database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-07-05 07:21:24 +03:00
Code Activity

During recovery, if we reach consistent state and still have entries in the

Browse Source 
invalid-page hash table, PANIC immediately. Immediate PANIC is much better
than waiting for end-of-recovery, which is what we did before, because the
end-of-recovery might not come until months later if this is a standby
server.

Also refrain from creating a restartpoint if there are invalid-page entries
in the hash table. Restarting recovery from such a restartpoint would not
see the invalid references, and wouldn't be able to cross-check them when
consistency is reached. That wouldn't matter when things are going smoothly,
but the more sanity checks you have the better.

Fujii Masao
This commit is contained in:
Heikki Linnakangas
2011-12-02 10:49:54 +02:00
parent 15a5006aac
commit 1e616f6391
4 changed files with 70 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
src/backend/access/transam/xlogutils.c
View File

@ -52,6 +52,22 @@ typedef struct xl_invalid_page
static HTAB *invalid_page_tab = NULL;
/* Report a reference to an invalid page */
static void
report_invalid_page(int elevel, RelFileNode node, ForkNumber forkno,
BlockNumber blkno, bool present)
{
char *path = relpathperm(node, forkno);
if (present)
elog(elevel, "page %u of relation %s is uninitialized",
blkno, path);
else
elog(elevel, "page %u of relation %s does not exist",
blkno, path);
pfree(path);
}
/* Log a reference to an invalid page */
static void
log_invalid_page(RelFileNode node, ForkNumber forkno, BlockNumber blkno,
@ -61,23 +77,27 @@ log_invalid_page(RelFileNode node, ForkNumber forkno, BlockNumber blkno,
xl_invalid_page *hentry;
bool found;
/*
* Once recovery has reached a consistent state, the invalid-page table
* should be empty and remain so. If a reference to an invalid page is
* found after consistency is reached, PANIC immediately. This might
* seem aggressive, but it's better than letting the invalid reference
* linger in the hash table until the end of recovery and PANIC there,
* which might come only much later if this is a standby server.
*/
if (reachedMinRecoveryPoint)
{
report_invalid_page(WARNING, node, forkno, blkno, present);
elog(PANIC, "WAL contains references to invalid pages");
}
/*
* Log references to invalid pages at DEBUG1 level. This allows some
* tracing of the cause (note the elog context mechanism will tell us
* something about the XLOG record that generated the reference).
*/
if (log_min_messages <= DEBUG1 || client_min_messages <= DEBUG1)
{
char *path = relpathperm(node, forkno);
if (present)
elog(DEBUG1, "page %u of relation %s is uninitialized",
blkno, path);
else
elog(DEBUG1, "page %u of relation %s does not exist",
blkno, path);
pfree(path);
}
report_invalid_page(DEBUG1, node, forkno, blkno, present);
if (invalid_page_tab == NULL)
{
@ -181,6 +201,16 @@ forget_invalid_pages_db(Oid dbid)
}
}
/* Are there any unresolved references to invalid pages? */
bool
XLogHaveInvalidPages(void)
{
if (invalid_page_tab != NULL &&
hash_get_num_entries(invalid_page_tab) > 0)
return true;
return false;
}
/* Complain about any remaining invalid-page entries */
void
XLogCheckInvalidPages(void)
@ -200,15 +230,8 @@ XLogCheckInvalidPages(void)
*/
while ((hentry = (xl_invalid_page *) hash_seq_search(&status)) != NULL)
{
char *path = relpathperm(hentry->key.node, hentry->key.forkno);
if (hentry->present)
elog(WARNING, "page %u of relation %s was uninitialized",
hentry->key.blkno, path);
else
elog(WARNING, "page %u of relation %s did not exist",
hentry->key.blkno, path);
pfree(path);
report_invalid_page(WARNING, hentry->key.node, hentry->key.forkno,
hentry->key.blkno, hentry->present);
foundone = true;
}