GitLab

Signed-off-by: Cong Xu <cong.xu@intel.com>

1. At log parsing time, pass Lustre striping information to DXLT module
  a. Obtain Lustre striping information in Lustre Module.
  b. Cache file striping information and map it to file name.
  c. Pass file striping information to DXLT module for each file.

2. In DXLT module, print Lustre striping and OST information if file system type is Lustre.
Signed-off-by: Cong Xu <cong.xu@intel.com>

2. Refactor DXLT to be a generic IO tracing tool for files on any file system.
3. Add file type information in DXLT log parser.

Next steps:
1. Based on the file type information in DXLT log parser, add information for specific file types. (For instance, add OST information for files on Lustre)
2. In the process of parsing DXLT logs, figure out how to obtain Lustre striping information from Lustre module.
3. Rename DXLT to be "Darshan eXtended Tracing (DXT)" or "Darshan eXtended IO Tracing (DXIOT)".
Signed-off-by: Cong Xu <cong.xu@intel.com>

Signed-off-by: Cong Xu <cong.xu@intel.com>

1. Use Lustre Module in Darshan
2. Integrate DXLT IO tracing code into one module
3. Add hooks in POSIX and MPI Modules
4. Add Intel copyright
Signed-off-by: Cong Xu <cong.xu@intel.com>

1. Use Lustre Module in Darshan
2. Integrate DXLT IO tracing code into one module
3. Add hooks in POSIX and MPI Modules
4. Add Intel copyright
Signed-off-by: Cong Xu <cong.xu@intel.com>

The stdio module stores names for the default streams (stdin,
stderr, stdout) in the following format: <STDERR>. The '<' and
'>' symbols require proper escape characters in order to be
properly interpretated by the darshan-job-summary (perl) script.

POSIX_F_OPEN_TIMESTAMP is now POSIX_F_OPEN_START_TIMESTAMP
POSIX_F_CLOSE_TIMESTAMP is now POSIX_F_CLOSE_END_TIMESTAMP

I also added POSIX_F_OPEN_END_TIMESTAMP and
POSIX_F_CLOSE_START_TIMESTAMP, so we can better understand how
long open and close phases are for some applications.

We don't currently have a system to try this out on, but just
wanted to make sure something was there as a failsafe. The current
implementation should be able to correctly aggregate all counters
in BGQ records, except for BGQ_INODES.

this includes defining an example logutils function for
aggregating null records into a single shared null record (needed
for darshan-merge utility)

also, bug fix to avoid any attempt of reading log file for
modules with no data present in the log