Can you perhaps send on the log and the traceback from the panic call. From the error message we may be able to tell you why your process is failing.
/Bruce > -----Original Message----- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Zhangkun (K) > Sent: Friday, September 05, 2014 4:40 AM > To: Masaru Oki > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] Are there considerations about resource recycling by > the > process, not by the OS? > > Hi, > Yes, the program is running as root. > I want to know if or not the DPDK Community considers about resource > recycling. > > From: Masaru Oki [mailto:m-oki at stratosphere.co.jp] > Date: 2014?9?5? 11:18 > To: Zhangkun (K) > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] Are there considerations about resource recycling by > the > process, not by the OS? > > Hi, > > you may try > $ gdb your_program > gdb> b rte_panic > gdb> run > stopped at rte_panic > gdb> bt > > sorry, it is not answer for your question. > by the way, do you run the program as root? > > > 2014-09-05 12:07 GMT+09:00 Zhangkun (K) > <zhang.zhangkun at huawei.com<mailto:zhang.zhangkun at huawei.com>>: > Hi, > I develop the program with the use of dpdk and the process is core dump > when > the program is started. > The process is crash in case of initing memory failed and calling rte_panic > function. > I search all rte_panic function in the dpdk, and find it so many. Therefore, > in > case the pr ocess happen fail, > it will abort. The resource allocated before is not released by the process, > but by > the OS system. > So I have a question: Are there considerations about resource recycling by the > process, not by the OS ?