Re: [PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

> Hi Pavel, you might want to pull lock optimization out of this patch series. > The parallelization by itself is valuable, and optimizations for individual > devices including locks can come later. Hi Steve, Yes, I will pull this patch out of the series. Thank you for the suggestion. Pavel

Re: [PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

On 5/3/2018 9:46 AM, Alexander Duyck wrote: > On Thu, May 3, 2018 at 6:30 AM, Pavel Tatashin > wrote: >> Hi Alex, > > Hi Pavel, > >>> I'm not a fan of dropping the mutex while we go through >>> ixgbe_close_suspend. I'm concerned it will result in us having a >>>

Re: [PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

On Thu, May 3, 2018 at 6:30 AM, Pavel Tatashin wrote: > Hi Alex, Hi Pavel, >> I'm not a fan of dropping the mutex while we go through >> ixgbe_close_suspend. I'm concerned it will result in us having a >> number of races on shutdown. > > I would agree, but

Re: [PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

Hi Alex, > I'm not a fan of dropping the mutex while we go through > ixgbe_close_suspend. I'm concerned it will result in us having a > number of races on shutdown. I would agree, but ixgbe_close_suspend() is already called without this mutex from ixgbe_close(). This path is executed also during

Re: [PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

On Wed, May 2, 2018 at 8:59 PM, Pavel Tatashin wrote: > Currently, during device_shutdown() ixgbe holds rtnl_lock for the duration > of lengthy ixgbe_close_suspend(). On machines with multiple ixgbe cards > this lock prevents scaling if device_shutdown() function is

[PATCH 1/2] ixgbe: release lock for the duration of ixgbe_suspend_close()

Currently, during device_shutdown() ixgbe holds rtnl_lock for the duration of lengthy ixgbe_close_suspend(). On machines with multiple ixgbe cards this lock prevents scaling if device_shutdown() function is multi-threaded. It is not necessary to hold this lock during ixgbe_close_suspend() as it