66d000029cf757ba0d0ce0e5cf7a4d058331ad64
[lttv.git] / ltt / branches / poly / doc / developer / lttng-lttv-roadmap.html
1 <html>
2 <body>
3 <center><big><big>LTTV & LTTng roadmap<small><small></center>
4 <br>
5 <br>
6 Here are the roadmaps for the LTTV and LTTng development. I use a priority indice
7 for the TODO items :<br>
8 (1) : very high priority<br>
9 (10): lowest priority<br>
10 <br>
11 <br>
12 Dependencies are written between brackets [ ].<br>
13 The # symbol marks who is currently working on the item.<br>
14 The % symbol marks who is interested in the realisation of the item.<br>
15 <br>
16 <big>LTTV Roadmap<small><br>
17 <br>
18 * TODO<br>
19 (2) Add support for "stop" button in event list. (disabling event request
20 scheduler)<br>
21 (2) Finish pre-computing of states to a file.<br>
22 (3) Add cluster support.<br>
23 # <A HREF="mailto:Eric Clement <eric.clement@polymtl.ca>">Eric Clement</A><br>
24 (3) Make LTTV aware of type formats (visual separators) defined in the XML
25 file.<br>
26 (3) Use a per architecture enumeration for traps.<br>
27 (4) Add event specific fields support to filter.<br>
28 (4) Add a periodic event interval view. (useful to verify event periodicity)<br>
29 (4) create a graphical per cpu activity view.<br>
30 (5) Add Python scripting hooks.<br>
31 (5) Flight recorder : start lttd automatically upon GUI trace control stop.<br>
32 (5) Automatically detect traces with too much processes and disable faulty operations.<br>
33 (5) Event sequence detector (inspired from regular expressions).<br>
34 (7) Create a hardware counter viewer (low cost rate counters : L1 cache miss,
35 page faults, interrupts...). This will be a generalisation of the event rate
36 view into a view of the evolution of a user definable event field.<br>
37 <br>
38 * TO FIX<br>
39 (10) Event filter : event.time does not work.<br>
40 (10) Add cancel button to LTTV filter GUI window.<br>
41 (10) Sometimes, in the control flow view, a process with 0 creation time is
42 created in addition to the real process itself. Seems to be caused by end of
43 process life.<br>
44 (10) Statistics do not take in account the time spent in the mode present at
45 the beginning of the trace. Example : real time spent in system call on behalf
46 of process 0.<br>
47 <br>
48 <br>
49 <big>LTT Next Generation Roadmap<small><br>
50 <br>
51 * TODO<br>
52 (4) Add Xen support.<br>
53 # <A HREF="mailto:Mathieu Desnoyers <compudj@krystal.dyndns.org>">Mathieu Desnoyers</A><br>
54 # <A HREF="mailto:Parisa Heidari <parisa.heidari@polymtl.ca>">Parisa Heidari</A><br>
55 (4) efficient dynamic event filtering while recording trace.<br>
56 % Sensis Corp. <A HREF="mailto:Bish, Tim <Tim.Bish@Sensis.com>">Tim Bish</A><br>
57 (4) instrument kernel bottom half irqsave, spinlocks, rwlocks, seqlocks, semaphores, mutexes, brlock.<br>
58 (4) integrate NPTL instrumentation (see
59 <A HREF="http://nptltracetool.sourceforge.net/">PTT</A>).<br>
60 (5) Support CPUs with scalable frequency.<br>
61 (5) Integrate LTTng and lttd with LKCD.<br>
62 (7) Integrate periodical dump of perfctr hardware counters.<br>
63 (8) Integrate periodical dump of SystemTAP computed information.<br>
64 (8) Integrate SystemTAP logging with LTTng.<br>
65 (9) Add support for setjmp/longjmp and jump tables instrumentation to
66 ltt-instrument-functions.<br>
67 (9) Make ltt-usertrace-fast support internal heartbeat timer.<br>
68 (3) port LTTng to :<br>
69 x86_64<BR>
70 #Autodesk <A HREF="mailto:Francois L'Archeveque <fla@discreet.com>">Francois
71 L'Archeveque</A> for 2.6.9 RedHat Enterprise (patch available in contrib, still
72 has to be ported to 2.6.14, thanks!)<BR>
73 # Wind River for 2.6.14<BR>
74 PPC<BR>
75 PPC64<BR>
76 # Wind River for 2.6.14<BR>
77 alpha<BR>
78 user-mode Linux<BR>
79 Xen<BR>
80 # IBM<BR>
81 MIPS<BR>
82 MIPS64<BR>
83 % Wind River for 2.6.14<BR>
84 # Tim Bird <A HREF="mailto:tim.bird@as.sony.com">Tim Bird</A><br>
85 S/390<BR>
86 RTLinux<BR>
87 % Wind River for 2.6.14<BR>
88 <br>
89 <br>
90 <br>
91 * TODO (low priority)<br>
92 enhance RPM packages for lttng kernel<br>
93 Integrate header generation (genevent) in kernel build system.<br>
94 Find a different way to printk from instrumentation : forbidden from schedule
95 and wakeup (causes a deadlock). -> Modify printk so it uses LTTng tracer!<br>
96 Export channels via network sockets instead of writing them to disk.<br>
97 Export buffers with time constraint for "live" visualisation. Use
98 ltt_force_switch periodically from a timer to insure slow channels do not
99 interfere with viewing.<br>
100 Have an optional round-robin mode to write information into multiple channels
101 from the same source.<br>
102 <br>
103 * Need to be discussed<br>
104 Use 2.6.14 RelayFS control files.<br>
105 Drop ltt-module-register and ltt-module-unregister, use exported variables.<br>
106 drop ltt_filter_control, use functions pointers instead.<br>
107 Merge facilities headers into one big header.<br>
108 Change the name of XML files from XML to something else.<br>
109 Remove ltt-base.c.<br>
110 <br>
111 <br>
112 * lttng patch division (0.5.10+) :<br>
113 <br>
114 instrumentation.diff<br>
115 instrumentation-arm.diff<br>
116 instrumentation-i386.diff<br>
117 instrumentation-mips.diff<br>
118 instrumentation-powerpc.diff<br>
119 instrumentation-ppc.diff<br>
120 instrumentation-s390.diff<br>
121 instrumentation-sh.diff<br>
122 ltt-facilities-headers.diff<br>
123 ltt-facilities-loader.diff<br>
124 ltt-facilities.diff<br>
125 ltt-relayfs.diff<br>
126 ltt-core.diff<br>
127 ltt-build.diff<br>
128 <br>
129 <br>
130 Mathieu Desnoyers<br>
131
132
133 </body>
134 </html>
This page took 0.0324 seconds and 4 git commands to generate.