src/db.zig

@@ -165,7 +165,13 @@ pub const Collection = struct {
         // an extent recycled off the free list starts *below* the mark and is
         // still writable. Asking the mark meant every recycled extent was thrown
         // away after one document, so churn never reused anything.
-        if (self.pager.is_unpublished_at(self.slab_tail) and self.slab_tail + len <= self.slab_end) return;
+        //
+        // Room is checked from the *rounded-up* cursor rather than the cursor
+        // itself, so the round-up `slab_append` may have to do is guaranteed to
+        // fit. Without that the append's own re-check could discover it needs a
+        // fresh extent, which is fallible, after the log record is already
+        // durable. Costs under one system page per extent.
+        if (self.pager.is_unpublished_at(self.slab_tail) and self.appendable_end(len)) return;
         // The page holding the tail is frozen, but the *rest* of the extent is
         // not: nothing above the live cursor is referenced by the image or by an
         // index. So skip to the next system page and keep the extent, instead of
@@ -179,8 +185,8 @@ pub const Collection = struct {
         // collections: the data file reached 11.8x the live data and grew by
         // ~335 MB per checkpoint, heading for DatabaseTooLarge at around 6 GB of
         // real data.
-        const resumed = std.mem.alignForward(u64, self.slab_tail, pgr.map_align);
-        if (resumed + len <= self.slab_end) {
+        if (self.appendable_end(len)) {
+            const resumed = std.mem.alignForward(u64, self.slab_tail, pgr.map_align);
             self.pager.mark_appendable(resumed, self.slab_end);
             self.slab_tail = resumed;
             return;
@@ -198,9 +204,34 @@ pub const Collection = struct {
         self.slab_end = self.slab_tail + (@as(u64, want_pages) << pgr.page_shift);
     }
 
+    /// Whether a document of `len` bytes fits in this extent even if the cursor
+    /// first has to be rounded up to a system page. The reservation and the
+    /// append both ask this, so they agree on what "there is room" means.
+    fn appendable_end(self: *const Collection, len: usize) bool {
+        return std.mem.alignForward(u64, self.slab_tail, pgr.map_align) + len <= self.slab_end;
+    }
+
     /// Copy `bytes` into the slab and return its absolute file offset.
     /// Infallible: slab_reserve must have run for at least this many bytes.
     fn slab_append(self: *Collection, bytes: []const u8) u64 {
+        // The cursor was checked in `slab_reserve`, but a checkpoint can have
+        // published since -- the reservation runs before the log append and this
+        // runs after it, with an fsync in between. `publish` clears the whole
+        // unpublished set, so a cursor that was writable then can be inside the
+        // frozen image now, and the copy below would store into it: a bus error
+        // where the protection is compiled in, and a silent overwrite of durable
+        // data in ReleaseFast, where it is not.
+        //
+        // Re-arming is infallible because `slab_reserve` measured its room from
+        // the rounded-up cursor. The pager's append lock holds off the next
+        // publish for the rest of this function, so the answer stays true.
+        self.pager.lock_append();
+        defer self.pager.unlock_append();
+        if (!self.pager.is_unpublished_at(self.slab_tail)) {
+            const resumed = std.mem.alignForward(u64, self.slab_tail, pgr.map_align);
+            self.pager.mark_appendable(resumed, self.slab_end);
+            self.slab_tail = resumed;
+        }
         assert_msg(
             self.slab_tail + bytes.len <= self.slab_end,
             "document append overran the slab reservation",

src/pager.zig

@@ -241,6 +241,21 @@ pub const Pager = struct {
     /// the log append -- that is what per-consumer reservations buy.
     alloc_lock: std.Io.Mutex,
 
+    /// Separates a publish from the appends that are mid-flight.
+    ///
+    /// An appender asks `is_unpublished_at` whether its cursor is still
+    /// writable, and copies bytes there afterwards. `publish` clears the whole
+    /// unpublished set and mprotects the image between those two steps, so the
+    /// answer was stale by the time it was used and the copy landed in the
+    /// published image: SIGBUS where the protection is compiled in, a silent
+    /// store into the durable image in ReleaseFast, where it is not.
+    ///
+    /// Shared by appenders so writers on different collections still run
+    /// concurrently -- the decomposition ROADMAP item 5 measured is not given
+    /// back. Exclusive only for the tail of a publish, which happens once per
+    /// checkpoint.
+    append_lock: std.Io.RwLock,
+
     /// True when this file was created by this open (no checkpoint to load).
     fresh: bool,
 
@@ -358,6 +373,7 @@ pub const Pager = struct {
             .alloc_tail = page_first_data,
             .reserved_pages = 0,
             .alloc_lock = .init,
+            .append_lock = .init,
             .fresh = created,
             .loaded = .{},
             .generation = 0,
@@ -529,6 +545,18 @@ pub const Pager = struct {
         return self.is_unpublished(@intCast(off >> page_shift));
     }
 
+    /// Hold off the next publish while an append decides where to put its bytes
+    /// and puts them there. Uncancelable and infallible: the append runs after
+    /// the log record is durable, where there is nowhere to report a failure.
+    /// See `append_lock`.
+    pub fn lock_append(self: *Pager) void {
+        self.append_lock.lockSharedUncancelable(self.io);
+    }
+
+    pub fn unlock_append(self: *Pager) void {
+        self.append_lock.unlockShared(self.io);
+    }
+
     /// The one page a write may legitimately land on below the stable mark: a
     /// watermark slot. Overwriting the *inactive* slot is the whole mechanism --
     /// alternating by generation parity is what makes it safe, where every other
@@ -1037,6 +1065,15 @@ pub const Pager = struct {
 
         // 6. only now is the new image current: advance the stable mark and
         //    rotate the free lists by one generation.
+        //
+        //    Exclusive against the appenders for this step alone. Freezing the
+        //    image while one of them is between "is my cursor still writable"
+        //    and the copy that relies on the answer is what put documents into
+        //    the durable image; holding them off here is what makes the answer
+        //    still true when it is used. Taken before `alloc_lock`, the order
+        //    `mark_appendable` uses on the appender's side.
+        self.append_lock.lockUncancelable(self.io);
+        defer self.append_lock.unlock(self.io);
         self.generation = wm.generation;
         self.loaded = wm;
         // The free lists and the unpublished set are allocator state, so the