From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail.sigma-star.at ([95.130.255.111]) by bombadil.infradead.org with esmtp (Exim 4.80.1 #2 (Red Hat Linux)) id 1Zylij-0005CE-RR for linux-mtd@lists.infradead.org; Tue, 17 Nov 2015 19:15:14 +0000 Received: from localhost (localhost.localdomain [127.0.0.1]) by mail.sigma-star.at (Postfix) with ESMTP id 121EF24E0002 for ; Tue, 17 Nov 2015 20:14:50 +0100 (CET) Received: from dw-book (80-110-107-146.cgn.dynamic.surfer.at [80.110.107.146]) by mail.sigma-star.at (Postfix) with ESMTPSA id AD95024E0001 for ; Tue, 17 Nov 2015 20:14:48 +0100 (CET) Date: Tue, 17 Nov 2015 20:14:48 +0100 From: Daniel Walter To: linux-mtd@lists.infradead.org Subject: [RFC] Trace-events for mtd Message-ID: <20151117191448.GA5367@dw-nb.local> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline List-Id: Linux MTD discussion mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Hi, I currently working on ways to find out if any processes are producing heavy I/O loads on a mtd device. I've implemented traceevents for mtd_read and mtd_write which allow us to at least get a rough overview on the read/write load. Although it kinda works, I could not find a way to find out which processes actually produce write load, since all writes are writebacks from page_cache and therefor we mostly get a kworker thread as the main origin of any write load. I wanted to reach out to the broader community to find out if I missed somethings and to get overall feedback if more traceevents would be useful to help us debugging mtd i/o a little bit better. any comments are highly appreciated. Cheers, daniel