public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v2 2/5] Refactor pg_rewind for more clear decision making. 45+ messages / 4 participants [nested] [flat]
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 558 +++++++++++++++++--------------- src/bin/pg_rewind/filemap.h | 69 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 373 insertions(+), 306 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f186..18fad32600 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20b..ec37d0b2e0 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1abc257177..6d19d2be61 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,12 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -377,120 +282,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -581,16 +442,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -631,26 +482,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -670,13 +521,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -825,3 +676,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170..a5e8df57f4 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; - - file_action_t action; - - /* for a regular file */ - size_t oldsize; - size_t newsize; bool isrelfile; /* is it a relation data file? */ - datapagemap_t pagemap; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + datapagemap_t target_modified_pages; + + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ + + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b9..7fc9161b8c 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9a..2baeb74ae9 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 5a7ab764db..e0ed1759cb 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); + + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ filemap_finalize(); - if (showprogress) calculate_totals(); -- 2.18.4 ----Next_Part(Fri_Sep_18_16_41_50_2020_369)-- Content-Type: Text/X-Patch; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="v2_5-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 569 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 371 insertions(+), 317 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..7971daeda5e 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,25 +215,12 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,142 +237,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,14 +253,9 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -361,17 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +281,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); - - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + int64 end_offset; - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +441,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +481,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +520,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +675,180 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Also remove all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + * in the target. + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* FIXME: Check if it points to the same target? */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------BF34D0120055DC3839060F92 Content-Type: text/x-patch; charset=UTF-8; name="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v2-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-08-19 12:34 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 514 ++++++++++++++++---------------- src/bin/pg_rewind/filemap.h | 67 +++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 332 insertions(+), 301 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..18fad32600e 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1879257b66a..431e8e760e0 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,6 +148,65 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_modified_pages.bitmap = NULL; + entry->target_modified_pages.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * @@ -154,18 +215,19 @@ filemap_create(void) * exists in the target and whether the size matches. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); + Assert(filemap->array == NULL); + + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; /* * Skip any files matching the exclusion filters. This has the effect to @@ -199,142 +261,12 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* @@ -345,33 +277,24 @@ process_source_file(const char *path, file_type_t type, size_t newsize, * deletion. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; + /* + * Skip the control file. It is handled specially, after copying all the + * other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return; + /* * Do not apply any exclusion filters here. This has advantage to remove * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -389,120 +312,76 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the + * block that have changed in the target system. It makes note of all the * changed blocks in the pagemap of the file. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { + int64 end_offset; + Assert(entry->isrelfile); - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; - - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", + entry->path); + + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_modified_pages, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -593,16 +472,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -643,26 +512,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_modified_pages.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_modified_pages); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -682,13 +551,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_modified_pages.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_modified_pages.bitmapsize > 0) + datapagemap_print(&entry->target_modified_pages); } } fflush(stdout); @@ -837,3 +706,126 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what to do with each file. + */ +void +filemap_finalize() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + file_action_t action; + + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy + * it in toto. (If it's a relation data file, WAL replay + * after rewinding should re-create it anyway. But there's + * no harm in copying it now.) + */ + if (entry->source_type == FILE_TYPE_DIRECTORY || + entry->source_type == FILE_TYPE_SYMLINK) + { + action = FILE_ACTION_CREATE; + } + else + action = FILE_ACTION_COPY; + } + else if (entry->target_exists && !entry->source_exists) + { + /* Delete file from target */ + action = FILE_ACTION_REMOVE; + } + else if (entry->target_exists && entry->source_exists) + { + /* File exists in both systems */ + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_SYMLINK: + // FIXME: Check if it points to the same target? + action = FILE_ACTION_NONE; + break; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing for. Copy + * it in toto. + * + * An exception: PG_VERSIONs should be identical, but avoid + * overwriting it for paranoia. + */ + if (!pg_str_endswith(entry->path, "PG_VERSION")) + action = FILE_ACTION_COPY; + else + action = FILE_ACTION_NONE; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + action = FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + action = FILE_ACTION_TRUNCATE; + else + action = FILE_ACTION_NONE; + } + break; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else + { + /* Doesn't exist in either server. Why does it have an entry at all?? */ + action = FILE_ACTION_NONE; + } + entry->action = action; + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..a5e8df57f40 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,30 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + datapagemap_t target_modified_pages; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -70,20 +87,19 @@ typedef struct filemap_t /* * After processing all the remote files, the entries in the linked list - * are moved to this array. After processing local files, too, all the + * are moved to this array. After processing local files, too, all the * local entries are added to the array by filemap_finalize, and sorted in - * the final order. After filemap_finalize, all the entries are in the + * the final order. After filemap_finalize, all the entries are in the * array, and the linked list is empty. */ file_entry_t **array; int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +110,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); extern void filemap_finalize(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..7fc9161b8c8 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_modified_pages, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index c9b9e480c0f..210984d302b 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + filemap_finalize(); if (showprogress) calculate_totals(); -- 2.20.1 --------------D93EDEBFB124D563B723F4BD Content-Type: text/x-patch; charset=UTF-8; name="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="0003-pg_rewind-Replace-the-hybrid-list-array-data-structu.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. @ 2020-09-24 17:08 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Heikki Linnakangas @ 2020-09-24 17:08 UTC (permalink / raw) Deciding what to do with each file is now a separate step after all the necessary information has been gathered. It is more clear that way. Previously, the decision-making was divided between process_source_file() and process_target_file(), and it was a bit hard to piece together what the overall rules were. Reviewed-by: Kyotaro Horiguchi, Soumyadeep Chakraborty Discussion: https://www.postgresql.org/message-id/0c5b3783-af52-3ee5-f8fa-6e794061f70d%40iki.fi --- src/bin/pg_rewind/copy_fetch.c | 14 +- src/bin/pg_rewind/file_ops.c | 16 +- src/bin/pg_rewind/filemap.c | 571 +++++++++++++++++--------------- src/bin/pg_rewind/filemap.h | 69 ++-- src/bin/pg_rewind/libpq_fetch.c | 12 +- src/bin/pg_rewind/parsexlog.c | 2 +- src/bin/pg_rewind/pg_rewind.c | 8 +- 7 files changed, 381 insertions(+), 311 deletions(-) diff --git a/src/bin/pg_rewind/copy_fetch.c b/src/bin/pg_rewind/copy_fetch.c index 1edab5f1867..e4b8ce6aaf4 100644 --- a/src/bin/pg_rewind/copy_fetch.c +++ b/src/bin/pg_rewind/copy_fetch.c @@ -210,7 +210,7 @@ copy_executeFileMap(filemap_t *map) for (i = 0; i < map->narray; i++) { entry = map->array[i]; - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_pages_to_overwrite, entry->path); switch (entry->action) { @@ -219,16 +219,16 @@ copy_executeFileMap(filemap_t *map) break; case FILE_ACTION_COPY: - rewind_copy_file_range(entry->path, 0, entry->newsize, true); + rewind_copy_file_range(entry->path, 0, entry->source_size, true); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - rewind_copy_file_range(entry->path, entry->oldsize, - entry->newsize, false); + rewind_copy_file_range(entry->path, entry->target_size, + entry->source_size, false); break; case FILE_ACTION_CREATE: @@ -238,6 +238,10 @@ copy_executeFileMap(filemap_t *map) case FILE_ACTION_REMOVE: remove_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/file_ops.c b/src/bin/pg_rewind/file_ops.c index 55439db20ba..ec37d0b2e0d 100644 --- a/src/bin/pg_rewind/file_ops.c +++ b/src/bin/pg_rewind/file_ops.c @@ -126,8 +126,9 @@ void remove_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_REMOVE); + Assert(entry->target_exists); - switch (entry->type) + switch (entry->target_type) { case FILE_TYPE_DIRECTORY: remove_target_dir(entry->path); @@ -140,6 +141,10 @@ remove_target(file_entry_t *entry) case FILE_TYPE_SYMLINK: remove_target_symlink(entry->path); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } @@ -147,21 +152,26 @@ void create_target(file_entry_t *entry) { Assert(entry->action == FILE_ACTION_CREATE); + Assert(!entry->target_exists); - switch (entry->type) + switch (entry->source_type) { case FILE_TYPE_DIRECTORY: create_target_dir(entry->path); break; case FILE_TYPE_SYMLINK: - create_target_symlink(entry->path, entry->link_target); + create_target_symlink(entry->path, entry->source_link_target); break; case FILE_TYPE_REGULAR: /* can't happen. Regular files are created with open_target_file. */ pg_fatal("invalid action (CREATE) for regular file"); break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("undefined file type for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/filemap.c b/src/bin/pg_rewind/filemap.c index 1abc257177e..79e5bfdc7d1 100644 --- a/src/bin/pg_rewind/filemap.c +++ b/src/bin/pg_rewind/filemap.c @@ -26,6 +26,8 @@ static bool isRelDataFile(const char *path); static char *datasegpath(RelFileNode rnode, ForkNumber forknum, BlockNumber segno); static int path_cmp(const void *a, const void *b); + +static file_entry_t *get_filemap_entry(const char *path, bool create); static int final_filemap_cmp(const void *a, const void *b); static void filemap_list_to_array(filemap_t *map); static bool check_file_excluded(const char *path, bool is_source); @@ -146,33 +148,79 @@ filemap_create(void) filemap = map; } +/* Look up or create entry for 'path' */ +static file_entry_t * +get_filemap_entry(const char *path, bool create) +{ + filemap_t *map = filemap; + file_entry_t *entry; + file_entry_t **e; + file_entry_t key; + file_entry_t *key_ptr; + + if (map->array) + { + key.path = (char *) path; + key_ptr = &key; + e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), + path_cmp); + } + else + e = NULL; + + if (e) + entry = *e; + else if (!create) + entry = NULL; + else + { + /* Create a new entry for this file */ + entry = pg_malloc(sizeof(file_entry_t)); + entry->path = pg_strdup(path); + entry->isrelfile = isRelDataFile(path); + entry->action = FILE_ACTION_UNDECIDED; + + entry->target_exists = false; + entry->target_type = FILE_TYPE_UNDEFINED; + entry->target_size = 0; + entry->target_link_target = NULL; + entry->target_pages_to_overwrite.bitmap = NULL; + entry->target_pages_to_overwrite.bitmapsize = 0; + + entry->source_exists = false; + entry->source_type = FILE_TYPE_UNDEFINED; + entry->source_size = 0; + entry->source_link_target = NULL; + + entry->next = NULL; + + if (map->last) + { + map->last->next = entry; + map->last = entry; + } + else + map->first = map->last = entry; + map->nlist++; + } + + return entry; +} + /* * Callback for processing source file list. * - * This is called once for every file in the source server. We decide what - * action needs to be taken for the file, depending on whether the file - * exists in the target and whether the size matches. + * This is called once for every file in the source server. We record the + * type and size of file, so that decide_file_action() can later decide what + * to do with it. */ void -process_source_file(const char *path, file_type_t type, size_t newsize, +process_source_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - char localpath[MAXPGPATH]; - struct stat statbuf; - filemap_t *map = filemap; - file_action_t action = FILE_ACTION_NONE; - size_t oldsize = 0; file_entry_t *entry; - Assert(map->array == NULL); - - /* - * Skip any files matching the exclusion filters. This has the effect to - * remove all those files on the target. - */ - if (check_file_excluded(path, true)) - return; + Assert(filemap->array == NULL); /* * Pretend that pg_wal is a directory, even if it's really a symlink. We @@ -182,16 +230,6 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - /* - * Skip temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* in source. - * This has the effect that all temporary files in the destination will be - * removed. - */ - if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL) - return; - if (strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) - return; - /* * sanity check: a filename that looks like a data file better be a * regular file @@ -199,158 +237,25 @@ process_source_file(const char *path, file_type_t type, size_t newsize, if (type != FILE_TYPE_REGULAR && isRelDataFile(path)) pg_fatal("data file \"%s\" in source is not a regular file", path); - snprintf(localpath, sizeof(localpath), "%s/%s", datadir_target, path); - - /* Does the corresponding file exist in the target data dir? */ - if (lstat(localpath, &statbuf) < 0) - { - if (errno != ENOENT) - pg_fatal("could not stat file \"%s\": %m", - localpath); - - exists = false; - } - else - exists = true; - - switch (type) - { - case FILE_TYPE_DIRECTORY: - if (exists && !S_ISDIR(statbuf.st_mode) && strcmp(path, "pg_wal") != 0) - { - /* it's a directory in source, but not in target. Strange.. */ - pg_fatal("\"%s\" is not a directory", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_SYMLINK: - if (exists && -#ifndef WIN32 - !S_ISLNK(statbuf.st_mode) -#else - !pgwin32_is_junction(localpath) -#endif - ) - { - /* - * It's a symbolic link in source, but not in target. - * Strange.. - */ - pg_fatal("\"%s\" is not a symbolic link", localpath); - } - - if (!exists) - action = FILE_ACTION_CREATE; - else - action = FILE_ACTION_NONE; - oldsize = 0; - break; - - case FILE_TYPE_REGULAR: - if (exists && !S_ISREG(statbuf.st_mode)) - pg_fatal("\"%s\" is not a regular file", localpath); - - if (!exists || !isRelDataFile(path)) - { - /* - * File exists in source, but not in target. Or it's a - * non-data file that we have no special processing for. Copy - * it in toto. - * - * An exception: PG_VERSIONs should be identical, but avoid - * overwriting it for paranoia. - */ - if (pg_str_endswith(path, "PG_VERSION")) - { - action = FILE_ACTION_NONE; - oldsize = statbuf.st_size; - } - else - { - action = FILE_ACTION_COPY; - oldsize = 0; - } - } - else - { - /* - * It's a data file that exists in both. - * - * If it's larger in target, we can truncate it. There will - * also be a WAL record of the truncation in the source - * system, so WAL replay would eventually truncate the target - * too, but we might as well do it now. - * - * If it's smaller in the target, it means that it has been - * truncated in the target, or enlarged in the source, or - * both. If it was truncated in the target, we need to copy - * the missing tail from the source system. If it was enlarged - * in the source system, there will be WAL records in the - * source system for the new blocks, so we wouldn't need to - * copy them here. But we don't know which scenario we're - * dealing with, and there's no harm in copying the missing - * blocks now, so do it now. - * - * If it's the same size, do nothing here. Any blocks modified - * in the target will be copied based on parsing the target - * system's WAL, and any blocks modified in the source will be - * updated after rewinding, when the source system's WAL is - * replayed. - */ - oldsize = statbuf.st_size; - if (oldsize < newsize) - action = FILE_ACTION_COPY_TAIL; - else if (oldsize > newsize) - action = FILE_ACTION_TRUNCATE; - else - action = FILE_ACTION_NONE; - } - break; - } - - /* Create a new entry for this file */ - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = action; - entry->oldsize = oldsize; - entry->newsize = newsize; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last) - { - map->last->next = entry; - map->last = entry; - } - else - map->first = map->last = entry; - map->nlist++; + /* Remember this source file */ + entry = get_filemap_entry(path, true); + entry->source_exists = true; + entry->source_type = type; + entry->source_size = size; + entry->source_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * Callback for processing target file list. * - * All source files must be already processed before calling this. This only - * marks target data directory's files that didn't exist in the source for - * deletion. + * All source files must be already processed before calling this. We record + * the type and size of file, so that decide_file_action() can later decide + * what to do with it. */ void -process_target_file(const char *path, file_type_t type, size_t oldsize, +process_target_file(const char *path, file_type_t type, size_t size, const char *link_target) { - bool exists; - file_entry_t key; - file_entry_t *key_ptr; filemap_t *map = filemap; file_entry_t *entry; @@ -359,7 +264,6 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, * from the target data folder all paths which have been filtered out from * the source data folder when processing the source files. */ - if (map->array == NULL) { /* on first call, initialize lookup array */ @@ -377,120 +281,77 @@ process_target_file(const char *path, file_type_t type, size_t oldsize, } /* - * Like in process_source_file, pretend that xlog is always a directory. + * Like in process_source_file, pretend that pg_wal is always a directory. */ if (strcmp(path, "pg_wal") == 0 && type == FILE_TYPE_SYMLINK) type = FILE_TYPE_DIRECTORY; - key.path = (char *) path; - key_ptr = &key; - exists = (bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp) != NULL); - - /* Remove any file or folder that doesn't exist in the source system. */ - if (!exists) - { - entry = pg_malloc(sizeof(file_entry_t)); - entry->path = pg_strdup(path); - entry->type = type; - entry->action = FILE_ACTION_REMOVE; - entry->oldsize = oldsize; - entry->newsize = 0; - entry->link_target = link_target ? pg_strdup(link_target) : NULL; - entry->next = NULL; - entry->pagemap.bitmap = NULL; - entry->pagemap.bitmapsize = 0; - entry->isrelfile = isRelDataFile(path); - - if (map->last == NULL) - map->first = entry; - else - map->last->next = entry; - map->last = entry; - map->nlist++; - } - else - { - /* - * We already handled all files that exist in the source system in - * process_source_file(). - */ - } + /* Remember this target file */ + entry = get_filemap_entry(path, true); + entry->target_exists = true; + entry->target_type = type; + entry->target_size = size; + entry->target_link_target = link_target ? pg_strdup(link_target) : NULL; } /* * This callback gets called while we read the WAL in the target, for every - * block that have changed in the target system. It makes note of all the - * changed blocks in the pagemap of the file. + * block that has changed in the target system. It decides if the given + * 'blkno' in the target relfile needs to be overwritten from the source, and + * if so, records it in 'target_pages_to_overwrite' bitmap. + * + * NOTE: All the files on both systems must have already been added to the + * file map! */ void -process_block_change(ForkNumber forknum, RelFileNode rnode, BlockNumber blkno) +process_target_wal_block_change(ForkNumber forknum, RelFileNode rnode, + BlockNumber blkno) { char *path; - file_entry_t key; - file_entry_t *key_ptr; file_entry_t *entry; BlockNumber blkno_inseg; int segno; - filemap_t *map = filemap; - file_entry_t **e; - Assert(map->array); + Assert(filemap->array); segno = blkno / RELSEG_SIZE; blkno_inseg = blkno % RELSEG_SIZE; path = datasegpath(rnode, forknum, segno); - - key.path = (char *) path; - key_ptr = &key; - - e = bsearch(&key_ptr, map->array, map->narray, sizeof(file_entry_t *), - path_cmp); - if (e) - entry = *e; - else - entry = NULL; + entry = get_filemap_entry(path, false); pfree(path); if (entry) { - Assert(entry->isrelfile); + int64 end_offset; - switch (entry->action) - { - case FILE_ACTION_NONE: - case FILE_ACTION_TRUNCATE: - /* skip if we're truncating away the modified block anyway */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->newsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; - - case FILE_ACTION_COPY_TAIL: - - /* - * skip the modified block if it is part of the "tail" that - * we're copying anyway. - */ - if ((blkno_inseg + 1) * BLCKSZ <= entry->oldsize) - datapagemap_add(&entry->pagemap, blkno_inseg); - break; + Assert(entry->isrelfile); - case FILE_ACTION_COPY: - case FILE_ACTION_REMOVE: - break; + if (entry->target_type != FILE_TYPE_REGULAR) + pg_fatal("unexpected page modification for non-regular file \"%s\"", + entry->path); - case FILE_ACTION_CREATE: - pg_fatal("unexpected page modification for directory or symbolic link \"%s\"", entry->path); - } + /* + * If the block beyond the EOF in the source system, no need to + * remember it now, because we're going to truncate it away from the + * target anyway. Also no need to remember the block if it's beyond + * the current EOF in the target system; we will copy it over with the + * "tail" from the source system, anyway. + */ + end_offset = (blkno_inseg + 1) * BLCKSZ; + if (end_offset <= entry->source_size && + end_offset <= entry->target_size) + datapagemap_add(&entry->target_pages_to_overwrite, blkno_inseg); } else { /* * If we don't have any record of this file in the file map, it means - * that it's a relation that doesn't exist in the source system, and - * it was subsequently removed in the target system, too. We can - * safely ignore it. + * that it's a relation that doesn't exist in the source system. It + * could exist in the target system; we haven't moved the target-only + * entries from the linked list to the array yet! But in any case, if + * it doesn't exist in the source it will be removed from the target + * too, and we can safely ignore it. */ } } @@ -505,6 +366,15 @@ check_file_excluded(const char *path, bool is_source) int excludeIdx; const char *filename; + /* + * Skip all temporary files, .../pgsql_tmp/... and .../pgsql_tmp.* + */ + if (strstr(path, "/" PG_TEMP_FILE_PREFIX) != NULL || + strstr(path, "/" PG_TEMP_FILES_DIR "/") != NULL) + { + return true; + } + /* check individual files... */ for (excludeIdx = 0; excludeFiles[excludeIdx].name != NULL; excludeIdx++) { @@ -581,16 +451,6 @@ filemap_list_to_array(filemap_t *map) map->first = map->last = NULL; } -void -filemap_finalize(void) -{ - filemap_t *map = filemap; - - filemap_list_to_array(map); - qsort(map->array, map->narray, sizeof(file_entry_t *), - final_filemap_cmp); -} - static const char * action_to_str(file_action_t action) { @@ -631,26 +491,26 @@ calculate_totals(void) { entry = map->array[i]; - if (entry->type != FILE_TYPE_REGULAR) + if (entry->source_type != FILE_TYPE_REGULAR) continue; - map->total_size += entry->newsize; + map->total_size += entry->source_size; if (entry->action == FILE_ACTION_COPY) { - map->fetch_size += entry->newsize; + map->fetch_size += entry->source_size; continue; } if (entry->action == FILE_ACTION_COPY_TAIL) - map->fetch_size += (entry->newsize - entry->oldsize); + map->fetch_size += (entry->source_size - entry->target_size); - if (entry->pagemap.bitmapsize > 0) + if (entry->target_pages_to_overwrite.bitmapsize > 0) { datapagemap_iterator_t *iter; BlockNumber blk; - iter = datapagemap_iterate(&entry->pagemap); + iter = datapagemap_iterate(&entry->target_pages_to_overwrite); while (datapagemap_next(iter, &blk)) map->fetch_size += BLCKSZ; @@ -670,13 +530,13 @@ print_filemap(void) { entry = map->array[i]; if (entry->action != FILE_ACTION_NONE || - entry->pagemap.bitmapsize > 0) + entry->target_pages_to_overwrite.bitmapsize > 0) { pg_log_debug("%s (%s)", entry->path, action_to_str(entry->action)); - if (entry->pagemap.bitmapsize > 0) - datapagemap_print(&entry->pagemap); + if (entry->target_pages_to_overwrite.bitmapsize > 0) + datapagemap_print(&entry->target_pages_to_overwrite); } } fflush(stdout); @@ -825,3 +685,170 @@ final_filemap_cmp(const void *a, const void *b) else return strcmp(fa->path, fb->path); } + +/* + * Decide what action to perform to a file. + */ +static file_action_t +decide_file_action(file_entry_t *entry) +{ + const char *path = entry->path; + + /* + * Don't touch the control file. It is handled specially, after copying + * all the other files. + */ + if (strcmp(path, "global/pg_control") == 0) + return FILE_ACTION_NONE; + + /* + * Remove all files matching the exclusion filters in the target. + */ + if (check_file_excluded(path, true)) + { + if (entry->target_exists) + return FILE_ACTION_REMOVE; + else + return FILE_ACTION_NONE; + } + + /* + * Handle cases where the file is missing from one of the systems. + */ + if (!entry->target_exists && entry->source_exists) + { + /* + * File exists in source, but not in target. Copy it in toto. (If it's + * a relation data file, WAL replay after rewinding should re-create + * it anyway. But there's no harm in copying it now.) + */ + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + case FILE_TYPE_SYMLINK: + return FILE_ACTION_CREATE; + case FILE_TYPE_REGULAR: + return FILE_ACTION_COPY; + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", entry->path); + break; + } + } + else if (entry->target_exists && !entry->source_exists) + { + /* File exists in target, but not source. Remove it. */ + return FILE_ACTION_REMOVE; + } + else if (!entry->target_exists && !entry->source_exists) + { + /* + * Doesn't exist in either server. Why does it have an entry in the + * first place?? + */ + Assert(false); + return FILE_ACTION_NONE; + } + + /* + * Otherwise, the file exists on both systems + */ + Assert(entry->target_exists && entry->source_exists); + + if (entry->source_type != entry->target_type) + { + /* But it's a different kind of object. Strange.. */ + pg_fatal("file \"%s\" is of different type in source and target", entry->path); + } + + /* + * PG_VERSION files should be identical on both systems, but avoid + * overwriting them for paranoia. + */ + if (pg_str_endswith(entry->path, "PG_VERSION")) + return FILE_ACTION_NONE; + + switch (entry->source_type) + { + case FILE_TYPE_DIRECTORY: + return FILE_ACTION_NONE; + + case FILE_TYPE_SYMLINK: + /* + * XXX: Should we check if it points to the same target? + */ + return FILE_ACTION_NONE; + + case FILE_TYPE_REGULAR: + if (!entry->isrelfile) + { + /* + * It's a non-data file that we have no special processing + * for. Copy it in toto. + */ + return FILE_ACTION_COPY; + } + else + { + /* + * It's a data file that exists in both systems. + * + * If it's larger in target, we can truncate it. There will + * also be a WAL record of the truncation in the source + * system, so WAL replay would eventually truncate the target + * too, but we might as well do it now. + * + * If it's smaller in the target, it means that it has been + * truncated in the target, or enlarged in the source, or + * both. If it was truncated in the target, we need to copy + * the missing tail from the source system. If it was enlarged + * in the source system, there will be WAL records in the + * source system for the new blocks, so we wouldn't need to + * copy them here. But we don't know which scenario we're + * dealing with, and there's no harm in copying the missing + * blocks now, so do it now. + * + * If it's the same size, do nothing here. Any blocks modified + * in the target will be copied based on parsing the target + * system's WAL, and any blocks modified in the source will be + * updated after rewinding, when the source system's WAL is + * replayed. + */ + if (entry->target_size < entry->source_size) + return FILE_ACTION_COPY_TAIL; + else if (entry->target_size > entry->source_size) + return FILE_ACTION_TRUNCATE; + else + return FILE_ACTION_NONE; + } + break; + + case FILE_TYPE_UNDEFINED: + pg_fatal("unknown file type for \"%s\"", path); + break; + } + + /* unreachable */ + pg_fatal("could not decide what to do with file \"%s\"", path); +} + +/* + * Decide what to do with each file. + */ +void +decide_file_actions() +{ + int i; + + filemap_list_to_array(filemap); + + for (i = 0; i < filemap->narray; i++) + { + file_entry_t *entry = filemap->array[i]; + + entry->action = decide_file_action(entry); + } + + /* Sort the actions to the order that they should be performed */ + qsort(filemap->array, filemap->narray, sizeof(file_entry_t *), + final_filemap_cmp); +} diff --git a/src/bin/pg_rewind/filemap.h b/src/bin/pg_rewind/filemap.h index 0cb7425170c..73c687e4e34 100644 --- a/src/bin/pg_rewind/filemap.h +++ b/src/bin/pg_rewind/filemap.h @@ -14,17 +14,21 @@ /* * For every file found in the local or remote system, we have a file entry - * which says what we are going to do with the file. For relation files, - * there is also a page map, marking pages in the file that were changed - * locally. - * - * The enum values are sorted in the order we want actions to be processed. + * that contains information about the file on both systems. For relation + * files, there is also a page map that marks pages in the file that were + * changed in the target after the last common checkpoint. Each entry also + * contains an 'action' field, which says what we are going to do with the + * file. */ + +/* these enum values are sorted in the order we want actions to be processed */ typedef enum { + FILE_ACTION_UNDECIDED = 0, /* not decided yet */ + FILE_ACTION_CREATE, /* create local directory or symbolic link */ FILE_ACTION_COPY, /* copy whole file, overwriting if exists */ - FILE_ACTION_COPY_TAIL, /* copy tail from 'oldsize' to 'newsize' */ + FILE_ACTION_COPY_TAIL, /* copy tail from 'source_size' to 'target_size' */ FILE_ACTION_NONE, /* no action (we might still copy modified * blocks based on the parsed WAL) */ FILE_ACTION_TRUNCATE, /* truncate local file to 'newsize' bytes */ @@ -33,6 +37,8 @@ typedef enum typedef enum { + FILE_TYPE_UNDEFINED = 0, + FILE_TYPE_REGULAR, FILE_TYPE_DIRECTORY, FILE_TYPE_SYMLINK @@ -41,19 +47,34 @@ typedef enum typedef struct file_entry_t { char *path; - file_type_t type; + bool isrelfile; /* is it a relation data file? */ - file_action_t action; + /* + * Status of the file in the target. + */ + bool target_exists; + file_type_t target_type; + size_t target_size; /* for a regular file */ + char *target_link_target; /* for a symlink */ - /* for a regular file */ - size_t oldsize; - size_t newsize; - bool isrelfile; /* is it a relation data file? */ + /* + * Pages that were modified in the target and need to be replaced + * from the source. + */ + datapagemap_t target_pages_to_overwrite; - datapagemap_t pagemap; + /* + * Status of the file in the source. + */ + bool source_exists; + file_type_t source_type; + size_t source_size; + char *source_link_target; /* for a symlink */ - /* for a symlink */ - char *link_target; + /* + * What will we do to the file? + */ + file_action_t action; struct file_entry_t *next; } file_entry_t; @@ -79,11 +100,10 @@ typedef struct filemap_t int narray; /* current length of array */ /* - * Summary information. total_size is the total size of the source - * cluster, and fetch_size is the number of bytes that needs to be copied. + * Summary information. */ - uint64 total_size; - uint64 fetch_size; + uint64 total_size; /* total size of the source cluster */ + uint64 fetch_size; /* number of bytes that needs to be copied */ } filemap_t; extern filemap_t *filemap; @@ -94,11 +114,12 @@ extern void print_filemap(void); /* Functions for populating the filemap */ extern void process_source_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); + size_t size, const char *link_target); extern void process_target_file(const char *path, file_type_t type, - size_t newsize, const char *link_target); -extern void process_block_change(ForkNumber forknum, RelFileNode rnode, - BlockNumber blkno); -extern void filemap_finalize(void); + size_t size, const char *link_target); +extern void process_target_wal_block_change(ForkNumber forknum, + RelFileNode rnode, + BlockNumber blkno); +extern void decide_file_actions(void); #endif /* FILEMAP_H */ diff --git a/src/bin/pg_rewind/libpq_fetch.c b/src/bin/pg_rewind/libpq_fetch.c index bf4dfc23b96..2fc4a784bdb 100644 --- a/src/bin/pg_rewind/libpq_fetch.c +++ b/src/bin/pg_rewind/libpq_fetch.c @@ -465,7 +465,7 @@ libpq_executeFileMap(filemap_t *map) entry = map->array[i]; /* If this is a relation file, copy the modified blocks */ - execute_pagemap(&entry->pagemap, entry->path); + execute_pagemap(&entry->target_pages_to_overwrite, entry->path); switch (entry->action) { @@ -476,15 +476,15 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_COPY: /* Truncate the old file out of the way, if any */ open_target_file(entry->path, true); - fetch_file_range(entry->path, 0, entry->newsize); + fetch_file_range(entry->path, 0, entry->source_size); break; case FILE_ACTION_TRUNCATE: - truncate_target_file(entry->path, entry->newsize); + truncate_target_file(entry->path, entry->source_size); break; case FILE_ACTION_COPY_TAIL: - fetch_file_range(entry->path, entry->oldsize, entry->newsize); + fetch_file_range(entry->path, entry->target_size, entry->source_size); break; case FILE_ACTION_REMOVE: @@ -494,6 +494,10 @@ libpq_executeFileMap(filemap_t *map) case FILE_ACTION_CREATE: create_target(entry); break; + + case FILE_ACTION_UNDECIDED: + pg_fatal("no action decided for \"%s\"", entry->path); + break; } } diff --git a/src/bin/pg_rewind/parsexlog.c b/src/bin/pg_rewind/parsexlog.c index 2229c86f9af..2baeb74ae93 100644 --- a/src/bin/pg_rewind/parsexlog.c +++ b/src/bin/pg_rewind/parsexlog.c @@ -436,6 +436,6 @@ extractPageInfo(XLogReaderState *record) if (forknum != MAIN_FORKNUM) continue; - process_block_change(forknum, rnode, blkno); + process_target_wal_block_change(forknum, rnode, blkno); } } diff --git a/src/bin/pg_rewind/pg_rewind.c b/src/bin/pg_rewind/pg_rewind.c index 5a7ab764db4..4760090d06e 100644 --- a/src/bin/pg_rewind/pg_rewind.c +++ b/src/bin/pg_rewind/pg_rewind.c @@ -369,7 +369,7 @@ main(int argc, char **argv) chkpttli); /* - * Build the filemap, by comparing the source and target data directories. + * Collect information about all files in the target and source systems. */ filemap_create(); if (showprogress) @@ -390,8 +390,12 @@ main(int argc, char **argv) pg_log_info("reading WAL in target"); extractPageMap(datadir_target, chkptrec, lastcommontliIndex, ControlFile_target.checkPoint, restore_command); - filemap_finalize(); + /* + * We have collected all information we need from both systems. Decide + * what to do with each file. + */ + decide_file_actions(); if (showprogress) calculate_totals(); -- 2.20.1 --------------E5E97ECB089CAF17EDB11AD4 Content-Type: text/x-patch; charset=UTF-8; name="v3-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.patch" Content-Transfer-Encoding: 7bit Content-Disposition: attachment; filename*0="v3-0003-pg_rewind-Replace-the-hybrid-list-array-data-stru.pa"; filename*1="tch" ^ permalink raw reply [nested|flat] 45+ messages in thread
* Re: table_tuple_lock's snapshot argument @ 2025-01-21 10:05 Alexander Korotkov <[email protected]> 0 siblings, 1 reply; 45+ messages in thread From: Alexander Korotkov @ 2025-01-21 10:05 UTC (permalink / raw) To: Heikki Linnakangas <[email protected]>; +Cc: pgsql-hackers On Tue, Jan 21, 2025 at 12:03 PM Alexander Korotkov <[email protected]> wrote: > On Sun, Dec 29, 2024 at 3:59 PM Heikki Linnakangas <[email protected]> wrote: > > > > > /* > > > * Lock a tuple in the specified mode. > > > * > > > * Input parameters: > > > * relation: relation containing tuple (caller must hold suitable lock) > > > * tid: TID of tuple to lock > > > * snapshot: snapshot to use for visibility determinations > > > * cid: current command ID (used for visibility test, and stored into > > > * tuple's cmax if lock is successful) > > > * mode: lock mode desired > > > * wait_policy: what to do if tuple lock is not available > > > * flags: > > > * If TUPLE_LOCK_FLAG_LOCK_UPDATE_IN_PROGRESS, follow the update chain to > > > * also lock descendant tuples if lock modes don't conflict. > > > * If TUPLE_LOCK_FLAG_FIND_LAST_VERSION, follow the update chain and lock > > > * latest version. > > > * > > > * Output parameters: > > > * *slot: contains the target tuple > > > * *tmfd: filled in failure cases (see below) > > > * > > > * Function result may be: > > > * TM_Ok: lock was successfully acquired > > > * TM_Invisible: lock failed because tuple was never visible to us > > > * TM_SelfModified: lock failed because tuple updated by self > > > * TM_Updated: lock failed because tuple updated by other xact > > > * TM_Deleted: lock failed because tuple deleted by other xact > > > * TM_WouldBlock: lock couldn't be acquired and wait_policy is skip > > > * > > > * In the failure cases other than TM_Invisible and TM_Deleted, the routine > > > * fills *tmfd with the tuple's t_ctid, t_xmax, and, if possible, t_cmax. See > > > * comments for struct TM_FailureData for additional info. > > > */ > > > static inline TM_Result > > > table_tuple_lock(Relation rel, ItemPointer tid, Snapshot snapshot, > > > TupleTableSlot *slot, CommandId cid, LockTupleMode mode, > > > LockWaitPolicy wait_policy, uint8 flags, > > > TM_FailureData *tmfd) > > > > What are the semantics of the 'snapshot' argument? In the heapam > > implementation, it's not used for anything. What visibility checks the > > function might do in a different implementation? I vaguely remember that > > the idea was that the TID might not be sufficient to uniquely identify > > the row version in something like zheap, which updates the row in place. > > In that case, all the different row versions are represented by the same > > TID, and the snapshot identifies the version. > > > > There are a few callers of table_tuple_lock: > > > > 1. trigger.c: GetTupleForTrigger > > 2. nodeModifyTable.c > > 3. nodeLockRows.c > > 4. execReplication.c > > > > The first three callers pass the EState's snapshot, the same that was > > used in a table or index scan that returned the TID. That makes sense. > > But the calls in execReplication.c look fishy: > > > > > PushActiveSnapshot(GetLatestSnapshot()); > > > > > > res = table_tuple_lock(rel, &(outslot->tts_tid), GetLatestSnapshot(), > > > outslot, > > > GetCurrentCommandId(false), > > > lockmode, > > > LockWaitBlock, > > > 0 /* don't follow updates */ , > > > &tmfd); > > > > > > PopActiveSnapshot(); > > > > > > if (should_refetch_tuple(res, &tmfd)) > > > goto retry; > > > > Firstly, this calls GetLatestSnapshot() twice, which seems plain wrong. > > I think the idea was to push the latest snapshot and use the same > > snapshot in the call to table_tuple_lock(). But because each call to > > GetLatestSnapshot() takes a new snapshot, this pushes one snapshot as > > the active snapshot and passes a *different* snapshot to > > table_tuple_lock(). This went wrong in commit 5db6df0c01, which > > introduced the update/delete/insert/lock table AM interface. The > > argument to table_tuple_lock() was supposed to be GetActiveSnapshot(). > > > > However, I think GetLatestSnapshot() is wrong here anyway. None of this > > matters for heapam which just ignores the 'snapshot' argument, but let's > > assume a different AM that would use the snapshot to identify the tuple > > version. The TID was fetched from an index using an index scan with > > SnapshotDirty. There's no guarantee that the LatestSnapshot would match > > the same tuple version that the index scan found. If an MVCC snapshot is > > needed, surely it should be acquired before the index scan, and used for > > the index scan as well. > > > > I see three options: > > > > 1. Remove the 'snapshot' argument, since it's not used by heapam. If we > > get a table AM where a single TID represents multiple row versions, this > > will need to be revisited. > > > > 2. Rewrite the recheck code in execReplication.c so that it uses the > > snapshot in a more consistent fashion. Call GetLatestSnapshot() first, > > and use the same snapshot in the index scan and table_tuple_lock(). > > Acquiring a snapshot isn't free though, so it would be nice to avoid > > doing that when the heapam is just going to ignore it anyway. If we go > > with this option, I think we could reuse the snapshot that is already > > active in most cases, and only take a new snapshot if the tuple was > > concurrently updated. > > > > 3. Modify the tableam interface so that the index scan can return a more > > unique identifier of the tuple version. In heapam, it could be the TID > > like today, but a different AM could return some other token. Continue > > to use SnapshotDirty in the index scan, but in the call to > > table_tuple_lock(), instead of passing GetLatestSnapshot() and TID, pass > > the token you got index_getnext_slot(). > > Thank you for your finding and analysis. I would vote for #3. > Currently snapshot argument is not properly used, and the heapam code > doesn't check it. I think allowing flexible tuple identifier is > essential for future of table AM API. Therefore, any > snapshot/visibility information could be put inside that tuple > identifier if needed. To be more specific, I vote for #1 + #3. Remove the snapshot argument for now, then work on flexible tuple identifier. ------ Regards, Alexander Korotkov Supabase ^ permalink raw reply [nested|flat] 45+ messages in thread
* Re: table_tuple_lock's snapshot argument @ 2025-03-10 15:22 Heikki Linnakangas <[email protected]> parent: Alexander Korotkov <[email protected]> 0 siblings, 1 reply; 45+ messages in thread From: Heikki Linnakangas @ 2025-03-10 15:22 UTC (permalink / raw) To: Alexander Korotkov <[email protected]>; +Cc: pgsql-hackers On 21/01/2025 12:05, Alexander Korotkov wrote: > On Tue, Jan 21, 2025 at 12:03 PM Alexander Korotkov > <[email protected]> wrote: >> On Sun, Dec 29, 2024 at 3:59 PM Heikki Linnakangas <[email protected]> wrote: >>> However, I think GetLatestSnapshot() is wrong here anyway. None of this >>> matters for heapam which just ignores the 'snapshot' argument, but let's >>> assume a different AM that would use the snapshot to identify the tuple >>> version. The TID was fetched from an index using an index scan with >>> SnapshotDirty. There's no guarantee that the LatestSnapshot would match >>> the same tuple version that the index scan found. If an MVCC snapshot is >>> needed, surely it should be acquired before the index scan, and used for >>> the index scan as well. >>> >>> I see three options: >>> >>> 1. Remove the 'snapshot' argument, since it's not used by heapam. If we >>> get a table AM where a single TID represents multiple row versions, this >>> will need to be revisited. >>> >>> 2. Rewrite the recheck code in execReplication.c so that it uses the >>> snapshot in a more consistent fashion. Call GetLatestSnapshot() first, >>> and use the same snapshot in the index scan and table_tuple_lock(). >>> Acquiring a snapshot isn't free though, so it would be nice to avoid >>> doing that when the heapam is just going to ignore it anyway. If we go >>> with this option, I think we could reuse the snapshot that is already >>> active in most cases, and only take a new snapshot if the tuple was >>> concurrently updated. >>> >>> 3. Modify the tableam interface so that the index scan can return a more >>> unique identifier of the tuple version. In heapam, it could be the TID >>> like today, but a different AM could return some other token. Continue >>> to use SnapshotDirty in the index scan, but in the call to >>> table_tuple_lock(), instead of passing GetLatestSnapshot() and TID, pass >>> the token you got index_getnext_slot(). >> >> Thank you for your finding and analysis. I would vote for #3. >> Currently snapshot argument is not properly used, and the heapam code >> doesn't check it. I think allowing flexible tuple identifier is >> essential for future of table AM API. Therefore, any >> snapshot/visibility information could be put inside that tuple >> identifier if needed. > > To be more specific, I vote for #1 + #3. Remove the snapshot argument > for now, then work on flexible tuple identifier. I committed and backpatched the trivial fix for not, just replacing GetLatestSnapshot() with GetActiveSnapshot(). I got cold feet on just removing the argument without providing a replacement, because it's not 100% clear to me if the current situation is broken or not. To summarize the issue, RelationFindReplTupleByIndex() performs an index scan with DirtySnapshot, and then calls table_tuple_lock() with a fresh MVCC snapshot to lock the row. There's no guarantee that the index scan found the same row version that table_tuple_lock() will lock, if the TID alone doesn't uniquely identify it. But that's still OK as long as the key column hasn't changed, like with heapam's HOT updates. I couldn't convince myself that it's broken nor that it's guaranteed to be correct with other AMs. Thanks! -- Heikki Linnakangas Neon (https://neon.tech) ^ permalink raw reply [nested|flat] 45+ messages in thread
* Re: table_tuple_lock's snapshot argument @ 2025-03-10 16:20 Ranier Vilela <[email protected]> parent: Heikki Linnakangas <[email protected]> 0 siblings, 1 reply; 45+ messages in thread From: Ranier Vilela @ 2025-03-10 16:20 UTC (permalink / raw) To: Heikki Linnakangas <[email protected]>; +Cc: Alexander Korotkov <[email protected]>; pgsql-hackers Em seg., 10 de mar. de 2025 às 12:22, Heikki Linnakangas <[email protected]> escreveu: > On 21/01/2025 12:05, Alexander Korotkov wrote: > > On Tue, Jan 21, 2025 at 12:03 PM Alexander Korotkov > > <[email protected]> wrote: > >> On Sun, Dec 29, 2024 at 3:59 PM Heikki Linnakangas <[email protected]> > wrote: > >>> However, I think GetLatestSnapshot() is wrong here anyway. None of this > >>> matters for heapam which just ignores the 'snapshot' argument, but > let's > >>> assume a different AM that would use the snapshot to identify the tuple > >>> version. The TID was fetched from an index using an index scan with > >>> SnapshotDirty. There's no guarantee that the LatestSnapshot would match > >>> the same tuple version that the index scan found. If an MVCC snapshot > is > >>> needed, surely it should be acquired before the index scan, and used > for > >>> the index scan as well. > >>> > >>> I see three options: > >>> > >>> 1. Remove the 'snapshot' argument, since it's not used by heapam. If we > >>> get a table AM where a single TID represents multiple row versions, > this > >>> will need to be revisited. > >>> > >>> 2. Rewrite the recheck code in execReplication.c so that it uses the > >>> snapshot in a more consistent fashion. Call GetLatestSnapshot() first, > >>> and use the same snapshot in the index scan and table_tuple_lock(). > >>> Acquiring a snapshot isn't free though, so it would be nice to avoid > >>> doing that when the heapam is just going to ignore it anyway. If we go > >>> with this option, I think we could reuse the snapshot that is already > >>> active in most cases, and only take a new snapshot if the tuple was > >>> concurrently updated. > >>> > >>> 3. Modify the tableam interface so that the index scan can return a > more > >>> unique identifier of the tuple version. In heapam, it could be the TID > >>> like today, but a different AM could return some other token. Continue > >>> to use SnapshotDirty in the index scan, but in the call to > >>> table_tuple_lock(), instead of passing GetLatestSnapshot() and TID, > pass > >>> the token you got index_getnext_slot(). > >> > >> Thank you for your finding and analysis. I would vote for #3. > >> Currently snapshot argument is not properly used, and the heapam code > >> doesn't check it. I think allowing flexible tuple identifier is > >> essential for future of table AM API. Therefore, any > >> snapshot/visibility information could be put inside that tuple > >> identifier if needed. > > > > To be more specific, I vote for #1 + #3. Remove the snapshot argument > > for now, then work on flexible tuple identifier. > > I committed and backpatched the trivial fix for not, just replacing > GetLatestSnapshot() with GetActiveSnapshot(). I got cold feet on just > removing the argument without providing a replacement, because it's not > 100% clear to me if the current situation is broken or not. > > To summarize the issue, RelationFindReplTupleByIndex() performs an index > scan with DirtySnapshot, and then calls table_tuple_lock() with a fresh > MVCC snapshot to lock the row. There's no guarantee that the index scan > found the same row version that table_tuple_lock() will lock, if the TID > alone doesn't uniquely identify it. But that's still OK as long as the > key column hasn't changed, like with heapam's HOT updates. I couldn't > convince myself that it's broken nor that it's guaranteed to be correct > with other AMs. > Just for curiosity. *RelationFindReplTupleSeq* on the same source, does not suffer from the same issue? PushActiveSnapshot(GetLatestSnapshot()); res = table_tuple_lock(rel, &(outslot->tts_tid), GetLatestSnapshot(), best regards, Ranier Vilela ^ permalink raw reply [nested|flat] 45+ messages in thread
* Re: table_tuple_lock's snapshot argument @ 2025-03-10 16:52 Heikki Linnakangas <[email protected]> parent: Ranier Vilela <[email protected]> 0 siblings, 1 reply; 45+ messages in thread From: Heikki Linnakangas @ 2025-03-10 16:52 UTC (permalink / raw) To: Ranier Vilela <[email protected]>; +Cc: Alexander Korotkov <[email protected]>; pgsql-hackers On 10/03/2025 18:20, Ranier Vilela wrote: > Just for curiosity. > *RelationFindReplTupleSeq* on the same source, does not suffer > from the same issue? > > PushActiveSnapshot(GetLatestSnapshot()); > > res = table_tuple_lock(rel, &(outslot->tts_tid), GetLatestSnapshot(), :facepalm: yep, it sure does, and FindConflictTuple() too. Thanks, I'll go fix those too. -- Heikki Linnakangas Neon (https://neon.tech) ^ permalink raw reply [nested|flat] 45+ messages in thread
* Re: table_tuple_lock's snapshot argument @ 2025-03-10 16:55 Ranier Vilela <[email protected]> parent: Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 45+ messages in thread From: Ranier Vilela @ 2025-03-10 16:55 UTC (permalink / raw) To: Heikki Linnakangas <[email protected]>; +Cc: Alexander Korotkov <[email protected]>; pgsql-hackers Em seg., 10 de mar. de 2025 às 13:52, Heikki Linnakangas <[email protected]> escreveu: > On 10/03/2025 18:20, Ranier Vilela wrote: > > Just for curiosity. > > *RelationFindReplTupleSeq* on the same source, does not suffer > > from the same issue? > > > > PushActiveSnapshot(GetLatestSnapshot()); > > > > res = table_tuple_lock(rel, &(outslot->tts_tid), GetLatestSnapshot(), > > :facepalm: yep, it sure does, and FindConflictTuple() too. Thanks, I'll > go fix those too. > Thanks. best regards, Ranier Vilela ^ permalink raw reply [nested|flat] 45+ messages in thread
end of thread, other threads:[~2025-03-10 16:55 UTC | newest] Thread overview: 45+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH v2 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-08-19 12:34 [PATCH 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2020-09-24 17:08 [PATCH v3 2/5] Refactor pg_rewind for more clear decision making. Heikki Linnakangas <[email protected]> 2025-01-21 10:05 Re: table_tuple_lock's snapshot argument Alexander Korotkov <[email protected]> 2025-03-10 15:22 ` Re: table_tuple_lock's snapshot argument Heikki Linnakangas <[email protected]> 2025-03-10 16:20 ` Re: table_tuple_lock's snapshot argument Ranier Vilela <[email protected]> 2025-03-10 16:52 ` Re: table_tuple_lock's snapshot argument Heikki Linnakangas <[email protected]> 2025-03-10 16:55 ` Re: table_tuple_lock's snapshot argument Ranier Vilela <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox