DPDK processes now allocates a large area of virtual memory address space, with this change during rte_abort FreeBSD now dumps the contents of the whole reserved memory range, not just the used portion, to a core dump file. Write this large core file can take a significant amount of time, causing processes to appear hung on the system. The work around for the issue is to set the system resource limits for core dumps before running any tests e.g."limit coredumpsize 0". This will effectively disable core dumps on FreeBSD. If they are not to be completely disabled, a suitable limit, e.g. 1G might be specified instead of 0. This needs to be run per-shell session, or before every test run. This change can also be made persistent by adding "kern.coredump=0" to /etc/sysctl.conf
Bruce, Can anything be done about this? Thanks
The workaround Reshma suggests above is the best solution we have found thus far. Other potential option might be to reduce the size of the reserved memory used by BSD to only that needed.
So what's the next step? Document and close this? Or??
There is some code in 18.08 to partially address this issue, see this patch series: http://patches.dpdk.org/project/dpdk/list/?series=289&state=* This reduces the amount of memory BSD reserves at startup.
I'm not aware of any additional action which can be taken here, the workaround is the best solution I'm aware of, though Anatoly's patch does help. I suggest document and close once documented. I'll see if I can get a doc patch done and upstreamed.
This is already documented in known issues for 18.05. doc.dpdk.org/guides/rel_notes/release_18_05.html#known-issues Recommend close at this point.
* Documented as known issue: doc.dpdk.org/guides/rel_notes/release_18_05.html#known-issues * Workaround covered in documentation * Some mitigation in place to help: http://patches.dpdk.org/project/dpdk/list/?series=289&state * No other fixes known at this point Closing as WONTFIX
This was already documented in last release. We can close this now. John asked me log this bug and add as reference in the" work around documentation patch" which I sent in the last release. > -----Original Message----- > From: bugzilla@dpdk.org [mailto:bugzilla@dpdk.org] > Sent: Friday, September 28, 2018 1:48 PM > To: Pattan, Reshma <reshma.pattan@intel.com> > Subject: [Bug 53] rte abort issue on FreeBSD > > https://bugs.dpdk.org/show_bug.cgi?id=53 > > --- Comment #5 from Bruce Richardson (bruce.richardson@intel.com) --- I'm > not aware of any additional action which can be taken here, the workaround > is the best solution I'm aware of, though Anatoly's patch does help. I > suggest > document and close once documented. I'll see if I can get a doc patch done > and upstreamed. > > -- > You are receiving this mail because: > You reported the bug.