RE: [PATCH 09/10] scsi/ibmvscsi: Replace srp tasklet with work

2022-06-14 Thread David Laight
From: Sebastian Andrzej Siewior > Sent: 14 June 2022 14:26 ... > > These changes seem to drop the priority from above that of the > > highest priority RT process down to that of a default priority > > user process. > > There is no real guarantee that the latter will run 'any time soon'. > > Not

Re: [PATCH 09/10] scsi/ibmvscsi: Replace srp tasklet with work

2022-06-14 Thread 'Sebastian Andrzej Siewior'
On 2022-06-09 15:46:04 [+], David Laight wrote: > From: Sebastian Andrzej Siewior > > Sent: 09 June 2022 16:03 > > > > On 2022-05-30 16:15:11 [-0700], Davidlohr Bueso wrote: > > > Tasklets have long been deprecated as being too heavy on the system > > > by running in irq context - and this is

RE: [PATCH 09/10] scsi/ibmvscsi: Replace srp tasklet with work

2022-06-09 Thread David Laight
From: Sebastian Andrzej Siewior > Sent: 09 June 2022 16:03 > > On 2022-05-30 16:15:11 [-0700], Davidlohr Bueso wrote: > > Tasklets have long been deprecated as being too heavy on the system > > by running in irq context - and this is not a performance critical > > path. If a higher priority

Re: [PATCH 09/10] scsi/ibmvscsi: Replace srp tasklet with work

2022-06-09 Thread Sebastian Andrzej Siewior
On 2022-05-30 16:15:11 [-0700], Davidlohr Bueso wrote: > Tasklets have long been deprecated as being too heavy on the system > by running in irq context - and this is not a performance critical > path. If a higher priority process wants to run, it must wait for > the tasklet to finish before doing

[PATCH 09/10] scsi/ibmvscsi: Replace srp tasklet with work

2022-05-30 Thread Davidlohr Bueso
Tasklets have long been deprecated as being too heavy on the system by running in irq context - and this is not a performance critical path. If a higher priority process wants to run, it must wait for the tasklet to finish before doing so. Process srps asynchronously in process context in a