Perform a lot more sanity checks when freezing tuples.

The previous commit has shown that the sanity checks around freezing
aren't strong enough. Strengthening them seems especially important
because the existance of the bug has caused corruption that we don't
want to make even worse during future vacuum cycles.

The errors are emitted with ereport rather than elog, despite being
"should never happen" messages, so a proper error code is emitted. To
avoid superflous translations, mark messages as internal.

Author: Andres Freund and Alvaro Herrera
Reviewed-By: Alvaro Herrera, Michael Paquier
Discussion: https://postgr.es/m/20171102112019.33wb7g5wp4zpjelu@alap3.anarazel.de
Backpatch: 9.3-

diff --git a/src/backend/access/heap/heapam.c b/src/backend/access/heap/heapam.c
index 3acef279f473069f7de9ff289d3f92a75b5dec1f..54f1100ffdfaa3ee4ba4f8d70eb83ee3b081fa88 100644 (file)
--- a/src/backend/access/heap/heapam.c
+++ b/src/backend/access/heap/heapam.c
@@ -6357,6 +6357,7 @@ heap_inplace_update(Relation relation, HeapTuple tuple)
  */
 static TransactionId
 FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
+                                 TransactionId relfrozenxid, TransactionId relminmxid,
                                  TransactionId cutoff_xid, MultiXactId cutoff_multi,
                                  uint16 *flags)
 {
@@ -6383,16 +6384,26 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
                *flags |= FRM_INVALIDATE_XMAX;
                return InvalidTransactionId;
        }
+       else if (MultiXactIdPrecedes(multi, relminmxid))
+               ereport(ERROR,
+                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                errmsg_internal("found multixact %u from before relminmxid %u",
+                                                                multi, relminmxid)));
        else if (MultiXactIdPrecedes(multi, cutoff_multi))
        {
                /*
-                * This old multi cannot possibly have members still running.  If it
-                * was a locker only, it can be removed without any further
-                * consideration; but if it contained an update, we might need to
-                * preserve it.
+                * This old multi cannot possibly have members still running, but
+                * verify just in case.  If it was a locker only, it can be removed
+                * without any further consideration; but if it contained an update, we
+                * might need to preserve it.
                 */
-               Assert(!MultiXactIdIsRunning(multi,
-                                                                        HEAP_XMAX_IS_LOCKED_ONLY(t_infomask)));
+               if (MultiXactIdIsRunning(multi,
+                                                                HEAP_XMAX_IS_LOCKED_ONLY(t_infomask)))
+                       ereport(ERROR,
+                                       (errcode(ERRCODE_DATA_CORRUPTED),
+                                        errmsg_internal("multixact %u from before cutoff %u found to be still running",
+                                                                        multi, cutoff_multi)));
+
                if (HEAP_XMAX_IS_LOCKED_ONLY(t_infomask))
                {
                        *flags |= FRM_INVALIDATE_XMAX;
@@ -6406,13 +6417,22 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
                        /* wasn't only a lock, xid needs to be valid */
                        Assert(TransactionIdIsValid(xid));
 
+                       if (TransactionIdPrecedes(xid, relfrozenxid))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                                errmsg_internal("found update xid %u from before relfrozenxid %u",
+                                                                                xid, relfrozenxid)));
+
                        /*
                         * If the xid is older than the cutoff, it has to have aborted,
                         * otherwise the tuple would have gotten pruned away.
                         */
                        if (TransactionIdPrecedes(xid, cutoff_xid))
                        {
-                               Assert(!TransactionIdDidCommit(xid));
+                               if (TransactionIdDidCommit(xid))
+                                       ereport(ERROR,
+                                                       (errcode(ERRCODE_DATA_CORRUPTED),
+                                                        errmsg_internal("cannot freeze committed update xid %u", xid)));
                                *flags |= FRM_INVALIDATE_XMAX;
                                xid = InvalidTransactionId; /* not strictly necessary */
                        }
@@ -6484,6 +6504,13 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
                {
                        TransactionId xid = members[i].xid;
 
+                       Assert(TransactionIdIsValid(xid));
+                       if (TransactionIdPrecedes(xid, relfrozenxid))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                                errmsg_internal("found update xid %u from before relfrozenxid %u",
+                                                                                xid, relfrozenxid)));
+
                        /*
                         * It's an update; should we keep it?  If the transaction is known
                         * aborted or crashed then it's okay to ignore it, otherwise not.
@@ -6512,18 +6539,26 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
                                update_committed = true;
                                update_xid = xid;
                        }
-
-                       /*
-                        * Not in progress, not committed -- must be aborted or crashed;
-                        * we can ignore it.
-                        */
+                       else
+                       {
+                               /*
+                                * Not in progress, not committed -- must be aborted or crashed;
+                                * we can ignore it.
+                                */
+                       }
 
                        /*
                         * Since the tuple wasn't marked HEAPTUPLE_DEAD by vacuum, the
-                        * update Xid cannot possibly be older than the xid cutoff.
+                        * update Xid cannot possibly be older than the xid cutoff. The
+                        * presence of such a tuple would cause corruption, so be paranoid
+                        * and check.
                         */
-                       Assert(!TransactionIdIsValid(update_xid) ||
-                                  !TransactionIdPrecedes(update_xid, cutoff_xid));
+                       if (TransactionIdIsValid(update_xid) &&
+                               TransactionIdPrecedes(update_xid, cutoff_xid))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                                errmsg_internal("found update xid %u from before xid cutoff %u",
+                                                                                update_xid, cutoff_xid)));
 
                        /*
                         * If we determined that it's an Xid corresponding to an update
@@ -6620,8 +6655,9 @@ FreezeMultiXactId(MultiXactId multi, uint16 t_infomask,
  * recovery.  We really need to remove old xids.
  */
 bool
-heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
-                                                 TransactionId cutoff_multi,
+heap_prepare_freeze_tuple(HeapTupleHeader tuple,
+                                                 TransactionId relfrozenxid, TransactionId relminmxid,
+                                                 TransactionId cutoff_xid, TransactionId cutoff_multi,
                                                  xl_heap_freeze_tuple *frz, bool *totally_frozen_p)
 {
        bool            changed = false;
@@ -6638,8 +6674,20 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
        xid = HeapTupleHeaderGetXmin(tuple);
        if (TransactionIdIsNormal(xid))
        {
+               if (TransactionIdPrecedes(xid, relfrozenxid))
+                       ereport(ERROR,
+                                       (errcode(ERRCODE_DATA_CORRUPTED),
+                                        errmsg_internal("found xmin %u from before relfrozenxid %u",
+                                                                        xid, relfrozenxid)));
+
                if (TransactionIdPrecedes(xid, cutoff_xid))
                {
+                       if (!TransactionIdDidCommit(xid))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                                errmsg_internal("uncommitted xmin %u from before xid cutoff %u needs to be frozen",
+                                                                                xid, cutoff_xid)));
+
                        frz->t_infomask |= HEAP_XMIN_FROZEN;
                        changed = true;
                }
@@ -6664,6 +6712,7 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
                uint16          flags;
 
                newxmax = FreezeMultiXactId(xid, tuple->t_infomask,
+                                                                       relfrozenxid, relminmxid,
                                                                        cutoff_xid, cutoff_multi, &flags);
 
                if (flags & FRM_INVALIDATE_XMAX)
@@ -6713,8 +6762,28 @@ heap_prepare_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
        }
        else if (TransactionIdIsNormal(xid))
        {
+               if (TransactionIdPrecedes(xid, relfrozenxid))
+                       ereport(ERROR,
+                                       (errcode(ERRCODE_DATA_CORRUPTED),
+                                        errmsg_internal("found xmax %u from before relfrozenxid %u",
+                                                                        xid, relfrozenxid)));
+
                if (TransactionIdPrecedes(xid, cutoff_xid))
+               {
+                       /*
+                        * If we freeze xmax, make absolutely sure that it's not an XID
+                        * that is important.  (Note, a lock-only xmax can be removed
+                        * independent of committedness, since a committed lock holder has
+                        * released the lock).
+                        */
+                       if (!(tuple->t_infomask & HEAP_XMAX_LOCK_ONLY) &&
+                               TransactionIdDidCommit(xid))
+                               ereport(ERROR,
+                                               (errcode(ERRCODE_DATA_CORRUPTED),
+                                                errmsg_internal("cannot freeze committed xmax %u",
+                                                                                xid)));
                        freeze_xmax = true;
+               }
                else
                        totally_frozen = false;
        }
@@ -6819,14 +6888,17 @@ heap_execute_freeze_tuple(HeapTupleHeader tuple, xl_heap_freeze_tuple *frz)
  * Useful for callers like CLUSTER that perform their own WAL logging.
  */
 bool
-heap_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
-                                 TransactionId cutoff_multi)
+heap_freeze_tuple(HeapTupleHeader tuple,
+                                 TransactionId relfrozenxid, TransactionId relminmxid,
+                                 TransactionId cutoff_xid, TransactionId cutoff_multi)
 {
        xl_heap_freeze_tuple frz;
        bool            do_freeze;
        bool            tuple_totally_frozen;
 
-       do_freeze = heap_prepare_freeze_tuple(tuple, cutoff_xid, cutoff_multi,
+       do_freeze = heap_prepare_freeze_tuple(tuple,
+                                                                                 relfrozenxid, relminmxid,
+                                                                                 cutoff_xid, cutoff_multi,
                                                                                  &frz, &tuple_totally_frozen);
 
        /*

diff --git a/src/backend/access/heap/rewriteheap.c b/src/backend/access/heap/rewriteheap.c
index f93c194e182c4fc4bd5680eb516baacdc3c8525c..7d163c91379e84cdc734e5d37a9fc96b5046e60a 100644 (file)
--- a/src/backend/access/heap/rewriteheap.c
+++ b/src/backend/access/heap/rewriteheap.c
@@ -407,7 +407,10 @@ rewrite_heap_tuple(RewriteState state,
         * While we have our hands on the tuple, we may as well freeze any
         * eligible xmin or xmax, so that future VACUUM effort can be saved.
         */
-       heap_freeze_tuple(new_tuple->t_data, state->rs_freeze_xid,
+       heap_freeze_tuple(new_tuple->t_data,
+                                         state->rs_old_rel->rd_rel->relfrozenxid,
+                                         state->rs_old_rel->rd_rel->relminmxid,
+                                         state->rs_freeze_xid,
                                          state->rs_cutoff_multi);
 
        /*

diff --git a/src/backend/commands/vacuumlazy.c b/src/backend/commands/vacuumlazy.c
index 20ce431e46c9f92035d9505101b0e4716c170fb7..f95346acdb5cbe25ecb5bce02eb0748a7274231d 100644 (file)
--- a/src/backend/commands/vacuumlazy.c
+++ b/src/backend/commands/vacuumlazy.c
@@ -467,6 +467,8 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats,
                                blkno;
        HeapTupleData tuple;
        char       *relname;
+       TransactionId relfrozenxid = onerel->rd_rel->relfrozenxid;
+       TransactionId relminmxid = onerel->rd_rel->relminmxid;
        BlockNumber empty_pages,
                                vacuumed_pages;
        double          num_tuples,
@@ -1004,6 +1006,13 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats,
                                         * tuple, we choose to keep it, because it'll be a lot
                                         * cheaper to get rid of it in the next pruning pass than
                                         * to treat it like an indexed tuple.
+                                        *
+                                        * If this were to happen for a tuple that actually needed
+                                        * to be deleted, we'd be in trouble, because it'd
+                                        * possibly leave a tuple below the relation's xmin
+                                        * horizon alive.  heap_prepare_freeze_tuple() is prepared
+                                        * to detect that case and abort the transaction,
+                                        * preventing corruption.
                                         */
                                        if (HeapTupleIsHotUpdated(&tuple) ||
                                                HeapTupleIsHeapOnly(&tuple))
@@ -1095,8 +1104,10 @@ lazy_scan_heap(Relation onerel, int options, LVRelStats *vacrelstats,
                                 * Each non-removable tuple must be checked to see if it needs
                                 * freezing.  Note we already have exclusive buffer lock.
                                 */
-                               if (heap_prepare_freeze_tuple(tuple.t_data, FreezeLimit,
-                                                                                         MultiXactCutoff, &frozen[nfrozen],
+                               if (heap_prepare_freeze_tuple(tuple.t_data,
+                                                                                         relfrozenxid, relminmxid,
+                                                                                         FreezeLimit, MultiXactCutoff,
+                                                                                         &frozen[nfrozen],
                                                                                          &tuple_totally_frozen))
                                        frozen[nfrozen++].offset = offnum;
 

diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h
index 4e41024e9260701445cdd1daa0608ccb2e4962a2..f1366ed9581c6f061e1b32e921385dd5126e8935 100644 (file)
--- a/src/include/access/heapam.h
+++ b/src/include/access/heapam.h
@@ -168,8 +168,9 @@ extern HTSU_Result heap_lock_tuple(Relation relation, HeapTuple tuple,
                                bool follow_update,
                                Buffer *buffer, HeapUpdateFailureData *hufd);
 extern void heap_inplace_update(Relation relation, HeapTuple tuple);
-extern bool heap_freeze_tuple(HeapTupleHeader tuple, TransactionId cutoff_xid,
-                                 TransactionId cutoff_multi);
+extern bool heap_freeze_tuple(HeapTupleHeader tuple,
+                                 TransactionId relfrozenxid, TransactionId relminmxid,
+                                 TransactionId cutoff_xid, TransactionId cutoff_multi);
 extern bool heap_tuple_needs_freeze(HeapTupleHeader tuple, TransactionId cutoff_xid,
                                                MultiXactId cutoff_multi, Buffer buf);
 extern bool heap_tuple_needs_eventual_freeze(HeapTupleHeader tuple);

diff --git a/src/include/access/heapam_xlog.h b/src/include/access/heapam_xlog.h
index 5e4dee60c74f22cfa83688f823055ded5d2efada..38f7f639840d0c90c6ef8d0251b4da14b252589d 100644 (file)
--- a/src/include/access/heapam_xlog.h
+++ b/src/include/access/heapam_xlog.h
@@ -384,6 +384,8 @@ extern XLogRecPtr log_heap_freeze(Relation reln, Buffer buffer,
                                TransactionId cutoff_xid, xl_heap_freeze_tuple *tuples,
                                int ntuples);
 extern bool heap_prepare_freeze_tuple(HeapTupleHeader tuple,
+                                                 TransactionId relfrozenxid,
+                                                 TransactionId relminmxid,
                                                  TransactionId cutoff_xid,
                                                  TransactionId cutoff_multi,
                                                  xl_heap_freeze_tuple *frz,