Currently you can only set the packet processing limits via boot only tunables under hw.ix, this adds per adapter limits that allow live tuning
Details
Details
- Reviewers
erj sbruno - Group Reviewers
Intel Networking
Verified the new sysctls inherit the default or the boot time setting, and that changing them affects the next run of rxeof()/txeof()
Diff Detail
Diff Detail
- Repository
- rS FreeBSD src repository - subversion
- Lint
Lint Passed - Unit
No Test Coverage - Build Status
Buildable 589 Build 589: arc lint + arc unit
Event Timeline
Comment Actions
Clean up now unused old process_limits, we use the ones in the adapter struct for all limits in the rx/tx task queues.
Comment Actions
Looks okay to me except the ix_txrx.c change of exposing struct adapter.
I'll let Sean/Eric have a final say.
Good work, Jason!