diff options
author | Alexander Korotkov <akorotkov@postgresql.org> | 2024-03-30 22:34:04 +0200 |
---|---|---|
committer | Alexander Korotkov <akorotkov@postgresql.org> | 2024-03-30 22:34:04 +0200 |
commit | 27bc1772fc814946918a5ac8ccb9b5c5ad0380aa (patch) | |
tree | beb4fac8dfb2756c86f3ac13ec21d72f69daa55c /src/backend/access/heap/heapam_handler.c | |
parent | b154d8a6d0e52e5f6b09739639fdf55fa88bc6b8 (diff) | |
download | postgresql-27bc1772fc814946918a5ac8ccb9b5c5ad0380aa.tar.gz postgresql-27bc1772fc814946918a5ac8ccb9b5c5ad0380aa.zip |
Generalize relation analyze in table AM interface
Currently, there is just one algorithm for sampling tuples from a table written
in acquire_sample_rows(). Custom table AM can just redefine the way to get the
next block/tuple by implementing scan_analyze_next_block() and
scan_analyze_next_tuple() API functions.
This approach doesn't seem general enough. For instance, it's unclear how to
sample this way index-organized tables. This commit allows table AM to
encapsulate the whole sampling algorithm (currently implemented in
acquire_sample_rows()) into the relation_analyze() API function.
Discussion: https://postgr.es/m/CAPpHfdurb9ycV8udYqM%3Do0sPS66PJ4RCBM1g-bBpvzUfogY0EA%40mail.gmail.com
Reviewed-by: Pavel Borisov, Matthias van de Meent
Diffstat (limited to 'src/backend/access/heap/heapam_handler.c')
-rw-r--r-- | src/backend/access/heap/heapam_handler.c | 29 |
1 files changed, 21 insertions, 8 deletions
diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 6abfe36dec7..a7ef0cf72d3 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -50,7 +50,6 @@ static TM_Result heapam_tuple_lock(Relation relation, ItemPointer tid, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, uint8 flags, TM_FailureData *tmfd); - static void reform_and_rewrite_tuple(HeapTuple tuple, Relation OldHeap, Relation NewHeap, Datum *values, bool *isnull, RewriteState rwstate); @@ -1052,7 +1051,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, pfree(isnull); } -static bool +/* + * Prepare to analyze block `blockno` of `scan`. The scan has been started + * with SO_TYPE_ANALYZE option. + * + * This routine holds a buffer pin and lock on the heap page. They are held + * until heapam_scan_analyze_next_tuple() returns false. That is until all the + * items of the heap page are analyzed. + */ +void heapam_scan_analyze_next_block(TableScanDesc scan, BlockNumber blockno, BufferAccessStrategy bstrategy) { @@ -1072,12 +1079,19 @@ heapam_scan_analyze_next_block(TableScanDesc scan, BlockNumber blockno, hscan->rs_cbuf = ReadBufferExtended(scan->rs_rd, MAIN_FORKNUM, blockno, RBM_NORMAL, bstrategy); LockBuffer(hscan->rs_cbuf, BUFFER_LOCK_SHARE); - - /* in heap all blocks can contain tuples, so always return true */ - return true; } -static bool +/* + * Iterate over tuples in the block selected with + * heapam_scan_analyze_next_block(). If a tuple that's suitable for sampling + * is found, true is returned and a tuple is stored in `slot`. When no more + * tuples for sampling, false is returned and the pin and lock acquired by + * heapam_scan_analyze_next_block() are released. + * + * *liverows and *deadrows are incremented according to the encountered + * tuples. + */ +bool heapam_scan_analyze_next_tuple(TableScanDesc scan, TransactionId OldestXmin, double *liverows, double *deadrows, TupleTableSlot *slot) @@ -2637,10 +2651,9 @@ static const TableAmRoutine heapam_methods = { .relation_copy_data = heapam_relation_copy_data, .relation_copy_for_cluster = heapam_relation_copy_for_cluster, .relation_vacuum = heap_vacuum_rel, - .scan_analyze_next_block = heapam_scan_analyze_next_block, - .scan_analyze_next_tuple = heapam_scan_analyze_next_tuple, .index_build_range_scan = heapam_index_build_range_scan, .index_validate_scan = heapam_index_validate_scan, + .relation_analyze = heapam_analyze, .free_rd_amcache = NULL, .relation_size = table_block_relation_size, |