- Oct 12, 2017
-
-
Michael Davis authored
-
- Oct 11, 2017
-
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
As EOS is parsing stderr to get the archive ID
-
Michael Davis authored
-
Michael Davis authored
Recovery blob is deprecated. EOS will fill in metadata fields in the protocol buffer and we need to decide what will be stored in the database.
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
-
- Oct 10, 2017
-
-
Michael Davis authored
-
Michael Davis authored
So we can see how bash shell strings are being escaped and what actually appears in the protocol buffer.
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
Sets retrieve workflow in eos_wfe_scripts back to the old cta command for now. Try to get simple test to work first.
-
- Oct 09, 2017
-
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
-
Julien Leduc authored
-
Julien Leduc authored
-
Michael Davis authored
-
Michael Davis authored
-
Michael Davis authored
This will be validated in the ssi branch and merged into master later.
-
Eric Cano authored
The code in this part was uselessly taking exclusive root locks, leading to locking fights when starting all drive as the same time in bigger systems.
-
Eric Cano authored
-
Michael Davis authored
-
Michael Davis authored
-
- Oct 08, 2017
-
-
Eric Cano authored
This happens when the notification is received multiple times. This did not show before full scale test.
-
Eric Cano authored
The locking is now handled in a single function. This functions is also used in the asynchronous operations. This operations have been simplified in this operation: we now do a synchronous stat after the locking. Previously stat was the first asynchronous operation. This will slightly slow down the async operations (for the gain of code simplicity).
-
Eric Cano authored
This commit only replaces backoff with notifications in exclusive locks, for validation with a multithreaded unit test. This proof of concept is considered as working, as the measured gap between a lock release and a lock take never exceeds ~1/4 of a second, with a typical release-lock gap in the few ms to few tens of ms.
- Oct 06, 2017
-
-
Michael Davis authored
-
Michael Davis authored
- Oct 05, 2017
-
-
Steven Murray authored
Done.
-
Michael Davis authored
-
- Oct 03, 2017
-
-
Steven Murray authored
Replaced set_target_properties( .. .. INSTALL_RPATH ..) with set_property (TARGET .. APPEND PROPERTY INSTALL_RPATH ..)
-