Index index by Group index by Distribution index by Vendor index by creation date index by Name Mirrors Help Search

blktrace-1.1.0+git.20170126-lp150.1.4 RPM for ppc64le

From OpenSuSE Ports Leap 15.0 for ppc64le

Name: blktrace Distribution: openSUSE Leap 15.0
Version: 1.1.0+git.20170126 Vendor: openSUSE
Release: lp150.1.4 Build date: Thu May 17 00:39:20 2018
Group: Development/Tools/Other Build host: obs-power8-03
Size: 1442166 Source RPM: blktrace-1.1.0+git.20170126-lp150.1.4.src.rpm
Summary: Block IO tracer
blktrace is a block layer IO tracing mechanism which provides detailed
information about request queue operations up to user space. This is
valuable for diagnosing and fixing performance or application problems
relating to block layer io.






* Fri Jul 28 2017
  - Update to version 1.1.0+git.20170126:
    * blktrace: Add support for sparse CPU numbers
    * blktrace: Reorganize creation of output file name
    * blktrace: Create empty output files for non-existent cpus
* Fri Nov 25 2016
  - Update to version 1.1.0+git.20160823:
    * Use maximum over all traces for queue depth
    * Process notify events outside of given interval
    * iowatcher: Use queue events if issue not available
    * btt: Replace overlapping IO
    * Zero sectors are strange
    * Don't prepend blktrace destination dir if we didn't run blktrace
    * Separate prefix in legend with space
    * Fixup graph name in help text
    * blktrace: remove -k from manpage synopsis
    * iowatcher: link with -lrt
* Tue Apr 26 2016
  - Update to version 1.1.0+git.20160425:
    * Refer to sda instead of hda in man pages
    * btreplay: Fix typo in scaling up the dynamic cpu set size.
    * include sys/types.h for dev_t definition
    * Fix warnings on newer gcc
    * Add the "-a discard" filter option to the blktrace.8 man page
    * blktrace: Use number of online CPUs
    * btreplay: fix memory corruption caused by CPU_ZERO_S
    * btreplay: fix sched_{set|get}affinity
    * btreplay: make Ctrl-C work
    * btreplay: remove timestamps
* Tue Apr 26 2016
  - Add _service for automatic git syncing
    + exclude .git when generating tarball
    + enable automatic changelog updating
* Fri Oct 03 2014
  - Update to 1.1.0:
    - merge iowatcher
* Sat Dec 29 2012
  - Update to 1.0.5 version:
    * Fix compiler warnings
    * avoid string overflows
  - Some improvements like using macro instead of RPM variables
* Mon Jul 23 2012
  - Add some missed fonts
* Tue Jul 10 2012
  - Make it build with latest TeXLive 2012 with new package layout
* Thu Oct 27 2011
  - Update to v1.0.3 (bnc#720300 and others).
    - Updated documentation
    - Fixed multiple output errors
    - Added FLUSH/FUA support
    - Misc bug fixes
* Wed Sep 21 2011
  - disable parallel build again
* Sat Sep 17 2011
  - Remove redundant tags/sections from specfile
  - Use %_smp_mflags for parallel build
* Sat Sep 03 2011
  - Fix build with no-add-needed (missing -pthread)
* Thu Oct 15 2009
  - Fix memory leak (bnc #546035)
* Tue Jul 21 2009
  - Fix memory leak in btrecord (bnc #523444).
* Tue Jun 16 2009
  - Fix typo in btt (bnc #511264).
* Fri May 29 2009
  - Update to version 1.0.1:
    * blkrawverify: warn and return error if no traces are found
    * blkiomon manpage and usage reference invalid "msg-queue-name" option
    * fix up btrace options & manpage
    * more manpage fixups
    * fix max-pkts option inconsistencies
    * Converted to using the correct remap entries
    * blkiomon: fix unaligned accesses on ia64
    * fix off-by-one issues in blkiomon.h
    * fix include statement in stats.h
    * handle race to mkdir at startup
    * Fixed plug/unplug logic in btt
    * Working on fixing % time q plugged
    * fix trivial typo in manpage
    * Add NOTIFY to activity mask
    * Blktrace failed to lock reader threads on the cpu used by the
      corresponding writer. This resulted in stale data being consumed when
      blktrace accidently read at a position that was being written to at the
      same time. This issue surfaced as "bad trace magic" warnings emitted by
      blktrace tools.
    * Generate matplotlib plots for btt generated data
    * Update Jenkins hash to lookup3() variant
    * Fixed EAGAIN handling in blktrace.c
    * O_NOATIME isn't always present
    * btt: Added no remap option
    * btt general cleanup plus valgrind clean
    * btt: Missed fopen conversion to my_fopen
    * Code review updates
    * Reworked blktrace master/thread interface
    * Cleaned up devs that have no data
    * Moved starting of tracing after tracers are going
    * btt: fixed open in setup_ifile
    * Synchronized trace gathering
    * Invoke gethostbyname once, handle errors better
    * Added accept as a system call needing resource increases
    * Rewrote blktrace to have a single thread per CPU
    * Fix btt to handle large numbers of output files
    * Increased limits to allow for large system runs
    * A couple of min-counters weren't initialised correctly (thrput_r,
      thrput_w). We have got a perfectly working init function for this
      purpose. Removing partially duplicated code.
    * The git commit 11914a53d2ec2974a565311af327b8983d8c820d added
      __BLK_TA_ABORT to blktrace_api.h. A corresponding addition to the blktrace
      tools repository has been missing, breaking the API. Blkparse complained:
      "Bad fs action 40010011"
    * Added no messages option to blkparse.c
    * gcc 4.3.2 has started to warn about:
    * Added -P to create a data file w/ Q, D and C per line
    * Fixed 'M' displays on per-io output and added in I/O separator
    * Fixed segfault in aqd.c : need to check for NULL (not requested)
    * Added in -z to provide running waiting-for-issue latencies
    * Moved btrecord/btreplay to version 1.0.0
* Thu Apr 30 2009
  - Build with docs by default.



Generated by rpm2html 1.8.1

Fabrice Bellet, Tue Nov 9 10:26:55 2021