From mboxrd@z Thu Jan 1 00:00:00 1970 From: Marc Sune Subject: Re: Valgrind and DPDK - does it work ? Date: Fri, 07 Nov 2014 01:29:40 +0100 Message-ID: <545C1274.8020708@bisdn.de> References: <007501cfd1a3$573fff00$05bffd00$@xenanetworks.com> <545C10D9.9020902@bisdn.de> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: quoted-printable To: dev-VfR2kkLFssw@public.gmane.org Return-path: In-Reply-To: <545C10D9.9020902-kpkqNMk1I7M@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 07/11/14 01:22, Marc Sune wrote: > On 16/09/14 13:42, Morten Jagd Christensen wrote: >> Hi all, >> >> >> I am interested to hear if anyone here have had any luck running=20 >> Valgrind on >> DPDK applications? >> >> >> I tried to use this some time ago, but Valgrind does not seem to work >> together with hugepages =96 or >> >> I am doing something wrong ;-) >> >> >> I would like to hear form anyone having success or failure with=20 >> Valgrind and >> DPDK. > > Found some time to have a close look. I also wanted to check a DPDK=20 > app against valgrind. It works! > > I downloaded and compiled valgrind from sources (3.10.0) and applied=20 > (manually) this patch: > > https://bugs.kde.org/attachment.cgi?id=3D85950&action=3Dedit > > (Applied around line 2216) > > From this post: > > http://valgrind.10908.n7.nabble.com/mpich-unable-to-munmap-hugepages-td= 49150.html=20 > > > Happy debugging > Marc > Btw, I will debug closer my DPDK application, but a quick start and stop=20 shows already some warnings: =3D=3D27534=3D=3D Thread 2: =3D=3D27534=3D=3D Syscall param epoll_ctl(event) points to uninitialised = byte(s) =3D=3D27534=3D=3D at 0x65E6DBA: epoll_ctl (syscall-template.S:82) =3D=3D27534=3D=3D by 0x58DAEC: eal_intr_thread_main (in=20 /home/marc/xdpd/build/src/xdpd/xdpd) =3D=3D27534=3D=3D by 0x5DD7B4F: start_thread (pthread_create.c:304) =3D=3D27534=3D=3D by 0x65E67BC: clone (clone.S:112) =3D=3D27534=3D=3D Address 0x7717d78 is on thread 2's stack =3D=3D27534=3D=3D in frame #1, created by eal_intr_thread_main (???) =3D=3D27534=3D=3D Regards Marc