v13-0004-Checking-toast-separately-from-the-main-table.patch
application/octet-stream
Filename: v13-0004-Checking-toast-separately-from-the-main-table.patch
Type: application/octet-stream
Part: 3
Message:
Re: pg_amcheck contrib application
Patch
Format: format-patch
Series: patch v13-0004
Subject: Checking toast separately from the main table.
| File | + | − |
|---|---|---|
| contrib/amcheck/verify_heapam.c | 200 | 215 |
| src/tools/pgindent/typedefs.list | 1 | 0 |
From f6399dcd6e37cd29d3df03eeca5c557843d97db5 Mon Sep 17 00:00:00 2001
From: Mark Dilger <mark.dilger@enterprisedb.com>
Date: Mon, 29 Mar 2021 14:40:45 -0700
Subject: [PATCH v13 4/4] Checking toast separately from the main table.
Rather than checking toasted attributes as we find them, creating a
list of them and checking all the toast in the list after releasing
the buffer lock for each main table page.
---
contrib/amcheck/verify_heapam.c | 415 +++++++++++++++----------------
src/tools/pgindent/typedefs.list | 1 +
2 files changed, 201 insertions(+), 215 deletions(-)
diff --git a/contrib/amcheck/verify_heapam.c b/contrib/amcheck/verify_heapam.c
index c5bde63ea7..e3163e4bfa 100644
--- a/contrib/amcheck/verify_heapam.c
+++ b/contrib/amcheck/verify_heapam.c
@@ -58,6 +58,26 @@ typedef enum SkipPages
SKIP_PAGES_NONE
} SkipPages;
+/*
+ * Struct holding information necessary to check a toasted attribute, including
+ * the toast pointer, state about the current toast chunk being checked, and
+ * the location in the main table of the toasted attribute. We have to track
+ * the tuple's location in the main table for reporting purposes because by the
+ * time the toast is checked our HeapCheckContext will no longer be pointing to
+ * the relevant tuple.
+ */
+typedef struct ToastCheckContext
+{
+ struct varatt_external toast_pointer;
+ BlockNumber blkno; /* block in main table */
+ OffsetNumber offnum; /* offset in main table */
+ AttrNumber attnum; /* attribute in main table */
+ int32 chunkno; /* chunk number in toast table */
+ int32 attrsize; /* size of toasted attribute */
+ int32 endchunk; /* last chunk number in toast table */
+ int32 totalchunks; /* total chunks in toast table */
+} ToastCheckContext;
+
/*
* Struct holding the running context information during
* a lifetime of a verify_heapam execution.
@@ -119,11 +139,11 @@ typedef struct HeapCheckContext
/* True if toast for this tuple could be vacuumed away */
bool tuple_is_volatile;
- /* Values for iterating over toast for the attribute */
- int32 chunkno;
- int32 attrsize;
- int32 endchunk;
- int32 totalchunks;
+ /*
+ * List of ToastCheckContext structs for toasted attributes which are not
+ * in danger of being vacuumed way and should be checked
+ */
+ List *toasted_attributes;
/* Whether verify_heapam has yet encountered any corrupt tuples */
bool is_corrupt;
@@ -136,13 +156,18 @@ typedef struct HeapCheckContext
/* Internal implementation */
static void sanity_check_relation(Relation rel);
static void check_tuple(HeapCheckContext *ctx);
-static void check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx);
+static void check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx,
+ ToastCheckContext *tctx);
-static bool check_tuple_attribute(HeapCheckContext *ctx);
static bool check_tuple_header(HeapCheckContext *ctx);
static bool check_tuple_visibility(HeapCheckContext *ctx);
+static bool check_tuple_attribute(HeapCheckContext *ctx);
+static void check_toasted_attributes(HeapCheckContext *ctx);
+
static void report_main_corruption(HeapCheckContext *ctx, char *msg);
+static void report_toast_corruption(HeapCheckContext *ctx,
+ ToastCheckContext *tctx, char *msg);
static TupleDesc verify_heapam_tupdesc(void);
static FullTransactionId FullTransactionIdFromXidAndCtx(TransactionId xid,
const HeapCheckContext *ctx);
@@ -253,6 +278,7 @@ verify_heapam(PG_FUNCTION_ARGS)
memset(&ctx, 0, sizeof(HeapCheckContext));
ctx.cached_xid = InvalidTransactionId;
+ ctx.toasted_attributes = NIL;
/*
* Any xmin newer than the xmin of our snapshot can't become all-visible
@@ -469,6 +495,14 @@ verify_heapam(PG_FUNCTION_ARGS)
/* clean up */
UnlockReleaseBuffer(ctx.buffer);
+ /*
+ * Check any toast pointers from the page whose lock we just released
+ * and reset the list to NIL.
+ */
+ if (ctx.toasted_attributes != NIL)
+ check_toasted_attributes(&ctx);
+ Assert(ctx.toasted_attributes == NIL);
+
if (on_error_stop && ctx.is_corrupt)
break;
}
@@ -510,14 +544,13 @@ sanity_check_relation(Relation rel)
}
/*
- * Record a single corruption found in the table. The values in ctx should
- * reflect the location of the corruption, and the msg argument should contain
- * a human-readable description of the corruption.
- *
- * The msg argument is pfree'd by this function.
+ * Shared internal implementation for report_main_corruption and
+ * report_toast_corruption.
*/
static void
-report_main_corruption(HeapCheckContext *ctx, char *msg)
+report_corruption(Tuplestorestate *tupstore, TupleDesc tupdesc,
+ BlockNumber blkno, OffsetNumber offnum, AttrNumber attnum,
+ char *msg)
{
Datum values[HEAPCHECK_RELATION_COLS];
bool nulls[HEAPCHECK_RELATION_COLS];
@@ -525,10 +558,10 @@ report_main_corruption(HeapCheckContext *ctx, char *msg)
MemSet(values, 0, sizeof(values));
MemSet(nulls, 0, sizeof(nulls));
- values[0] = Int64GetDatum(ctx->blkno);
- values[1] = Int32GetDatum(ctx->offnum);
- values[2] = Int32GetDatum(ctx->attnum);
- nulls[2] = (ctx->attnum < 0);
+ values[0] = Int64GetDatum(blkno);
+ values[1] = Int32GetDatum(offnum);
+ values[2] = Int32GetDatum(attnum);
+ nulls[2] = (attnum < 0);
values[3] = CStringGetTextDatum(msg);
/*
@@ -541,8 +574,39 @@ report_main_corruption(HeapCheckContext *ctx, char *msg)
*/
pfree(msg);
- tuple = heap_form_tuple(ctx->tupdesc, values, nulls);
- tuplestore_puttuple(ctx->tupstore, tuple);
+ tuple = heap_form_tuple(tupdesc, values, nulls);
+ tuplestore_puttuple(tupstore, tuple);
+}
+
+/*
+ * Record a single corruption found in the main table. The values in ctx should
+ * indicate the location of the corruption, and the msg argument should contain
+ * a human-readable description of the corruption.
+ *
+ * The msg argument is pfree'd by this function.
+ */
+static void
+report_main_corruption(HeapCheckContext *ctx, char *msg)
+{
+ report_corruption(ctx->tupstore, ctx->tupdesc, ctx->blkno, ctx->offnum,
+ ctx->attnum, msg);
+ ctx->is_corrupt = true;
+}
+
+/*
+ * Record corruption found in the toast table. The values in tctx should
+ * indicate the location in the main table where the toast pointer was
+ * encountered, and the msg argument should contain a human-readable
+ * description of the toast table corruption.
+ *
+ * As above, the msg argument is pfree'd by this function.
+ */
+static void
+report_toast_corruption(HeapCheckContext *ctx, ToastCheckContext *tctx,
+ char *msg)
+{
+ report_corruption(ctx->tupstore, ctx->tupdesc, tctx->blkno, tctx->offnum,
+ tctx->attnum, msg);
ctx->is_corrupt = true;
}
@@ -1086,7 +1150,6 @@ check_tuple_visibility(HeapCheckContext *ctx)
return false; /* not reached */
}
-
/*
* Check the current toast tuple against the state tracked in ctx, recording
* any corruption found in ctx->tupstore.
@@ -1099,7 +1162,8 @@ check_tuple_visibility(HeapCheckContext *ctx)
* as each toast tuple having its varlena structure sanity checked.
*/
static void
-check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx)
+check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx,
+ ToastCheckContext *tctx)
{
int32 curchunk;
Pointer chunk;
@@ -1114,16 +1178,16 @@ check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx)
ctx->toast_rel->rd_att, &isnull));
if (isnull)
{
- report_main_corruption(ctx,
- pstrdup("toast chunk sequence number is null"));
+ report_toast_corruption(ctx, tctx,
+ pstrdup("toast chunk sequence number is null"));
return;
}
chunk = DatumGetPointer(fastgetattr(toasttup, 3,
ctx->toast_rel->rd_att, &isnull));
if (isnull)
{
- report_main_corruption(ctx,
- pstrdup("toast chunk data is null"));
+ report_toast_corruption(ctx, tctx,
+ pstrdup("toast chunk data is null"));
return;
}
if (!VARATT_IS_EXTENDED(chunk))
@@ -1140,37 +1204,37 @@ check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx)
/* should never happen */
uint32 header = ((varattrib_4b *) chunk)->va_4byte.va_header;
- report_main_corruption(ctx,
- psprintf("corrupt extended toast chunk has invalid varlena header: %0x (sequence number %d)",
- header, curchunk));
+ report_toast_corruption(ctx, tctx,
+ psprintf("corrupt extended toast chunk has invalid varlena header: %0x (sequence number %d)",
+ header, curchunk));
return;
}
/*
* Some checks on the data we've found
*/
- if (curchunk != ctx->chunkno)
+ if (curchunk != tctx->chunkno)
{
- report_main_corruption(ctx,
- psprintf("toast chunk sequence number %u does not match the expected sequence number %u",
- curchunk, ctx->chunkno));
+ report_toast_corruption(ctx, tctx,
+ psprintf("toast chunk sequence number %u does not match the expected sequence number %u",
+ curchunk, tctx->chunkno));
return;
}
- if (curchunk > ctx->endchunk)
+ if (curchunk > tctx->endchunk)
{
- report_main_corruption(ctx,
- psprintf("toast chunk sequence number %u exceeds the end chunk sequence number %u",
- curchunk, ctx->endchunk));
+ report_toast_corruption(ctx, tctx,
+ psprintf("toast chunk sequence number %u exceeds the end chunk sequence number %u",
+ curchunk, tctx->endchunk));
return;
}
- expected_size = curchunk < ctx->totalchunks - 1 ? TOAST_MAX_CHUNK_SIZE
- : ctx->attrsize - ((ctx->totalchunks - 1) * TOAST_MAX_CHUNK_SIZE);
+ expected_size = curchunk < tctx->totalchunks - 1 ? TOAST_MAX_CHUNK_SIZE
+ : tctx->attrsize - ((tctx->totalchunks - 1) * TOAST_MAX_CHUNK_SIZE);
if (chunksize != expected_size)
{
- report_main_corruption(ctx,
- psprintf("toast chunk size %u differs from the expected size %u",
- chunksize, expected_size));
+ report_toast_corruption(ctx, tctx,
+ psprintf("toast chunk size %u differs from the expected size %u",
+ chunksize, expected_size));
return;
}
}
@@ -1180,17 +1244,17 @@ check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx)
* found in ctx->tupstore.
*
* This function follows the logic performed by heap_deform_tuple(), and in the
- * case of a toasted value, optionally continues along the logic of
- * detoast_external_attr(), checking for any conditions that would result in
- * either of those functions Asserting or crashing the backend. The checks
- * performed by Asserts present in those two functions are also performed here.
- * In cases where those two functions are a bit cavalier in their assumptions
- * about data being correct, we perform additional checks not present in either
- * of those two functions. Where some condition is checked in both of those
- * functions, we perform it here twice, as we parallel the logical flow of
- * those two functions. The presence of duplicate checks seems a reasonable
- * price to pay for keeping this code tightly coupled with the code it
- * protects.
+ * case of a toasted value, optionally stores the toast pointer so later it can
+ * be checked following the logic of detoast_external_attr(), checking for any
+ * conditions that would result in either of those functions Asserting or
+ * crashing the backend. The checks performed by Asserts present in those two
+ * functions are also performed here and in check_toasted_attributes. In cases
+ * where those two functions are a bit cavalier in their assumptions about data
+ * being correct, we perform additional checks not present in either of those
+ * two functions. Where some condition is checked in both of those functions,
+ * we perform it here twice, as we parallel the logical flow of those two
+ * functions. The presence of duplicate checks seems a reasonable price to pay
+ * for keeping this code tightly coupled with the code it protects.
*
* Returns true if the tuple attribute is sane enough for processing to
* continue on to the next attribute, false otherwise.
@@ -1198,12 +1262,6 @@ check_toast_tuple(HeapTuple toasttup, HeapCheckContext *ctx)
static bool
check_tuple_attribute(HeapCheckContext *ctx)
{
- struct varatt_external toast_pointer;
- ScanKeyData toastkey;
- SysScanDesc toastscan;
- SnapshotData SnapshotToast;
- HeapTuple toasttup;
- bool found_toasttup;
Datum attdatum;
struct varlena *attr;
char *tp; /* pointer to the tuple data */
@@ -1338,191 +1396,114 @@ check_tuple_attribute(HeapCheckContext *ctx)
return true;
/*
- * Must copy attr into toast_pointer for alignment considerations
+ * If this tuple is at risk of being vacuumed away, we cannot check the
+ * toast. Otherwise, we push a copy of the toast tuple so we can check it
+ * after releasing the main table buffer lock.
*/
- VARATT_EXTERNAL_GET_POINTER(toast_pointer, attr);
+ if (!ctx->tuple_is_volatile)
+ {
+ ToastCheckContext *tctx;
- ctx->attrsize = VARATT_EXTERNAL_GET_EXTSIZE(toast_pointer);
- ctx->endchunk = (ctx->attrsize - 1) / TOAST_MAX_CHUNK_SIZE;
- ctx->totalchunks = ctx->endchunk + 1;
+ tctx = (ToastCheckContext *) palloc0fast(sizeof(ToastCheckContext));
- /*
- * Setup a scan key to find chunks in toast table with matching va_valueid
- */
- ScanKeyInit(&toastkey,
- (AttrNumber) 1,
- BTEqualStrategyNumber, F_OIDEQ,
- ObjectIdGetDatum(toast_pointer.va_valueid));
-
- /*
- * Check if any chunks for this toasted object exist in the toast table,
- * accessible via the index.
- */
- init_toast_snapshot(&SnapshotToast);
- toastscan = systable_beginscan_ordered(ctx->toast_rel,
- ctx->valid_toast_index,
- &SnapshotToast, 1,
- &toastkey);
- ctx->chunkno = 0;
- found_toasttup = false;
- while ((toasttup =
- systable_getnext_ordered(toastscan,
- ForwardScanDirection)) != NULL)
- {
- found_toasttup = true;
- check_toast_tuple(toasttup, ctx);
- ctx->chunkno++;
+ VARATT_EXTERNAL_GET_POINTER(tctx->toast_pointer, attr);
+ tctx->blkno = ctx->blkno;
+ tctx->offnum = ctx->offnum;
+ tctx->attnum = ctx->attnum;
+ ctx->toasted_attributes = lappend(ctx->toasted_attributes, tctx);
}
- if (!found_toasttup)
- report_main_corruption(ctx,
- psprintf("toasted value for attribute %u missing from toast table",
- ctx->attnum));
- else if (ctx->chunkno != (ctx->endchunk + 1))
- report_main_corruption(ctx,
- psprintf("final toast chunk number %u differs from expected value %u",
- ctx->chunkno, (ctx->endchunk + 1)));
- systable_endscan_ordered(toastscan);
return true;
}
/*
- * Check the current tuple as tracked in ctx, recording any corruption found in
- * ctx->tupstore.
+ * For each attribute collected in ctx->toasted_attributes, look up the value
+ * in the toast table and perform checks on it. This function should only be
+ * called on toast pointers which cannot be vacuumed away during our
+ * processing.
*/
static void
-check_tuple(HeapCheckContext *ctx)
+check_toasted_attributes(HeapCheckContext *ctx)
{
- TransactionId xmin;
- TransactionId xmax;
- bool fatal = false;
- uint16 infomask = ctx->tuphdr->t_infomask;
+ ListCell *cell;
- /* If xmin is normal, it should be within valid range */
- xmin = HeapTupleHeaderGetXmin(ctx->tuphdr);
- switch (get_xid_status(xmin, ctx, NULL))
+ foreach(cell, ctx->toasted_attributes)
{
- case XID_INVALID:
- case XID_BOUNDS_OK:
- break;
- case XID_IN_FUTURE:
- report_main_corruption(ctx,
- psprintf("xmin %u equals or exceeds next valid transaction ID %u:%u",
- xmin,
- EpochFromFullTransactionId(ctx->next_fxid),
- XidFromFullTransactionId(ctx->next_fxid)));
- fatal = true;
- break;
- case XID_PRECEDES_CLUSTERMIN:
- report_main_corruption(ctx,
- psprintf("xmin %u precedes oldest valid transaction ID %u:%u",
- xmin,
- EpochFromFullTransactionId(ctx->oldest_fxid),
- XidFromFullTransactionId(ctx->oldest_fxid)));
- fatal = true;
- break;
- case XID_PRECEDES_RELMIN:
- report_main_corruption(ctx,
- psprintf("xmin %u precedes relation freeze threshold %u:%u",
- xmin,
- EpochFromFullTransactionId(ctx->relfrozenfxid),
- XidFromFullTransactionId(ctx->relfrozenfxid)));
- fatal = true;
- break;
- }
+ ToastCheckContext *tctx;
+ SnapshotData SnapshotToast;
+ ScanKeyData toastkey;
+ SysScanDesc toastscan;
+ bool found_toasttup;
+ HeapTuple toasttup;
+
+ tctx = lfirst(cell);
+ tctx->attrsize = VARATT_EXTERNAL_GET_EXTSIZE(tctx->toast_pointer);
+ tctx->endchunk = (tctx->attrsize - 1) / TOAST_MAX_CHUNK_SIZE;
+ tctx->totalchunks = tctx->endchunk + 1;
- xmax = HeapTupleHeaderGetRawXmax(ctx->tuphdr);
+ /*
+ * Setup a scan key to find chunks in toast table with matching
+ * va_valueid
+ */
+ ScanKeyInit(&toastkey,
+ (AttrNumber) 1,
+ BTEqualStrategyNumber, F_OIDEQ,
+ ObjectIdGetDatum(tctx->toast_pointer.va_valueid));
- if (infomask & HEAP_XMAX_IS_MULTI)
- {
- /* xmax is a multixact, so it should be within valid MXID range */
- switch (check_mxid_valid_in_rel(xmax, ctx))
- {
- case XID_INVALID:
- report_main_corruption(ctx,
- pstrdup("multitransaction ID is invalid"));
- fatal = true;
- break;
- case XID_PRECEDES_RELMIN:
- report_main_corruption(ctx,
- psprintf("multitransaction ID %u precedes relation minimum multitransaction ID threshold %u",
- xmax, ctx->relminmxid));
- fatal = true;
- break;
- case XID_PRECEDES_CLUSTERMIN:
- report_main_corruption(ctx,
- psprintf("multitransaction ID %u precedes oldest valid multitransaction ID threshold %u",
- xmax, ctx->oldest_mxact));
- fatal = true;
- break;
- case XID_IN_FUTURE:
- report_main_corruption(ctx,
- psprintf("multitransaction ID %u equals or exceeds next valid multitransaction ID %u",
- xmax,
- ctx->next_mxact));
- fatal = true;
- break;
- case XID_BOUNDS_OK:
- break;
- }
- }
- else
- {
/*
- * xmax is not a multixact and is normal, so it should be within the
- * valid XID range.
+ * Check if any chunks for this toasted object exist in the toast
+ * table, accessible via the index.
*/
- switch (get_xid_status(xmax, ctx, NULL))
+ init_toast_snapshot(&SnapshotToast);
+ toastscan = systable_beginscan_ordered(ctx->toast_rel,
+ ctx->valid_toast_index,
+ &SnapshotToast, 1,
+ &toastkey);
+ tctx->chunkno = 0;
+ found_toasttup = false;
+ while ((toasttup =
+ systable_getnext_ordered(toastscan,
+ ForwardScanDirection)) != NULL)
{
- case XID_INVALID:
- case XID_BOUNDS_OK:
- break;
- case XID_IN_FUTURE:
- report_main_corruption(ctx,
- psprintf("xmax %u equals or exceeds next valid transaction ID %u:%u",
- xmax,
- EpochFromFullTransactionId(ctx->next_fxid),
- XidFromFullTransactionId(ctx->next_fxid)));
- fatal = true;
- break;
- case XID_PRECEDES_CLUSTERMIN:
- report_main_corruption(ctx,
- psprintf("xmax %u precedes oldest valid transaction ID %u:%u",
- xmax,
- EpochFromFullTransactionId(ctx->oldest_fxid),
- XidFromFullTransactionId(ctx->oldest_fxid)));
- fatal = true;
- break;
- case XID_PRECEDES_RELMIN:
- report_main_corruption(ctx,
- psprintf("xmax %u precedes relation freeze threshold %u:%u",
- xmax,
- EpochFromFullTransactionId(ctx->relfrozenfxid),
- XidFromFullTransactionId(ctx->relfrozenfxid)));
- fatal = true;
+ found_toasttup = true;
+ check_toast_tuple(toasttup, ctx, tctx);
+ tctx->chunkno++;
}
+ if (!found_toasttup)
+ report_toast_corruption(ctx, tctx,
+ psprintf("toasted value for attribute %u missing from toast table",
+ tctx->attnum));
+ else if (tctx->chunkno != (tctx->endchunk + 1))
+ report_toast_corruption(ctx, tctx,
+ psprintf("final toast chunk number %u differs from expected value %u",
+ tctx->chunkno, (tctx->endchunk + 1)));
+ systable_endscan_ordered(toastscan);
+
+ pfree(tctx);
}
+ list_free(ctx->toasted_attributes);
+ ctx->toasted_attributes = NIL;
+}
- /*
- * Cannot process tuple data if tuple header was corrupt, as the offsets
- * within the page cannot be trusted, leaving too much risk of reading
- * garbage if we continue.
- *
- * We also cannot process the tuple if the xmin or xmax were invalid
- * relative to relfrozenxid or relminmxid, as clog entries for the xids
- * may already be gone.
- */
- if (fatal)
- return;
-
+/*
+ * Check the current tuple as tracked in ctx, recording any corruption found in
+ * ctx->tupstore.
+ */
+static void
+check_tuple(HeapCheckContext *ctx)
+{
/*
* Check various forms of tuple header corruption. If the header is too
- * corrupt to continue checking, or if the tuple is not visible to anyone,
- * we cannot continue with other checks.
+ * corrupt to continue checking, we cannot continue with other checks.
*/
if (!check_tuple_header(ctx))
return;
+ /*
+ * Check tuple visibility. If the inserting transaction aborted, we
+ * cannot assume our relation description matches the tuple structure, and
+ * therefore cannot check it.
+ */
if (!check_tuple_visibility(ctx))
return;
@@ -1545,6 +1526,10 @@ check_tuple(HeapCheckContext *ctx)
* next, at which point we abort further attribute checks for this tuple.
* Note that we don't abort for all types of corruption, only for those
* types where we don't know how to continue.
+ *
+ * While checking the tuple attributes, we build a list of toast pointers
+ * we encounter, to be checked later. If further attribute checking is
+ * aborted, we still have the pointers collected prior to aborting.
*/
ctx->offset = 0;
for (ctx->attnum = 0; ctx->attnum < ctx->natts; ctx->attnum++)
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 9e6777e9d0..0ce261e2a2 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2557,6 +2557,7 @@ TimestampTz
TmFromChar
TmToChar
ToastAttrInfo
+ToastCheckContext
ToastTupleContext
TocEntry
TokenAuxData
--
2.21.1 (Apple Git-122.3)