On 12-Aug-19 11:21 AM, Van Haaren, Harry wrote:
-----Original Message-----
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of David Marchand
Sent: Monday, August 12, 2019 11:04 AM
To: Burakov, Anatoly <anatoly.bura...@intel.com>
Cc: dev <dev@dpdk.org>; Richardson, Bruce <bruce.richard...@intel.com>;
Stephen Hemminger <step...@networkplumber.org>; dpdk stable <sta...@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v4] eal: fix proc type auto detection
On Wed, Jul 24, 2019 at 6:08 PM Anatoly Burakov
<anatoly.bura...@intel.com> wrote:
Currently, primary process holds an exclusive lock on the config
file, thereby preventing other primaries from spinning up. However,
when the primary dies, the lock is no longer being held, even though
there might be other secondary processes still running.
The fix is two-fold. First of all, downgrade the primary process's
exclusive lock to a shared lock once we have it. Second of all,
also take out shared locks on the config from the secondaries. We
are using fcntl() locks, which get dropped when the file handle is
closed, so also remove the closure of config file handle.
Fixes: af75078fece3 ("first public release")
Cc: sta...@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.bura...@intel.com>
Apologies I'm late to the conversation.
Will the rte_eal_primary_proc_alive() function still detect the primary
as alive, and not confuse secondaries with primaries in this new method?
Good question, i'll have to investigate. Maybe we'll have to change the
lock from the fcntl() locks to flock()-based locks.
Currently, the pri_proc_alive() code uses lockf(fd, F_TEST, 0); to detect
if a primary is alive. I'm not familiar enough with shared locks to know
if the new behavior would be consistent with the old.
-H
--
Thanks,
Anatoly
