNAL_ARGS)
{
/* set flag to do a final cycle and shut down afterwards */
ready_to_stop = true;
+ /* Let the waiting loop iterate */
+ SetLatch(&mainloop_latch);
}
/*
@@ -334,6 +351,13 @@ pgarch_MainLoop(void)
do
{
+ /*
+ * There shouldn't be anything for the archiver to do except to wait
+ * on a latch ... however, the archiver exists to protect our data,
+ * so she wakes up occasionally to allow herself to be proactive.
+ */
+ ResetLatch(&mainloop_latch);
+
/* When we get SIGUSR2, we do one more archive cycle, then exit */
time_to_stop = ready_to_stop;
@@ -371,25 +395,27 @@ pgarch_MainLoop(void)
}
/*
- * There shouldn't be anything for the archiver to do except to wait
- * for a signal ... however, the archiver exists to protect our data,
- * so she wakes up occasionally to allow herself to be proactive.
+ * Wait on latch, until various signals are received, or
+ * until a poll will be forced by PGARCH_AUTOWAKE_INTERVAL
+ * having passed since last_copy_time, or on the postmaster's
+ * untimely demise.
*
- * On some platforms, signals won't interrupt the sleep. To ensure we
- * respond reasonably promptly when someone signals us, break down the
- * sleep into 1-second increments, and check for interrupts after each
- * nap.
+ * The caveat about signals resetting the timeout of
+ * WaitLatch()/select() on some platforms can be safely disregarded,
+ * because we handle all expected signals, and all handlers
+ * call SetLatch() where that matters anyway
*/
- while (!(wakened || ready_to_stop || got_SIGHUP ||
- !PostmasterIsAlive(true)))
- {
- time_t curtime;
- pg_usleep(1000000L);
+ if (!time_to_stop) /* Don't wait during last iteration */
+ {
+ time_t curtime = time(NULL);
+ unsigned int timeout_secs = (unsigned int) PGARCH_AUTOWAKE_INTERVAL -
+ (unsigned int) (curtime - last_copy_time);
+ WaitLatch(&mainloop_latch, WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH, timeout_secs * 1000000L);
curtime = time(NULL);
if ((unsigned int) (curtime - last_copy_time) >=
(unsigned int) PGARCH_AUTOWAKE_INTERVAL)
- wakened = true;
+ wakened = true; /* wakened by timeout - this wasn't a SIGHUP, etc */
}
/*
diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 6572292..1ec4fda 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -443,6 +443,7 @@ typedef struct
HANDLE syslogPipe[2];
#else
int syslogPipe[2];
+ int postmaster_alive_fds[2];
#endif
char my_exec_path[MAXPGPATH];
char pkglib_path[MAXPGPATH];
@@ -472,6 +473,13 @@ static void ShmemBackendArrayRemove(Backend *bn);
#define EXIT_STATUS_0(st) ((st) == 0)
#define EXIT_STATUS_1(st) (WIFEXITED(st) && WEXITSTATUS(st) == 1)
+/*
+ * 2 file descriptors that monitoring if postmaster is alive.
+ * First is POSTMASTER_FD_WATCH, second is POSTMASTER_FD_OWN.
+ */
+#ifndef WIN32
+int postmaster_alive_fds[2] = { -1, -1 };
+#endif
/*
* Postmaster main entry point
@@ -998,6 +1006,12 @@ PostmasterMain(int argc, char *argv[])
ereport(FATAL,
(errmsg_internal("could not duplicate postmaster handle: error code %d",
(int) GetLastError())));
+#else
+ /*
+ * Initialise mechanism that allows waiting latch clients to wake on
+ * postmaster death, to finish their remaining business
+ */
+ InitPostmasterDeathWatchHandle();
#endif
/*
@@ -1312,7 +1326,7 @@ pmdaemonize(void)
/*
* Okay to fork.
*/
- pid = fork_process();
+ pid = fork_process_remain_postmaster();
if (pid == (pid_t) -1)
{
write_stderr("%s: could not fork background process: %s\n",
@@ -4758,6 +4772,9 @@ save_backend_variables(BackendParameters *param, Port *port,
memcpy(¶m->syslogPipe, &syslogPipe, sizeof(syslogPipe));
+#ifndef WIN32
+ memcpy(¶m->postmaster_alive_fds, &postmaster_alive_fds, sizeof(postmaster_alive_fds));
+#endif
strlcpy(param->my_exec_path, my_exec_path, MAXPGPATH);
strlcpy(param->pkglib_path, pkglib_path, MAXPGPATH);
@@ -4973,6 +4990,10 @@ restore_backend_variables(BackendParameters *param, Port *port)
memcpy(&syslogPipe, ¶m->syslogPipe, sizeof(syslogPipe));
+#ifndef WIN32
+ memcpy(&postmaster_alive_fds, ¶m->postmaster_alive_fds, sizeof(postmaster_alive_fds));
+#endif
+
strlcpy(my_exec_path, param->my_exec_path, MAXPGPATH);
strlcpy(pkglib_path, param->pkglib_path, MAXPGPATH);
@@ -5088,5 +5109,79 @@ pgwin32_deadchild_callback(PVOID lpParameter, BOOLEAN TimerOrWaitFired)
/* Queue SIGCHLD signal */
pg_queue_signal(SIGCHLD);
}
+#else
+/*
+ * Initialise one and only handle for monitoring postmaster death.
+ *
+ * Called once from the postmaster, so that child processes can subsequently
+ * monitor if their parent is dead. We open up an anoymous pipe, and have child
+ * processes block on a select() call that examines if the read file descriptor
+ * is ready for reading. They do so through a latch.
+ *
+ * Child processes are responsible for releasing the death watch handler, so
+ * that only the postmaster holds it, and a select() on the fd returns upon the
+ * one and only holder (the postmaster) dying.
+ *
+ * This is a trick that obviates the need for auxiliary backends to have tight
+ * polling loops where they check if the postmaster is alive. We do this because
+ * that pattern results in an excessive number of wakeups per second when idle.
+ */
+void
+InitPostmasterDeathWatchHandle(void)
+{
+ /*
+ * Create pipe. The postmaster is deemed dead if
+ * no process has the writing end (POSTMASTER_FD_OWN) open.
+ */
+ Assert(MyProcPid == PostmasterPid);
+ if (pipe(postmaster_alive_fds))
+ {
+ ereport(FATAL,
+ (errcode_for_socket_access(),
+ errmsg( "pipe() call failed to create pipe to monitor postmaster death: %m")));
+ }
+ /*
+ * Set O_NONBLOCK to allow checking for the fd's presence with a select() call
+ */
+ if (fcntl(postmaster_alive_fds[POSTMASTER_FD_WATCH], F_SETFL, O_NONBLOCK))
+ {
+ ereport(FATAL,
+ (errcode_for_socket_access(),
+ errmsg("failed to set the postmaster death watching fd's flags: %m")));
+ }
+}
-#endif /* WIN32 */
+/*
+ * Release postmaster death watch handle.
+ *
+ * Important: This must be called immediately after a process
+ * forks from the postmaster. Otherwise, latch clients will
+ * not wake up on postmaster death, even if they have requested
+ * to.
+ *
+ * Even some hypothetical backend that doesn't care about postmaster
+ * death has a responsibility to call this function - otherwise,
+ * some other latch client backend could wait in vain to be informed
+ * of postmaster death, because the irresponsible backend held open
+ * the ownership file descriptor and outlived the postmaster.
+ *
+ * We call this function within the fork machinery to handle all cases,
+ * so backends need not bother with it themselves.
+ */
+void
+ReleasePostmasterDeathWatchHandle(void)
+{
+ /* MyProcPid won't have been set yet */
+ Assert(PostmasterPid != getpid());
+ /* Please don't ask twice */
+ Assert(postmaster_alive_fds[POSTMASTER_FD_OWN] != -1);
+ /* Release parent's ownership fd - only postmaster should hold it */
+ if (close(postmaster_alive_fds[POSTMASTER_FD_OWN]))
+ {
+ ereport(FATAL,
+ (errcode_for_socket_access(),
+ errmsg("failed to close file descriptor associated with postmaster death in child process")));
+ }
+ postmaster_alive_fds[POSTMASTER_FD_OWN] = -1;
+}
+#endif
diff --git a/src/backend/replication/syncrep.c b/src/backend/replication/syncrep.c
index 2b52d16..7cf6206 100644
--- a/src/backend/replication/syncrep.c
+++ b/src/backend/replication/syncrep.c
@@ -171,7 +171,7 @@ SyncRepWaitForLSN(XLogRecPtr XactCommitLSN)
* postmaster death regularly while waiting. Note that timeout here
* does not necessarily release from loop.
*/
- WaitLatch(&MyProc->waitLatch, 60000000L);
+ WaitLatch(&MyProc->waitLatch, WL_LATCH_SET | WL_TIMEOUT, 60000000L);
/* Must reset the latch before testing state. */
ResetLatch(&MyProc->waitLatch);
diff --git a/src/backend/replication/walsender.c b/src/backend/replication/walsender.c
index 470e6d1..090b831 100644
--- a/src/backend/replication/walsender.c
+++ b/src/backend/replication/walsender.c
@@ -779,6 +779,7 @@ WalSndLoop(void)
{
TimestampTz finish_time = 0;
long sleeptime;
+ int wakeEvents;
/* Reschedule replication timeout */
if (replication_timeout > 0)
@@ -805,9 +806,11 @@ WalSndLoop(void)
}
/* Sleep */
- WaitLatchOrSocket(&MyWalSnd->latch, MyProcPort->sock,
- true, pq_is_send_pending(),
- sleeptime * 1000L);
+ wakeEvents = WL_LATCH_SET | WL_SOCKET_READABLE | WL_TIMEOUT;
+ if (pq_is_send_pending())
+ wakeEvents |= WL_SOCKET_WRITEABLE;
+ WaitLatchOrSocket(&MyWalSnd->latch, wakeEvents,
+ MyProcPort->sock, sleeptime * 1000L);
/* Check for replication timeout */
if (replication_timeout > 0 &&
diff --git a/src/include/postmaster/fork_process.h b/src/include/postmaster/fork_process.h
index 0553fd2..e0abe5d 100644
--- a/src/include/postmaster/fork_process.h
+++ b/src/include/postmaster/fork_process.h
@@ -12,6 +12,8 @@
#ifndef FORK_PROCESS_H
#define FORK_PROCESS_H
-extern pid_t fork_process(void);
+extern pid_t do_fork_process(bool remain_postmaster);
+#define fork_process() do_fork_process(false)
+#define fork_process_remain_postmaster() do_fork_process(true)
#endif /* FORK_PROCESS_H */
diff --git a/src/include/postmaster/postmaster.h b/src/include/postmaster/postmaster.h
index 25cc84a..497cf51 100644
--- a/src/include/postmaster/postmaster.h
+++ b/src/include/postmaster/postmaster.h
@@ -33,6 +33,25 @@ extern bool restart_after_crash;
#ifdef WIN32
extern HANDLE PostmasterHandle;
+#else
+/*
+ * Constants that represent which of a pair of fds given
+ * to pipe() is watched and owned in the context of
+ * dealing with postmaster death
+ */
+#define POSTMASTER_FD_WATCH 0
+#define POSTMASTER_FD_OWN 1
+extern int postmaster_alive_fds[2];
+/*
+ * On unix, it is necessary to Init monitoring
+ * of postmaster being alive
+ */
+extern void InitPostmasterDeathWatchHandle(void);
+/*
+ * It is also necessary to call ReleasePostmasterDeathWatchHandle()
+ * after forking from PM for the Unix implementation
+ */
+extern void ReleasePostmasterDeathWatchHandle(void);
#endif
extern const char *progname;
diff --git a/src/include/storage/latch.h b/src/include/storage/latch.h
index 03ec071..6865ac7 100644
--- a/src/include/storage/latch.h
+++ b/src/include/storage/latch.h
@@ -38,9 +38,8 @@ extern void InitLatch(volatile Latch *latch);
extern void InitSharedLatch(volatile Latch *latch);
extern void OwnLatch(volatile Latch *latch);
extern void DisownLatch(volatile Latch *latch);
-extern bool WaitLatch(volatile Latch *latch, long timeout);
-extern int WaitLatchOrSocket(volatile Latch *latch, pgsocket sock,
- bool forRead, bool forWrite, long timeout);
+extern int WaitLatch(volatile Latch *latch, int wakeEvents, long timeout);
+extern int WaitLatchOrSocket(volatile Latch *latch, int wakeEvents, pgsocket sock, long timeout);
extern void SetLatch(volatile Latch *latch);
extern void ResetLatch(volatile Latch *latch);
@@ -56,4 +55,11 @@ extern void latch_sigusr1_handler(void);
#define latch_sigusr1_handler()
#endif
+/* Bitmasks for events that may wake-up WaitLatch() clients */
+#define WL_LATCH_SET (1 << 0)
+#define WL_SOCKET_READABLE (1 << 1)
+#define WL_SOCKET_WRITEABLE (1 << 2)
+#define WL_TIMEOUT (1 << 3)
+#define WL_POSTMASTER_DEATH (1 << 4)
+
#endif /* LATCH_H */
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
