/*------------------------------------------------------------------------- * * File-processing utility routines. * * Assorted utility functions to work on files. * * * Portions Copyright (c) 1996-2016, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * * src/common/file_utils.c * *------------------------------------------------------------------------- */ #include "postgres_fe.h" #include #include #include #include #include "common/file_utils.h" /* Define PG_FLUSH_DATA_WORKS if we have an implementation for pg_flush_data */ #if defined(HAVE_SYNC_FILE_RANGE) #define PG_FLUSH_DATA_WORKS 1 #elif defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED) #define PG_FLUSH_DATA_WORKS 1 #endif #ifdef PG_FLUSH_DATA_WORKS static void pre_sync_fname(const char *fname, bool isdir, const char *progname); #endif static void walkdir(const char *path, void (*action) (const char *fname, bool isdir, const char *progname), bool process_symlinks, const char *progname); /* * Issue fsync recursively on PGDATA and all its contents. * * We fsync regular files and directories wherever they are, but we * follow symlinks only for pg_xlog and immediately under pg_tblspc. * Other symlinks are presumed to point at files we're not responsible * for fsyncing, and might not have privileges to write at all. * * Errors are reported but not considered fatal. */ void fsync_pgdata(const char *pg_data, const char *progname) { bool xlog_is_symlink; char pg_xlog[MAXPGPATH]; char pg_tblspc[MAXPGPATH]; snprintf(pg_xlog, MAXPGPATH, "%s/pg_xlog", pg_data); snprintf(pg_tblspc, MAXPGPATH, "%s/pg_tblspc", pg_data); /* * If pg_xlog is a symlink, we'll need to recurse into it separately, * because the first walkdir below will ignore it. */ xlog_is_symlink = false; #ifndef WIN32 { struct stat st; if (lstat(pg_xlog, &st) < 0) fprintf(stderr, _("%s: could not stat file \"%s\": %s\n"), progname, pg_xlog, strerror(errno)); else if (S_ISLNK(st.st_mode)) xlog_is_symlink = true; } #else if (pgwin32_is_junction(pg_xlog)) xlog_is_symlink = true; #endif /* * If possible, hint to the kernel that we're soon going to fsync the data * directory and its contents. */ #ifdef PG_FLUSH_DATA_WORKS walkdir(pg_data, pre_sync_fname, false, progname); if (xlog_is_symlink) walkdir(pg_xlog, pre_sync_fname, false, progname); walkdir(pg_tblspc, pre_sync_fname, true, progname); #endif /* * Now we do the fsync()s in the same order. * * The main call ignores symlinks, so in addition to specially processing * pg_xlog if it's a symlink, pg_tblspc has to be visited separately with * process_symlinks = true. Note that if there are any plain directories * in pg_tblspc, they'll get fsync'd twice. That's not an expected case * so we don't worry about optimizing it. */ walkdir(pg_data, fsync_fname, false, progname); if (xlog_is_symlink) walkdir(pg_xlog, fsync_fname, false, progname); walkdir(pg_tblspc, fsync_fname, true, progname); } /* * walkdir: recursively walk a directory, applying the action to each * regular file and directory (including the named directory itself). * * If process_symlinks is true, the action and recursion are also applied * to regular files and directories that are pointed to by symlinks in the * given directory; otherwise symlinks are ignored. Symlinks are always * ignored in subdirectories, ie we intentionally don't pass down the * process_symlinks flag to recursive calls. * * Errors are reported but not considered fatal. * * See also walkdir in fd.c, which is a backend version of this logic. */ static void walkdir(const char *path, void (*action) (const char *fname, bool isdir, const char *progname), bool process_symlinks, const char *progname) { DIR *dir; struct dirent *de; dir = opendir(path); if (dir == NULL) { fprintf(stderr, _("%s: could not open directory \"%s\": %s\n"), progname, path, strerror(errno)); return; } while (errno = 0, (de = readdir(dir)) != NULL) { char subpath[MAXPGPATH]; struct stat fst; int sret; if (strcmp(de->d_name, ".") == 0 || strcmp(de->d_name, "..") == 0) continue; snprintf(subpath, MAXPGPATH, "%s/%s", path, de->d_name); if (process_symlinks) sret = stat(subpath, &fst); else sret = lstat(subpath, &fst); if (sret < 0) { fprintf(stderr, _("%s: could not stat file \"%s\": %s\n"), progname, subpath, strerror(errno)); continue; } if (S_ISREG(fst.st_mode)) (*action) (subpath, false, progname); else if (S_ISDIR(fst.st_mode)) walkdir(subpath, action, false, progname); } if (errno) fprintf(stderr, _("%s: could not read directory \"%s\": %s\n"), progname, path, strerror(errno)); (void) closedir(dir); /* * It's important to fsync the destination directory itself as individual * file fsyncs don't guarantee that the directory entry for the file is * synced. Recent versions of ext4 have made the window much wider but * it's been an issue for ext3 and other filesystems in the past. */ (*action) (path, true, progname); } /* * Hint to the OS that it should get ready to fsync() this file. * * Ignores errors trying to open unreadable files, and reports other errors * non-fatally. */ #ifdef PG_FLUSH_DATA_WORKS static void pre_sync_fname(const char *fname, bool isdir, const char *progname) { int fd; fd = open(fname, O_RDONLY | PG_BINARY); if (fd < 0) { if (errno == EACCES || (isdir && errno == EISDIR)) return; fprintf(stderr, _("%s: could not open file \"%s\": %s\n"), progname, fname, strerror(errno)); return; } /* * We do what pg_flush_data() would do in the backend: prefer to use * sync_file_range, but fall back to posix_fadvise. We ignore errors * because this is only a hint. */ #if defined(HAVE_SYNC_FILE_RANGE) (void) sync_file_range(fd, 0, 0, SYNC_FILE_RANGE_WRITE); #elif defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED) (void) posix_fadvise(fd, 0, 0, POSIX_FADV_DONTNEED); #else #error PG_FLUSH_DATA_WORKS should not have been defined #endif (void) close(fd); } #endif /* PG_FLUSH_DATA_WORKS */ /* * fsync_fname -- Try to fsync a file or directory * * Ignores errors trying to open unreadable files, or trying to fsync * directories on systems where that isn't allowed/required. Reports * other errors non-fatally. */ void fsync_fname(const char *fname, bool isdir, const char *progname) { int fd; int flags; int returncode; /* * Some OSs require directories to be opened read-only whereas other * systems don't allow us to fsync files opened read-only; so we need both * cases here. Using O_RDWR will cause us to fail to fsync files that are * not writable by our userid, but we assume that's OK. */ flags = PG_BINARY; if (!isdir) flags |= O_RDWR; else flags |= O_RDONLY; /* * Open the file, silently ignoring errors about unreadable files (or * unsupported operations, e.g. opening a directory under Windows), and * logging others. */ fd = open(fname, flags); if (fd < 0) { if (errno == EACCES || (isdir && errno == EISDIR)) return; fprintf(stderr, _("%s: could not open file \"%s\": %s\n"), progname, fname, strerror(errno)); return; } returncode = fsync(fd); /* * Some OSes don't allow us to fsync directories at all, so we can ignore * those errors. Anything else needs to be reported. */ if (returncode != 0 && !(isdir && errno == EBADF)) fprintf(stderr, _("%s: could not fsync file \"%s\": %s\n"), progname, fname, strerror(errno)); (void) close(fd); }