RFC Trace Clock v2
Get series with b4
b4 am [email protected]Versions newest first
- v1 RFC Latest18 patches 72 repliesIn review
Patches in v1 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/18 | get_cycles() : kconfig HAVE_GET_CYCLESinit/ | +10 | 0 replies | |
| 2/18 | get_cycles() : x86 HAVE_GET_CYCLESarch/ arch/ | +13 | 0 replies | |
| 3/18 | get_cycles() : sparc64 HAVE_GET_CYCLESarch/ arch/ arch/ | +21 | 0 replies | |
| 4/18 | get_cycles() : powerpc64 HAVE_GET_CYCLESarch/ arch/ | +12 | 2 replies | |
| 5/18 | get_cycles() : MIPS HAVE_GET_CYCLES_32arch/ arch/ | +29 | 0 replies | |
| 6/18 | Trace clock genericinclude/ include/ kernel/ | +88 | 0 replies | |
| 7/18 | Trace clock coreinit/ kernel/ kernel/ +1 more | +302 | 6 replies | |
| 8/18 | cnt32_to_63 should use smp_rmb()include/ | +6 | 88 replies | |
| 9/18 | Powerpc : Trace clockarch/ arch/ | +51 | 0 replies | |
| 10/18 | Sparc64 : Trace clockarch/ arch/ | +47 | 1 reply | |
| 11/18 | LTTng timestamp sharch/ arch/ arch/ | +68 | 0 replies | |
| 12/18 | LTTng - TSC synchronicity testDocumentation/ init/ kernel/ +1 more | +325 | 0 replies | |
| 13/18 | x86 : remove arch-specific tsc_sync.carch/ arch/ arch/ +1 more | +12 | 0 replies | |
| 14/18 | MIPS use tsc_sync.carch/ arch/ | +27 | 0 replies | |
| 15/18 | MIPS : export hpt frequency for trace_clock.arch/ arch/ | +3 | 0 replies | |
| 16/18 | MIPS create empty sync_core()arch/ | +6 | 0 replies | |
| 17/18 | MIPS : Trace clockarch/ arch/ arch/ +2 more | +261 | 2 replies | |
| 18/18 | x86 trace clockarch/ arch/ arch/ +1 more | +323 | 0 replies |
Reviews trailers per patch
2 of 18 patches have a Reviewed-by or Acked-by.
| Patch | David S. Miller |
|---|---|
| 1/18 | |
| 2/18 | |
| 3/18 | A-b |
| 4/18 | |
| 5/18 | |
| 6/18 | |
| 7/18 | |
| 8/18 | |
| 9/18 | |
| 10/18 | A-b |
| 11/18 | |
| 12/18 | |
| 13/18 | |
| 14/18 | |
| 15/18 | |
| 16/18 | |
| 17/18 | |
| 18/18 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [RFC patch 00/18] Trace Clock v2
Hi,
I've cleaned up the LTTng timestamping code, renamed it into "trace clock", ripped apart the tsc_sync.c x86 code, added documentation (printk to the console when the tracing clock is used) about what to do when an unsync TSC is detected. I however kept the cache-line bouncing workaround for now. However, I now synchronize the counters every jiffy with a per-cpu timer so it gives an upper bound to the time imprecision.
The trace clock works with a trace_clock_get()/put(), so all the mechanic and overhead that might be required to provide correct timestamps on weird systems is *only* enabled when tracing is active.
I plan to stick to this simple solution for now so we can get reliable tracing for 95ish% of systems out there, and to keep room for improvement (nice NTP-like schemes) for a later version. (sadly, given this is actually v2, I cannot say "let's keep that for v2") ;)
This patchset applies on top of 2.6.28-rc3.
Mathieu
Signature · 2 lines
Mathieu Desnoyers OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68