From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: Polling too often at lower packet rates? Date: Thu, 9 Apr 2015 14:24:37 -0700 Message-ID: <20150409142437.203fed44@urahara> References: <5D6C8629-393C-4195-8063-8168E206335B@arbor.net> <16D8F22D-333F-499F-8B5A-4839E582054D@arbor.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: "dev-VfR2kkLFssw@public.gmane.org" To: Aaron Campbell Return-path: In-Reply-To: <16D8F22D-333F-499F-8B5A-4839E582054D-rd7evPjynkNeoWH0uzbU5w@public.gmane.org> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" On Thu, 9 Apr 2015 15:26:23 -0300 Aaron Campbell wrote: > Hi Stephen, >=20 > Thanks, that was an informative talk. In this case, are you referring to= your comments about the thermal budget? >=20 > That=E2=80=99s definitely interesting, but there must be more to it than = that. Again, if I loop over all 6 ports (i.e., continue to keep the CPU bu= sy), it works around the problem. >=20 > I agree that adaptive polling makes sense and will look into it. But wil= l still take any further ideas on what is going on here. >=20 > -Aaron Your excess polling consumes PCI bandwidth which is a fixed resource.