Re: index prefetching

Peter Geoghegan <pg@bowt.ie>

From: Peter Geoghegan <pg@bowt.ie>

To: Tomas Vondra <tomas@vondra.me>

Cc: Nazir Bilal Yavuz <byavuz81@gmail.com>, Thomas Munro <thomas.munro@gmail.com>, Andres Freund <andres@anarazel.de>, Robert Haas <robertmhaas@gmail.com>, Melanie Plageman <melanieplageman@gmail.com>, PostgreSQL Hackers <pgsql-hackers@lists.postgresql.org>, Georgios <gkokolatos@protonmail.com>, Konstantin Knizhnik <knizhnik@garret.ru>, Dilip Kumar <dilipbalaut@gmail.com>

Date: 2025-07-24T02:18:55Z

Lists: pgsql-hackers

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

aio: io_uring: Trigger async processing for large IOs
- a9ee66881744 19 (unreleased) landed
read stream: Split decision about look ahead for AIO and combining
- 8ca147d582a5 19 (unreleased) landed
read_stream: Only increase read-ahead distance when waiting for IO
- f63ca3379025 19 (unreleased) landed
read_stream: Prevent distance from decaying too quickly
- 6e36930f9aaf 19 (unreleased) landed
Reduce ExecSeqScan* code size using pg_assume()
- b227b0bb4e03 19 (unreleased) cited
Fix rare bug in read_stream.c's split IO handling.
- b421223172a2 19 (unreleased) cited
Fix multiranges to behave more like dependent types.
- 3e8235ba4f9c 17.0 cited
Add EXPLAIN (MEMORY) to report planner memory consumption
- 5de890e3610d 17.0 cited
Optimize nbtree backward scan boundary cases.
- c9c0589fda0e 17.0 cited
Increment xactCompletionCount during subtransaction abort.
- 90c885cdab8b 14.0 cited
Add nbtree Valgrind buffer lock checks.
- 4a70f829d86c 14.0 cited
Add nbtree high key "continuescan" optimization.
- 29b64d1de7c7 12.0 cited
Reduce pinning and buffer content locking for btree scans.
- 2ed5b87f96d4 9.5.0 cited
Teach btree to handle ScalarArrayOpExpr quals natively.
- 9e8da0f75731 9.2.0 cited

On Wed, Jul 23, 2025 at 9:59 PM Peter Geoghegan <pg@bowt.ie> wrote:
> Tomas' index-prefetch-simple-master branch:
> │         I/O Timings: shared read=1490.918
> │ Execution Time: 2015.731 ms

> Complex patch (same prewarming/eviction are omitted this time):
> │         I/O Timings: shared read=138.856
> │ Execution Time: 768.454 ms

> I'm using direct IO in both cases. This can easily be repeated, and is stable.

Forget to add context about the master branch: Master can do this in
2386.850 ms, with "I/O Timings: shared read=1825.161". That's with
buffered I/O (not direct I/O), and with the same pg_prewarm +
pg_buffercache_evict_relation function calls as before. I'm running
"echo 3 > /proc/sys/vm/drop_caches" to drop the filesystem cache here,
too (unlike when testing the patches, where my use of direct i/o makes
that step unnecessary).

In summary, the simple patch + direct I/O clearly beats the master
branch + buffered I/O here -- though not by much. While the complex
patch gets a far greater benefit.

-- 
Peter Geoghegan