* unix_latch.c
* Routines for inter-process latches
*
- * A latch is a boolean variable, with operations that let you to sleep
- * until it is set. A latch can be set from another process, or a signal
- * handler within the same process.
- *
- * The latch interface is a reliable replacement for the common pattern of
- * using pg_usleep() or select() to wait until a signal arrives, where the
- * signal handler sets a global variable. Because on some platforms, an
- * incoming signal doesn't interrupt sleep, and even on platforms where it
- * does there is a race condition if the signal arrives just before
- * entering the sleep, the common pattern must periodically wake up and
- * poll the global variable. pselect() system call was invented to solve
- * the problem, but it is not portable enough. Latches are designed to
- * overcome these limitations, allowing you to sleep without polling and
- * ensuring a quick response to signals from other processes.
- *
- * There are two kinds of latches: local and shared. A local latch is
- * initialized by InitLatch, and can only be set from the same process.
- * A local latch can be used to wait for a signal to arrive, by calling
- * SetLatch in the signal handler. A shared latch resides in shared memory,
- * and must be initialized at postmaster startup by InitSharedLatch. Before
- * a shared latch can be waited on, it must be associated with a process
- * with OwnLatch. Only the process owning the latch can wait on it, but any
- * process can set it.
- *
- * There are three basic operations on a latch:
- *
- * SetLatch - Sets the latch
- * ResetLatch - Clears the latch, allowing it to be set again
- * WaitLatch - Waits for the latch to become set
- *
- * The correct pattern to wait for an event is:
- *
- * for (;;)
- * {
- * ResetLatch();
- * if (work to do)
- * Do Stuff();
- *
- * WaitLatch();
- * }
- *
- * It's important to reset the latch *before* checking if there's work to
- * do. Otherwise, if someone sets the latch between the check and the
- * ResetLatch call, you will miss it and Wait will block.
- *
- * To wake up the waiter, you must first set a global flag or something
- * else that the main loop tests in the "if (work to do)" part, and call
- * SetLatch *after* that. SetLatch is designed to return quickly if the
- * latch is already set.
- *
- *
- * Implementation
- * --------------
- *
* The Unix implementation uses the so-called self-pipe trick to overcome
* the race condition involved with select() and setting a global flag
* in the signal handler. When a latch is set and the current process
* interrupt select() on all platforms, and even on platforms where it
* does, a signal that arrives just before the select() call does not
* prevent the select() from entering sleep. An incoming byte on a pipe
- * however reliably interrupts the sleep, and makes select() to return
- * immediately if the signal arrives just before select() begins.
+ * however reliably interrupts the sleep, and causes select() to return
+ * immediately even if the signal arrives before select() begins.
*
* When SetLatch is called from the same process that owns the latch,
* SetLatch writes the byte directly to the pipe. If it's owned by another
/* Are we currently in WaitLatch? The signal handler would like to know. */
static volatile sig_atomic_t waiting = false;
-/* Read and write end of the self-pipe */
+/* Read and write ends of the self-pipe */
static int selfpipe_readfd = -1;
static int selfpipe_writefd = -1;
void
InitLatch(volatile Latch *latch)
{
- /* Initialize the self pipe if this is our first latch in the process */
+ /* Initialize the self-pipe if this is our first latch in the process */
if (selfpipe_readfd == -1)
initSelfPipe();
/*
* Initialize a shared latch that can be set from other processes. The latch
- * is initially owned by no-one, use OwnLatch to associate it with the
+ * is initially owned by no-one; use OwnLatch to associate it with the
* current process.
*
* InitSharedLatch needs to be called in postmaster before forking child
* processes, usually right after allocating the shared memory block
- * containing the latch with ShmemInitStruct. The Unix implementation
- * doesn't actually require that, but the Windows one does.
+ * containing the latch with ShmemInitStruct. (The Unix implementation
+ * doesn't actually require that, but the Windows one does.) Because of
+ * this restriction, we have no concurrency issues to worry about here.
*/
void
InitSharedLatch(volatile Latch *latch)
/*
* Associate a shared latch with the current process, allowing it to
- * wait on it.
+ * wait on the latch.
*
- * Make sure that latch_sigusr1_handler() is called from the SIGUSR1 signal
- * handler, as shared latches use SIGUSR1 to for inter-process communication.
+ * Although there is a sanity check for latch-already-owned, we don't do
+ * any sort of locking here, meaning that we could fail to detect the error
+ * if two processes try to own the same latch at about the same time. If
+ * there is any risk of that, caller must provide an interlock to prevent it.
+ *
+ * In any process that calls OwnLatch(), make sure that
+ * latch_sigusr1_handler() is called from the SIGUSR1 signal handler,
+ * as shared latches use SIGUSR1 for inter-process communication.
*/
void
OwnLatch(volatile Latch *latch)
{
Assert(latch->is_shared);
- /* Initialize the self pipe if this is our first latch in the process */
+ /* Initialize the self-pipe if this is our first latch in this process */
if (selfpipe_readfd == -1)
initSelfPipe();
/* sanity check */
if (latch->owner_pid != 0)
elog(ERROR, "latch already owned");
+
latch->owner_pid = MyProcPid;
}
{
Assert(latch->is_shared);
Assert(latch->owner_pid == MyProcPid);
+
latch->owner_pid = 0;
}
int hifd;
/*
- * Clear the pipe, and check if the latch is set already. If someone
+ * Clear the pipe, then check if the latch is set already. If someone
* sets the latch between this and the select() below, the setter will
* write a byte to the pipe (or signal us and the signal handler will
* do that), and the 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 (latch->is_set)
{
result = 1;
break;
}
+ /* Must wait ... set up the event masks for select() */
FD_ZERO(&input_mask);
+ FD_ZERO(&output_mask);
+
FD_SET(selfpipe_readfd, &input_mask);
hifd = selfpipe_readfd;
+
if (sock != PGINVALID_SOCKET && forRead)
{
FD_SET(sock, &input_mask);
hifd = sock;
}
- FD_ZERO(&output_mask);
if (sock != PGINVALID_SOCKET && forWrite)
{
FD_SET(sock, &output_mask);
}
/*
- * Sets a latch and wakes up anyone waiting on it. Returns quickly if the
- * latch is already set.
+ * Sets a latch and wakes up anyone waiting on it.
+ *
+ * This is cheap if the latch is already set, otherwise not so much.
*/
void
SetLatch(volatile Latch *latch)
{
pid_t owner_pid;
+ /*
+ * XXX there really ought to be a memory barrier operation right here,
+ * to ensure that any flag variables we might have changed get flushed
+ * to main memory before we check/set is_set. Without that, we have to
+ * require that callers provide their own synchronization for machines
+ * with weak memory ordering (see latch.h).
+ */
+
/* Quick exit if already set */
if (latch->is_set)
return;
* we're in a signal handler. We use the self-pipe to wake up the select()
* in that case. If it's another process, send a signal.
*
- * Fetch owner_pid only once, in case the owner simultaneously disowns the
- * latch and clears owner_pid. XXX: This assumes that pid_t is atomic,
- * which isn't guaranteed to be true! In practice, the effective range of
- * pid_t fits in a 32 bit integer, and so should be atomic. In the worst
- * case, we might end up signaling wrong process if the right one disowns
- * the latch just as we fetch owner_pid. Even then, you're very unlucky if
- * a process with that bogus pid exists.
+ * Fetch owner_pid only once, in case the latch is concurrently getting
+ * owned or disowned. XXX: This assumes that pid_t is atomic, which isn't
+ * guaranteed to be true! In practice, the effective range of pid_t fits
+ * in a 32 bit integer, and so should be atomic. In the worst case, we
+ * might end up signaling the wrong process. Even then, you're very
+ * unlucky if a process with that bogus pid exists and belongs to
+ * Postgres; and PG database processes should handle excess SIGUSR1
+ * interrupts without a problem anyhow.
+ *
+ * Another sort of race condition that's possible here is for a new process
+ * to own the latch immediately after we look, so we don't signal it.
+ * This is okay so long as all callers of ResetLatch/WaitLatch follow the
+ * standard coding convention of waiting at the bottom of their loops,
+ * not the top, so that they'll correctly process latch-setting events that
+ * happen before they enter the loop.
*/
owner_pid = latch->owner_pid;
if (owner_pid == 0)
Assert(latch->owner_pid == MyProcPid);
latch->is_set = false;
+
+ /*
+ * XXX there really ought to be a memory barrier operation right here, to
+ * ensure that the write to is_set gets flushed to main memory before we
+ * examine any flag variables. Otherwise a concurrent SetLatch might
+ * falsely conclude that it needn't signal us, even though we have missed
+ * seeing some flag updates that SetLatch was supposed to inform us of.
+ * For the moment, callers must supply their own synchronization of flag
+ * variables (see latch.h).
+ */
}
/*
- * SetLatch uses SIGUSR1 to wake up the process waiting on the latch. Wake
- * up WaitLatch.
+ * SetLatch uses SIGUSR1 to wake up the process waiting on the latch.
+ *
+ * Wake up WaitLatch, if we're waiting. (We might not be, since SIGUSR1 is
+ * overloaded for multiple purposes.)
*/
void
latch_sigusr1_handler(void)
/*-------------------------------------------------------------------------
*
* win32_latch.c
- * Windows implementation of latches.
+ * Routines for inter-process latches
*
- * See unix_latch.c for information on usage.
+ * See unix_latch.c for header comments for the exported functions;
+ * the API presented here is supposed to be the same as there.
*
* The Windows implementation uses Windows events that are inherited by
* all postmaster child processes.
#include <unistd.h>
#include "miscadmin.h"
-#include "replication/walsender.h"
#include "storage/latch.h"
#include "storage/shmem.h"
}
int
-WaitLatchOrSocket(volatile Latch *latch, SOCKET sock, bool forRead,
+WaitLatchOrSocket(volatile Latch *latch, pgsocket sock, bool forRead,
bool forWrite, long timeout)
{
DWORD rc;
int numevents;
int result = 0;
+ if (latch->owner_pid != MyProcPid)
+ elog(ERROR, "cannot wait on a latch owned by another process");
+
latchevent = latch->event;
events[0] = latchevent;
/*
* See if anyone's waiting for the latch. It can be the current process if
- * we're in a signal handler. Use a local variable here in case the latch
- * is just disowned between the test and the SetEvent call, and event
- * field set to NULL.
+ * we're in a signal handler.
*
- * Fetch handle field only once, in case the owner simultaneously disowns
- * the latch and clears handle. This assumes that HANDLE is atomic, which
- * isn't guaranteed to be true! In practice, it should be, and in the
- * worst case we end up calling SetEvent with a bogus handle, and SetEvent
- * will return an error with no harm done.
+ * Use a local variable here just in case somebody changes the event field
+ * concurrently (which really should not happen).
*/
handle = latch->event;
if (handle)
void
ResetLatch(volatile Latch *latch)
{
+ /* Only the owner should reset the latch */
+ Assert(latch->owner_pid == MyProcPid);
+
latch->is_set = false;
}
* latch.h
* Routines for interprocess latches
*
+ * A latch is a boolean variable, with operations that let processes sleep
+ * until it is set. A latch can be set from another process, or a signal
+ * handler within the same process.
+ *
+ * The latch interface is a reliable replacement for the common pattern of
+ * using pg_usleep() or select() to wait until a signal arrives, where the
+ * signal handler sets a flag variable. Because on some platforms an
+ * incoming signal doesn't interrupt sleep, and even on platforms where it
+ * does there is a race condition if the signal arrives just before
+ * entering the sleep, the common pattern must periodically wake up and
+ * poll the flag variable. The pselect() system call was invented to solve
+ * this problem, but it is not portable enough. Latches are designed to
+ * overcome these limitations, allowing you to sleep without polling and
+ * ensuring quick response to signals from other processes.
+ *
+ * There are two kinds of latches: local and shared. A local latch is
+ * initialized by InitLatch, and can only be set from the same process.
+ * A local latch can be used to wait for a signal to arrive, by calling
+ * SetLatch in the signal handler. A shared latch resides in shared memory,
+ * and must be initialized at postmaster startup by InitSharedLatch. Before
+ * a shared latch can be waited on, it must be associated with a process
+ * with OwnLatch. Only the process owning the latch can wait on it, but any
+ * process can set it.
+ *
+ * There are three basic operations on a latch:
+ *
+ * SetLatch - Sets the latch
+ * ResetLatch - Clears the latch, allowing it to be set again
+ * WaitLatch - Waits for the latch to become set
+ *
+ * WaitLatch includes a provision for timeouts (which should hopefully not
+ * be necessary once the code is fully latch-ified).
+ * See unix_latch.c for detailed specifications for the exported functions.
+ *
+ * The correct pattern to wait for event(s) is:
+ *
+ * for (;;)
+ * {
+ * ResetLatch();
+ * if (work to do)
+ * Do Stuff();
+ * WaitLatch();
+ * }
+ *
+ * It's important to reset the latch *before* checking if there's work to
+ * do. Otherwise, if someone sets the latch between the check and the
+ * ResetLatch call, you will miss it and Wait will incorrectly block.
+ *
+ * To wake up the waiter, you must first set a global flag or something
+ * else that the wait loop tests in the "if (work to do)" part, and call
+ * SetLatch *after* that. SetLatch is designed to return quickly if the
+ * latch is already set.
+ *
+ * Presently, when using a shared latch for interprocess signalling, the
+ * flag variable(s) set by senders and inspected by the wait loop must
+ * be protected by spinlocks or LWLocks, else it is possible to miss events
+ * on machines with weak memory ordering (such as PPC). This restriction
+ * will be lifted in future by inserting suitable memory barriers into
+ * SetLatch and ResetLatch.
+ *
*
* Portions Copyright (c) 1996-2011, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
extern void SetLatch(volatile Latch *latch);
extern void ResetLatch(volatile Latch *latch);
-#define TestLatch(latch) (((volatile Latch *) latch)->is_set)
+/* beware of memory ordering issues if you use this macro! */
+#define TestLatch(latch) (((volatile Latch *) (latch))->is_set)
/*
- * Unix implementation uses SIGUSR1 for inter-process signaling, Win32 doesn't
- * need this.
+ * Unix implementation uses SIGUSR1 for inter-process signaling.
+ * Win32 doesn't need this.
*/
#ifndef WIN32
extern void latch_sigusr1_handler(void);
#else
-#define latch_sigusr1_handler()
+#define latch_sigusr1_handler() ((void) 0)
#endif
#endif /* LATCH_H */