Fix leaking of small spilled subtransactions during logical decoding.

When, during logical decoding, a transaction gets too big, it's
contents get spilled to disk. Not just the top-transaction gets
spilled, but *also* all of its subtransactions, even if they're not
that large themselves.  Unfortunately we didn't clean up
such small spilled subtransactions from disk.

Fix that, by keeping better track of whether a transaction has been
spilled to disk.

Author: Andres Freund
Reported-By: Dmitriy Sarafannikov, Fabrízio de Royes Mello
Discussion:
    https://postgr.es/m/1457621358.355011041@f382.i.mail.ru
    https://postgr.es/m/CAFcNs+qNMhNYii4nxpO6gqsndiyxNDYV0S=JNq0v_sEE+9PHXg@mail.gmail.com
Backpatch: 9.4-, where logical decoding was introduced

diff --git a/src/backend/replication/logical/reorderbuffer.c b/src/backend/replication/logical/reorderbuffer.c
index 524946a2a273ba91d102f28fc1a1469e0babfd56..8f4f7f842bc2cf57a42afa70c90ea9702d93f62b 100644 (file)
--- a/src/backend/replication/logical/reorderbuffer.c
+++ b/src/backend/replication/logical/reorderbuffer.c
@@ -893,7 +893,7 @@ ReorderBufferIterTXNInit(ReorderBuffer *rb, ReorderBufferTXN *txn)
        {
                ReorderBufferChange *cur_change;
 
-               if (txn->nentries != txn->nentries_mem)
+               if (txn->serialized)
                {
                        /* serialize remaining changes */
                        ReorderBufferSerializeTXN(rb, txn);
@@ -922,7 +922,7 @@ ReorderBufferIterTXNInit(ReorderBuffer *rb, ReorderBufferTXN *txn)
                {
                        ReorderBufferChange *cur_change;
 
-                       if (cur_txn->nentries != cur_txn->nentries_mem)
+                       if (cur_txn->serialized)
                        {
                                /* serialize remaining changes */
                                ReorderBufferSerializeTXN(rb, cur_txn);
@@ -1142,7 +1142,7 @@ ReorderBufferCleanupTXN(ReorderBuffer *rb, ReorderBufferTXN *txn)
        Assert(found);
 
        /* remove entries spilled to disk */
-       if (txn->nentries != txn->nentries_mem)
+       if (txn->serialized)
                ReorderBufferRestoreCleanup(rb, txn);
 
        /* deallocate */
@@ -2124,6 +2124,7 @@ ReorderBufferSerializeTXN(ReorderBuffer *rb, ReorderBufferTXN *txn)
        Assert(spilled == txn->nentries_mem);
        Assert(dlist_is_empty(&txn->changes));
        txn->nentries_mem = 0;
+       txn->serialized = true;
 
        if (fd != -1)
                CloseTransientFile(fd);

diff --git a/src/include/replication/reorderbuffer.h b/src/include/replication/reorderbuffer.h
index 17e47b385b7b83ae30c089ed8b8e78f5f5c0d05e..8d8d418e8e397e6ba15ea4e4942e74792a0a9904 100644 (file)
--- a/src/include/replication/reorderbuffer.h
+++ b/src/include/replication/reorderbuffer.h
@@ -212,6 +212,15 @@ typedef struct ReorderBufferTXN
         */
        uint64          nentries_mem;
 
+       /*
+        * Has this transaction been spilled to disk?  It's not always possible to
+        * deduce that fact by comparing nentries with nentries_mem, because
+        * e.g. subtransactions of a large transaction might get serialized
+        * together with the parent - if they're restored to memory they'd have
+        * nentries_mem == nentries.
+        */
+       bool            serialized;
+
        /*
         * List of ReorderBufferChange structs, including new Snapshots and new
         * CommandIds