[dpdk-dev] [PATCH] Fix regression for eal_flags_autotest introduced by tailq rework

Thomas Monjalon thomas.monjalon at 6wind.com
Wed Nov 5 18:48:35 CET 2014

2014-11-05 13:24, De Lara Guarch, Pablo:
> > -----Original Message-----
> > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Anatoly Burakov
> > Sent: Wednesday, November 05, 2014 12:11 PM
> > To: dev at dpdk.org
> > Subject: [dpdk-dev] [PATCH] Fix regression for eal_flags_autotest
> > introduced by tailq rework
> > 
> > As a result of moving tailq's into local memory, some tailq data
> > is now reserved in rte_malloc heaps (because it needs to be
> > shared across DPDK processes). The first thing DPDK initializes
> > is a log mempool, and since it creates a tailq, it reserves
> > space in rte_malloc heap before allocating the mempool itself.
> > By default, rte_malloc allocates way more space than is necessary,
> > so under some conditions (namely, overall memory available is low)
> > this results in malloc heap eating up so much memory that log
> > mempool is not able to allocate its memzone.
> > 
> > This patch fixes the unit tests to account for that change.
> > 
> > Signed-off-by: Anatoly Burakov <anatoly.burakov at intel.com>
> > ---
> Acked-by: Pablo de Lara <pablo.de.lara.guarch at intel.com>

Tested-by: Thomas Monjalon <thomas.monjalon at 6wind.com>

echo 9 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages
build/app/test -c 1 -n 1 -m 4

It works now. Thanks Anatoly!


Reminder for everyone: patches should be posted with --in-reply-to option
to insert the patch in the thread context of the mailing list.
It makes easier to follow discussions.
For a new version of a patchset, it's a good practice to reply to the cover
letter of the previous version.
For a bug fix (this case), it's a good idea to reply to the bug report.
So someone searching in the archives can find the fix he's looking for.


More information about the dev mailing list