* Count the number of CPUs and divide buffer_size_kb by the number of CPUs.
Users should watch for instances of "mmiotrace has lost events" in dmesg to make
sure the trace buffers are not too small. The original value for
buffer_size_kb was chosen somewhat arbitrarily. Empirical testing
has shown that its large enough, so we don't actually know where the lower
boundary lies.
-LP: #491943
-- Tim Gardner <email address hidden> Fri, 20 Aug 2010 12:19:31 -0600
This bug was fixed in the package ureadahead - 0.100.0-7
---------------
ureadahead (0.100.0-7) maverick; urgency=low
* Count the number of CPUs and divide buffer_size_kb by the number of CPUs.
Users should watch for instances of "mmiotrace has lost events" in dmesg to make
sure the trace buffers are not too small. The original value for
buffer_size_kb was chosen somewhat arbitrarily. Empirical testing
has shown that its large enough, so we don't actually know where the lower
boundary lies.
-LP: #491943
-- Tim Gardner <email address hidden> Fri, 20 Aug 2010 12:19:31 -0600