Commit 1cc4f536 authored by Magnus Hagander's avatar Magnus Hagander

Support huge pages on Windows

Add support for huge pages (called large pages on Windows) to the
Windows build.

This (probably) breaks compatibility with Windows versions prior to
Windows 2003 or Windows Vista.

Authors: Takayuki Tsunakawa and Thomas Munro
Reviewed by: Magnus Hagander, Amit Kapila
parent 5c15a54e
...@@ -1369,14 +1369,26 @@ include_dir 'conf.d' ...@@ -1369,14 +1369,26 @@ include_dir 'conf.d'
</para> </para>
<para> <para>
At present, this feature is supported only on Linux. The setting is At present, this feature is supported only on Linux and Windows. The
ignored on other systems when set to <literal>try</literal>. setting is ignored on other systems when set to <literal>try</literal>.
</para> </para>
<para> <para>
The use of huge pages results in smaller page tables and less CPU time The use of huge pages results in smaller page tables and less CPU time
spent on memory management, increasing performance. For more details, spent on memory management, increasing performance. For more details about
see <xref linkend="linux-huge-pages"/>. using huge pages on Linux, see <xref linkend="linux-huge-pages"/>.
</para>
<para>
Huge pages are known as large pages on Windows. To use them, you need to
assign the user right Lock Pages in Memory to the Windows user account
that runs <productname>PostgreSQL</productname>.
You can use Windows Group Policy tool (gpedit.msc) to assign the user right
Lock Pages in Memory.
To start the database server on the command prompt as a standalone process,
not as a Windows service, the command prompt must be run as an administrator
User Access Control (UAC) must be disabled. When the UAC is enabled, the normal
command prompt revokes the user right Lock Pages in Memory when started.
</para> </para>
<para> <para>
......
...@@ -21,6 +21,7 @@ HANDLE UsedShmemSegID = INVALID_HANDLE_VALUE; ...@@ -21,6 +21,7 @@ HANDLE UsedShmemSegID = INVALID_HANDLE_VALUE;
void *UsedShmemSegAddr = NULL; void *UsedShmemSegAddr = NULL;
static Size UsedShmemSegSize = 0; static Size UsedShmemSegSize = 0;
static bool EnableLockPagesPrivilege(int elevel);
static void pgwin32_SharedMemoryDelete(int status, Datum shmId); static void pgwin32_SharedMemoryDelete(int status, Datum shmId);
/* /*
...@@ -103,6 +104,66 @@ PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2) ...@@ -103,6 +104,66 @@ PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2)
return true; return true;
} }
/*
* EnableLockPagesPrivilege
*
* Try to acquire SeLockMemoryPrivilege so we can use large pages.
*/
static bool
EnableLockPagesPrivilege(int elevel)
{
HANDLE hToken;
TOKEN_PRIVILEGES tp;
LUID luid;
if (!OpenProcessToken(GetCurrentProcess(), TOKEN_ADJUST_PRIVILEGES | TOKEN_QUERY, &hToken))
{
ereport(elevel,
(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
errdetail("Failed system call was %s.", "OpenProcessToken")));
return FALSE;
}
if (!LookupPrivilegeValue(NULL, SE_LOCK_MEMORY_NAME, &luid))
{
ereport(elevel,
(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
errdetail("Failed system call was %s.", "LookupPrivilegeValue")));
CloseHandle(hToken);
return FALSE;
}
tp.PrivilegeCount = 1;
tp.Privileges[0].Luid = luid;
tp.Privileges[0].Attributes = SE_PRIVILEGE_ENABLED;
if (!AdjustTokenPrivileges(hToken, FALSE, &tp, 0, NULL, NULL))
{
ereport(elevel,
(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
errdetail("Failed system call was %s.", "AdjustTokenPrivileges")));
CloseHandle(hToken);
return FALSE;
}
if (GetLastError() != ERROR_SUCCESS)
{
if (GetLastError() == ERROR_NOT_ALL_ASSIGNED)
ereport(elevel,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("could not enable Lock Pages in Memory user right"),
errhint("Assign Lock Pages in Memory user right to the Windows user account which runs PostgreSQL.")));
else
ereport(elevel,
(errmsg("could not enable Lock Pages in Memory user right: error code %lu", GetLastError()),
errdetail("Failed system call was %s.", "AdjustTokenPrivileges")));
CloseHandle(hToken);
return FALSE;
}
CloseHandle(hToken);
return TRUE;
}
/* /*
* PGSharedMemoryCreate * PGSharedMemoryCreate
...@@ -127,11 +188,9 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port, ...@@ -127,11 +188,9 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
int i; int i;
DWORD size_high; DWORD size_high;
DWORD size_low; DWORD size_low;
SIZE_T largePageSize = 0;
if (huge_pages == HUGE_PAGES_ON) Size orig_size = size;
ereport(ERROR, DWORD flProtect = PAGE_READWRITE;
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("huge pages not supported on this platform")));
/* Room for a header? */ /* Room for a header? */
Assert(size > MAXALIGN(sizeof(PGShmemHeader))); Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
...@@ -140,6 +199,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port, ...@@ -140,6 +199,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
UsedShmemSegAddr = NULL; UsedShmemSegAddr = NULL;
if (huge_pages == HUGE_PAGES_ON || huge_pages == HUGE_PAGES_TRY)
{
/* Does the processor support large pages? */
largePageSize = GetLargePageMinimum();
if (largePageSize == 0)
{
ereport(huge_pages == HUGE_PAGES_ON ? FATAL : DEBUG1,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("the processor does not support large pages")));
ereport(DEBUG1,
(errmsg("disabling huge pages")));
}
else if (!EnableLockPagesPrivilege(huge_pages == HUGE_PAGES_ON ? FATAL : DEBUG1))
{
ereport(DEBUG1,
(errmsg("disabling huge pages")));
}
else
{
/* Huge pages available and privilege enabled, so turn on */
flProtect = PAGE_READWRITE | SEC_COMMIT | SEC_LARGE_PAGES;
/* Round size up as appropriate. */
if (size % largePageSize != 0)
size += largePageSize - (size % largePageSize);
}
}
retry:
#ifdef _WIN64 #ifdef _WIN64
size_high = size >> 32; size_high = size >> 32;
#else #else
...@@ -163,16 +251,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port, ...@@ -163,16 +251,35 @@ PGSharedMemoryCreate(Size size, bool makePrivate, int port,
hmap = CreateFileMapping(INVALID_HANDLE_VALUE, /* Use the pagefile */ hmap = CreateFileMapping(INVALID_HANDLE_VALUE, /* Use the pagefile */
NULL, /* Default security attrs */ NULL, /* Default security attrs */
PAGE_READWRITE, /* Memory is Read/Write */ flProtect,
size_high, /* Size Upper 32 Bits */ size_high, /* Size Upper 32 Bits */
size_low, /* Size Lower 32 bits */ size_low, /* Size Lower 32 bits */
szShareMem); szShareMem);
if (!hmap) if (!hmap)
{
if (GetLastError() == ERROR_NO_SYSTEM_RESOURCES &&
huge_pages == HUGE_PAGES_TRY &&
(flProtect & SEC_LARGE_PAGES) != 0)
{
elog(DEBUG1, "CreateFileMapping(%zu) with SEC_LARGE_PAGES failed, "
"huge pages disabled",
size);
/*
* Use the original size, not the rounded-up value, when falling back
* to non-huge pages.
*/
size = orig_size;
flProtect = PAGE_READWRITE;
goto retry;
}
else
ereport(FATAL, ereport(FATAL,
(errmsg("could not create shared memory segment: error code %lu", GetLastError()), (errmsg("could not create shared memory segment: error code %lu", GetLastError()),
errdetail("Failed system call was CreateFileMapping(size=%zu, name=%s).", errdetail("Failed system call was CreateFileMapping(size=%zu, name=%s).",
size, szShareMem))); size, szShareMem)));
}
/* /*
* If the segment already existed, CreateFileMapping() will return a * If the segment already existed, CreateFileMapping() will return a
......
...@@ -3913,7 +3913,7 @@ static struct config_enum ConfigureNamesEnum[] = ...@@ -3913,7 +3913,7 @@ static struct config_enum ConfigureNamesEnum[] =
{ {
{"huge_pages", PGC_POSTMASTER, RESOURCES_MEM, {"huge_pages", PGC_POSTMASTER, RESOURCES_MEM,
gettext_noop("Use of huge pages on Linux."), gettext_noop("Use of huge pages on Linux or Windows."),
NULL NULL
}, },
&huge_pages, &huge_pages,
......
...@@ -144,6 +144,7 @@ static void WINAPI pgwin32_ServiceHandler(DWORD); ...@@ -144,6 +144,7 @@ static void WINAPI pgwin32_ServiceHandler(DWORD);
static void WINAPI pgwin32_ServiceMain(DWORD, LPTSTR *); static void WINAPI pgwin32_ServiceMain(DWORD, LPTSTR *);
static void pgwin32_doRunAsService(void); static void pgwin32_doRunAsService(void);
static int CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_service); static int CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_service);
static PTOKEN_PRIVILEGES GetPrivilegesToDelete(HANDLE hToken);
#endif #endif
static pgpid_t get_pgpid(bool is_status_request); static pgpid_t get_pgpid(bool is_status_request);
...@@ -1623,11 +1624,6 @@ typedef BOOL (WINAPI * __SetInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, L ...@@ -1623,11 +1624,6 @@ typedef BOOL (WINAPI * __SetInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, L
typedef BOOL (WINAPI * __AssignProcessToJobObject) (HANDLE, HANDLE); typedef BOOL (WINAPI * __AssignProcessToJobObject) (HANDLE, HANDLE);
typedef BOOL (WINAPI * __QueryInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, LPVOID, DWORD, LPDWORD); typedef BOOL (WINAPI * __QueryInformationJobObject) (HANDLE, JOBOBJECTINFOCLASS, LPVOID, DWORD, LPDWORD);
/* Windows API define missing from some versions of MingW headers */
#ifndef DISABLE_MAX_PRIVILEGE
#define DISABLE_MAX_PRIVILEGE 0x1
#endif
/* /*
* Create a restricted token, a job object sandbox, and execute the specified * Create a restricted token, a job object sandbox, and execute the specified
* process with it. * process with it.
...@@ -1650,6 +1646,7 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser ...@@ -1650,6 +1646,7 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
HANDLE restrictedToken; HANDLE restrictedToken;
SID_IDENTIFIER_AUTHORITY NtAuthority = {SECURITY_NT_AUTHORITY}; SID_IDENTIFIER_AUTHORITY NtAuthority = {SECURITY_NT_AUTHORITY};
SID_AND_ATTRIBUTES dropSids[2]; SID_AND_ATTRIBUTES dropSids[2];
PTOKEN_PRIVILEGES delPrivs;
/* Functions loaded dynamically */ /* Functions loaded dynamically */
__CreateRestrictedToken _CreateRestrictedToken = NULL; __CreateRestrictedToken _CreateRestrictedToken = NULL;
...@@ -1708,14 +1705,21 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser ...@@ -1708,14 +1705,21 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
return 0; return 0;
} }
/* Get list of privileges to remove */
delPrivs = GetPrivilegesToDelete(origToken);
if (delPrivs == NULL)
/* Error message already printed */
return 0;
b = _CreateRestrictedToken(origToken, b = _CreateRestrictedToken(origToken,
DISABLE_MAX_PRIVILEGE, 0,
sizeof(dropSids) / sizeof(dropSids[0]), sizeof(dropSids) / sizeof(dropSids[0]),
dropSids, dropSids,
0, NULL, delPrivs->PrivilegeCount, delPrivs->Privileges,
0, NULL, 0, NULL,
&restrictedToken); &restrictedToken);
free(delPrivs);
FreeSid(dropSids[1].Sid); FreeSid(dropSids[1].Sid);
FreeSid(dropSids[0].Sid); FreeSid(dropSids[0].Sid);
CloseHandle(origToken); CloseHandle(origToken);
...@@ -1832,6 +1836,65 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser ...@@ -1832,6 +1836,65 @@ CreateRestrictedProcess(char *cmd, PROCESS_INFORMATION *processInfo, bool as_ser
*/ */
return r; return r;
} }
/*
* Get a list of privileges to delete from the access token. We delete all privileges
* except SeLockMemoryPrivilege which is needed to use large pages, and
* SeChangeNotifyPrivilege which is enabled by default in DISABLE_MAX_PRIVILEGE.
*/
static PTOKEN_PRIVILEGES
GetPrivilegesToDelete(HANDLE hToken)
{
int i, j;
DWORD length;
PTOKEN_PRIVILEGES tokenPrivs;
LUID luidLockPages;
LUID luidChangeNotify;
if (!LookupPrivilegeValue(NULL, SE_LOCK_MEMORY_NAME, &luidLockPages) ||
!LookupPrivilegeValue(NULL, SE_CHANGE_NOTIFY_NAME, &luidChangeNotify))
{
write_stderr(_("%s: could not get LUIDs for privileges: error code %lu\n"),
progname, (unsigned long) GetLastError());
return NULL;
}
if (!GetTokenInformation(hToken, TokenPrivileges, NULL, 0, &length) &&
GetLastError() != ERROR_INSUFFICIENT_BUFFER)
{
write_stderr(_("%s: could not get token information: error code %lu\n"),
progname, (unsigned long) GetLastError());
return NULL;
}
tokenPrivs = (PTOKEN_PRIVILEGES) malloc(length);
if (tokenPrivs == NULL)
{
write_stderr(_("%s: out of memory\n"), progname);
return NULL;
}
if (!GetTokenInformation(hToken, TokenPrivileges, tokenPrivs, length, &length))
{
write_stderr(_("%s: could not get token information: error code %lu\n"),
progname, (unsigned long) GetLastError());
free(tokenPrivs);
return NULL;
}
for (i = 0; i < tokenPrivs->PrivilegeCount; i++)
{
if (memcmp(&tokenPrivs->Privileges[i].Luid, &luidLockPages, sizeof(LUID)) == 0 ||
memcmp(&tokenPrivs->Privileges[i].Luid, &luidChangeNotify, sizeof(LUID)) == 0)
{
for (j = i; j < tokenPrivs->PrivilegeCount - 1; j++)
tokenPrivs->Privileges[j] = tokenPrivs->Privileges[j + 1];
tokenPrivs->PrivilegeCount--;
}
}
return tokenPrivs;
}
#endif /* WIN32 */ #endif /* WIN32 */
static void static void
......
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