Hello, Jens. This is the second take. Changes from the first take[L] are
* writeback_dirty_buffer TP was botched. It made build fail when CONFIG_BLOCK is not set (reported by Fengguang) and I somehow lost its actual triggering in mark_buffer_dirty() while splitting patches. Made it a block TP instead so that it can share TP definition with block_touch_buffer and restored the triggering from mark_buffer_dirty(). This patchset fixes/improves bio_complete TP so that block layer proper triggers for all completing bios instead of stackign drivers triggering them manually and adds more buffer / block / writeback TPs. These improve visibility in general and are already in use in google. This patchset contains the following five patches. 0001-block-add-missing-block_bio_complete-tracepoint.patch 0002-block-add-req-to-bio_-front-back-_merge-tracepoints.patch 0003-buffer-make-touch_buffer-an-exported-function.patch 0004-block-add-block_-touch-dirty-_buffer-tracepoint.patch 0005-writeback-add-more-tracepoints.patch It's based on top of v3.8-rc2 and also available in the following git branch. git://git.kernel.org/pub/scm/linux/kernel/git/tj/misc.git block-tps diffstat follows. Thanks. block/blk-core.c | 5 - drivers/md/dm.c | 1 drivers/md/raid5.c | 11 --- fs/bio.c | 2 fs/buffer.c | 10 +++ fs/fs-writeback.c | 16 ++++- include/linux/blktrace_api.h | 1 include/linux/buffer_head.h | 2 include/trace/events/block.h | 104 +++++++++++++++++++++++++++++----- include/trace/events/writeback.h | 116 +++++++++++++++++++++++++++++++++++++++ kernel/trace/blktrace.c | 28 ++++++++- mm/page-writeback.c | 2 12 files changed, 263 insertions(+), 35 deletions(-) -- tejun [L] http://thread.gmane.org/gmane.linux.kernel/1419141 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
