Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-03-16 Thread Ilya Maximets
On 3/4/20 4:51 PM, Eli Britstein wrote: > > On 3/3/2020 4:44 PM, Eli Britstein wrote: >> >> On 2/28/2020 11:03 AM, Ilya Maximets wrote: >>> On 2/27/20 10:00 AM, Eli Britstein wrote: On 2/26/2020 2:31 PM, Ilya Maximets wrote: > On 2/26/20 1:05 PM, Eli Britstein wrote: >> On 2/24/2020 1

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-03-04 Thread Eli Britstein
On 3/3/2020 4:44 PM, Eli Britstein wrote: On 2/28/2020 11:03 AM, Ilya Maximets wrote: On 2/27/20 10:00 AM, Eli Britstein wrote: On 2/26/2020 2:31 PM, Ilya Maximets wrote: On 2/26/20 1:05 PM, Eli Britstein wrote: On 2/24/2020 1:06 PM, Ilya Maximets wrote: On 2/23/20 3:32 PM, Eli Britstein w

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-03-03 Thread Eli Britstein
On 2/28/2020 11:03 AM, Ilya Maximets wrote: On 2/27/20 10:00 AM, Eli Britstein wrote: On 2/26/2020 2:31 PM, Ilya Maximets wrote: On 2/26/20 1:05 PM, Eli Britstein wrote: On 2/24/2020 1:06 PM, Ilya Maximets wrote: On 2/23/20 3:32 PM, Eli Britstein wrote: On 2/21/2020 4:54 PM, Ilya Maximets w

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-28 Thread Ilya Maximets
On 2/27/20 10:00 AM, Eli Britstein wrote: > > On 2/26/2020 2:31 PM, Ilya Maximets wrote: >> On 2/26/20 1:05 PM, Eli Britstein wrote: >>> On 2/24/2020 1:06 PM, Ilya Maximets wrote: On 2/23/20 3:32 PM, Eli Britstein wrote: > On 2/21/2020 4:54 PM, Ilya Maximets wrote: >> If the offloadin

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-27 Thread Eli Britstein
On 2/26/2020 2:31 PM, Ilya Maximets wrote: On 2/26/20 1:05 PM, Eli Britstein wrote: On 2/24/2020 1:06 PM, Ilya Maximets wrote: On 2/23/20 3:32 PM, Eli Britstein wrote: On 2/21/2020 4:54 PM, Ilya Maximets wrote: If the offloading queue is big and filled continuously, offloading thread may hav

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-26 Thread Ilya Maximets
On 2/26/20 1:05 PM, Eli Britstein wrote: > > On 2/24/2020 1:06 PM, Ilya Maximets wrote: >> On 2/23/20 3:32 PM, Eli Britstein wrote: >>> On 2/21/2020 4:54 PM, Ilya Maximets wrote: If the offloading queue is big and filled continuously, offloading thread may have no chance to quiesce block

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-26 Thread Eli Britstein
On 2/24/2020 1:06 PM, Ilya Maximets wrote: On 2/23/20 3:32 PM, Eli Britstein wrote: On 2/21/2020 4:54 PM, Ilya Maximets wrote: If the offloading queue is big and filled continuously, offloading thread may have no chance to quiesce blocking rcu callbacks and other threads waiting for synchroniz

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-24 Thread Ilya Maximets
On 2/23/20 3:32 PM, Eli Britstein wrote: > > On 2/21/2020 4:54 PM, Ilya Maximets wrote: >> If the offloading queue is big and filled continuously, offloading >> thread may have no chance to quiesce blocking rcu callbacks and >> other threads waiting for synchronization. >> >> Fix that by entering

Re: [ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-23 Thread Eli Britstein
On 2/21/2020 4:54 PM, Ilya Maximets wrote: If the offloading queue is big and filled continuously, offloading thread may have no chance to quiesce blocking rcu callbacks and other threads waiting for synchronization. Fix that by entering momentary quiescent state after each operation since we'r

[ovs-dev] [PATCH] dpif-netdev: Enter quiescent state after each offloading operation.

2020-02-21 Thread Ilya Maximets
If the offloading queue is big and filled continuously, offloading thread may have no chance to quiesce blocking rcu callbacks and other threads waiting for synchronization. Fix that by entering momentary quiescent state after each operation since we're not holding any rcu-protected memory here.