Re: [PATCH v2] service: fix deadlock on worker lcore exit

2024-10-11 Thread David Marchand
com ; > > tho...@monjalon.net ; sta...@dpdk.org > > ; Tyler Retzlaff ; Aaron > > Conole > > Subject: Re: [PATCH v2] service: fix deadlock on worker lcore exit > > > > On Thu, Oct 3, 2024 at 8:57 AM David Marchand > > wrote: > > > > > > From:

Re: [PATCH v2] service: fix deadlock on worker lcore exit

2024-10-03 Thread Van Haaren, Harry
; > Subject: Re: [PATCH v2] service: fix deadlock on worker lcore exit > > On Thu, Oct 3, 2024 at 8:57 AM David Marchand > wrote: > > > > From: Mattias Rönnblom > > > > Calling rte_exit() from a worker lcore thread causes a deadlock in > > rte_service_fina

Re: [PATCH v2] service: fix deadlock on worker lcore exit

2024-10-03 Thread David Marchand
On Thu, Oct 3, 2024 at 8:57 AM David Marchand wrote: > > From: Mattias Rönnblom > > Calling rte_exit() from a worker lcore thread causes a deadlock in > rte_service_finalize(). > > This patch makes rte_service_finalize() deadlock-free by avoiding the > need to synchronize with service lcore threa

[PATCH v2] service: fix deadlock on worker lcore exit

2024-10-02 Thread David Marchand
From: Mattias Rönnblom Calling rte_exit() from a worker lcore thread causes a deadlock in rte_service_finalize(). This patch makes rte_service_finalize() deadlock-free by avoiding the need to synchronize with service lcore threads, which in turn is achieved by moving service and per-lcore state