postgres.git / summary / log / commit / refs

commit    45e004fb4e3937dbdabf6d5c1706f1a02fdceb94
Author:   Tom Lane <tgl@sss.pgh.pa.us>
Date:     Mon Jul 10 15:00:09 2017 +0000

    On Windows, retry process creation if we fail to reserve shared memory.
    
    We've heard occasional reports of backend launch failing because
    pgwin32_ReserveSharedMemoryRegion() fails, indicating that something
    has already used that address space in the child process.  It's not
    very clear what, given that we disable ASLR in Windows builds, but
    suspicion falls on antivirus products.  It'd be better if we didn't
    have to disable ASLR, anyway.  So let's try to ameliorate the problem
    by retrying the process launch after such a failure, up to 100 times.
    
    Patch by me, based on previous work by Amit Kapila and others.
    This is a longstanding issue, so back-patch to all supported branches.
    
    Discussion: https://postgr.es/m/CAA4eK1+R6hSx6t_yvwtx+NRzneVp+MRqXAdGJZChcau8Uij-8g@mail.gmail.com


 src/backend/postmaster/postmaster.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 5f4dd689410..95180b2ef59 100644
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -4510,6 +4510,7 @@ internal_forkexec(int argc, char *argv[], Port *port)
 static pid_t
 internal_forkexec(int argc, char *argv[], Port *port)
 {
+	int			retry_count = 0;
 	STARTUPINFO si;
 	PROCESS_INFORMATION pi;
 	int			i;
@@ -4527,6 +4528,9 @@ internal_forkexec(int argc, char *argv[], Port *port)
 	Assert(strncmp(argv[1], "--fork", 6) == 0);
 	Assert(argv[2] == NULL);
 
+	/* Resume here if we need to retry */
+retry:
+
 	/* Set up shared memory for parameter passing */
 	ZeroMemory(&sa, sizeof(sa));
 	sa.nLength = sizeof(sa);
@@ -4618,22 +4622,26 @@ internal_forkexec(int argc, char *argv[], Port *port)
 
 	/*
 	 * Reserve the memory region used by our main shared memory segment before
-	 * we resume the child process.
+	 * we resume the child process.  Normally this should succeed, but if ASLR
+	 * is active then it might sometimes fail due to the stack or heap having
+	 * gotten mapped into that range.  In that case, just terminate the
+	 * process and retry.
 	 */
 	if (!pgwin32_ReserveSharedMemoryRegion(pi.hProcess))
 	{
-		/*
-		 * Failed to reserve the memory, so terminate the newly created
-		 * process and give up.
-		 */
+		/* pgwin32_ReserveSharedMemoryRegion already made a log entry */
 		if (!TerminateProcess(pi.hProcess, 255))
 			ereport(LOG,
 					(errmsg_internal("could not terminate process that failed to reserve memory: error code %lu",
 									 GetLastError())));
 		CloseHandle(pi.hProcess);
 		CloseHandle(pi.hThread);
-		return -1;				/* logging done made by
-								 * pgwin32_ReserveSharedMemoryRegion() */
+		if (++retry_count < 100)
+			goto retry;
+		ereport(LOG,
+				(errmsg("giving up after too many tries to reserve shared memory"),
+				 errhint("This might be caused by ASLR or antivirus software.")));
+		return -1;
 	}
 
 	/*


[parent: d137a6dc239b]