summaryrefslogtreecommitdiffstats
path: root/fs/kernfs
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2019-03-06 00:45:45 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2019-03-06 06:07:17 +0100
commit147e1a97c4a0bdd43f55a582a9416bb9092563a9 (patch)
tree261bb3a16a21250de5ae7df11d0e7a8c6caef6c4 /fs/kernfs
parentmm, compaction: capture a page under direct compaction (diff)
downloadlinux-147e1a97c4a0bdd43f55a582a9416bb9092563a9.tar.xz
linux-147e1a97c4a0bdd43f55a582a9416bb9092563a9.zip
fs: kernfs: add poll file operation
Patch series "psi: pressure stall monitors", v3. 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 straightforward. 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 1-4 prepare the psi code for polling support. Patch 5 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. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Li Zefan <lizefan@huawei.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/kernfs')
-rw-r--r--fs/kernfs/file.c31
1 files changed, 20 insertions, 11 deletions
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index f8d5021a652e..ae948aaa4c53 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
* to see if it supports poll (Neither 'poll' nor 'select' return
* an appropriate error code). When in doubt, set a suitable timeout value.
*/
+__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
+{
+ struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry);
+ struct kernfs_open_node *on = kn->attr.open;
+
+ poll_wait(of->file, &on->poll, wait);
+
+ if (of->event != atomic_read(&on->event))
+ return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
+
+ return DEFAULT_POLLMASK;
+}
+
static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
{
struct kernfs_open_file *of = kernfs_of(filp);
struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
- struct kernfs_open_node *on = kn->attr.open;
+ __poll_t ret;
if (!kernfs_get_active(kn))
- goto trigger;
+ return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
- poll_wait(filp, &on->poll, wait);
+ if (kn->attr.ops->poll)
+ ret = kn->attr.ops->poll(of, wait);
+ else
+ ret = kernfs_generic_poll(of, wait);
kernfs_put_active(kn);
-
- if (of->event != atomic_read(&on->event))
- goto trigger;
-
- return DEFAULT_POLLMASK;
-
- trigger:
- return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
+ return ret;
}
static void kernfs_notify_workfn(struct work_struct *work)