[lttv.git] / doc / developer / lttng-lttv-roadmap.html

<html>
<body>
<center><big><big>LTTV & LTTng roadmap<small><small></center>
<br>
<br>
Here are the roadmaps for the LTTV and LTTng development. I use a priority indice
for the TODO items :<br>
(1) : very high priority<br>
(10): lowest priority<br>
<br>
<br>
Dependencies are written between brackets [ ].<br>
The # symbol marks who is currently working on the item.<br>
The % symbol marks who is interested in the realisation of the item.<br>
The $ symbol marks who is contributing funding for the realisation of the item.<br>
<br>
<br>
<big>LTT Next Generation Roadmap<small><br>
<br>
* TODO (high priority)<br>
<BR>
(1) LTTng event description: move from tracepoint/markers to Ftrace TRACE_EVENT
 declarations. Extend TRACE_EVENT as needed.<br>
# <A HREF="mailto: Douglas Santos <douglas.santos@polymtl.ca>">Douglas Santos</A>)<BR>
(1) LTTng ring buffer adaptation for FTrace.
(1) FTrace/LTTng trace format standardization.<BR>
(1) Extend NO_HZ support vs trace streaming support to other architectures (need
to add cpu idle notifiers and test).<br>
(1) Make sure ltt-ascii kernel text dump fits well with streaming hooked into
cpu idle.<br>
(1) Support CPUs with scalable frequency with a time-consistent increment and
with an approach scalable to SMP. (done for ARM OMAP3 UP only, but the OMAP3
approach should be tested and probably derived into an SMP implementation)<br>
<br>
<br>
* Nice to have<br>
<br>
(3) Bring stack dump in sync with new lttng.<br>
(4) Dump mounts. (to fix)<br>
(4) Add Xen support. (Trace buffer desallocation needs to be fixed)<br>
(4) integrate NPTL instrumentation (see
<A HREF="http://nptltracetool.sourceforge.net/">PTT</A>).<br>
(4) Probe calibration kernel module.<br>
(4) Make page faults detect nested fault without nesting 4 times in the page
fault handler. (or use vmalloc_sync_all at each tracing module load)<br>
(5) Add boot time tracing support.<br>
(5) Integrate LTTng and lttd with LKCD.<br>
	# <A HREF="mailto:Lai Jiangshan <laijs@cn.fujitsu.com>>">Lai Jiangshan</A><br>
(7) Integrate periodical dump of perfctr hardware counters.<br>
(8) Integrate SystemTAP logging with LTTng.<br>
(8) Integrate periodical dump of SystemTAP computed information.<br>
(9) Add support for setjmp/longjmp and jump tables instrumentation to
ltt-instrument-functions.<br>
<br>
<br>
* Done<br>
<br>
- (2009) Port LTTng to ARM OMAP3 with power management and dynamic frequency scaling
  support. (Done by Mathieu Desnoyers, funded by Nokia).<br>
- (2009) Improvement of trace streaming power consumption efficiency (NO_HZ
  support) (x86 only for now).<br>
- (2009) Periodic flush for trace streaming (Mathieu Desnoyers).<br>
- (2009) Ascii text output from LTTng. (started by Lai Jiangshan (Fujitsu),
  completed by Mathieu Desnoyers)<br>
<br>
<br>
<big>LTTV Roadmap<small><br>
<br>
Note: new feature development is currently done in the Linux Tools Project:
LTTng Integration. Mainwhile, LTTV is maintained as a known-stable viewer.<br>
<br>
<br>
* Nice to have<br>
<br>
(4) Statistics per time window.<br>
(4) Add Xen per physical CPU view.<br>
(4) Add Xen per vcpu view.<br>
(4) Disable plugins when threshold reached (i.e. too much process in control
flow view). Draw, and, when the threshold is reached, stop drawing. The global
statistics view can inhibit showing the per process stats.<br>
(4) Add a visual artifact : PID 0 could be named swapper instead of UNNAMED for
cpus > 0.<br>
(4) Add event specific fields support to filter.<br>
(4) Add a periodic event interval view. (useful to verify event periodicity)<br>
(4) create a graphical per cpu activity view.<br>
(4) Filter by target process.<br>
(4) Compensate for time spent in probes in LTTV analysis.<br>
(4) Add CPU, network, disk, memory usage histogram. [Per interval statistics]<br>
(4) Add sort by process priority in the control flow view (must also instrument
priority information of the processes).<br>
% Airbus<br>
(5) Add Python scripting hooks.<br>
(5) Add GUI interface to take an hybrid trace.<br>
(5) Automatically detect traces with too much processes and disable faulty operations.<br>
(5) Event sequence detector (inspired from regular expressions).<br>
(7) Create a hardware counter viewer (low cost rate counters : L1 cache miss,
page faults, interrupts...). This will be a generalisation of the event rate
view into a view of the evolution of a user definable event field.<br>
<br>
* TO FIX<br>
<br>
(10) Add cancel button to LTTV filter GUI window.<br>
(10) Sometimes, in the control flow view, a process with 0 creation time is
created in addition to the real process itself. Seems to be caused by end of
process life.<br>
(10) Statistics do not take in account the time spent in the mode present at
the beginning of the trace. Example : real time spent in system call on behalf
of process 0.<br>
<br>
<br>
Mathieu Desnoyers<br>


</body>
</html>
Commit	Line	Data
1f2c88b1	1	<html>
1f2c88b1	2	<body>
e3a30a9e	3	<center><big><big>LTTV & LTTng roadmap<small><small></center>
674fa3b3	4	<br>
674fa3b3	5	<br>
5e11a375	6	Here are the roadmaps for the LTTV and LTTng development. I use a priority indice
fc5993d2	7	for the TODO items :<br>
90d65afc	8	(1) : very high priority<br>
90d65afc	9	(10): lowest priority<br>
fc5993d2	10	<br>
fc5993d2	11	<br>
6b18b620	12	Dependencies are written between brackets [ ].<br>
59656e3f	13	The # symbol marks who is currently working on the item.<br>
e565223b	14	The % symbol marks who is interested in the realisation of the item.<br>
35e68130	15	The $ symbol marks who is contributing funding for the realisation of the item.<br>
59656e3f	16	<br>
b894bf02	17	<br>
	18	<big>LTT Next Generation Roadmap<small><br>
	19	<br>
83b3ebc4 MD	20	* TODO (high priority)<br>
83b3ebc4 MD	21	<BR>
c311e9d5	22	(1) LTTng event description: move from tracepoint/markers to Ftrace TRACE_EVENT
35e68130 MD	23	declarations. Extend TRACE_EVENT as needed.<br>
	24	# <A HREF="mailto: Douglas Santos <douglas.santos@polymtl.ca>">Douglas Santos</A>)<BR>
	25	(1) LTTng ring buffer adaptation for FTrace.
c311e9d5 MD	26	(1) FTrace/LTTng trace format standardization.<BR>
	27	(1) Extend NO_HZ support vs trace streaming support to other architectures (need
	28	to add cpu idle notifiers and test).<br>
	29	(1) Make sure ltt-ascii kernel text dump fits well with streaming hooked into
	30	cpu idle.<br>
83b3ebc4 MD	31	(1) Support CPUs with scalable frequency with a time-consistent increment and
	32	with an approach scalable to SMP. (done for ARM OMAP3 UP only, but the OMAP3
	33	approach should be tested and probably derived into an SMP implementation)<br>
c311e9d5 MD	34	<br>
	35	<br>
	36	* Nice to have<br>
35e68130	37	<br>
b894bf02	38	(3) Bring stack dump in sync with new lttng.<br>
	39	(4) Dump mounts. (to fix)<br>
	40	(4) Add Xen support. (Trace buffer desallocation needs to be fixed)<br>
	41	(4) integrate NPTL instrumentation (see
	42	<A HREF="http://nptltracetool.sourceforge.net/">PTT</A>).<br>
	43	(4) Probe calibration kernel module.<br>
	44	(4) Make page faults detect nested fault without nesting 4 times in the page
	45	fault handler. (or use vmalloc_sync_all at each tracing module load)<br>
	46	(5) Add boot time tracing support.<br>
	47	(5) Integrate LTTng and lttd with LKCD.<br>
	48	# <A HREF="mailto:Lai Jiangshan <laijs@cn.fujitsu.com>>">Lai Jiangshan</A><br>
	49	(7) Integrate periodical dump of perfctr hardware counters.<br>
	50	(8) Integrate SystemTAP logging with LTTng.<br>
	51	(8) Integrate periodical dump of SystemTAP computed information.<br>
	52	(9) Add support for setjmp/longjmp and jump tables instrumentation to
	53	ltt-instrument-functions.<br>
c311e9d5	54	<br>
b894bf02	55	<br>
35e68130 MD	56	* Done<br>
	57	<br>
	58	- (2009) Port LTTng to ARM OMAP3 with power management and dynamic frequency scaling
	59	support. (Done by Mathieu Desnoyers, funded by Nokia).<br>
	60	- (2009) Improvement of trace streaming power consumption efficiency (NO_HZ
	61	support) (x86 only for now).<br>
	62	- (2009) Periodic flush for trace streaming (Mathieu Desnoyers).<br>
	63	- (2009) Ascii text output from LTTng. (started by Lai Jiangshan (Fujitsu),
	64	completed by Mathieu Desnoyers)<br>
	65	<br>
b894bf02	66	<br>
c8a111eb	67	<big>LTTV Roadmap<small><br>
c8a111eb	68	<br>
c311e9d5 MD	69	Note: new feature development is currently done in the Linux Tools Project:
	70	LTTng Integration. Mainwhile, LTTV is maintained as a known-stable viewer.<br>
	71	<br>
	72	<br>
	73	* Nice to have<br>
35e68130	74	<br>
3ccb19e4	75	(4) Statistics per time window.<br>
ea53f068	76	(4) Add Xen per physical CPU view.<br>
ea53f068	77	(4) Add Xen per vcpu view.<br>
3ccb19e4	78	(4) Disable plugins when threshold reached (i.e. too much process in control
	79	flow view). Draw, and, when the threshold is reached, stop drawing. The global
	80	statistics view can inhibit showing the per process stats.<br>
568c21ab	81	(4) Add a visual artifact : PID 0 could be named swapper instead of UNNAMED for
568c21ab	82	cpus > 0.<br>
16fe6efa	83	(4) Add event specific fields support to filter.<br>
6ed34001	84	(4) Add a periodic event interval view. (useful to verify event periodicity)<br>
2d569f51	85	(4) create a graphical per cpu activity view.<br>
e6284587	86	(4) Filter by target process.<br>
cdee9265	87	(4) Compensate for time spent in probes in LTTV analysis.<br>
568c21ab	88	(4) Add CPU, network, disk, memory usage histogram. [Per interval statistics]<br>
42c475ad	89	(4) Add sort by process priority in the control flow view (must also instrument
	90	priority information of the processes).<br>
	91	% Airbus<br>
b35779fc	92	(5) Add Python scripting hooks.<br>
80f91a14	93	(5) Add GUI interface to take an hybrid trace.<br>
caf22319	94	(5) Automatically detect traces with too much processes and disable faulty operations.<br>
b0a1cd56	95	(5) Event sequence detector (inspired from regular expressions).<br>
c5cab5d9	96	(7) Create a hardware counter viewer (low cost rate counters : L1 cache miss,
	97	page faults, interrupts...). This will be a generalisation of the event rate
	98	view into a view of the evolution of a user definable event field.<br>
b85b85e5	99	<br>
162990b3	100	* TO FIX<br>
35e68130	101	<br>
b85b85e5	102	(10) Add cancel button to LTTV filter GUI window.<br>
	103	(10) Sometimes, in the control flow view, a process with 0 creation time is
	104	created in addition to the real process itself. Seems to be caused by end of
	105	process life.<br>
5355b763	106	(10) Statistics do not take in account the time spent in the mode present at
	107	the beginning of the trace. Example : real time spent in system call on behalf
	108	of process 0.<br>
c8a111eb	109	<br>
c8a111eb	110	<br>
b720b182	111	Mathieu Desnoyers<br>
1f2c88b1	112
	113
	114	</body>
	115	</html>