Received: from malur.postgresql.org ([217.196.149.56]) by arkaria.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.98.2) (envelope-from ) id 1x8rkC-00000001Z0a-2WBY for pgsql-hackers@arkaria.postgresql.org; Tue, 22 Sep 2026 04:04:36 +0000 Received: from localhost ([127.0.0.1] helo=malur.postgresql.org) by malur.postgresql.org with esmtp (Exim 4.98.2) (envelope-from ) id 1x8rjC-0000000DHbk-2wgX for pgsql-hackers@arkaria.postgresql.org; Tue, 22 Sep 2026 04:03:34 +0000 Received: from makus.postgresql.org ([2001:4800:3e1:1::229]) by malur.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.98.2) (envelope-from ) id 1x8rjC-0000000DHbc-1hUK for pgsql-hackers@lists.postgresql.org; Tue, 22 Sep 2026 04:03:34 +0000 Received: from mail-pj2-x0f.google.com ([2607:f8b0:4864:39::f]) by makus.postgresql.org with esmtps (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 (Exim 4.98.2) (envelope-from ) id 1x8rj9-00000000bZz-3U0J for pgsql-hackers@lists.postgresql.org; Tue, 22 Sep 2026 04:03:33 +0000 Received: by mail-pj2-x0f.google.com with SMTP id d9443c01a7336-2d747ed6d6eso36480355ad.2 for ; Mon, 21 Sep 2026 21:03:32 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1790049811; x=1790654611; darn=lists.postgresql.org; h=to:references:message-id:content-transfer-encoding:cc:date :in-reply-to:from:subject:mime-version:content-type:from:to:cc :subject:date:message-id:reply-to:content-type; bh=vQuWyBn0OX8cy7edmduZY7bRclvlzCZSwP8Rr/PCjdM=; b=pU3Few1XZO94pBM2hWOBZfw8vj1Yh9XDlHQjgnb7XWUoUvDw4usf1a1gilXqpON0oh LVUyzBNw/Kv87bTJ62b7aLRJAy4Z9J3TUgcMR36/+1gKCiTn98jleIZtBZq504Fiku1j biOwfcXOa2neM7tOj7F1oO3GhGBjgVRYUM35vwm+ifX/LXtWm4wMtBjEJoj/zI5J/aGs gnQWlzqtdbMRnstTlKmjEm/40cMUM70cEN4zSrs2ZjdFiVAuTbih6DJgWkAesnJvwC8m cL7eQwtMGVDELus2g0guV+VA56dt+pBP86SI17QyBAUgRTIIR3SF8ow4H6cwH0k2yNzZ AaZQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1790049811; x=1790654611; h=to:references:message-id:content-transfer-encoding:cc:date :in-reply-to:from:subject:mime-version:content-type:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=vQuWyBn0OX8cy7edmduZY7bRclvlzCZSwP8Rr/PCjdM=; b=A7NQmeleSpWG4/2BMb545cibm2uNKpiiTxT1RY2d+ELI4JPaccUbiHzNs4OMDXhOL0 NqIY/3vB3OKw95ouvuj2ptYaM/DZvuVpo+v4VZHUHj0hCFEOno/uw8euK7ly/9gxVVNZ bhrvw8LeW7u8Nh24FqCyum0EOVGiFUIYztuaJEhUdV31gWhEd9xgXYi4ys2gJ2sSztTO M1ha9dV0a40TjXhrGQuZCown6q/+QQyyT6alRIdst2sm+3yUc+w+77bnB+7IcoSaDAyt r/bnKlBjun5ZjXRJIIfkHRhhJSmrf+/t0qYqMU6mVIk8kCHsffC13aHq8hlDxEKiPHKK XY8w== X-Forwarded-Encrypted: i=1; AKwUvBzfIuW5XwU4JMSZqvnVEsJtPEop3aTlXfp6Gnb9qSAG6PS1NLqbRm9Fm3tvjNpDLNf+PZ8axVExAUshtI/c@lists.postgresql.org X-Gm-Message-State: AFuF++nrgjo0sDqRfcKJk0uJMk2u+uVG5GJP1bqEmeOt6k/InI/joOyh BriZbNfLjL9jYgKqZ7mW1AZZi3YSp9WuDLQVW27KpfsEXpPAo5zuzkot X-Gm-Gg: AYBFou0F3zE11mmBSn0/1DwPqVSjcFrEQvqYA5pqg09ytHbo7MVomv9LsuyAAuJgEQz 7L++J0+ZVGD3IitKCON5hR0Du/hfjOaCrGzDVCSGktAlQq284B0hDAJOKcT4GB1FjcbySzs0tH2 Nj2NCA7T2GrQ0C2RhQrPEXHXyzhOp9bQN5oxXrcUheWP5k5+gjpa8jDtw18W3HuNcV1PGTbVnr/ 3q0mf+efFz0zZK+KLRwVtZ8cFai3+kywQf7ANUSN+0iPlvus71z3FSL3g5k841XgazoxG8bYkOO HiEioxbrJQ8C9/hlVrLFIJYg5oMAY0pwhywom//Lt7OvnmuejtMjN8szFZHdFyRDWTGLR0hixqx mC8cZtXaSU10b/Bjue/zYU9N4kyi1k5/VPJoREFWyAdlo+G1cMvrOeUDbQ98Xm3Tqqx4uvV4KRN V+w8xEwyRR//T0bfswnGZQxtLvmQcpVHXHME3gNt62J/gCs1sBwXSU4ZHKYA2mmCS7FYSNqXjvU sCV4AXMkr9AWEs= X-Received: by 2002:a17:902:d4c4:b0:2d8:d4dd:24c0 with SMTP id d9443c01a7336-2ddb1b97ee1mr186283955ad.21.1790049811331; Mon, 21 Sep 2026 21:03:31 -0700 (PDT) Received: from smtpclient.apple ([128.14.31.146]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-33e612c9ca7sm1849237eec.17.2026.09.21.21.03.29 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Mon, 21 Sep 2026 21:03:30 -0700 (PDT) Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3901.100.1.1.11\)) Subject: Re: aio: Async fsyncs for crash recovery and checkpointer From: Yuhang Qiu In-Reply-To: Date: Tue, 22 Sep 2026 12:03:17 +0800 Cc: Nitin Jadhav , PostgreSQL Hackers , Andres Freund Content-Transfer-Encoding: 7bit Message-Id: References: To: Nazir Bilal Yavuz X-Mailer: Apple Mail (2.3901.100.1.1.11) List-Id: List-Help: List-Subscribe: List-Post: List-Owner: List-Archive: Archived-At: Precedence: bulk Hi Nazir, Thanks for the comparison. The main benefit of this patch series seems to be in checkpointing rather than crash recovery, so I think further testing should focus on that. > For now, ordinary reopen failures for both relation and SLRU fsyncs > return -errno. > > Done. Relation fsync requests now use io_max_concurrency as their > limit. These two changes LGTM. > However, I think increasing the number of worker processes > should solve this problem. Increasing the worker count may help with worker availability, but it doesn't address contention for storage bandwidth. One more point: when a worker calls pg_fsync() or pg_fdatasync(), it checks its own enableFsync. If the issuer has reloaded fsync=on but the worker still has the old off value, the worker can skip the sync and report success. Should the issuer's setting or the worker's determine whether the sync is performed? Best regards, Yuhang Qiu