From owner-freebsd-hackers Sun Jan 13 14:23:54 2002 Delivered-To: freebsd-hackers@freebsd.org Received: from resnet.uoregon.edu (resnet.uoregon.edu [128.223.122.47]) by hub.freebsd.org (Postfix) with ESMTP id 016BC37B404 for ; Sun, 13 Jan 2002 14:23:53 -0800 (PST) Received: from localhost (dwhite@localhost) by resnet.uoregon.edu (8.11.3/8.10.1) with ESMTP id g0DMOIM53117; Sun, 13 Jan 2002 14:24:18 -0800 (PST) Date: Sun, 13 Jan 2002 14:24:17 -0800 (PST) From: Doug White To: k Macy Cc: freebsd-hackers@FreeBSD.ORG Subject: Re: How well does EVFILT_AIO work? In-Reply-To: <20020113062729.45895.qmail@web14003.mail.yahoo.com> Message-ID: <20020113142249.U51854-100000@resnet.uoregon.edu> X-All-Your-Base: are belong to us MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On Sat, 12 Jan 2002, k Macy wrote: > Has anybody used AIO in conjunction with kevent? I am seeing as much as > a 12 second latency between when I do an 8k aio_write to a file on local > disk and kevent returning its completion (I'm calling kevent every > ~20ms). Using regular writes works fine, but this is a multi-threaded > application so they cause the entire process to block. I think you've overdone the async idea here. Threads already do non-blocking I/O but appear to block by various trickery. If you are doing AIO in threads then you could just as easily dispose of the threads and streamline your code. Doug White | FreeBSD: The Power to Serve dwhite@resnet.uoregon.edu | www.FreeBSD.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message