* It doesn't matter whether the bits are on spinning rust or some other
* storage technology.
*
- * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
#include <sys/file.h>
#include "miscadmin.h"
+#include "access/xlogutils.h"
#include "access/xlog.h"
-#include "catalog/catalog.h"
+#include "pgstat.h"
#include "portability/instr_time.h"
#include "postmaster/bgwriter.h"
#include "storage/fd.h"
* out to an unlinked old copy of a segment file that will eventually
* disappear.
*
- * The file descriptor pointer (md_fd field) stored in the SMgrRelation
- * cache is, therefore, just the head of a list of MdfdVec objects, one
- * per segment. But note the md_fd pointer can be NULL, indicating
- * relation not open.
- *
- * Also note that mdfd_chain == NULL does not necessarily mean the relation
- * doesn't have another segment after this one; we may just not have
- * opened the next segment yet. (We could not have "all segments are
- * in the chain" as an invariant anyway, since another backend could
- * extend the relation when we weren't looking.) We do not make chain
+ * File descriptors are stored in the per-fork md_seg_fds arrays inside
+ * SMgrRelation. The length of these arrays is stored in md_num_open_segs.
+ * Note that a fork's md_num_open_segs having a specific value does not
+ * necessarily mean the relation doesn't have additional segments; we may
+ * just not have opened the next segment yet. (We could not have "all
+ * segments are in the array" as an invariant anyway, since another backend
+ * could extend the relation while we aren't looking.) We do not have
* entries for inactive segments, however; as soon as we find a partial
* segment, we assume that any subsequent segments are inactive.
*
- * All MdfdVec objects are palloc'd in the MdCxt memory context.
+ * The entire MdfdVec array is palloc'd in the MdCxt memory context.
*/
typedef struct _MdfdVec
{
File mdfd_vfd; /* fd number in fd.c's pool */
BlockNumber mdfd_segno; /* segment number, from 0 */
- struct _MdfdVec *mdfd_chain; /* next segment, or NULL */
} MdfdVec;
static MemoryContext MdCxt; /* context for all MdfdVec objects */
static HTAB *pendingOpsTable = NULL;
static List *pendingUnlinks = NIL;
-static MemoryContext pendingOpsCxt; /* context for the above */
+static MemoryContext pendingOpsCxt; /* context for the above */
static CycleCtr mdsync_cycle_ctr = 0;
static CycleCtr mdckpt_cycle_ctr = 0;
-typedef enum /* behavior for mdopen & _mdfd_getseg */
-{
- EXTENSION_FAIL, /* ereport if segment not present */
- EXTENSION_RETURN_NULL, /* return NULL if not present */
- EXTENSION_CREATE /* create new segments as needed */
-} ExtensionBehavior;
+/*** behavior for mdopen & _mdfd_getseg ***/
+/* ereport if segment not present */
+#define EXTENSION_FAIL (1 << 0)
+/* return NULL if segment not present */
+#define EXTENSION_RETURN_NULL (1 << 1)
+/* create new segments as needed */
+#define EXTENSION_CREATE (1 << 2)
+/* create new segments if needed during recovery */
+#define EXTENSION_CREATE_RECOVERY (1 << 3)
+/*
+ * Allow opening segments which are preceded by segments smaller than
+ * RELSEG_SIZE, e.g. inactive segments (see above). Note that this is breaks
+ * mdnblocks() and related functionality henceforth - which currently is ok,
+ * because this is only required in the checkpointer which never uses
+ * mdnblocks().
+ */
+#define EXTENSION_DONT_CHECK_SIZE (1 << 4)
+
/* local routines */
static void mdunlinkfork(RelFileNodeBackend rnode, ForkNumber forkNum,
bool isRedo);
-static MdfdVec *mdopen(SMgrRelation reln, ForkNumber forknum,
- ExtensionBehavior behavior);
+static MdfdVec *mdopen(SMgrRelation reln, ForkNumber forknum, int behavior);
static void register_dirty_segment(SMgrRelation reln, ForkNumber forknum,
MdfdVec *seg);
static void register_unlink(RelFileNodeBackend rnode);
-static MdfdVec *_fdvec_alloc(void);
+static void _fdvec_resize(SMgrRelation reln,
+ ForkNumber forknum,
+ int nseg);
static char *_mdfd_segpath(SMgrRelation reln, ForkNumber forknum,
BlockNumber segno);
static MdfdVec *_mdfd_openseg(SMgrRelation reln, ForkNumber forkno,
BlockNumber segno, int oflags);
static MdfdVec *_mdfd_getseg(SMgrRelation reln, ForkNumber forkno,
- BlockNumber blkno, bool skipFsync, ExtensionBehavior behavior);
+ BlockNumber blkno, bool skipFsync, int behavior);
static BlockNumber _mdnblocks(SMgrRelation reln, ForkNumber forknum,
MdfdVec *seg);
{
MdCxt = AllocSetContextCreate(TopMemoryContext,
"MdSmgr",
- ALLOCSET_DEFAULT_MINSIZE,
- ALLOCSET_DEFAULT_INITSIZE,
- ALLOCSET_DEFAULT_MAXSIZE);
+ ALLOCSET_DEFAULT_SIZES);
/*
* Create pending-operations hashtable if we need it. Currently, we need
/*
* XXX: The checkpointer needs to add entries to the pending ops table
* when absorbing fsync requests. That is done within a critical
- * section, which isn't usually allowed, but we make an exception.
- * It means that there's a theoretical possibility that you run out of
+ * section, which isn't usually allowed, but we make an exception. It
+ * means that there's a theoretical possibility that you run out of
* memory while absorbing fsync requests, which leads to a PANIC.
* Fortunately the hash table is small so that's unlikely to happen in
* practice.
*/
pendingOpsCxt = AllocSetContextCreate(MdCxt,
- "Pending Ops Context",
- ALLOCSET_DEFAULT_MINSIZE,
- ALLOCSET_DEFAULT_INITSIZE,
- ALLOCSET_DEFAULT_MAXSIZE);
+ "Pending ops context",
+ ALLOCSET_DEFAULT_SIZES);
MemoryContextAllowInCriticalSection(pendingOpsCxt, true);
MemSet(&hash_ctl, 0, sizeof(hash_ctl));
void
mdcreate(SMgrRelation reln, ForkNumber forkNum, bool isRedo)
{
+ MdfdVec *mdfd;
char *path;
File fd;
- if (isRedo && reln->md_fd[forkNum] != NULL)
+ if (isRedo && reln->md_num_open_segs[forkNum] > 0)
return; /* created and opened already... */
- Assert(reln->md_fd[forkNum] == NULL);
+ Assert(reln->md_num_open_segs[forkNum] == 0);
path = relpath(reln->smgr_rnode, forkNum);
- fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY, 0600);
+ fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY);
if (fd < 0)
{
* already, even if isRedo is not set. (See also mdopen)
*/
if (isRedo || IsBootstrapProcessingMode())
- fd = PathNameOpenFile(path, O_RDWR | PG_BINARY, 0600);
+ fd = PathNameOpenFile(path, O_RDWR | PG_BINARY);
if (fd < 0)
{
/* be sure to report the error reported by create, not open */
pfree(path);
- reln->md_fd[forkNum] = _fdvec_alloc();
-
- reln->md_fd[forkNum]->mdfd_vfd = fd;
- reln->md_fd[forkNum]->mdfd_segno = 0;
- reln->md_fd[forkNum]->mdfd_chain = NULL;
+ _fdvec_resize(reln, forkNum, 1);
+ mdfd = &reln->md_seg_fds[forkNum][0];
+ mdfd->mdfd_vfd = fd;
+ mdfd->mdfd_segno = 0;
}
/*
/* truncate(2) would be easier here, but Windows hasn't got it */
int fd;
- fd = OpenTransientFile(path, O_RDWR | PG_BINARY, 0);
+ fd = OpenTransientFile(path, O_RDWR | PG_BINARY);
if (fd >= 0)
{
int save_errno;
if (errno != ENOENT)
ereport(WARNING,
(errcode_for_file_access(),
- errmsg("could not remove file \"%s\": %m", segpath)));
+ errmsg("could not remove file \"%s\": %m", segpath)));
break;
}
}
v = _mdfd_getseg(reln, forknum, blocknum, skipFsync, EXTENSION_CREATE);
- seekpos = (off_t) BLCKSZ *(blocknum % ((BlockNumber) RELSEG_SIZE));
+ seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- /*
- * Note: because caller usually obtained blocknum by calling mdnblocks,
- * which did a seek(SEEK_END), this seek is often redundant and will be
- * optimized away by fd.c. It's not redundant, however, if there is a
- * partial page at the end of the file. In that case we want to try to
- * overwrite the partial page with a full page. It's also not redundant
- * if bufmgr.c had to dump another buffer of the same file to make room
- * for the new page's buffer.
- */
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ)) != BLCKSZ)
+ if ((nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_EXTEND)) != BLCKSZ)
{
if (nbytes < 0)
ereport(ERROR,
* invent one out of whole cloth.
*/
static MdfdVec *
-mdopen(SMgrRelation reln, ForkNumber forknum, ExtensionBehavior behavior)
+mdopen(SMgrRelation reln, ForkNumber forknum, int behavior)
{
MdfdVec *mdfd;
char *path;
File fd;
/* No work if already open */
- if (reln->md_fd[forknum])
- return reln->md_fd[forknum];
+ if (reln->md_num_open_segs[forknum] > 0)
+ return &reln->md_seg_fds[forknum][0];
path = relpath(reln->smgr_rnode, forknum);
- fd = PathNameOpenFile(path, O_RDWR | PG_BINARY, 0600);
+ fd = PathNameOpenFile(path, O_RDWR | PG_BINARY);
if (fd < 0)
{
* substitute for mdcreate() in bootstrap mode only. (See mdcreate)
*/
if (IsBootstrapProcessingMode())
- fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY, 0600);
+ fd = PathNameOpenFile(path, O_RDWR | O_CREAT | O_EXCL | PG_BINARY);
if (fd < 0)
{
- if (behavior == EXTENSION_RETURN_NULL &&
+ if ((behavior & EXTENSION_RETURN_NULL) &&
FILE_POSSIBLY_DELETED(errno))
{
pfree(path);
pfree(path);
- reln->md_fd[forknum] = mdfd = _fdvec_alloc();
-
+ _fdvec_resize(reln, forknum, 1);
+ mdfd = &reln->md_seg_fds[forknum][0];
mdfd->mdfd_vfd = fd;
mdfd->mdfd_segno = 0;
- mdfd->mdfd_chain = NULL;
+
Assert(_mdnblocks(reln, forknum, mdfd) <= ((BlockNumber) RELSEG_SIZE));
return mdfd;
void
mdclose(SMgrRelation reln, ForkNumber forknum)
{
- MdfdVec *v = reln->md_fd[forknum];
+ int nopensegs = reln->md_num_open_segs[forknum];
/* No work if already closed */
- if (v == NULL)
+ if (nopensegs == 0)
return;
- reln->md_fd[forknum] = NULL; /* prevent dangling pointer after error */
-
- while (v != NULL)
+ /* close segments starting from the end */
+ while (nopensegs > 0)
{
- MdfdVec *ov = v;
+ MdfdVec *v = &reln->md_seg_fds[forknum][nopensegs - 1];
/* if not closed already */
if (v->mdfd_vfd >= 0)
+ {
FileClose(v->mdfd_vfd);
- /* Now free vector */
- v = v->mdfd_chain;
- pfree(ov);
+ v->mdfd_vfd = -1;
+ }
+
+ nopensegs--;
}
+
+ /* resize just once, avoids pointless reallocations */
+ _fdvec_resize(reln, forknum, 0);
}
/*
v = _mdfd_getseg(reln, forknum, blocknum, false, EXTENSION_FAIL);
- seekpos = (off_t) BLCKSZ *(blocknum % ((BlockNumber) RELSEG_SIZE));
+ seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- (void) FilePrefetch(v->mdfd_vfd, seekpos, BLCKSZ);
-#endif /* USE_PREFETCH */
+ (void) FilePrefetch(v->mdfd_vfd, seekpos, BLCKSZ, WAIT_EVENT_DATA_FILE_PREFETCH);
+#endif /* USE_PREFETCH */
}
+/*
+ * mdwriteback() -- Tell the kernel to write pages back to storage.
+ *
+ * This accepts a range of blocks because flushing several pages at once is
+ * considerably more efficient than doing so individually.
+ */
+void
+mdwriteback(SMgrRelation reln, ForkNumber forknum,
+ BlockNumber blocknum, BlockNumber nblocks)
+{
+ /*
+ * Issue flush requests in as few requests as possible; have to split at
+ * segment boundaries though, since those are actually separate files.
+ */
+ while (nblocks > 0)
+ {
+ BlockNumber nflush = nblocks;
+ off_t seekpos;
+ MdfdVec *v;
+ int segnum_start,
+ segnum_end;
+
+ v = _mdfd_getseg(reln, forknum, blocknum, true /* not used */ ,
+ EXTENSION_RETURN_NULL);
+
+ /*
+ * We might be flushing buffers of already removed relations, that's
+ * ok, just ignore that case.
+ */
+ if (!v)
+ return;
+
+ /* compute offset inside the current segment */
+ segnum_start = blocknum / RELSEG_SIZE;
+
+ /* compute number of desired writes within the current segment */
+ segnum_end = (blocknum + nblocks - 1) / RELSEG_SIZE;
+ if (segnum_start != segnum_end)
+ nflush = RELSEG_SIZE - (blocknum % ((BlockNumber) RELSEG_SIZE));
+
+ Assert(nflush >= 1);
+ Assert(nflush <= nblocks);
+
+ seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
+
+ FileWriteback(v->mdfd_vfd, seekpos, (off_t) BLCKSZ * nflush, WAIT_EVENT_DATA_FILE_FLUSH);
+
+ nblocks -= nflush;
+ blocknum += nflush;
+ }
+}
/*
* mdread() -- Read the specified block from a relation.
reln->smgr_rnode.node.relNode,
reln->smgr_rnode.backend);
- v = _mdfd_getseg(reln, forknum, blocknum, false, EXTENSION_FAIL);
+ v = _mdfd_getseg(reln, forknum, blocknum, false,
+ EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);
- seekpos = (off_t) BLCKSZ *(blocknum % ((BlockNumber) RELSEG_SIZE));
+ seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ);
+ nbytes = FileRead(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_READ);
TRACE_POSTGRESQL_SMGR_MD_READ_DONE(forknum, blocknum,
reln->smgr_rnode.node.spcNode,
reln->smgr_rnode.node.relNode,
reln->smgr_rnode.backend);
- v = _mdfd_getseg(reln, forknum, blocknum, skipFsync, EXTENSION_FAIL);
+ v = _mdfd_getseg(reln, forknum, blocknum, skipFsync,
+ EXTENSION_FAIL | EXTENSION_CREATE_RECOVERY);
- seekpos = (off_t) BLCKSZ *(blocknum % ((BlockNumber) RELSEG_SIZE));
+ seekpos = (off_t) BLCKSZ * (blocknum % ((BlockNumber) RELSEG_SIZE));
Assert(seekpos < (off_t) BLCKSZ * RELSEG_SIZE);
- if (FileSeek(v->mdfd_vfd, seekpos, SEEK_SET) != seekpos)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not seek to block %u in file \"%s\": %m",
- blocknum, FilePathName(v->mdfd_vfd))));
-
- nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ);
+ nbytes = FileWrite(v->mdfd_vfd, buffer, BLCKSZ, seekpos, WAIT_EVENT_DATA_FILE_WRITE);
TRACE_POSTGRESQL_SMGR_MD_WRITE_DONE(forknum, blocknum,
reln->smgr_rnode.node.spcNode,
* mdnblocks() -- Get the number of blocks stored in a relation.
*
* Important side effect: all active segments of the relation are opened
- * and added to the mdfd_chain list. If this routine has not been
+ * and added to the mdfd_seg_fds array. If this routine has not been
* called, then only segments up to the last one actually touched
- * are present in the chain.
+ * are present in the array.
*/
BlockNumber
mdnblocks(SMgrRelation reln, ForkNumber forknum)
BlockNumber nblocks;
BlockNumber segno = 0;
+ /* mdopen has opened the first segment */
+ Assert(reln->md_num_open_segs[forknum] > 0);
+
/*
- * Skip through any segments that aren't the last one, to avoid redundant
- * seeks on them. We have previously verified that these segments are
- * exactly RELSEG_SIZE long, and it's useless to recheck that each time.
+ * Start from the last open segments, to avoid redundant seeks. We have
+ * previously verified that these segments are exactly RELSEG_SIZE long,
+ * and it's useless to recheck that each time.
*
* NOTE: this assumption could only be wrong if another backend has
* truncated the relation. We rely on higher code levels to handle that
* scenario by closing and re-opening the md fd, which is handled via
* relcache flush. (Since the checkpointer doesn't participate in
- * relcache flush, it could have segment chain entries for inactive
- * segments; that's OK because the checkpointer never needs to compute
- * relation size.)
+ * relcache flush, it could have segment entries for inactive segments;
+ * that's OK because the checkpointer never needs to compute relation
+ * size.)
*/
- while (v->mdfd_chain != NULL)
- {
- segno++;
- v = v->mdfd_chain;
- }
+ segno = reln->md_num_open_segs[forknum] - 1;
+ v = &reln->md_seg_fds[forknum][segno];
for (;;)
{
*/
segno++;
- if (v->mdfd_chain == NULL)
- {
- /*
- * Because we pass O_CREAT, we will create the next segment (with
- * zero length) immediately, if the last segment is of length
- * RELSEG_SIZE. While perhaps not strictly necessary, this keeps
- * the logic simple.
- */
- v->mdfd_chain = _mdfd_openseg(reln, forknum, segno, O_CREAT);
- if (v->mdfd_chain == NULL)
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not open file \"%s\": %m",
- _mdfd_segpath(reln, forknum, segno))));
- }
-
- v = v->mdfd_chain;
+ /*
+ * We used to pass O_CREAT here, but that's has the disadvantage that
+ * it might create a segment which has vanished through some operating
+ * system misadventure. In such a case, creating the segment here
+ * undermines _mdfd_getseg's attempts to notice and report an error
+ * upon access to a missing segment.
+ */
+ v = _mdfd_openseg(reln, forknum, segno, 0);
+ if (v == NULL)
+ return segno * ((BlockNumber) RELSEG_SIZE);
}
}
void
mdtruncate(SMgrRelation reln, ForkNumber forknum, BlockNumber nblocks)
{
- MdfdVec *v;
BlockNumber curnblk;
BlockNumber priorblocks;
+ int curopensegs;
/*
* NOTE: mdnblocks makes sure we have opened all active segments, so that
if (nblocks == curnblk)
return; /* no work */
- v = mdopen(reln, forknum, EXTENSION_FAIL);
-
- priorblocks = 0;
- while (v != NULL)
+ /*
+ * Truncate segments, starting at the last one. Starting at the end makes
+ * managing the memory for the fd array easier, should there be errors.
+ */
+ curopensegs = reln->md_num_open_segs[forknum];
+ while (curopensegs > 0)
{
- MdfdVec *ov = v;
+ MdfdVec *v;
+
+ priorblocks = (curopensegs - 1) * RELSEG_SIZE;
+
+ v = &reln->md_seg_fds[forknum][curopensegs - 1];
if (priorblocks > nblocks)
{
/*
- * This segment is no longer active (and has already been unlinked
- * from the mdfd_chain). We truncate the file, but do not delete
- * it, for reasons explained in the header comments.
+ * This segment is no longer active. We truncate the file, but do
+ * not delete it, for reasons explained in the header comments.
*/
- if (FileTruncate(v->mdfd_vfd, 0) < 0)
+ if (FileTruncate(v->mdfd_vfd, 0, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
ereport(ERROR,
(errcode_for_file_access(),
errmsg("could not truncate file \"%s\": %m",
if (!SmgrIsTemp(reln))
register_dirty_segment(reln, forknum, v);
- v = v->mdfd_chain;
- Assert(ov != reln->md_fd[forknum]); /* we never drop the 1st
- * segment */
- pfree(ov);
+
+ /* we never drop the 1st segment */
+ Assert(v != &reln->md_seg_fds[forknum][0]);
+
+ FileClose(v->mdfd_vfd);
+ _fdvec_resize(reln, forknum, curopensegs - 1);
}
else if (priorblocks + ((BlockNumber) RELSEG_SIZE) > nblocks)
{
/*
* This is the last segment we want to keep. Truncate the file to
- * the right length, and clear chain link that points to any
- * remaining segments (which we shall zap). NOTE: if nblocks is
- * exactly a multiple K of RELSEG_SIZE, we will truncate the K+1st
- * segment to 0 length but keep it. This adheres to the invariant
- * given in the header comments.
+ * the right length. NOTE: if nblocks is exactly a multiple K of
+ * RELSEG_SIZE, we will truncate the K+1st segment to 0 length but
+ * keep it. This adheres to the invariant given in the header
+ * comments.
*/
BlockNumber lastsegblocks = nblocks - priorblocks;
- if (FileTruncate(v->mdfd_vfd, (off_t) lastsegblocks * BLCKSZ) < 0)
+ if (FileTruncate(v->mdfd_vfd, (off_t) lastsegblocks * BLCKSZ, WAIT_EVENT_DATA_FILE_TRUNCATE) < 0)
ereport(ERROR,
(errcode_for_file_access(),
- errmsg("could not truncate file \"%s\" to %u blocks: %m",
- FilePathName(v->mdfd_vfd),
- nblocks)));
+ errmsg("could not truncate file \"%s\" to %u blocks: %m",
+ FilePathName(v->mdfd_vfd),
+ nblocks)));
if (!SmgrIsTemp(reln))
register_dirty_segment(reln, forknum, v);
- v = v->mdfd_chain;
- ov->mdfd_chain = NULL;
}
else
{
/*
- * We still need this segment and 0 or more blocks beyond it, so
- * nothing to do here.
+ * We still need this segment, so nothing to do for this and any
+ * earlier segment.
*/
- v = v->mdfd_chain;
+ break;
}
- priorblocks += RELSEG_SIZE;
+ curopensegs--;
}
}
void
mdimmedsync(SMgrRelation reln, ForkNumber forknum)
{
- MdfdVec *v;
+ int segno;
/*
* NOTE: mdnblocks makes sure we have opened all active segments, so that
*/
mdnblocks(reln, forknum);
- v = mdopen(reln, forknum, EXTENSION_FAIL);
+ segno = reln->md_num_open_segs[forknum];
- while (v != NULL)
+ while (segno > 0)
{
- if (FileSync(v->mdfd_vfd) < 0)
- ereport(ERROR,
+ MdfdVec *v = &reln->md_seg_fds[forknum][segno - 1];
+
+ if (FileSync(v->mdfd_vfd, WAIT_EVENT_DATA_FILE_IMMEDIATE_SYNC) < 0)
+ ereport(data_sync_elevel(ERROR),
(errcode_for_file_access(),
errmsg("could not fsync file \"%s\": %m",
FilePathName(v->mdfd_vfd))));
- v = v->mdfd_chain;
+ segno--;
}
}
* The bitmap manipulations are slightly tricky, because we can call
* AbsorbFsyncRequests() inside the loop and that could result in
* bms_add_member() modifying and even re-palloc'ing the bitmapsets.
- * This is okay because we unlink each bitmapset from the hashtable
- * entry before scanning it. That means that any incoming fsync
- * requests will be processed now if they reach the table before we
- * begin to scan their fork.
+ * So we detach it, but if we fail we'll merge it with any new
+ * requests that have arrived in the meantime.
*/
for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
{
entry->requests[forknum] = NULL;
entry->canceled[forknum] = false;
- while ((segno = bms_first_member(requests)) >= 0)
+ segno = -1;
+ while ((segno = bms_next_member(requests, segno)) >= 0)
{
int failures;
/* Attempt to open and fsync the target segment */
seg = _mdfd_getseg(reln, forknum,
- (BlockNumber) segno * (BlockNumber) RELSEG_SIZE,
- false, EXTENSION_RETURN_NULL);
+ (BlockNumber) segno * (BlockNumber) RELSEG_SIZE,
+ false,
+ EXTENSION_RETURN_NULL
+ | EXTENSION_DONT_CHECK_SIZE);
INSTR_TIME_SET_CURRENT(sync_start);
if (seg != NULL &&
- FileSync(seg->mdfd_vfd) >= 0)
+ FileSync(seg->mdfd_vfd, WAIT_EVENT_DATA_FILE_SYNC) >= 0)
{
/* Success; update statistics about sync timing */
INSTR_TIME_SET_CURRENT(sync_end);
longest = elapsed;
total_elapsed += elapsed;
processed++;
+ requests = bms_del_member(requests, segno);
if (log_checkpoints)
elog(DEBUG1, "checkpoint sync: number=%d file=%s time=%.3f msec",
processed,
*/
if (!FILE_POSSIBLY_DELETED(errno) ||
failures > 0)
- ereport(ERROR,
+ {
+ Bitmapset *new_requests;
+
+ /*
+ * We need to merge these unsatisfied requests with
+ * any others that have arrived since we started.
+ */
+ new_requests = entry->requests[forknum];
+ entry->requests[forknum] =
+ bms_join(new_requests, requests);
+
+ errno = save_errno;
+ ereport(data_sync_elevel(ERROR),
(errcode_for_file_access(),
errmsg("could not fsync file \"%s\": %m",
path)));
+ }
else
ereport(DEBUG1,
(errcode_for_file_access(),
- errmsg("could not fsync file \"%s\" but retrying: %m",
- path)));
+ errmsg("could not fsync file \"%s\" but retrying: %m",
+ path)));
pfree(path);
/*
ereport(DEBUG1,
(errmsg("could not forward fsync request because request queue is full")));
- if (FileSync(seg->mdfd_vfd) < 0)
- ereport(ERROR,
+ if (FileSync(seg->mdfd_vfd, WAIT_EVENT_DATA_FILE_SYNC) < 0)
+ ereport(data_sync_elevel(ERROR),
(errcode_for_file_access(),
errmsg("could not fsync file \"%s\": %m",
FilePathName(seg->mdfd_vfd))));
}
}
+/*
+ * DropRelationFiles -- drop files of all given relations
+ */
+void
+DropRelationFiles(RelFileNode *delrels, int ndelrels, bool isRedo)
+{
+ SMgrRelation *srels;
+ int i;
+
+ srels = palloc(sizeof(SMgrRelation) * ndelrels);
+ for (i = 0; i < ndelrels; i++)
+ {
+ SMgrRelation srel = smgropen(delrels[i], InvalidBackendId);
+
+ if (isRedo)
+ {
+ ForkNumber fork;
+
+ for (fork = 0; fork <= MAX_FORKNUM; fork++)
+ XLogDropRelation(delrels[i], fork);
+ }
+ srels[i] = srel;
+ }
+
+ smgrdounlinkall(srels, ndelrels, isRedo);
+
+ /*
+ * Call smgrclose() in reverse order as when smgropen() is called.
+ * This trick enables remove_from_unowned_list() in smgrclose()
+ * to search the SMgrRelation from the unowned list,
+ * with O(1) performance.
+ */
+ for (i = ndelrels - 1; i >= 0; i--)
+ smgrclose(srels[i]);
+ pfree(srels);
+}
+
/*
- * _fdvec_alloc() -- Make a MdfdVec object.
+ * _fdvec_resize() -- Resize the fork's open segments array
*/
-static MdfdVec *
-_fdvec_alloc(void)
+static void
+_fdvec_resize(SMgrRelation reln,
+ ForkNumber forknum,
+ int nseg)
{
- return (MdfdVec *) MemoryContextAlloc(MdCxt, sizeof(MdfdVec));
+ if (nseg == 0)
+ {
+ if (reln->md_num_open_segs[forknum] > 0)
+ {
+ pfree(reln->md_seg_fds[forknum]);
+ reln->md_seg_fds[forknum] = NULL;
+ }
+ }
+ else if (reln->md_num_open_segs[forknum] == 0)
+ {
+ reln->md_seg_fds[forknum] =
+ MemoryContextAlloc(MdCxt, sizeof(MdfdVec) * nseg);
+ }
+ else
+ {
+ /*
+ * It doesn't seem worthwhile complicating the code by having a more
+ * aggressive growth strategy here; the number of segments doesn't
+ * grow that fast, and the memory context internally will sometimes
+ * avoid doing an actual reallocation.
+ */
+ reln->md_seg_fds[forknum] =
+ repalloc(reln->md_seg_fds[forknum],
+ sizeof(MdfdVec) * nseg);
+ }
+
+ reln->md_num_open_segs[forknum] = nseg;
}
/*
fullpath = _mdfd_segpath(reln, forknum, segno);
/* open the file */
- fd = PathNameOpenFile(fullpath, O_RDWR | PG_BINARY | oflags, 0600);
+ fd = PathNameOpenFile(fullpath, O_RDWR | PG_BINARY | oflags);
pfree(fullpath);
if (fd < 0)
return NULL;
- /* allocate an mdfdvec entry for it */
- v = _fdvec_alloc();
+ if (segno <= reln->md_num_open_segs[forknum])
+ _fdvec_resize(reln, forknum, segno + 1);
/* fill the entry */
+ v = &reln->md_seg_fds[forknum][segno];
v->mdfd_vfd = fd;
v->mdfd_segno = segno;
- v->mdfd_chain = NULL;
+
Assert(_mdnblocks(reln, forknum, v) <= ((BlockNumber) RELSEG_SIZE));
/* all done */
*/
static MdfdVec *
_mdfd_getseg(SMgrRelation reln, ForkNumber forknum, BlockNumber blkno,
- bool skipFsync, ExtensionBehavior behavior)
+ bool skipFsync, int behavior)
{
- MdfdVec *v = mdopen(reln, forknum, behavior);
+ MdfdVec *v;
BlockNumber targetseg;
BlockNumber nextsegno;
- if (!v)
- return NULL; /* only possible if EXTENSION_RETURN_NULL */
+ /* some way to handle non-existent segments needs to be specified */
+ Assert(behavior &
+ (EXTENSION_FAIL | EXTENSION_CREATE | EXTENSION_RETURN_NULL));
targetseg = blkno / ((BlockNumber) RELSEG_SIZE);
- for (nextsegno = 1; nextsegno <= targetseg; nextsegno++)
+
+ /* if an existing and opened segment, we're done */
+ if (targetseg < reln->md_num_open_segs[forknum])
+ {
+ v = &reln->md_seg_fds[forknum][targetseg];
+ return v;
+ }
+
+ /*
+ * The target segment is not yet open. Iterate over all the segments
+ * between the last opened and the target segment. This way missing
+ * segments either raise an error, or get created (according to
+ * 'behavior'). Start with either the last opened, or the first segment if
+ * none was opened before.
+ */
+ if (reln->md_num_open_segs[forknum] > 0)
+ v = &reln->md_seg_fds[forknum][reln->md_num_open_segs[forknum] - 1];
+ else
{
+ v = mdopen(reln, forknum, behavior);
+ if (!v)
+ return NULL; /* if behavior & EXTENSION_RETURN_NULL */
+ }
+
+ for (nextsegno = reln->md_num_open_segs[forknum];
+ nextsegno <= targetseg; nextsegno++)
+ {
+ BlockNumber nblocks = _mdnblocks(reln, forknum, v);
+ int flags = 0;
+
Assert(nextsegno == v->mdfd_segno + 1);
- if (v->mdfd_chain == NULL)
+ if (nblocks > ((BlockNumber) RELSEG_SIZE))
+ elog(FATAL, "segment too big");
+
+ if ((behavior & EXTENSION_CREATE) ||
+ (InRecovery && (behavior & EXTENSION_CREATE_RECOVERY)))
{
/*
* Normally we will create new segments only if authorized by the
* caller (i.e., we are doing mdextend()). But when doing WAL
* recovery, create segments anyway; this allows cases such as
* replaying WAL data that has a write into a high-numbered
- * segment of a relation that was later deleted. We want to go
+ * segment of a relation that was later deleted. We want to go
* ahead and create the segments so we can finish out the replay.
+ * However if the caller has specified
+ * EXTENSION_REALLY_RETURN_NULL, then extension is not desired
+ * even in recovery; we won't reach this point in that case.
*
* We have to maintain the invariant that segments before the last
- * active segment are of size RELSEG_SIZE; therefore, pad them out
- * with zeroes if needed. (This only matters if caller is
- * extending the relation discontiguously, but that can happen in
- * hash indexes.)
+ * active segment are of size RELSEG_SIZE; therefore, if
+ * extending, pad them out with zeroes if needed. (This only
+ * matters if in recovery, or if the caller is extending the
+ * relation discontiguously, but that can happen in hash indexes.)
*/
- if (behavior == EXTENSION_CREATE || InRecovery)
+ if (nblocks < ((BlockNumber) RELSEG_SIZE))
{
- if (_mdnblocks(reln, forknum, v) < RELSEG_SIZE)
- {
- char *zerobuf = palloc0(BLCKSZ);
+ char *zerobuf = palloc0(BLCKSZ);
- mdextend(reln, forknum,
- nextsegno * ((BlockNumber) RELSEG_SIZE) - 1,
- zerobuf, skipFsync);
- pfree(zerobuf);
- }
- v->mdfd_chain = _mdfd_openseg(reln, forknum, +nextsegno, O_CREAT);
+ mdextend(reln, forknum,
+ nextsegno * ((BlockNumber) RELSEG_SIZE) - 1,
+ zerobuf, skipFsync);
+ pfree(zerobuf);
}
- else
- {
- /* We won't create segment if not existent */
- v->mdfd_chain = _mdfd_openseg(reln, forknum, nextsegno, 0);
- }
- if (v->mdfd_chain == NULL)
+ flags = O_CREAT;
+ }
+ else if (!(behavior & EXTENSION_DONT_CHECK_SIZE) &&
+ nblocks < ((BlockNumber) RELSEG_SIZE))
+ {
+ /*
+ * When not extending (or explicitly including truncated
+ * segments), only open the next segment if the current one is
+ * exactly RELSEG_SIZE. If not (this branch), either return NULL
+ * or fail.
+ */
+ if (behavior & EXTENSION_RETURN_NULL)
{
- if (behavior == EXTENSION_RETURN_NULL &&
- FILE_POSSIBLY_DELETED(errno))
- return NULL;
- ereport(ERROR,
- (errcode_for_file_access(),
- errmsg("could not open file \"%s\" (target block %u): %m",
- _mdfd_segpath(reln, forknum, nextsegno),
- blkno)));
+ /*
+ * Some callers discern between reasons for _mdfd_getseg()
+ * returning NULL based on errno. As there's no failing
+ * syscall involved in this case, explicitly set errno to
+ * ENOENT, as that seems the closest interpretation.
+ */
+ errno = ENOENT;
+ return NULL;
}
+
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not open file \"%s\" (target block %u): previous segment is only %u blocks",
+ _mdfd_segpath(reln, forknum, nextsegno),
+ blkno, nblocks)));
+ }
+
+ v = _mdfd_openseg(reln, forknum, nextsegno, flags);
+
+ if (v == NULL)
+ {
+ if ((behavior & EXTENSION_RETURN_NULL) &&
+ FILE_POSSIBLY_DELETED(errno))
+ return NULL;
+ ereport(ERROR,
+ (errcode_for_file_access(),
+ errmsg("could not open file \"%s\" (target block %u): %m",
+ _mdfd_segpath(reln, forknum, nextsegno),
+ blkno)));
}
- v = v->mdfd_chain;
}
+
return v;
}
{
off_t len;
- len = FileSeek(seg->mdfd_vfd, 0L, SEEK_END);
+ len = FileSize(seg->mdfd_vfd);
if (len < 0)
ereport(ERROR,
(errcode_for_file_access(),
projects / postgresql / blobdiff