Commit 45e004fb authored by Tom Lane's avatar Tom Lane

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
parent d137a6dc
...@@ -4510,6 +4510,7 @@ internal_forkexec(int argc, char *argv[], Port *port) ...@@ -4510,6 +4510,7 @@ internal_forkexec(int argc, char *argv[], Port *port)
static pid_t static pid_t
internal_forkexec(int argc, char *argv[], Port *port) internal_forkexec(int argc, char *argv[], Port *port)
{ {
int retry_count = 0;
STARTUPINFO si; STARTUPINFO si;
PROCESS_INFORMATION pi; PROCESS_INFORMATION pi;
int i; int i;
...@@ -4527,6 +4528,9 @@ internal_forkexec(int argc, char *argv[], Port *port) ...@@ -4527,6 +4528,9 @@ internal_forkexec(int argc, char *argv[], Port *port)
Assert(strncmp(argv[1], "--fork", 6) == 0); Assert(strncmp(argv[1], "--fork", 6) == 0);
Assert(argv[2] == NULL); Assert(argv[2] == NULL);
/* Resume here if we need to retry */
retry:
/* Set up shared memory for parameter passing */ /* Set up shared memory for parameter passing */
ZeroMemory(&sa, sizeof(sa)); ZeroMemory(&sa, sizeof(sa));
sa.nLength = sizeof(sa); sa.nLength = sizeof(sa);
...@@ -4618,22 +4622,26 @@ internal_forkexec(int argc, char *argv[], Port *port) ...@@ -4618,22 +4622,26 @@ internal_forkexec(int argc, char *argv[], Port *port)
/* /*
* Reserve the memory region used by our main shared memory segment before * 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)) if (!pgwin32_ReserveSharedMemoryRegion(pi.hProcess))
{ {
/* /* pgwin32_ReserveSharedMemoryRegion already made a log entry */
* Failed to reserve the memory, so terminate the newly created
* process and give up.
*/
if (!TerminateProcess(pi.hProcess, 255)) if (!TerminateProcess(pi.hProcess, 255))
ereport(LOG, ereport(LOG,
(errmsg_internal("could not terminate process that failed to reserve memory: error code %lu", (errmsg_internal("could not terminate process that failed to reserve memory: error code %lu",
GetLastError()))); GetLastError())));
CloseHandle(pi.hProcess); CloseHandle(pi.hProcess);
CloseHandle(pi.hThread); CloseHandle(pi.hThread);
return -1; /* logging done made by if (++retry_count < 100)
* pgwin32_ReserveSharedMemoryRegion() */ 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;
} }
/* /*
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment