agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 2/5] Refactor pg_rewind for more clear decision making. 59+ messages / 7 participants [nested] [flat]
* [PATCH 2/5] Refactor pg_rewind for more clear decision making. @ 2020-08-19 12:34 Heikki Linnakangas <[email protected]> 0 siblings, 0 replies; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ 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; 59+ 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] 59+ messages in thread
* Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-19 16:44 Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-19 16:44 UTC (permalink / raw) To: [email protected] Dear, Last week I installed Postgres 15.8 on my Windows server 2016, I installed the pgadmin thats comes packed with postgresql installer. I already have postgres 12.1 with pgAdmin installed on my server. After installing Postgres 15.8, the respective pgAdmin was not working, it showed error 'Postgres server could not be contacted' But the old pgAdmin(of Postgres12) was working fine, but was not displaying the postgres15 server on server list on pgAdmin. But, I wanted to work on the new pgAdmin (which was installed with postgres15). So I tried to find the solution on internet, and I got the solution. It was just to delete the pgAdmin.bak file from 'C\Users\Username\AppData\Roaming\pgAdmin\' And I did that and It worked, the bew PgAdmin started to work, it also displayed the Postgres15 connection se server list. But after 2 hours, my Windows Server 2016 crashed, and I am not able to boot my system. So on hard restart the system and it restarted well. And I quickly uninstalled the Postgres15 with its pgadmin from the machine. But the system crashed again after uninstalling the postgres 15. Now I am not able to boot the system. Its been 2 days the system is not able to boot. The system is on dell iDrac PowerEdge M6300. Is there any solution for this, I can try the solution if you suggest. We cannot format the Storage as our data is within the hardisk (Raid) type. And we dont have any data backup too. Please help if possible ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-20 12:36 Tomas Vondra <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Tomas Vondra @ 2024-11-20 12:36 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; [email protected] This seems like a combination of (at least) two independent issues - the pgadmin issue and the crash. On 11/19/24 17:44, Sanjay Khatri wrote: > Dear, > Last week I installed Postgres 15.8 on my Windows server 2016, I > installed the pgadmin thats comes packed with postgresql installer. > I already have postgres 12.1 with pgAdmin installed on my server. > After installing Postgres 15.8, the respective pgAdmin was not working, > it showed error 'Postgres server could not be contacted' > But the old pgAdmin(of Postgres12) was working fine, but was not > displaying the postgres15 server on server list on pgAdmin. I don't use pgadmin (or Windows) so I don't have any ideas why it might be having these connection problems, and I'm not sure I quite understand what you did. But it seems the new 15.8 server simply was not running, that would explain all the symptoms. > But, I wanted to work on the new pgAdmin (which was installed with > postgres15). So I tried to find the solution on internet, and I got the > solution. It was just to delete the pgAdmin.bak file from > 'C\Users\Username\AppData\Roaming\pgAdmin\' > And I did that and It worked, the bew PgAdmin started to work, it also > displayed the Postgres15 connection se server list. That is weird, TBH. No idea why deleting a .bak file would matter. > But after 2 hours, my Windows Server 2016 crashed, and I am not able to > boot my system. So on hard restart the system and it restarted well. And > I quickly uninstalled the Postgres15 with its pgadmin from the machine. > But the system crashed again after uninstalling the postgres 15. Now I > am not able to boot the system. Its been 2 days the system is not able > to boot. > The system is on dell iDrac PowerEdge M6300. > Is there any solution for this, I can try the solution if you suggest. > We cannot format the Storage as our data is within the hardisk (Raid) > type. And we dont have any data backup too. > Please help if possible It's very unlikely a Postgres issue would make the whole system crash, particularly in a way that prevents it from booting again. I don't think anyone will be able to help you without more info - you need to make it boot again, inspect the Postgres logs, etc. regards -- Tomas Vondra ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-20 12:56 Daniel Gustafsson <[email protected]> parent: Tomas Vondra <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Daniel Gustafsson @ 2024-11-20 12:56 UTC (permalink / raw) To: Tomas Vondra <[email protected]>; +Cc: Sanjay Khatri <[email protected]>; [email protected] > On 20 Nov 2024, at 13:36, Tomas Vondra <[email protected]> wrote: > On 11/19/24 17:44, Sanjay Khatri wrote: >> And we dont have any data backup too. This will be your first priority once the system is up and running again, maybe even to the point of planning for what immediate action to take before the system boots to be able to act quickly in case it falls over again. > It's very unlikely a Postgres issue would make the whole system crash, > particularly in a way that prevents it from booting again. Agreed, especially since this crash reportedly happened after uninstalling postgres. If the uninstaller could corrupt the OS like that I have a feeling we'd heard about it by now. > I don't think > anyone will be able to help you without more info - you need to make it > boot again, inspect the Postgres logs, etc. I'm not familiar with Dell blade enclosures but if there is a similar system to the iLO Lights Out console that HP ships I would start there (a quick Google search hints at ePSA). -- Daniel Gustafsson ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-20 13:34 Sanjay Khatri <[email protected]> parent: Daniel Gustafsson <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-20 13:34 UTC (permalink / raw) To: [email protected]; +Cc: Tomas Vondra <[email protected]>; [email protected] These are the errors from the logs of iDrac M630. I uninstalled the Postgres 15.8 , once I got the connection. But sadly the server disconnected again and crashed, even after uninstalling. No I am not able to boot it. On Wed, 20 Nov 2024, 18:26 Daniel Gustafsson, <[email protected]> wrote: > > On 20 Nov 2024, at 13:36, Tomas Vondra <[email protected]> wrote: > > On 11/19/24 17:44, Sanjay Khatri wrote: > > >> And we dont have any data backup too. > > This will be your first priority once the system is up and running again, > maybe > even to the point of planning for what immediate action to take before the > system boots to be able to act quickly in case it falls over again. > > > It's very unlikely a Postgres issue would make the whole system crash, > > particularly in a way that prevents it from booting again. > > Agreed, especially since this crash reportedly happened after uninstalling > postgres. If the uninstaller could corrupt the OS like that I have a > feeling > we'd heard about it by now. > > > I don't think > > anyone will be able to help you without more info - you need to make it > > boot again, inspect the Postgres logs, etc. > > I'm not familiar with Dell blade enclosures but if there is a similar > system to > the iLO Lights Out console that HP ships I would start there (a quick > Google > search hints at ePSA). > > -- > Daniel Gustafsson > > Attachments: [image/jpeg] Image.jpg (318.2K, ../../CANLv43+f_oXwVH9egdFXYNwE58TJd2RPT0JHquN7vLsv9cqCKQ@mail.gmail.com/3-Image.jpg) download | view image ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-20 13:41 Daniel Gustafsson <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Daniel Gustafsson @ 2024-11-20 13:41 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] > On 20 Nov 2024, at 14:34, Sanjay Khatri <[email protected]> wrote: > > These are the errors from the logs of iDrac M630. > I uninstalled the Postgres 15.8 , once I got the connection. But sadly the server disconnected again and crashed, even after uninstalling. > No I am not able to boot it. I'm going to go out on a limb and say that this isn't a postgres bug, and highly unlikely to be caused by one. This smells like broken hardware and/or corrupted BIOS/firmware, you should contact your hardware vendor for support. -- Daniel Gustafsson ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-20 13:44 Sanjay Khatri <[email protected]> parent: Daniel Gustafsson <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-20 13:44 UTC (permalink / raw) To: Daniel Gustafsson <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] Yes...I will....but in case someone could provide help it would be good. Rest I will contact the Hardware Support. On Wed, 20 Nov 2024, 19:11 Daniel Gustafsson, <[email protected]> wrote: > > On 20 Nov 2024, at 14:34, Sanjay Khatri <[email protected]> > wrote: > > > > These are the errors from the logs of iDrac M630. > > I uninstalled the Postgres 15.8 , once I got the connection. But sadly > the server disconnected again and crashed, even after uninstalling. > > No I am not able to boot it. > > I'm going to go out on a limb and say that this isn't a postgres bug, and > highly unlikely to be caused by one. This smells like broken hardware > and/or > corrupted BIOS/firmware, you should contact your hardware vendor for > support. > > -- > Daniel Gustafsson > > ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 03:22 Sanjay Khatri <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 03:22 UTC (permalink / raw) To: Daniel Gustafsson <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] We tried it on another server with similar configurations. Just installed the Postgres 15 and its PgAdmin. Kept the server ONN for the whole day, the server was okay. But then we tried the pgAdmin workaround by deleting the pgAdmin.bak file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. Soon within an hour the server crashed. Its happening when PgAdmin workaround is performed. Do Let me know if someone else faced the same issue? On Wed, 20 Nov 2024, 19:14 Sanjay Khatri, <[email protected]> wrote: > Yes...I will....but in case someone could provide help it would be good. > Rest I will contact the Hardware Support. > > On Wed, 20 Nov 2024, 19:11 Daniel Gustafsson, <[email protected]> wrote: > >> > On 20 Nov 2024, at 14:34, Sanjay Khatri <[email protected]> >> wrote: >> > >> > These are the errors from the logs of iDrac M630. >> > I uninstalled the Postgres 15.8 , once I got the connection. But sadly >> the server disconnected again and crashed, even after uninstalling. >> > No I am not able to boot it. >> >> I'm going to go out on a limb and say that this isn't a postgres bug, and >> highly unlikely to be caused by one. This smells like broken hardware >> and/or >> corrupted BIOS/firmware, you should contact your hardware vendor for >> support. >> >> -- >> Daniel Gustafsson >> >> ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 12:16 Daniel Gustafsson <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Daniel Gustafsson @ 2024-11-21 12:16 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] > On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> wrote: > > We tried it on another server with similar configurations. > Just installed the Postgres 15 and its PgAdmin. > Kept the server ONN for the whole day, the server was okay. > But then we tried the pgAdmin workaround by deleting the pgAdmin.bak file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. > Soon within an hour the server crashed. Its happening when PgAdmin workaround is performed. > Do Let me know if someone else faced the same issue? Just to make sure we're talking about the same thing. Did Windows crash and required a restart when you removed a file from pgAdmin, or did the server get bricked and refused to boot at all with systems diagnostics issues? Also, I assume these machines are sitting behind ample firewall protection to keep outside bad actors from reaching them? -- Daniel Gustafsson ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 13:50 Sanjay Khatri <[email protected]> parent: Daniel Gustafsson <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 13:50 UTC (permalink / raw) To: Daniel Gustafsson <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] Yes we are talking about same thing. But this time a different server with Similar configuration. On deleting the pgAdmin.bak file after which I restarted pgAdmin. But after an hour or two, the machine crashed and refuses to boot. And yes these machines have enough firewall protection. On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: > > On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> > wrote: > > > > We tried it on another server with similar configurations. > > Just installed the Postgres 15 and its PgAdmin. > > Kept the server ONN for the whole day, the server was okay. > > But then we tried the pgAdmin workaround by deleting the pgAdmin.bak > file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. > > Soon within an hour the server crashed. Its happening when PgAdmin > workaround is performed. > > Do Let me know if someone else faced the same issue? > > Just to make sure we're talking about the same thing. Did Windows crash > and > required a restart when you removed a file from pgAdmin, or did the server > get > bricked and refused to boot at all with systems diagnostics issues? > > Also, I assume these machines are sitting behind ample firewall protection > to > keep outside bad actors from reaching them? > > -- > Daniel Gustafsson > > ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 14:03 Daniel Gustafsson <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Daniel Gustafsson @ 2024-11-21 14:03 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; +Cc: Tomas Vondra <[email protected]>; [email protected] > On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: > > On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> wrote: > > > > We tried it on another server with similar configurations. > > Just installed the Postgres 15 and its PgAdmin. > > Kept the server ONN for the whole day, the server was okay. > > But then we tried the pgAdmin workaround by deleting the pgAdmin.bak file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. > > Soon within an hour the server crashed. Its happening when PgAdmin workaround is performed. > > Do Let me know if someone else faced the same issue? > > Just to make sure we're talking about the same thing. Did Windows crash and > required a restart when you removed a file from pgAdmin, or did the server get > bricked and refused to boot at all with systems diagnostics issues? > > On 21 Nov 2024, at 14:50, Sanjay Khatri <[email protected]> wrote: > > Yes we are talking about same thing. > But this time a different server with Similar configuration. > On deleting the pgAdmin.bak file after which I restarted pgAdmin. But after an hour or two, the machine crashed and refuses to boot. If removing a file from pgAdmin can brick your server (regardless of it being standard operating procedure or not), then I think it's something which the pgAdmin developers should be made aware of. -- Daniel Gustafsson ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 14:19 Tomas Vondra <[email protected]> parent: Daniel Gustafsson <[email protected]> 0 siblings, 2 replies; 59+ messages in thread From: Tomas Vondra @ 2024-11-21 14:19 UTC (permalink / raw) To: Daniel Gustafsson <[email protected]>; Sanjay Khatri <[email protected]>; +Cc: [email protected] On 11/21/24 15:03, Daniel Gustafsson wrote: >> On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: >>> On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> wrote: >>> >>> We tried it on another server with similar configurations. >>> Just installed the Postgres 15 and its PgAdmin. >>> Kept the server ONN for the whole day, the server was okay. >>> But then we tried the pgAdmin workaround by deleting the pgAdmin.bak file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. >>> Soon within an hour the server crashed. Its happening when PgAdmin workaround is performed. >>> Do Let me know if someone else faced the same issue? >> >> Just to make sure we're talking about the same thing. Did Windows crash and >> required a restart when you removed a file from pgAdmin, or did the server get >> bricked and refused to boot at all with systems diagnostics issues? >> >> On 21 Nov 2024, at 14:50, Sanjay Khatri <[email protected]> wrote: >> >> Yes we are talking about same thing. >> But this time a different server with Similar configuration. >> On deleting the pgAdmin.bak file after which I restarted pgAdmin. But after an hour or two, the machine crashed and refuses to boot. > > If removing a file from pgAdmin can brick your server (regardless of it being > standard operating procedure or not), then I think it's something which the > pgAdmin developers should be made aware of. > Color me skeptical. Weird unexpected things happen, but I simply don't see how removing a .bak file from a regular application, could break the BIOS and cause machine check exceptions there. These things are at least two or three steps apart (BIOS <-> OS <-> application). It's far more likely this is just a traditional hardware issue. If you search for "dell machine check error" you'll find plenty of similar reports. I only checked a couple, but it's invariably some due to some hardware issue. regards -- Tomas Vondra ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 14:24 Sanjay Khatri <[email protected]> parent: Tomas Vondra <[email protected]> 1 sibling, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 14:24 UTC (permalink / raw) To: Tomas Vondra <[email protected]>; +Cc: Daniel Gustafsson <[email protected]>; [email protected] Yeah maybe, we contacted a Hardware Engineer, he told to clean the RAM, etc. If still does not works, then some issue with the motherboard. On Thu, 21 Nov 2024, 19:49 Tomas Vondra, <[email protected]> wrote: > > > On 11/21/24 15:03, Daniel Gustafsson wrote: > >> On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: > >>> On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> > wrote: > >>> > >>> We tried it on another server with similar configurations. > >>> Just installed the Postgres 15 and its PgAdmin. > >>> Kept the server ONN for the whole day, the server was okay. > >>> But then we tried the pgAdmin workaround by deleting the pgAdmin.bak > file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. > >>> Soon within an hour the server crashed. Its happening when PgAdmin > workaround is performed. > >>> Do Let me know if someone else faced the same issue? > >> > >> Just to make sure we're talking about the same thing. Did Windows > crash and > >> required a restart when you removed a file from pgAdmin, or did the > server get > >> bricked and refused to boot at all with systems diagnostics issues? > >> > >> On 21 Nov 2024, at 14:50, Sanjay Khatri <[email protected]> > wrote: > >> > >> Yes we are talking about same thing. > >> But this time a different server with Similar configuration. > >> On deleting the pgAdmin.bak file after which I restarted pgAdmin. But > after an hour or two, the machine crashed and refuses to boot. > > > > If removing a file from pgAdmin can brick your server (regardless of it > being > > standard operating procedure or not), then I think it's something which > the > > pgAdmin developers should be made aware of. > > > > Color me skeptical. Weird unexpected things happen, but I simply don't > see how removing a .bak file from a regular application, could break the > BIOS and cause machine check exceptions there. These things are at least > two or three steps apart (BIOS <-> OS <-> application). > > It's far more likely this is just a traditional hardware issue. If you > search for "dell machine check error" you'll find plenty of similar > reports. I only checked a couple, but it's invariably some due to some > hardware issue. > > > regards > > -- > Tomas Vondra > > ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 14:25 Sanjay Khatri <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 0 replies; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 14:25 UTC (permalink / raw) To: Tomas Vondra <[email protected]>; +Cc: Daniel Gustafsson <[email protected]>; [email protected] But my concern is it occured only after deleting the pgAdmin.bak file. On Thu, 21 Nov 2024, 19:54 Sanjay Khatri, <[email protected]> wrote: > Yeah maybe, we contacted a Hardware Engineer, he told to clean the RAM, > etc. If still does not works, then some issue with the motherboard. > > On Thu, 21 Nov 2024, 19:49 Tomas Vondra, <[email protected]> wrote: > >> >> >> On 11/21/24 15:03, Daniel Gustafsson wrote: >> >> On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: >> >>> On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> >> wrote: >> >>> >> >>> We tried it on another server with similar configurations. >> >>> Just installed the Postgres 15 and its PgAdmin. >> >>> Kept the server ONN for the whole day, the server was okay. >> >>> But then we tried the pgAdmin workaround by deleting the pgAdmin.bak >> file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. >> >>> Soon within an hour the server crashed. Its happening when PgAdmin >> workaround is performed. >> >>> Do Let me know if someone else faced the same issue? >> >> >> >> Just to make sure we're talking about the same thing. Did Windows >> crash and >> >> required a restart when you removed a file from pgAdmin, or did the >> server get >> >> bricked and refused to boot at all with systems diagnostics issues? >> >> >> >> On 21 Nov 2024, at 14:50, Sanjay Khatri <[email protected]> >> wrote: >> >> >> >> Yes we are talking about same thing. >> >> But this time a different server with Similar configuration. >> >> On deleting the pgAdmin.bak file after which I restarted pgAdmin. But >> after an hour or two, the machine crashed and refuses to boot. >> > >> > If removing a file from pgAdmin can brick your server (regardless of it >> being >> > standard operating procedure or not), then I think it's something which >> the >> > pgAdmin developers should be made aware of. >> > >> >> Color me skeptical. Weird unexpected things happen, but I simply don't >> see how removing a .bak file from a regular application, could break the >> BIOS and cause machine check exceptions there. These things are at least >> two or three steps apart (BIOS <-> OS <-> application). >> >> It's far more likely this is just a traditional hardware issue. If you >> search for "dell machine check error" you'll find plenty of similar >> reports. I only checked a couple, but it's invariably some due to some >> hardware issue. >> >> >> regards >> >> -- >> Tomas Vondra >> >> ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 14:53 Dave Page <[email protected]> parent: Tomas Vondra <[email protected]> 1 sibling, 1 reply; 59+ messages in thread From: Dave Page @ 2024-11-21 14:53 UTC (permalink / raw) To: Tomas Vondra <[email protected]>; +Cc: Daniel Gustafsson <[email protected]>; Sanjay Khatri <[email protected]>; [email protected] On Thu, 21 Nov 2024 at 14:19, Tomas Vondra <[email protected]> wrote: > > > On 11/21/24 15:03, Daniel Gustafsson wrote: > >> On Thu, 21 Nov 2024, 17:46 Daniel Gustafsson, <[email protected]> wrote: > >>> On 21 Nov 2024, at 04:22, Sanjay Khatri <[email protected]> > wrote: > >>> > >>> We tried it on another server with similar configurations. > >>> Just installed the Postgres 15 and its PgAdmin. > >>> Kept the server ONN for the whole day, the server was okay. > >>> But then we tried the pgAdmin workaround by deleting the pgAdmin.bak > file in 'AppData/Roaming/pgAdmin' and restarted the PgAdmin. > >>> Soon within an hour the server crashed. Its happening when PgAdmin > workaround is performed. > >>> Do Let me know if someone else faced the same issue? > >> > >> Just to make sure we're talking about the same thing. Did Windows > crash and > >> required a restart when you removed a file from pgAdmin, or did the > server get > >> bricked and refused to boot at all with systems diagnostics issues? > >> > >> On 21 Nov 2024, at 14:50, Sanjay Khatri <[email protected]> > wrote: > >> > >> Yes we are talking about same thing. > >> But this time a different server with Similar configuration. > >> On deleting the pgAdmin.bak file after which I restarted pgAdmin. But > after an hour or two, the machine crashed and refuses to boot. > > > > If removing a file from pgAdmin can brick your server (regardless of it > being > > standard operating procedure or not), then I think it's something which > the > > pgAdmin developers should be made aware of. > > > > Color me skeptical. Weird unexpected things happen, but I simply don't > see how removing a .bak file from a regular application, could break the > BIOS and cause machine check exceptions there. These things are at least > two or three steps apart (BIOS <-> OS <-> application). > Speaking as a pgAdmin dev, and someone with a fair amount of Windows experience over the years, I'd say there is approximately zero chance that deleting a file from a user's roaming profile directory would brick a server, especially a backup of the pgAdmin configuration database (which is a SQLite file). For those that don't know, the roaming profile directory on Windows is a directory where a user's config/data files get synchronised onto each machine they log into within the domain. The equivalent on Linux/macOS is a file in ~/.pgadmin4/ or something along those lines. It is absolutely not a critical part of the OS. > > It's far more likely this is just a traditional hardware issue. If you > search for "dell machine check error" you'll find plenty of similar > reports. I only checked a couple, but it's invariably some due to some > hardware issue. > > > regards > > -- > Tomas Vondra > > > > -- Dave Page pgAdmin: https://www.pgadmin.org PostgreSQL: https://www.postgresql.org ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 15:19 Robert Haas <[email protected]> parent: Dave Page <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Robert Haas @ 2024-11-21 15:19 UTC (permalink / raw) To: Dave Page <[email protected]>; +Cc: Tomas Vondra <[email protected]>; Daniel Gustafsson <[email protected]>; Sanjay Khatri <[email protected]>; [email protected] On Thu, Nov 21, 2024 at 9:53 AM Dave Page <[email protected]> wrote: > Speaking as a pgAdmin dev, and someone with a fair amount of Windows experience over the years, I'd say there is approximately zero chance that deleting a file from a user's roaming profile directory would brick a server, especially a backup of the pgAdmin configuration database (which is a SQLite file). I know a lot less about Windows than you do, but I'm sure you're correct, especially because the crash happened "an hour or two" after deleting pgAdmin.bak. This whole discussion seems quite silly to me. -- Robert Haas EDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 15:35 Sanjay Khatri <[email protected]> parent: Robert Haas <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 15:35 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: Dave Page <[email protected]>; Tomas Vondra <[email protected]>; Daniel Gustafsson <[email protected]>; [email protected] I know its hard to believe this. But you can try doing this from your side and respond here back again. On Thu, 21 Nov 2024, 20:49 Robert Haas, <[email protected]> wrote: > On Thu, Nov 21, 2024 at 9:53 AM Dave Page <[email protected]> wrote: > > Speaking as a pgAdmin dev, and someone with a fair amount of Windows > experience over the years, I'd say there is approximately zero chance that > deleting a file from a user's roaming profile directory would brick a > server, especially a backup of the pgAdmin configuration database (which is > a SQLite file). > > I know a lot less about Windows than you do, but I'm sure you're > correct, especially because the crash happened "an hour or two" after > deleting pgAdmin.bak. > > This whole discussion seems quite silly to me. > > -- > Robert Haas > EDB: http://www.enterprisedb.com > ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 15:42 Dave Page <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Dave Page @ 2024-11-21 15:42 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; +Cc: Robert Haas <[email protected]>; Tomas Vondra <[email protected]>; Daniel Gustafsson <[email protected]>; [email protected] On Thu, 21 Nov 2024 at 15:35, Sanjay Khatri <[email protected]> wrote: > I know its hard to believe this. But you can try doing this from your side > and respond here back again. > I can't speak for Robert, but I've installed and run pgAdmin literally hundreds of times on Windows, Mac, and Linux, and have never seen it even crash a whole machine, let alone render one unbootable. We also probably have hundreds of thousands of users on Windows (based on the number of downloads we get), and have never had such a problem reported. -- Dave Page pgAdmin: https://www.pgadmin.org PostgreSQL: https://www.postgresql.org pgEdge: https://www.pgedge.com ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 15:46 Sanjay Khatri <[email protected]> parent: Dave Page <[email protected]> 0 siblings, 1 reply; 59+ messages in thread From: Sanjay Khatri @ 2024-11-21 15:46 UTC (permalink / raw) To: Dave Page <[email protected]>; +Cc: Robert Haas <[email protected]>; Tomas Vondra <[email protected]>; Daniel Gustafsson <[email protected]>; [email protected] Yes...I have myself installed pgAmdin more than 50 times so far. But this, for the first time ever I have faced this issue. Just try deleting the pgAdmin.bak file for the pg15.8 on a Windows server 2016. Try doing that, lets see. On Thu, 21 Nov 2024, 21:13 Dave Page, <[email protected]> wrote: > > > On Thu, 21 Nov 2024 at 15:35, Sanjay Khatri <[email protected]> > wrote: > >> I know its hard to believe this. But you can try doing this from your >> side and respond here back again. >> > > I can't speak for Robert, but I've installed and run pgAdmin literally > hundreds of times on Windows, Mac, and Linux, and have never seen it even > crash a whole machine, let alone render one unbootable. We also probably > have hundreds of thousands of users on Windows (based on the number of > downloads we get), and have never had such a problem reported. > > -- > Dave Page > pgAdmin: https://www.pgadmin.org > PostgreSQL: https://www.postgresql.org > pgEdge: https://www.pgedge.com > > ^ permalink raw reply [nested|flat] 59+ messages in thread
* Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin @ 2024-11-21 16:29 Ranier Vilela <[email protected]> parent: Sanjay Khatri <[email protected]> 0 siblings, 0 replies; 59+ messages in thread From: Ranier Vilela @ 2024-11-21 16:29 UTC (permalink / raw) To: Sanjay Khatri <[email protected]>; +Cc: Dave Page <[email protected]>; Robert Haas <[email protected]>; Tomas Vondra <[email protected]>; Daniel Gustafsson <[email protected]>; [email protected] Hi. Em qui., 21 de nov. de 2024 às 12:46, Sanjay Khatri < [email protected]> escreveu: > Yes...I have myself installed pgAmdin more than 50 times so far. But this, > for the first time ever I have faced this issue. Just try deleting the > pgAdmin.bak file for the pg15.8 on a Windows server 2016. > Try doing that, lets see. > > On Thu, 21 Nov 2024, 21:13 Dave Page, <[email protected]> wrote: > >> >> >> On Thu, 21 Nov 2024 at 15:35, Sanjay Khatri <[email protected]> >> wrote: >> >>> I know its hard to believe this. But you can try doing this from your >>> side and respond here back again. >>> >> >> I can't speak for Robert, but I've installed and run pgAdmin literally >> hundreds of times on Windows, Mac, and Linux, and have never seen it even >> crash a whole machine, let alone render one unbootable. We also probably >> have hundreds of thousands of users on Windows (based on the number of >> downloads we get), and have never had such a problem reported. >> > I agree with Dave Page. There is a zero chance that Postgres or pgAdmin, may crash or damage the Windows Server. None of these has kernel access. You should be careful about: Old antivirus software Kernel storage incompative drivers Third-party drivers Hardware failure best regards, Ranier Vilela ^ permalink raw reply [nested|flat] 59+ messages in thread
end of thread, other threads:[~2024-11-21 16:29 UTC | newest] Thread overview: 59+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 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 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 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 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 v3 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 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 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 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]> 2024-11-19 16:44 Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-20 12:36 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Tomas Vondra <[email protected]> 2024-11-20 12:56 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Daniel Gustafsson <[email protected]> 2024-11-20 13:34 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-20 13:41 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Daniel Gustafsson <[email protected]> 2024-11-20 13:44 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 03:22 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 12:16 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Daniel Gustafsson <[email protected]> 2024-11-21 13:50 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 14:03 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Daniel Gustafsson <[email protected]> 2024-11-21 14:19 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Tomas Vondra <[email protected]> 2024-11-21 14:24 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 14:25 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 14:53 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Dave Page <[email protected]> 2024-11-21 15:19 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Robert Haas <[email protected]> 2024-11-21 15:35 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 15:42 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Dave Page <[email protected]> 2024-11-21 15:46 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin Sanjay Khatri <[email protected]> 2024-11-21 16:29 ` Re: Windows 2016 server crashed after changes in Postgres 15.8 pgAdmin 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