Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-04 Thread Ilya Maximets
On 03.12.2019 14:00, David Marchand wrote: > On Tue, Dec 3, 2019 at 12:34 PM Ilya Maximets wrote: >> >> On 02.12.2019 17:03, David Marchand wrote: >>> Most DPDK components make the assumption that rte_lcore_id() returns >>> a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of >>>

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-04 Thread David Marchand
On Wed, Dec 4, 2019 at 9:21 PM Flavio Leitner wrote: > BTW, it would be nice to have an ovs-appctl command to dump a list > of IDs and CPUs in case the logs are rotated, config changed and > whatnot. For instance, sos could get an accurate report dumping a > list. Good idea. I will look at this

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-04 Thread Flavio Leitner
On Wed, Dec 04, 2019 at 09:09:42PM +0100, David Marchand wrote: > On Wed, Dec 4, 2019 at 8:52 PM Flavio Leitner wrote: > > > > On Mon, Dec 02, 2019 at 05:03:30PM +0100, David Marchand wrote: > > > Most DPDK components make the assumption that rte_lcore_id() returns > > > a valid lcore_id in

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-04 Thread David Marchand
On Wed, Dec 4, 2019 at 8:52 PM Flavio Leitner wrote: > > On Mon, Dec 02, 2019 at 05:03:30PM +0100, David Marchand wrote: > > Most DPDK components make the assumption that rte_lcore_id() returns > > a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of > > the LCORE_ID_ANY special

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-04 Thread Flavio Leitner
On Mon, Dec 02, 2019 at 05:03:30PM +0100, David Marchand wrote: > Most DPDK components make the assumption that rte_lcore_id() returns > a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of > the LCORE_ID_ANY special value). > > OVS does not currently check which value is set in >

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-03 Thread David Marchand
On Tue, Dec 3, 2019 at 12:34 PM Ilya Maximets wrote: > > On 02.12.2019 17:03, David Marchand wrote: > > Most DPDK components make the assumption that rte_lcore_id() returns > > a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of > > the LCORE_ID_ANY special value). > > Do you

Re: [ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-03 Thread Ilya Maximets
On 02.12.2019 17:03, David Marchand wrote: > Most DPDK components make the assumption that rte_lcore_id() returns > a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of > the LCORE_ID_ANY special value). Do you think that makes a practical sense? In a real virtualization

[ovs-dev] [PATCH] dpdk: Support running PMD threads on cores > RTE_MAX_LCORE.

2019-12-02 Thread David Marchand
Most DPDK components make the assumption that rte_lcore_id() returns a valid lcore_id in [0..RTE_MAX_LCORE] range (with the exception of the LCORE_ID_ANY special value). OVS does not currently check which value is set in RTE_PER_LCORE(_lcore_id) which exposes us to potential crashes on DPDK side.