linux-toradex.git/drivers/block/drbd/drbd_actlog.c, branch v3.1.2

drbd: we should write meta data updates with FLUSH FUA

2011-06-30T07:23:46+00:00

We used to write these with BIO_RW_BARRIER aka REQ_HARDBARRIER (unless
disabled in the configuration). The correct semantic now would be to
write with FLUSH/FUA.
For example, with activity log transactions, FUA alone is not enough, we
need the corresponding bitmap update (and all related application
updates) on stable storage as well.

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: Fix spelling

2011-05-24T08:21:29+00:00

Found these with the help of ispell -l.

Signed-off-by: Bart Van Assche 
Signed-off-by: Lars Ellenberg 
Signed-off-by: Philipp Reisner

Fix common misspellings

2011-03-31T14:26:23+00:00

Fixes generated by 'codespell' and manually reviewed.

Signed-off-by: Lucas De Marchi

drbd: Remove unused function atodb_endio()

2011-03-10T10:48:15+00:00

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: kill dead code

2011-03-10T10:48:12+00:00

This code became obsolete and unused last December with
 drbd: bitmap keep track of changes vs on-disk bitmap

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: bitmap keep track of changes vs on-disk bitmap

2011-03-10T10:43:19+00:00

When we set or clear bits in a bitmap page,
also set a flag in the page->private pointer.

This allows us to skip writes of unchanged pages.

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: Use the standard bool, true, and false keywords

2011-03-10T10:36:24+00:00

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: Get rid of unnecessary macros (2)

2011-03-10T10:36:15+00:00

The FAULT_ACTIVE macro just wraps the drbd_insert_fault macro for no
apparent reason.

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: Removed 20 seconds upper bound for side-stepping

2011-03-10T10:35:09+00:00

Given low-enough network bandwidth combined with a IO
pattern that hammers onto a single RS-extent, side-stepping
might be necessary for much longer times.

Changed the code to print a single informal message after
20 seconds, but it keeps on stepping aside forever.

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg

drbd: Implemented side-stepping in drbd_res_begin_io()

2011-03-10T10:34:56+00:00

Before:
  drbd_rs_begin_io() locked app-IO out of an RS extent, and
  waited then until all previous app-IO in that area finished.
  (But not only until the disk-IO was finished but until the
   barrier/epoch ack came in for that == round trip time latency ++)

After:
  As soon as a new app-IO waits wants to start new IO on that
  RS extent, drbd_rs_begin_io() steps aside (clearing the
  BME_NO_WRITES flag again). It retries after 100ms.

Signed-off-by: Philipp Reisner 
Signed-off-by: Lars Ellenberg