1. The (arbitrarily) limited resources must be shared by all programs that use System V shared memory. For example on my Mac OS X computer, I have Postgres running a standalone database, but also as part of Apple Remote Desktop. Without manual adjustment, running both simultaneously causes one of them to fail. Correcting this in any robust way is challenging to automate for consumer-style (i.e. Mac) installers.
2. On these BSD's, this System V shared memory is wired down and cannot be swapped out for any reason. If Postgres is running as part of another software program or is a lower priority, other programs cannot use the potentially limited memory. This places the user or developer in a tricky position of having to minimize overall system impact, while permitting enough shared memory for Postgres to perform well.
To this end, I have "ported" the svsv_shmem.c layer to use the POSIX calls (which are some ways more robust w.r.t reducing collision by using strings as shared memory id's, instead of ints).
In principle, this should not have any significant affect on performance. Running PGBench on a few different load types gives very similar results (-3%/+1%), that aren't very statistically significant. Of course, on a un-tuned Mac OS X machine (where the original SysV version is limited to the default 4MB) the POSIX version outperforms significantly (+250%). Using the POSIX calls helps minimize the kernel side of the tuning, which is a big plus for integrated uses of Postgres, but also for other amateur installations (i.e. Fink).
If this is appropriate for the distribution, it could become a 'contrib' add-on or it could be a autoconf custom build option until it reached greater maturity.
Any thoughts? Suggestions? I would also appreciate any advice on more sophisticate ways to measure the performance impacts of a change like this.
Thanks, Chris Marcellino Apple Computer, Inc.
posix_shmem.c
Description: Binary data
src/backend/port/posix_shmem.c ===================================================================/ *----------------------------------------------------------------------- --
* * posix_shmem.c * Implement shared memory using POSIX facilities * * These routines represent a fairly thin layer on top of POSIX shared * memory functionality. ** Portions Copyright (c) 1996-2006, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California **----------------------------------------------------------------------- --
*/ #include "postgres.h" #include <signal.h> #include <unistd.h> #include <sys/file.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/mman.h> #ifdef HAVE_KERNEL_OS_H #include <kernel/OS.h> #endif #include "miscadmin.h" #include "storage/ipc.h" #include "storage/pg_shmem.h" #define IPCProtection (0600) /* access/modify by user only */#define IPCNameLength 32 /* must be long enough to contain all possible format strings
* see
GenerateIPDName */
unsigned long UsedShmemSegID = 0;
void *UsedShmemSegAddr = NULL;
static void GenerateIPCName(int memKey, char *dest);
static void *InternalIpcMemoryCreate(int memKey, Size size);
static void IpcMemoryDetach(int status, Datum shmaddr);
static void IpcMemoryDelete(int status, Datum memKey);
static PGShmemHeader *PGSharedMemoryAttach(int key);
/*
* GenerateIPCName(key, dest)
*
* Generate a shared memory object key name using the argument key.
* This uses the magic number and text to prevent collisions from other
* apps.
*/
static void
GenerateIPCName(int memKey, char *dest)
{
/* This must be 31 characters or less for portability (i.e. Mac OS
X) */
sprintf(dest, "PostgreSQL.%lx.%lx", PGShmemMagic, memKey);
}
/*
* InternalIpcMemoryCreate(memKey, size)
*
* Attempt to create a new shared memory segment with the specified
key.
* Will fail (return NULL) if such a segment already exists. If
successful,
* attach the segment to the current process and return its attached
address.
* On success, callbacks are registered with on_shmem_exit to detach
and
* delete the segment when on_shmem_exit is called. ** If we fail with a failure code other than collision-with-existing- segment, * print out an error and abort. Other types of errors are not recoverable.
*/
static void *
InternalIpcMemoryCreate(int memKey, Size size)
{
int fd;
void *memAddress;
char keyName[IPCNameLength];
struct stat statbuf;
GenerateIPCName(memKey, keyName);
fd = shm_open(keyName, O_RDWR | O_CREAT | O_EXCL, IPCProtection);
if (fd < 0)
{
/*
* Fail quietly if error indicates a collision with existing
segment.
* One would expect EEXIST, given that we said O_EXCL.
*/
if (errno == EEXIST || errno == EACCES)
return NULL;
/*
* Else complain and abort
*/
ereport(FATAL,
(errmsg("could not create shared memory segment:
%m"),
errdetail("Failed system call was shm_open(name=%s, oflag=%lu,
mode=%lu).",
keyName, (unsigned long) O_CREAT |
O_EXCL,
(unsigned long) IPCProtection),
(errno == EMFILE) ?
errhint("This error means that the process has
reached its limit "
"for open file descriptors.")
: 0,
(errno == ENOSPC) ?
errhint("This error means the process has ran out
of address "
"space.") : 0));
}
/* Register on-exit routine to delete the new segment */
on_shmem_exit(IpcMemoryDelete, Int32GetDatum(memKey));
/* Increase the size of the file descriptor to the desired length.
* If this fails so will mmap since it can't map size bytes. */
fstat(fd, &statbuf);
if (statbuf.st_size < size)
ftruncate(fd, size);
/* OK, should be able to attach to the segment */
memAddress = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
fd, 0);
close(fd);
if (memAddress == (void *) -1)
elog(FATAL, "mmap(fd=%d) failed: %m", fd);
/* Register on-exit routine to detach new segment before deleting */
on_shmem_exit(IpcMemoryDetach, PointerGetDatum(memAddress));
/* Record key and ID in lockfile for data directory. */
RecordSharedMemoryInLockFile((unsigned long) memKey, 0);
return memAddress;
}
/
************************************************************************
****/
/* IpcMemoryDetach(status, shmaddr) removes a shared memory segment
*/
/*
from process' address space */
/* (called as an on_shmem_exit callback, hence funny argument list)
*/
/
************************************************************************
****/
static void
IpcMemoryDetach(int status, Datum shmaddr)
{
PGShmemHeader *hdr;
hdr = (PGShmemHeader *) DatumGetPointer(shmaddr);
if (munmap(DatumGetPointer(shmaddr), hdr->totalsize) < 0)
elog(LOG, "munmap(%p, ...) failed: %m",
DatumGetPointer(shmaddr));
}
/
************************************************************************
****/
/* IpcMemoryDelete(status, fd) deletes a shared memory segment
*/
/* (called as an on_shmem_exit callback, hence funny argument list)
*/
/
************************************************************************
****/
static void
IpcMemoryDelete(int status, Datum memKey)
{
char keyName[IPCNameLength];
GenerateIPCName(memKey, keyName);
if (shm_unlink(keyName) < 0)
elog(LOG, "shm_unlink(%s) failed: %m", keyName);
}
/*
* PGSharedMemoryIsInUse
*
* Is a previously-existing shmem segment still existing and in use?
*
* The point of this exercise is to detect the case where a prior
postmaster
* crashed, but it left child backends that are still running.
Therefore
* we only care about shmem segments that are associated with the
intended
* DataDir. This is an important consideration since accidental
matches of
* shmem segment IDs are reasonably common.
*/
bool
PGSharedMemoryIsInUse(unsigned long id1, unsigned long id2)
{
char keyName[IPCNameLength];
PGShmemHeader *hdr;
int fd, isValidHeader;
#ifndef WIN32
struct stat statbuf;
#endif
GenerateIPCName(id1, keyName);
/*
* We detect whether a shared memory segment is in use by seeing
whether
* it (a) exists and (b) has any processes are attached to it.
*/
fd = shm_open(keyName, O_RDWR, 0);
if (fd < 0)
{
/*
* ENOENT means the segment no longer exists.
*/
if (errno == ENOENT)
return false;
/*
* EACCES implies that the segment belongs to some other
userid, which
* means it is not a Postgres shmem segment that is relevant to
our
* data directory.
*/
if (errno == EACCES)
return false;
/*
* Otherwise, we had better assume that the segment is in use.
*/
return true;
}
/*
* Try to attach to the segment and see if it matches our data
directory.
* This avoids fd-conflict problems on machines that are running
* several postmasters under the same userid. On Windows, which
doesn't
* have useful inode numbers, we can't do this so we punt and assume
there
* is a conflict.
*/
#ifdef WIN32
close(fd);
return true;
#endif
if (stat(DataDir, &statbuf) < 0)
{
close(fd);
return true; /* if can't stat, be
conservative */
}
hdr = (PGShmemHeader *) mmap(NULL, sizeof(PGShmemHeader), PROT_READ,
MAP_SHARED, fd, 0);
close(fd);
if (hdr == (PGShmemHeader *) -1)
return true; /* if can't attach, be
conservative */
isValidHeader = hdr->magic != PGShmemMagic ||
hdr->device != statbuf.st_dev ||
hdr->inode != statbuf.st_ino;
munmap((void *) hdr, sizeof(PGShmemHeader));
if (isValidHeader)
{
/*
* It's either not a Postgres segment, or not one for my data
* directory. In either case it poses no threat.
*/
munmap((void *) hdr, sizeof(PGShmemHeader));
return false;
}
/* Trouble --- looks a lot like there's still live backends */
return true;
}
/*
* PGSharedMemoryCreate
*
* Create a shared memory segment of the given size and initialize its
* standard header. Also, register an on_shmem_exit callback to
release
* the storage. ** Dead Postgres segments are recycled if found, but we do not fail upon * collision with non-Postgres shmem segments. The idea here is to detect and * re-use keys that may have been assigned by a crashed postmaster or backend.
** makePrivate means to always create a new segment, rather than attach to
* or recycle any existing segment. ** The port number is passed for possible use as a key (for SysV, we use
* it to generate the starting shmem key). In a standalone backend,
* zero will be passed.
*/
PGShmemHeader *
PGSharedMemoryCreate(Size size, bool makePrivate, int port)
{
int NextShmemSegID;
void *memAddress;
PGShmemHeader *hdr;
char keyName[IPCNameLength];
#ifndef WIN32
struct stat statbuf;
#endif
/* Room for a header? */
Assert(size > MAXALIGN(sizeof(PGShmemHeader)));
/* Make sure PGSharedMemoryAttach doesn't fail without need */
UsedShmemSegAddr = NULL;
/* Loop till we find a free IPC key */
NextShmemSegID = port * 1000;
for (NextShmemSegID++;; NextShmemSegID++)
{
/* Try to create new segment */
memAddress = InternalIpcMemoryCreate(NextShmemSegID, size);
if (memAddress)
break; /* successful create
and attach */
/* Check shared memory and possibly remove and recreate */
if (makePrivate) /* a standalone backend
shouldn't do this */
continue;
if ((memAddress = PGSharedMemoryAttach(NextShmemSegID)) == NULL)
continue; /* can't attach, not
one of mine */
/*
* If I am not the creator and it belongs to an extant process,
* continue.
*/
hdr = (PGShmemHeader *) memAddress;
if (hdr->creatorPID != getpid())
{
if (kill(hdr->creatorPID, 0) == 0 || errno != ESRCH)
{
munmap(memAddress, hdr->totalsize);
continue; /* segment belongs to a
live process */
}
}
/*
* The segment appears to be from a dead Postgres process, or
from a
* previous cycle of life in this same process. Zap it, if
possible.
* This probably shouldn't fail, but if it does, assume the
segment
* belongs to someone else after all, and continue quietly.
*/
GenerateIPCName(NextShmemSegID, keyName);
munmap(memAddress, hdr->totalsize);
if (shm_unlink(keyName) < 0)
continue;
/*
* Now try again to create the segment.
*/
memAddress = InternalIpcMemoryCreate(NextShmemSegID, size);
if (memAddress)
break; /* successful create
and attach */
/*
* Can only get here if some other process managed to create
the same
* shmem key before we did. Let him have that one, loop around
to try
* next key.
*/
}
/*
* OK, we created a new segment. Mark it as created by this
process. The
* order of assignments here is critical so that another Postgres
process
* can't see the header as valid but belonging to an invalid PID!
*/
hdr = (PGShmemHeader *) memAddress;
hdr->creatorPID = getpid();
hdr->magic = PGShmemMagic;
#ifndef WIN32
/* Fill in the data directory ID info, too */
if (stat(DataDir, &statbuf) < 0)
ereport(FATAL,
(errcode_for_file_access(),
errmsg("could not stat data directory \"%s\":
%m",
DataDir)));
hdr->device = statbuf.st_dev;
hdr->inode = statbuf.st_ino;
#endif
/*
* Initialize space allocation status for segment.
*/
hdr->totalsize = size;
hdr->freeoffset = MAXALIGN(sizeof(PGShmemHeader));
/* Save info for possible future use */
UsedShmemSegAddr = memAddress;
UsedShmemSegID = (unsigned long) NextShmemSegID;
return hdr;
}
#ifdef EXEC_BACKEND
/*
* PGSharedMemoryReAttach
*
* Re-attach to an already existing shared memory segment. In the non
* EXEC_BACKEND case this is not used, because postmaster children
inherit
* the shared memory segment attachment via fork(). * * UsedShmemSegID and UsedShmemSegAddr are implicit parameters to this* routine. The caller must have already restored them to the postmaster's
* values.
*/
void
PGSharedMemoryReAttach(void)
{
int fd;
void *hdr;
void *origUsedShmemSegAddr = UsedShmemSegAddr;
Assert(UsedShmemSegAddr != NULL);
Assert(IsUnderPostmaster);
#ifdef __CYGWIN__
/* cygipc (currently) appears to not detach on exec. */
PGSharedMemoryDetach();
UsedShmemSegAddr = origUsedShmemSegAddr;
#endif
elog(DEBUG3, "attaching to %p", UsedShmemSegAddr);
hdr = (void *) PGSharedMemoryAttach((int) UsedShmemSegID);
if (hdr == NULL)
elog(FATAL, "could not reattach to shared memory (key=%d, addr=%p):
%m",
(int) UsedShmemSegID, UsedShmemSegAddr);
if (hdr != origUsedShmemSegAddr)
elog(FATAL, "reattaching to shared memory returned unexpected
address (got %p, expected %p)",
hdr, origUsedShmemSegAddr);
UsedShmemSegAddr = hdr; /* probably redundant */
}
#endif /* EXEC_BACKEND */
/*
* PGSharedMemoryDetach
*
* Detach from the shared memory segment, if still attached. This
is not
* intended for use by the process that originally created the segment* (it will have an on_shmem_exit callback registered to do that). Rather, * this is for subprocesses that have inherited an attachment and want to
* get rid of it.
*/
void
PGSharedMemoryDetach(void)
{
PGShmemHeader *hdr;
if (UsedShmemSegAddr != NULL)
{
hdr = (PGShmemHeader *) UsedShmemSegAddr;
if (munmap(UsedShmemSegAddr, hdr->totalsize) < 0)
elog(LOG, "munmap(%p) failed: %m", UsedShmemSegAddr);
UsedShmemSegAddr = NULL;
}
}
/*
* Attach to shared memory and make sure it has a Postgres header
*
* Returns attach address if OK, else NULL
*/
static PGShmemHeader *
PGSharedMemoryAttach(int key)
{
PGShmemHeader *hdr;
char keyName[IPCNameLength];
Size size;
int fd;
GenerateIPCName(key, keyName);
if ((fd = shm_open(keyName, O_RDWR, 0)) < 0)
return NULL;
hdr = (PGShmemHeader *) mmap(UsedShmemSegAddr, sizeof(PGShmemHeader),
PROT_READ |
PROT_WRITE, MAP_SHARED, fd, 0);
if (hdr == (PGShmemHeader *) -1)
{
close(fd);
return NULL; /* failed: must be some other
app's */
}
if (hdr->magic != PGShmemMagic)
{
close(fd);
munmap((void *) hdr, sizeof(PGShmemHeader));
return NULL; /* segment belongs to a
non-Postgres app */
}
/* Since the segment has a valid Postgres header, unmap and re-map
it with the proper size */
size = hdr->totalsize;
munmap((void *) hdr, sizeof(PGShmemHeader));
hdr = (PGShmemHeader *) mmap(UsedShmemSegAddr, size, PROT_READ |
PROT_WRITE, MAP_SHARED, fd, 0);
close(fd);
return hdr;
}
---------------------------(end of broadcast)---------------------------
TIP 4: Have you searched our list archives?
http://archives.postgresql.org
