Difference between revisions of "Time namespace"
Jump to navigation
Jump to search
Line 19: | Line 19: | ||
==Maybe later== | ==Maybe later== | ||
− | * arm64/arm32/s390/power64 - add archs vvar support | + | * arm64/arm32/s390/power64 - add archs vvar support (nit: big/little-endianess for timespec::nsec) |
* REALTIME-related: | * REALTIME-related: | ||
** REALTIME offsets | ** REALTIME offsets |
Revision as of 22:12, 13 August 2018
Two things (for now) we want to solve with this:
- Shift timer's offsets
- Make start-time remain "unchanged" after C/R
- Continuous flow of monotonic time (CLOCK_MONOTONIC).
What about other kinds of counters like perf events and trace events?
TODO
Required in RFC
- timerfd
- timer_create()
- COARSE times
- RAW time
- clock_nanosleep()
- btime in /proc/stat (used by pstools)
- starttime in /proc/pid/stat
- selftests to test all we've added
- TIME_NS iffdefery everywhere
Maybe later
- arm64/arm32/s390/power64 - add archs vvar support (nit: big/little-endianess for timespec::nsec)
- REALTIME-related:
- REALTIME offsets
- vfs modification/creation time should work
- utime()/utimes()/futimesat() (with times == NULL)
- utimensat()/futimens() - with UTIME_NOW
- mq_timedsend()/mq_timedreceive()
- semtimedop()
- Adjtime (too complicated for PoC)
- Cpu time for thread/pid/pgid (times())
- /proc/stat ticks? (top uses them e.g.)
- pid creation time (probably different unrelated API)
- clock_tai - if we care about isolation from host's time