revert: "softirq: Let ksoftirqd do its job"
Due to the mentioned commit, when the ksoftirqd processes take charge of softirq processing, the system can experience high latencies. In the past a few workarounds have been implemented for specific side-effects of the above: commit 1ff68820 ("watchdog: core: make sure the watchdog_worker is not deferred") commit 8d5755b3 ("watchdog: softdog: fire watchdog even if softirqs do not get to run") commit 217f6974 ("net: busy-poll: allow preemption in sk_busy_loop()") commit 3c53776e ("Mark HI and TASKLET softirq synchronous") but the latency problem still exists in real-life workloads, see the link below. The reverted commit intended to solve a live-lock scenario that can now be addressed with the NAPI threaded mode, introduced with commit 29863d41 ("net: implement threaded-able napi poll loop support"), and nowadays in a pretty stable status. While a complete solution to put softirq processing under nice resource control would be preferable, that has proven to be a very hard task. In the short term, remove the main pain point, and also simplify a bit the current softirq implementation. Note that this change also reverts commit 3c53776e ("Mark HI and TASKLET softirq synchronous") and commit 1342d808 ("softirq: Don't skip softirq execution when softirq thread is parking"), which are direct follow-ups of the feature commit. A single change is preferred to avoid known bad intermediate states introduced by a patch series reverting them individually. Link: https://lore.kernel.org/netdev/305d7742212cbe98621b16be782b0562f1012cb6.camel@redhat.com/ Signed-off-by:Paolo Abeni <pabeni@redhat.com> Tested-by:
Jason Xing <kerneljasonxing@gmail.com> Reviewed-by:
Jakub Kicinski <kuba@kernel.org> Reviewed-by:
Eric Dumazet <edumazet@google.com> Reviewed-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> Link: https://lore.kernel.org/r/57e66b364f1b6f09c9bc0316742c3b14f4ce83bd.1683526542.git.pabeni@redhat.com Signed-off-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> (cherry picked from commit b8a04a538ed4755dc97c403ee3b8dd882955c98c) Signed-off-by:
Clark Williams <clark.williams@gmail.com> Signed-off-by:
Bruce Ashfield <bruce.ashfield@gmail.com>
Loading
Please register or sign in to comment