mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-03 19:42:55 +00:00
Always truncate WAL after restart (#4464)
c058e1cec2 skipped `truncate_wal()` it if `write_lsn` is equal to
truncation position, but didn't took into account that `write_lsn` is
reset on restart.
Fixes regression looking like:
```
ERROR WAL acceptor{cid=22 ...}:panic{thread=WAL acceptor 19b6c1743666ec02991a7633c57178db/b07db8c88f4c76ea5ed0954c04cc1e74 location=safekeeper/src/wal_storage.rs:230:13}: unexpected write into non-partial segment file
```
This fix will prevent skipping WAL truncation when we are running for
the first time after restart.
This commit is contained in:
committed by
GitHub
parent
e4f05ce0a2
commit
b0286e3c46
@@ -98,6 +98,22 @@ pub struct PhysicalStorage {
|
||||
/// - points to write_lsn, so no seek is needed for writing
|
||||
/// - doesn't point to the end of the segment
|
||||
file: Option<File>,
|
||||
|
||||
/// When false, we have just initialized storage using the LSN from find_end_of_wal().
|
||||
/// In this case, [`write_lsn`] can be less than actually written WAL on disk. In particular,
|
||||
/// there can be a case with unexpected .partial file.
|
||||
///
|
||||
/// Imagine the following:
|
||||
/// - 000000010000000000000001
|
||||
/// - it was fully written, but the last record is split between 2 segments
|
||||
/// - after restart, find_end_of_wal() returned 0/1FFFFF0, which is in the end of this segment
|
||||
/// - write_lsn, write_record_lsn and flush_record_lsn were initialized to 0/1FFFFF0
|
||||
/// - 000000010000000000000002.partial
|
||||
/// - it has only 1 byte written, which is not enough to make a full WAL record
|
||||
///
|
||||
/// Partial segment 002 has no WAL records, and it will be removed by the next truncate_wal().
|
||||
/// This flag will be set to true after the first truncate_wal() call.
|
||||
is_truncated_after_restart: bool,
|
||||
}
|
||||
|
||||
impl PhysicalStorage {
|
||||
@@ -157,6 +173,7 @@ impl PhysicalStorage {
|
||||
flush_record_lsn: flush_lsn,
|
||||
decoder: WalStreamDecoder::new(write_lsn, state.server.pg_version / 10000),
|
||||
file: None,
|
||||
is_truncated_after_restart: false,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -381,7 +398,10 @@ impl Storage for PhysicalStorage {
|
||||
|
||||
// Quick exit if nothing to do to avoid writing up to 16 MiB of zeros on
|
||||
// disk (this happens on each connect).
|
||||
if end_pos == self.write_lsn {
|
||||
if self.is_truncated_after_restart
|
||||
&& end_pos == self.write_lsn
|
||||
&& end_pos == self.flush_record_lsn
|
||||
{
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
@@ -414,6 +434,7 @@ impl Storage for PhysicalStorage {
|
||||
self.write_lsn = end_pos;
|
||||
self.write_record_lsn = end_pos;
|
||||
self.flush_record_lsn = end_pos;
|
||||
self.is_truncated_after_restart = true;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user