Skip to content

epoll keyed wakeups v3 - introduction

Davide Libenzi lkml 1 version New

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest6 patches 0 repliesNew

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/6epoll keyed wakeups v3 - add __wake_up_locked_key() and __wake_up_sync_key()include/linux/wait.h kernel/sched.c+24 -60 replies
2/6epoll keyed wakeups v3 - introduce new *_poll() wakeup macrosinclude/linux/wait.h+9 -130 replies
3/6epoll keyed wakeups v3 - make sockets use keyed wakeupsnet/core/sock.c+3 -30 replies
4/6epoll keyed wakeups v3 - teach epoll about hints coming with the wakeup keyfs/eventpoll.c+29 -20 replies
5/6epoll keyed wakeups v3 - make eventfd use keyed wakeupsfs/eventfd.c+3 -30 replies
6/6epoll keyed wakeups v3 - make tty use keyed wakeupsdrivers/char/tty_io.c+10 -100 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.

Read the v1 thread

Cover letter [patch 0/6] epoll keyed wakeups v3 - introduction

The follwing patch set introduces wakeup hints for some of the most popular (from epoll POV) devices, so that epoll code can avoid spurious wakeups on its waiters.
The problem with epoll is that the callback-based wakeups do not, ATM, carry any information about the events the wakeup is related to. So the only choice epoll has (not being able to call f_op->poll() from inside the callback), is to add the file* to a ready-list and resolve the real events later on, at epoll_wait() (or its own f_op->poll()) time. This can cause spurious wakeups, since the wake_up() itself might be for an event the caller is not interested into.
The rate of these spurious wakeup can be pretty high in case of many network sockets being monitored.
By allowing devices to report the events the wakeups refer to (at least the two major classes - POLLIN/POLLOUT), we are able to spare useless wakeups by proper handling inside the epoll's poll callback. Epoll will have in any case to call f_op->poll() on the file* later on, since the change to be done in order to have the full event set sent via wakeup, is too invasive for the way our f_op->poll() system works (the full event set is calculated inside the poll function - there are too many of them to even start thinking the change - also poll/select would need change too).
Epoll is changed in a way that both devices which send event hints, and the ones that don't, are correctly handled. The former will gain some efficiency though.
As a general rule for devices, would be to add an event mask by using poll wakeup macros, when making up poll wait queues.
I tested it (together with the epoll's poll fix patch Andrew has in -mm) and wakeups for the supported devices are correctly filtered. Test program available here:

http://www.xmailserver.org/epoll_test.c

ChangeLog / v3:

- wake_up_nested() was only used by epoll, so the new wake_up_nested_poll() has been moved into fs/eventpoll.c, and wake_up_nested() being no more used, has been dropped

ChangeLog / v2:

- No more kwake*() but *_poll()

- Do not add extra parameter to _locked() and _sync(), but create two new functions

- Actually make epoll used _poll() wakeups too for its own waiters

PS: Andrew, those are directly based over the bits you already have

    in -mm.

- Davide