On Tue, Mar 19, 2019 at 3:51 PM Minchan Kim <minchan@xxxxxxxxxx> wrote: > > On Fri, Mar 08, 2019 at 10:43:04AM -0800, Suren Baghdasaryan wrote: > > This is respin of: > > https://lwn.net/ml/linux-kernel/20190206023446.177362-1-surenb%40google.com/ > > > > Android is adopting psi to detect and remedy memory pressure that > > results in stuttering and decreased responsiveness on mobile devices. > > > > Psi gives us the stall information, but because we're dealing with > > latencies in the millisecond range, periodically reading the pressure > > files to detect stalls in a timely fashion is not feasible. Psi also > > doesn't aggregate its averages at a high-enough frequency right now. > > > > This patch series extends the psi interface such that users can > > configure sensitive latency thresholds and use poll() and friends to > > be notified when these are breached. > > > > As high-frequency aggregation is costly, it implements an aggregation > > method that is optimized for fast, short-interval averaging, and makes > > the aggregation frequency adaptive, such that high-frequency updates > > only happen while monitored stall events are actively occurring. > > > > With these patches applied, Android can monitor for, and ward off, > > mounting memory shortages before they cause problems for the user. > > For example, using memory stall monitors in userspace low memory > > killer daemon (lmkd) we can detect mounting pressure and kill less > > important processes before device becomes visibly sluggish. In our > > memory stress testing psi memory monitors produce roughly 10x less > > false positives compared to vmpressure signals. Having ability to > > specify multiple triggers for the same psi metric allows other parts > > of Android framework to monitor memory state of the device and act > > accordingly. > > > > The new interface is straight-forward. The user opens one of the > > pressure files for writing and writes a trigger description into the > > file descriptor that defines the stall state - some or full, and the > > maximum stall time over a given window of time. E.g.: > > > > /* Signal when stall time exceeds 100ms of a 1s window */ > > char trigger[] = "full 100000 1000000" > > fd = open("/proc/pressure/memory") > > write(fd, trigger, sizeof(trigger)) > > while (poll() >= 0) { > > ... > > }; > > close(fd); > > > > When the monitored stall state is entered, psi adapts its aggregation > > frequency according to what the configured time window requires in > > order to emit event signals in a timely fashion. Once the stalling > > subsides, aggregation reverts back to normal. > > > > The trigger is associated with the open file descriptor. To stop > > monitoring, the user only needs to close the file descriptor and the > > trigger is discarded. > > > > Patches 1-6 prepare the psi code for polling support. Patch 7 implements > > the adaptive polling logic, the pressure growth detection optimized for > > short intervals, and hooks up write() and poll() on the pressure files. > > > > The patches were developed in collaboration with Johannes Weiner. > > > > The patches are based on 5.0-rc8 (Merge tag 'drm-next-2019-03-06'). > > > > Suren Baghdasaryan (7): > > psi: introduce state_mask to represent stalled psi states > > psi: make psi_enable static > > psi: rename psi fields in preparation for psi trigger addition > > psi: split update_stats into parts > > psi: track changed states > > refactor header includes to allow kthread.h inclusion in psi_types.h > > psi: introduce psi monitor > > > > Documentation/accounting/psi.txt | 107 ++++++ > > include/linux/kthread.h | 3 +- > > include/linux/psi.h | 8 + > > include/linux/psi_types.h | 105 +++++- > > include/linux/sched.h | 1 - > > kernel/cgroup/cgroup.c | 71 +++- > > kernel/kthread.c | 1 + > > kernel/sched/psi.c | 613 ++++++++++++++++++++++++++++--- > > 8 files changed, 833 insertions(+), 76 deletions(-) > > > > Changes in v5: > > - Fixed sparse: error: incompatible types in comparison expression, as per > > Andrew > > - Changed psi_enable to static, as per Andrew > > - Refactored headers to be able to include kthread.h into psi_types.h > > without creating a circular inclusion, as per Johannes > > - Split psi monitor from aggregator, used RT worker for psi monitoring to > > prevent it being starved by other RT threads and memory pressure events > > being delayed or lost, as per Minchan and Android Performance Team > > - Fixed blockable memory allocation under rcu_read_lock inside > > psi_trigger_poll by using refcounting, as per Eva Huang and Minchan > > - Misc cleanup and improvements, as per Johannes > > > > Notes: > > 0001-psi-introduce-state_mask-to-represent-stalled-psi-st.patch is unchanged > > from the previous version and provided for completeness. > > Please fix kbuild test bot's warning in 6/7 > Other than that, for all patches, Thanks for the review! Pushed v6 with the fix for the warning: https://lkml.org/lkml/2019/3/19/987 Also fixed a bug introduced in https://lkml.org/lkml/2019/3/8/686 which I discovered while testing (description in the changelog of the new patchset). > > Acked-by: Minchan Kim <minchan@xxxxxxxxxx>
