[ovs-discuss] Intel DPDK testpmd application issues

Hiteshi Kalra hiteshi.kalra at tcs.com
Mon Dec 22 12:15:15 UTC 2014


Thanks kevin for helping us.

but i have got following error in changing value of C, even we can not give any value of C other than 1:

root at saloni-VirtualBox:/usr/src/dpdk-1.7.1/x86_64-native-linuxapp-gcc/build/app/test-pmd# ./testpmd -c 0xf -n4 -- -i --portmask=0x1 --nb-cores=2
EAL: Detected lcore 0 as core 0 on socket 0
EAL: Support maximum 64 logical core(s) by configuration.
EAL: Detected 1 lcore(s)
EAL: lcore 1 unavailable
EAL: invalid coremask

Usage: ./testpmd -c COREMASK -n NUM [-m NB] [-r NUM] [-b <domain:bus:devid.func>][--proc-type primary|secondary|auto]

EAL options:
  -c COREMASK  : A hexadecimal bitmask of cores to run on
  -n NUM       : Number of memory channels
  -v           : Display version information on startup
  -d LIB.so    : add driver (can be used multiple times)
  -m MB        : memory to allocate (see also --socket-mem)
  -r NUM       : force number of memory ranks (don't detect)
  --xen-dom0 : support application running on Xen Domain0 without hugetlbfs
  --syslog     : set syslog facility
  --socket-mem : memory to allocate on specific
                 sockets (use comma separated values)
  --huge-dir   : directory where hugetlbfs is mounted
  --proc-type  : type of this process
  --file-prefix: prefix for hugepage filenames

Thanks
Hiteshi

-----"Traynor, Kevin" <kevin.traynor at intel.com> wrote: -----
To: Hiteshi Kalra <hiteshi.kalra at tcs.com>, "discuss at openvswitch.org" <discuss at openvswitch.org>
From: "Traynor, Kevin" <kevin.traynor at intel.com>
Date: 12/19/2014 11:06PM
Subject: RE: [ovs-discuss] Intel DPDK testpmd application issues

       
 The core mask is set for 1 core with -c 0x1, but -&#8211;nb-cores=2 means that the app is to use 2 fwding cores. Try changing to &#8211;c 0xf
  
 Thanks,
 Kevin.
  
 
 
 
 From: discuss [mailto:discuss-bounces at openvswitch.org] On Behalf Of Hiteshi Kalra
 Sent: Friday, December 19, 2014 11:38 AM
 To: discuss at openvswitch.org
 Subject: [ovs-discuss] Intel DPDK testpmd application issues
    
 Hi Team,
 
 We are running OVS with Intel DPDK Sample applications.
 We have successfully run helloworld application as specified in Intel getting started guide.pdf
 
 But We are getting some issues in running testpmd application as speified in (http://www.intel.in/content/dam/www/public/us/en/documents/guides/intel-dpdk-testpmd-application-user-guide.pdf).
 
 We have used following command for it :
 
 sudo ./testpmd -c 0x1 -n 4 -- -i --portmask=0x1 --nb-cores=2
 
 EAL: Requesting 1238 pages of size 2MB from socket 0
 EAL: TSC frequency is ~3178599 KHz
 EAL: WARNING: cpu flags constant_tsc=yes nonstop_tsc=no -> using unreliable clock cycles !
 EAL: Master core 0 is ready (tid=888ca800)
 EAL: PCI device 0000:00:03.0 on NUMA socket -1
 EAL:   probe driver: 8086:100e rte_em_pmd
 EAL:   PCI memory mapped at 0x7fde88874000
 PANIC in main():
 Empty set of forwarding logical cores - check the core mask supplied in the command parameters
 5: [./testpmd() [0x4240a5]]
 4: [/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xed) [0x7fde879fb76d]]
 3: [./testpmd(main+0x4f2) [0x423df2]]
 2: [./testpmd(__rte_panic+0xc1) [0x42379a]]
 1: [./testpmd(rte_dump_stack+0x23) [0x486393]]
 
 
 Can anyone please help me in resloving error?
 
 Thanks
 Hiteshi 
 =====-----=====-----=====
 Notice: The information contained in this e-mail
 message and/or attachments to it may contain 
 confidential or privileged information. If you are 
 not the intended recipient, any dissemination, use, 
 review, distribution, printing or copying of the 
 information contained in this e-mail message 
 and/or attachments to it are strictly prohibited. If 
 you have received this communication in error, 
 please notify us by reply e-mail or telephone and 
 immediately and permanently delete the message 
 and any attachments. Thank you
     
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://openvswitch.org/pipermail/ovs-discuss/attachments/20141222/f069acc6/attachment-0002.html>


More information about the discuss mailing list