| From: | Nikolay Samokhvalov <nik(at)postgres(dot)ai> |
|---|---|
| To: | pgsql-hackers <pgsql-hackers(at)lists(dot)postgresql(dot)org> |
| Subject: | IO wait events for COPY FROM/TO PROGRAM or file |
| Date: | 2026-01-08 21:53:17 |
| Message-ID: | CAM527d_iDzz0Kqyi7HOfqa-Xzuq29jkR6AGXqfXLqA5PR5qsng@mail.gmail.com |
| Views: | Whole Thread | Raw Message | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Hi hackers,
Following up on the discussion about wait event coverage for COPY
operations [1], here's a tiny patch that adds two new IO wait events:
- COPY_DATA_READ: COPY FROM blocking on file/program read
- COPY_DATA_WRITE: COPY TO blocking on file/program write
This enables diagnosing for cases like:
- storage I/O bottlenecks during bulk loads slow exports to files (COPY
FROM/TO '/path/to/file')
- pipe buffer congestion in ETL pipelines (COPY FROM/TO PROGRAM)
Note: as it turned out, COPY FROM/TO STDIN/STDOUT already have coverage via
Client/ClientRead and Client/ClientWrite at the protocol layer (thus,
pg_dump/pg_restore are already covered). So only file/program cases needed
instrumentation.
Nikx
| Attachment | Content-Type | Size |
|---|---|---|
| v1-0001-Add-IO-wait-events-for-COPY-file-program-operations.patch | application/octet-stream | 3.6 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Masahiko Sawada | 2026-01-08 22:04:14 | Re: POC: enable logical decoding when wal_level = 'replica' without a server restart |
| Previous Message | Robert Haas | 2026-01-08 20:58:54 | Re: pg_plan_advice |