From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Mon, 8 Feb 2016 14:00:49 -0500 From: Julien Desfossez Message-ID: <20160208190049.GI26639@sinkpad.internal.efficios.com> References: <1478740846.7068.1454011725322.JavaMail.zimbra@efficios.com> <146B1557584B0B4DBD25ABAD45EF70F0F6E5164C@ALA-MBB.corp.ad.wrs.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <146B1557584B0B4DBD25ABAD45EF70F0F6E5164C@ALA-MBB.corp.ad.wrs.com> Subject: Re: [diamon-discuss] Diamon Meeting on Tuesday February 9th, 2016, at 11h EDT (15h UTC) List-Id: DiaMon diagnostic and monitoring workgroup general discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Oberhuber, Martin" Cc: "diamon-discuss@lists.linuxfoundation.org" Hi, > I don't think I would have much to contribute, but I am certainly > interested in what others say. Could the session be recorded, or > meeting notes posted? - Otherwise I'd be available from the 15th on, > in case you'd consider moving the session. We did not receive any other requests for moving the meeting, so we will do it tomorrow, I will try to record it. > Two questions came up for me when reading the blog, > > 1. Julien writes "We are not trying to solve a problem related to the interrupts > being masked for too long (ftrace already has some tools to help with that)." > Which are those tools? Any pointer would be appreciated. I was refering to the irqsoff tracer in ftrace. > 2. I really like the general usefulness of the latency_tracker and the many clever > ways it can be configured / leveraged - but it feels like an expert tool to me, > where you'd very clearly have to know what you're doing. Are there any ideas > making such expert tools more usable and discoverable by general users ? Indeed for now it is not very user-friendly as we are still defining all the knobs that we want to expose to the users. When we will have gathered enough feedback we will see if how we can adapt this to make it more easy to approach. Thanks for the feedback, Julien