fix(store): write transactions take the lock at BEGIN, not partway through

Two people saving at the same moment got a 500 after two milliseconds.

The DSN has set busy_timeout since the first commit, and it covered none
of the contention it looks like it covers. With a plain BEGIN a write
transaction starts as a reader and asks for the write lock at its first
UPDATE — and SQLite refuses that upgrade with SQLITE_BUSY immediately,
without applying busy_timeout to it. Backing off cannot help: the
transaction is already holding a read snapshot the other writer is
invalidating.

_txlock=immediate takes the lock at BEGIN instead, where the timeout does
apply and the second writer waits its turn. The driver leaves read-only
transactions deferred, so readers still run concurrently, and every one
of the twenty callers of db.Tx is a write.

Found by opening a task and saving a description, a sub-task and a
comment at once — three writes, one of which came back a 500. The test
fails without the flag.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kristian Wind
2026-08-17 10:56:33 +02:00
committed by Kristian Wind
co-authored by Claude Opus 5
parent 2a3367bfe0
commit 40a679edb6
2 changed files with 60 additions and 0 deletions
+14
View File
@@ -38,6 +38,20 @@ func Open(path string) (*DB, error) {
"_pragma=busy_timeout(5000)",
"_pragma=foreign_keys(ON)",
"_pragma=synchronous(NORMAL)",
// Every write transaction takes the write lock up front.
//
// Without this, `BEGIN` is deferred: a transaction starts as a reader and
// asks for the write lock at its first UPDATE. SQLite refuses that upgrade
// with SQLITE_BUSY *immediately* and does not apply busy_timeout to it —
// backing off cannot help, because the transaction is already holding a
// read snapshot that the other writer is invalidating. So the timeout above
// looks like it covers writer contention and covers none of it: two people
// saving at the same moment get a 500 in two milliseconds.
//
// `immediate` takes the lock at BEGIN instead, where busy_timeout does
// apply and the second writer waits its turn. The driver leaves read-only
// transactions deferred, so readers still run concurrently.
"_txlock=immediate",
// Keep the temp b-trees FTS5 and ORDER BY build in memory rather than
// spilling them into the data volume.
"_pragma=temp_store(MEMORY)",