mirror of
https://github.com/postgres/postgres.git
synced 2025-08-27 07:42:10 +03:00
e28cf2fbc2
Previously, in unlucky cases, it was possible for pg_rewind to remove
certain WAL segments from the rewound demoted primary. In particular
this happens if those files have been marked for archival (i.e., their
.ready files were created) but not yet archived; the newly promoted node
no longer has such files because of them having been recycled, but they
are likely critical for recovery in the demoted node. If pg_rewind
removes them, recovery is not possible anymore.
Fix this by maintaining a hash table of files in this situation in the
scan that looks for a checkpoint, which the decide_file_actions phase
can consult so that it knows to preserve them.
Backpatch to 14. The problem also exists in 13, but that branch was not
blessed with commit eb00f1d4bf, so this patch is difficult to apply
there. Users of older releases will just have to continue to be extra
careful when rewinding.
Co-authored-by: Полина Бунгина (Polina Bungina) <bungina@gmail.com>
Co-authored-by: Alexander Kukushkin <cyberdemn@gmail.com>
Reviewed-by: Kyotaro Horiguchi <horikyota.ntt@gmail.com>
Reviewed-by: Atsushi Torikoshi <torikoshia@oss.nttdata.com>
Discussion: https://postgr.es/m/CAAtGL4AhzmBRsEsaDdz7065T+k+BscNadfTqP1NcPmsqwA5HBw@mail.gmail.com
117 lines
3.5 KiB
C
117 lines
3.5 KiB
C
/*-------------------------------------------------------------------------
|
|
*
|
|
* filemap.h
|
|
*
|
|
* Copyright (c) 2013-2022, PostgreSQL Global Development Group
|
|
*-------------------------------------------------------------------------
|
|
*/
|
|
#ifndef FILEMAP_H
|
|
#define FILEMAP_H
|
|
|
|
#include "datapagemap.h"
|
|
#include "storage/block.h"
|
|
#include "storage/relfilenode.h"
|
|
|
|
/* 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 '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 */
|
|
FILE_ACTION_REMOVE /* remove local file / directory / symlink */
|
|
} file_action_t;
|
|
|
|
typedef enum
|
|
{
|
|
FILE_TYPE_UNDEFINED = 0,
|
|
|
|
FILE_TYPE_REGULAR,
|
|
FILE_TYPE_DIRECTORY,
|
|
FILE_TYPE_SYMLINK
|
|
} file_type_t;
|
|
|
|
/*
|
|
* For every file found in the local or remote system, we have a file entry
|
|
* 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.
|
|
*
|
|
* When gathering information, these are kept in a hash table, private to
|
|
* filemap.c. decide_file_actions() fills in the 'action' field, sorts all
|
|
* the entries, and returns them in an array, ready for executing the actions.
|
|
*/
|
|
typedef struct file_entry_t
|
|
{
|
|
uint32 status; /* hash status */
|
|
|
|
const char *path;
|
|
bool isrelfile; /* is it a relation data file? */
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
/*
|
|
* Pages that were modified in the target and need to be replaced from the
|
|
* source.
|
|
*/
|
|
datapagemap_t target_pages_to_overwrite;
|
|
|
|
/*
|
|
* 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;
|
|
} file_entry_t;
|
|
|
|
/*
|
|
* This contains the final decisions on what to do with each file.
|
|
* 'entries' array contains an entry for each file, sorted in the order
|
|
* that their actions should executed.
|
|
*/
|
|
typedef struct filemap_t
|
|
{
|
|
/* Summary information, filled by calculate_totals() */
|
|
uint64 total_size; /* total size of the source cluster */
|
|
uint64 fetch_size; /* number of bytes that needs to be copied */
|
|
|
|
int nentries; /* size of 'entries' array */
|
|
file_entry_t *entries[FLEXIBLE_ARRAY_MEMBER];
|
|
} filemap_t;
|
|
|
|
/* Functions for populating the filemap */
|
|
extern void filehash_init(void);
|
|
extern void process_source_file(const char *path, file_type_t type,
|
|
size_t size, const char *link_target);
|
|
extern void process_target_file(const char *path, file_type_t type,
|
|
size_t size, const char *link_target);
|
|
extern void process_target_wal_block_change(ForkNumber forknum,
|
|
RelFileNode rnode,
|
|
BlockNumber blkno);
|
|
|
|
extern filemap_t *decide_file_actions(void);
|
|
extern void calculate_totals(filemap_t *filemap);
|
|
extern void print_filemap(filemap_t *filemap);
|
|
|
|
extern void keepwal_init(void);
|
|
extern void keepwal_add_entry(const char *path);
|
|
|
|
#endif /* FILEMAP_H */
|