kernel-shark: Change the mechanism of the multi-threaded search
We switch from classical Map-Reduce approach in which the data is
divided in sub-sets and each thread searches into its own sub-set
to a solution in which all thread are progressing in the data in
parallel. Note that the Map-Reduce solution is more efficient
because at the end when we merge the searching results we simply
have to append the outputs of the threads, while in the case of
a parallel search we hare to also sort the merged outputs of the
threads. However, the parallel search allows the user to stop and
later restart the search at any time. The GUI buttons, needed to
stop and restart the multi-threaded search will be enabled in the
following patch.
Link: http://lore.kernel.org/linux-trace-devel/20200504174342.24615-3-y.karadz@gmail.com
Signed-off-by: Yordan Karadzhov (VMware) <y.karadz@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
4 files changed
