From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx.kolabnow.com (mx.kolabnow.com [185.254.79.33]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A1C752DF6E6 for ; Thu, 7 May 2026 17:43:34 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=185.254.79.33 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778175818; cv=none; b=gbVyYReAHMZZ2uhunHdoNcxhOCpLemWv837nM5b+2EHhGS2rIseX3bcA6iZERXvBOSIVx75XxPM70jXqT2sv2ZgRzwFQxeAWYTYac/jvWOlxV+YssE2ZZb6d2zBSuNYiBrqLlhsxcaLa7EmfWnCiADQxLOid2r+pjrCVeL0+scQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778175818; c=relaxed/simple; bh=D88owxq9Ze6civeY8QwnxsHQYi6XvR05xzlHYSxdF1s=; h=Message-ID:Date:MIME-Version:From:To:Cc:Subject:Content-Type; b=gJMunPBIzLeTodheBKLhSZ3lI6/q2aG/mA69mMLecjhw85VJnir/wSyTqwgMM8bYUHwooS7PRV8W3HQTka3AlASfj4F9gU15Nt/8oSohnVaBGKhLNwVNJr4ST6WJfwltNbD0fFFAumznYG+jWDOeqrTzTDnrXBOj9Rx0pSkKz64= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=hansg.org; spf=pass smtp.mailfrom=hansg.org; dkim=pass (2048-bit key) header.d=hansg.org header.i=@hansg.org header.b=HmETFgDK; arc=none smtp.client-ip=185.254.79.33 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=hansg.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=hansg.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=hansg.org header.i=@hansg.org header.b="HmETFgDK" Received: from postfix.kolabnow.com (unknown [10.17.5.252]) by mx.kolabnow.com (Postfix) with ESMTPS id F093F30DA753; Thu, 7 May 2026 19:34:08 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=hansg.org; h= content-transfer-encoding:content-type:content-type:subject :subject:content-language:from:from:mime-version:date:date :message-id; s=dkim2; t=1778175244; x=1779039245; bh=D88owxq9Ze6 civeY8QwnxsHQYi6XvR05xzlHYSxdF1s=; b=HmETFgDKEjF81VRRrNp8CgP4+dQ 5IkzMZHo+rcHH+fqCrYOIoVt4v+FVdsobRo8CXdJVvoQA4ORdJ4FPgwBwsudpkfz j4Y8lYvcH426qLxuDSuM7s0AU5uhJt0GFFBjmu80xK9DbYDBh0lI5aaGqJ2DVRkH NkD0NmKCbsGEH4lc0LlIvmTYC/XNFYggx2HSOlRkVwjZRchZesjBwVxIhqujHS3J Iz8pthxYUn5tQ1FMO2Rxnt/35oIA9UflZDIHjPUzZHqr/dxGSkvSLJ8qJqGvohw0 4uY03Q0L/2G36A2nt+rmBTdKEiLcNw5w+HHsBKzthYp/CR57bxTtExP2+AA== Message-ID: <8574e496-ed2e-4057-8614-726d079aac57@hansg.org> Date: Thu, 7 May 2026 19:33:58 +0200 Precedence: bulk X-Mailing-List: linux-trace-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 From: Hans de Goede Content-Language: en-US, nl To: Steven Rostedt , Masami Hiramatsu Cc: Linux trace kernel , Mario Limonciello Subject: CONFIG_FTRACE=y significantly slowing down module loading Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Hi Everyone, On some old hw CONFIG_FTRACE=y causes "modprobe amdgpu" to take 25-30 seconds, halting the entire boot process for that time. Where as with "# CONFIG_FTRACE is not set" this takes only 2 seconds. I believe this was reported before by Mario (in the Cc) and there was a fix of sorts merged for 6.15? But there still is a significant slowdown (especially on slow hardware). I was also the reason Mario originally reported this and Mario asked me to test 6.15 but I was busy with other stuff so from the better late then never department I only got around this now... I've tested this on 2 admittedly quite old and slow machines, but the impact is big enough that fixing this might also help speeding up modprobe on modern machines. This was tested on: MSI S270 laptop, AMD Turion 64 MT-30 CPU, RS480 iGPU FUJITSU D3003-S2 industrial PC, AMD G-T56N CPU, Radeon HD 6320 iGPU Both old machines where amdgpu.ko auto-loads. Kernel/modprobe real-/sys-time/FTRACE Kconfig enabled/machine 6.19.6 32.5s/31.8s yes MSI S270 7.0.0 25.5s/22.8s yes FUJITSU D3003-S2 6.15-rc7 27.7s/26.5s yes FUJITSU D3003-S2 7.0.0 1.9s/1.1s no FUJITSU D3003-S2 Regards, Hans