- Mar 26, 2019
-
- Mar 25, 2019
-
-
Marcin Ślusarz authored
-
Marcin Ślusarz authored
pool: fix obj pool layout printing by pmempool create
-
Marcin Ślusarz authored
pool: rename long option for clearing bad blocks
-
Krzysztof Kajrewicz authored
with pmempool create
-
Marcin Ślusarz authored
test: fix match files for pmempool info tests
-
Marcin Ślusarz authored
pool: fix pmempool create error msg
-
Marcin Ślusarz authored
Merge stable-1.5 to stable-1.6
-
Krzysztof Kajrewicz authored
-
Krzysztof Kajrewicz authored
-
Krzysztof Kajrewicz authored
Pool layout was not set at the moment of printing when pool creation was called with verbose option enabled.
-
Marcin Ślusarz authored
obj: fix runtime state corruption after undo recovery
-
Marcin Ślusarz authored
common: remove cto from the list of valid area names in a commit message
-
Krzysztof Kajrewicz authored
With pmdk 1.6 compat feature POOL_FEAT_CHECK_BAD_BLOCKS is enabled by default which affects 'Not mandatory features' field printed by pmempool info. Checking value of this field is not the key objective of modified tests so we can ignore it for compatibility with pmdk versions prior to 1.6.
-
- Mar 22, 2019
-
-
Krzysztof Kajrewicz authored
-
Piotr Balcer authored
The 'operation_context' structure was being created twice, once as part of lane initialization, and once as part of the recovery operation. The first context is used for all operations, whereas the second context lives only for the duration of the undo log recovery. The problem was that the recovery process can change the persistent state in such a way that the context runtime information becomes stale. This is perfectly fine, and it's handled for the operation that does the recovery - but at the same time, this makes the data of the lane context invalid. This bug was triggering ASSERTs in debug builds and might have led to NULL dereference on release builds. Fortunately the crash happens after recovery has been finished and simply restarting the application gets rid of the problem. The fix is quite simple: instead of duplicating the runtime state for the purpose of recovery, simply use the one that already exists in the lane.
-
Grzegorz Brzeziński authored
-
Marcin Ślusarz authored
pool: fix printing of error messages in pmempool tool
-
Grzegorz Brzeziński authored
-
Marcin Ślusarz authored
obj: do foogrind annotations at alloc time
-
- Mar 21, 2019
-
-
Marcin Ślusarz authored
test: add devdax and free space size requirements
-
Marcin Ślusarz authored
test: add devdax size limit
-
Dawid Paluszkiewicz authored
Ref: pmem/issues#1045
-
Dawid Paluszkiewicz authored
Ref: pmem/issues#1046
-
Adam Borowski authored
-
- Mar 19, 2019
-
-
Marcin Ślusarz authored
test: fix pmempool check tests
-
Łukasz Plewa authored
As we are clearing shutdown state incompat feature by pmemspoil we must reset SDS to 0 otherwise pmempool check will detect a pool corruption.
-
Marcin Ślusarz authored
test: add suppression for ndctl 63 memory leak
-
- Mar 18, 2019
-
-
Marcin Ślusarz authored
-
Marcin Ślusarz authored
test: make critnib tests fs type agnostic
-
Adam Borowski authored
They don't touch pmem anyway.
-
- Mar 15, 2019
-
-
Marcin Ślusarz authored
-
Marcin Ślusarz authored
tests: add variable to suppress badblocks FD leak in ndctl 63
-
Marcin Ślusarz authored
doc: automatic master docs update
-
Generic builder authored
-
Łukasz Plewa authored
-
Marcin Ślusarz authored
common: add variable to force use of old ndctl API
-
Marcin Ślusarz authored
Merge back changes from stable-1.5
-