</td>
</tr>
+<tr>
+<td style="vertical-align: top;">
+0.10.0-pre15<br>
+</td>
+<td style="vertical-align: top;">
+0.27<br>
+0.28<br>
+0.29<br>
+0.30<br>
+0.31<br>
+0.32<br>
+0.33<br>
+0.34<br>
+0.35<br>
+0.36<br>
+</td>
+<td style="vertical-align: top;">
+0.53<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+0.6<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+1.0<br>
+</td>
+<td style="vertical-align: top;">
+2.6.27-rc7<br>
+2.6.27-rc8<br>
+2.6.27-rc9<br>
+</td>
+<td style="vertical-align: top;">
+LTTng 0.27 and lttd (ltt-control) 0.53 implement a vmap-less buffering scheme
+using splice().<br>
+LTTng 0.28 includes a small build fix.<br>
+LTTng 0.29 supports 2.6.27-rc8.<br>
+LTTng 0.32 supports 2.6.27-rc9 and adds a spinlock/irqoff buffering scheme
+(can be used with lttctl -T relay-locked).<br>
+LTTng 0.33, 0.34 : checkpatch.pl coding style fixes. 0.35, 0.36 : size_t cast.<br>
+</td>
+<td style="vertical-align: top;">
+</td>
+<td style="vertical-align: top;">
+x86, alpha, arm26, avr32, cris, frv, h8300, m32r, m68knommu, parisc, sh, sh64,
+um, v850, xtensa.<br>
+arm, i686, ia64, m68k, mips, mipsel, x86_64, powerpc 405,
+powerpc64, s390, sparc, sparc64.<br>
+</td>
+</tr>
+<tr>
+<td style="vertical-align: top;">
+0.11.0<br>
+</td>
+<td style="vertical-align: top;">
+0.38<br>
+</td>
+<td style="vertical-align: top;">
+0.53<br>
+0.54<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+0.6<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+2.0<br>
+</td>
+<td style="vertical-align: top;">
+2.6.27<br>
+</td>
+<td style="vertical-align: top;">
+LTTng 0.38 and LTTV 0.11.0<br>
+<br>
+I just cleaned up the LTTng trace format heavily, got rid of the
+heartbeat timer (by checking for overflow at the tracing site), got rid
+of the "special" compact channel; it removed about 5 FIXMEs in LTTng
+(cpu hotplug and compact channel related). Everything is compact now :<br>
+<br>
+This is much more compact than the previous format, and permits a
+"tracer debug mode" in menuconfig which enables the "event size" field,
+which helps cross-checking the size expected by the userspace tool and
+the size written by the kernel.<br>
+<br>
+Note that this "event size" field can eventually be enabled on a
+per-event or per-channel basis. This will probably be useful to encode
+"binary blobs"...<br>
+<br>
+I also cleanup up the subbuffer header to make is much smaller than the
+previous one by removing unneeded information.<br>
+<br>
+I renamed the "facilities" channel to a better name : "metadata". It
+contains marker descriptions.<br>
+<br>
+The trace major number is bumped to "2" and is completely incompatible
+with old LTTV.<br>
+</td>
+<td style="vertical-align: top;">
+</td>
+<td style="vertical-align: top;">
+x86, alpha, arm26, avr32, cris, frv, h8300, m32r, m68knommu, parisc, sh, sh64,
+um, v850, xtensa.<br>
+arm, i686, ia64, m68k, mips, mipsel, x86_64, powerpc 405,
+powerpc64, s390, sparc, sparc64.<br>
+</td>
+</tr>
+
+<tr>
+<td style="vertical-align: top;">
+0.11.1<br>
+0.11.2<br>
+0.11.3<br>
+</td>
+<td style="vertical-align: top;">
+0.39<br>
+0.40<br>
+0.41<br>
+0.42<br>
+0.43<br>
+0.44<br>
+0.45<br>
+0.46<br>
+</td>
+<td style="vertical-align: top;">
+0.53<br>
+0.54<br>
+0.55<br>
+0.56<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+0.6<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+2.1<br>
+</td>
+<td style="vertical-align: top;">
+2.6.27<br>
+2.6.27.2<br>
+</td>
+<td style="vertical-align: top;">
+LTTng 0.39 and LTTV 0.11.1 fixes 32-64 bits subbuffer header portability.<br>
+LTTng 0.41 reintroduces the formal verification fix, which solves the
+case where the reader thinks the uncommitted subbuffer is fully committed.
+Unlikely to happen, but could, with small buffers especially.<br>
+</td>
+<td style="vertical-align: top;">
+</td>
+<td style="vertical-align: top;">
+x86, alpha, arm26, avr32, cris, frv, h8300, m32r, m68knommu, parisc, sh, sh64,
+um, v850, xtensa.<br>
+arm, i686, ia64, m68k, mips, mipsel, x86_64, powerpc 405,
+powerpc64, s390, sparc, sparc64.<br>
+</td>
+</tr>
+
+<tr>
+<td style="vertical-align: top;">
+0.11.4<br>
+0.11.5<br>
+0.11.6<br>
+</td>
+<td style="vertical-align: top;">
+0.47<br>
+0.48<br>
+0.49<br>
+0.50<br>
+0.51<br>
+0.52<br>
+0.53<br>
+0.54<br>
+0.55<br>
+0.56<br>
+0.57<br>
+</td>
+<td style="vertical-align: top;">
+0.53<br>
+0.54<br>
+0.55<br>
+0.56<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+0.6<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+2.2<br>
+</td>
+<td style="vertical-align: top;">
+2.6.27.4<br>
+2.6.27.6<br>
+</td>
+<td style="vertical-align: top;">
+LTTng 0.47 and LTTV 0.11.4 now saves the event lost count in the subbuffer
+header. It's printed as a lttv warning when encountered. LTTng 0.47 also
+implemented specialized trap probes.<br>
+LTTng 0.49 is a compile fix for userspace markers.<br>
+LTTng 0.50 fixes immediate values by reverting the "jump patching" version of
+immediate values. They were always on, and therefore broken. It also
+reimplements tracepoint, marker and imv mutexes.<br>
+LTTng 0.51 implements timestamping updates.<br>
+LTTng 0.53 implements a timer-based generic tracing clock, also includes
+various fixes.<br>
+LTTng 0.54 fixes the MIPS get_cycles_rate() and also change the freq_scale
+variable from a multiplier to a divisor.<br>
+LTTng 0.57 fixes the modification done to offset and commit count counters
+following formal verification so the overflow is dealt with correctly. It was
+causing problems on 32-bits machines after 4GB worth of data going through a
+buffer.<br>
+</td>
+<td style="vertical-align: top;">
+</td>
+<td style="vertical-align: top;">
+x86, alpha, arm26, avr32, cris, frv, h8300, m32r, m68knommu, parisc, sh, sh64,
+um, v850, xtensa.<br>
+arm, i686, ia64, m68k, mips, mipsel, x86_64, powerpc 405,
+powerpc64, s390, sparc, sparc64.<br>
+</td>
+</tr>
+
+
+<tr>
+<td style="vertical-align: top;">
+0.11.4<br>
+0.11.5<br>
+0.11.6<br>
+</td>
+<td style="vertical-align: top;">
+0.58<br>
+0.59<br>
+0.60<br>
+0.61<br>
+0.62<br>
+0.63<br>
+0.64<br>
+</td>
+<td style="vertical-align: top;">
+0.58<br>
+0.59<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+0.6<br>
+</td>
+<td style="vertical-align: top;">
+obsolete<br>
+</td>
+<td style="vertical-align: top;">
+2.2<br>
+</td>
+<td style="vertical-align: top;">
+2.6.27.7<br>
+2.6.27.8<br>
+</td>
+<td style="vertical-align: top;">
+LTTng 0.58 implements debugfs-based trace control which will gradually replace
+the netlink-based control.<br>
+ltt-control 0.58 expects the netlink negative error values.<br>
+LTTng 0.59 implements an exclusive wait poll to fix thundering herd problem and
+help scalability.<br>
+</td>
+<td style="vertical-align: top;">
+</td>
+<td style="vertical-align: top;">
+x86, alpha, arm26, avr32, cris, frv, h8300, m32r, m68knommu, parisc, sh, sh64,
+um, v850, xtensa.<br>
+arm, i686, ia64, m68k, mips, mipsel, x86_64, powerpc 405,
+powerpc64, s390, sparc, sparc64.<br>
+</td>
+</tr>
</tbody>
</table>
projects / lttv.git / blobdiff