[dpdk-dev] mmap() hint address

2014-06-20 Thread Burakov, Anatoly
Hi Stephen, You may want to look at the local tailqs patchset I've made. This may fix your issues as well. http://dpdk.org/ml/archives/dev/2014-June/003573.html I'm planning to respin a v4 of it, with an addition of using --base-virtaddr flag to also control where rte_config is mapped as well

[dpdk-dev] mmap() hint address

2014-06-20 Thread Gooch, Stephen
Hello, One item I should have included is this device is running 32-bit 2.6.27, quite old, and sharing 4GB of RAM with a number of applications. We were able to find the issue. In the failure case vDSO is mapped lower (toward [heap]) than normal. As a result , .rte_config was mapped into th

[dpdk-dev] mmap() hint address

2014-06-16 Thread Burakov, Anatoly
Hi Bruce, Stephen, > > Hello, > > > > I have seen a case where a secondary DPDK process tries to map uio > > resource in which mmap() normally sends the corresponding virtual > > address as a hint address. However on some instances mmap() returns a > > virtual address that is not the hint address

[dpdk-dev] mmap() hint address

2014-06-13 Thread Richardson, Bruce
> -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Gooch, Stephen > Sent: Friday, June 13, 2014 2:03 PM > To: dev at dpdk.org > Subject: [dpdk-dev] mmap() hint address > > Hello, > > I have seen a case where a secondary DPDK proces

[dpdk-dev] mmap() hint address

2014-06-13 Thread Gooch, Stephen
Hello, I have seen a case where a secondary DPDK process tries to map uio resource in which mmap() normally sends the corresponding virtual address as a hint address. However on some instances mmap() returns a virtual address that is not the hint address, and it result in rte_panic() and the s