github/ocf
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
709 Commits 1 Branch 1 Tag 4.1 MiB
5828a7d0ae
Commit Graph

709 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Kamil Lepek
5828a7d0ae Added codecov badge to README, added coverage files to .gitignore 2020-01-09 10:54:59 +01:00
Jan Musiał
1784d6e3a2
Merge pull request #337 from micrakow/security_test_fixes 
pyocf: fix security mngmt_start_fuzzy test
 2020-01-08 15:18:39 +01:00
Michal Rakowski
bc866e5f9a pyocf: fix security mngmt_start_fuzzy test 2020-01-08 14:06:54 +01:00
Michal Rakowski
f2754ff06f
Merge pull request #335 from KamilLepek/codecov 
Enable code coverage tracking in pyocf
 2020-01-08 13:04:11 +01:00
Kamil Lepek
0d6660d4f3 Enable code coverage tracking in pyocf 2020-01-08 11:02:07 +01:00
Michał Mielewczyk
b58ebd4b88
Merge pull request #334 from imjfckm/fix-nhit-deadlock 
Fix nhit deadlock
 2020-01-02 10:58:59 +01:00
Jan Musial
5eca548e22 Make sure NHIT won't attempt to take the same semaphore twice 
Signed-off-by: Jan Musial <jan.musial@intel.com>
 2019-12-31 14:16:18 +01:00
Jan Musial
4536a51f59 Fix init of nhit + code styling 
Signed-off-by: Jan Musial <jan.musial@intel.com>
 2019-12-31 14:16:18 +01:00
Robert Baldyga
1ec0a5c053
Merge pull request #332 from mmichal10/stop-pipeline-in-cache 
Keep stop pipeline in struct cache.
 2019-12-30 17:15:42 +01:00
Michal Rakowski
28caa25b7a
Merge pull request #333 from arutk/fix_div_round_up 
Change DIV_ROUND_UP to OCF_DIV_ROUND_UP
 2019-12-30 08:23:08 +01:00
Adam Rutkowski
92b36c3484 Change DIV_ROUND_UP to OCF_DIV_ROUND_UP 
This fixes compilation in SPDK env

Signed-off-by: Adam Rutkowski <adam.j.rutkowski@intel.com>
 2019-12-28 18:24:12 -05:00
Jan Musiał
9be9ca75d7
Merge pull request #331 from robertbaldyga/limit-metadata-reqs-v2 
Limit number of concurrent io submitted by metadata_io_i_asynch()
 2019-12-28 13:02:08 +01:00
Michal Mielewczyk
6ac3195823 Keep stop pipeline in struct cache. 
To eliminate possibility of allocation error in cache stop, pipeline is
allocated on attach.

Due this change, the only possible non-zero status of  ocf_mngt_cache_stop() is
just a warning and cache is always stopped after executing it.

Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-12-27 18:54:15 -05:00
Robert Baldyga
d1249e5238 Limit number of concurrent io submitted by metadata_io_i_asynch() 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-12-19 16:50:41 +01:00
Michał Mielewczyk
3aa68bcb15
Merge pull request #330 from robertbaldyga/cleaner-retrieve-core-from-map 
cleaner: Retrieve core object properly
 2019-12-19 16:00:48 +01:00
Robert Baldyga
e06832426d cleaner: Retrieve core object properly 
Cleaner doesn't set core object in req as it works in domain of cache
lines, which may belong to various cores. It this case should retrieve
core object not from the req, but from the map instead.

Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-12-19 14:44:04 +01:00
Michal Rakowski
a074026773
Merge pull request #329 from robertbaldyga/fix-cleaner-queue-change-before-put 
Put a queue before calling cleaner completion callback
 2019-12-19 11:33:27 +01:00
Robert Baldyga
32fd371583 Put a queue before calling cleaner completion callback 
This ensures that cleaner queue will not be changed
by starting another cleaning iteration before we put it.

Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-12-18 20:49:56 +01:00
Robert Baldyga
4e5530851b
Merge pull request #327 from mmichal10/fix-hang-on-start 
Revert "Limit number of concurrent io submitted by metadata_io_i_asyn…
 2019-12-17 16:35:26 +01:00
Michal Mielewczyk
fb95f048fd Revert "Limit number of concurrent io submitted by metadata_io_i_asynch()" 
Starting big caches hangs.

This reverts commit c2c9307b9b.

Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-12-17 10:29:44 -05:00
Michał Mielewczyk
6a753570b8
Merge pull request #325 from Ostrokrzew/upstream 
Add reschedule to metadata hash init
 2019-12-17 10:08:30 +01:00
Ostrokrzew
fc1847cf55 Add reschedule to metadata hash init 
Signed-off-by: Ostrokrzew <slawomir.jankowski@intel.com>
 2019-12-17 09:56:45 +01:00
Adam Rutkowski
57e6b96791
Merge pull request #323 from arutk/remove_fallthrough 
Remove switch/case fallthrough
 2019-12-12 11:49:08 +01:00
Adam Rutkowski
867e06ebf1 Remove switch/case fallthrough 
This construction breaks compilation on latest kernels.

Signed-off-by: Adam Rutkowski <adam.j.rutkowski@intel.com>
 2019-12-12 13:48:47 -05:00
Jan Musiał
1fa73a0a0e
Merge pull request #320 from robertbaldyga/limit-metadata-reqs 
Limit number of concurrent io submitted by metadata_io_i_asynch()
 2019-12-12 11:20:23 +01:00
Robert Baldyga
c2c9307b9b Limit number of concurrent io submitted by metadata_io_i_asynch() 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-12-11 14:57:20 +01:00
Jan Musiał
1b1bbbe4c5
Merge pull request #322 from robertbaldyga/fix-ut-deprecated-commands-module 
ut: Replace deprecated 'commands' module with 'subprocess'
 2019-12-11 08:20:39 +00:00
Robert Baldyga
2ca8dcd73e ut: Replace deprecated 'commands' module with 'subprocess' 
The 'commands' modules has been removed in python 3.

Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-12-10 17:39:17 +01:00
Robert Baldyga
e7280eb8f4
Merge pull request #321 from imjfckm/fix-wb-stats 
Fix counting occupancy on WB write insert error
 2019-12-09 18:20:41 +01:00
Jan Musial
94d27c0f43 Fix counting occupancy on WB write insert error 
During error handling in WB write insert we didn't invalidate affected
cache lines. Because of that the cache stopped properly (as it's
supposed to), but cache lines were marked as inserted which caused
occupancy stats to increase even though nothing was succesfully
inserted.

Signed-off-by: Jan Musial <jan.musial@intel.com>
 2019-12-09 11:01:28 +01:00
Adam Rutkowski
d8a01e359e
Merge pull request #319 from mmichal10/fix-ioclass-stats-for-cache 
Reset initial ioclass stats value when retrieving.
 2019-10-29 15:55:02 +01:00
Michal Mielewczyk
b61843d7df Reset initial ioclass stats value when retrieving. 
Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-10-29 09:53:36 -04:00
Michal Rakowski
e6bdc2d247
Merge pull request #316 from mmichal10/update-example-adapter 
Update example adapter
 2019-10-21 15:46:53 +02:00
Michal Mielewczyk
3fda55867a Pass linker flags as the last part of gcc command. 
Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-10-21 09:27:16 -04:00
Michal Mielewczyk
aef668040b Set core name with strcpy() instead of assignment. 
Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-10-21 09:26:14 -04:00
Jan Musiał
c8e72ad98d
Merge pull request #315 from arutk/alloc_optimizations 
Adapt OCF to vmalloc-based memory pools
 2019-10-21 09:49:59 +02:00
Adam Rutkowski
6423c48dfe cacheline concurrency: move allocation outside critical section 
Signed-off-by: Adam Rutkowski <adam.j.rutkowski@intel.com>
 2019-10-18 18:41:01 -04:00
Adam Rutkowski
07b1f0c064 Replace global concurrency rw spinlock with rw semaphore 
Signed-off-by: Adam Rutkowski <adam.j.rutkowski@intel.com>
 2019-10-18 18:19:05 -04:00
Jan Musiał
9e515e0271
Merge pull request #313 from mmichal10/fix-cache-stats-updating 
Fix cache stats updating.
 2019-10-08 15:23:58 +02:00
Michal Mielewczyk
db06783d56 Fix cache stats updating. 
When single request to cache was issued, stats updating function was called with
0 bytes as value to update. In case of many request issued to cache, stats were
updated only in case of error.

Signed-off-by: Michal Mielewczyk <michal.mielewczyk@intel.com>
 2019-10-08 08:49:24 -04:00
Robert Bałdyga
17ec78d88f
Merge pull request #312 from robertbaldyga/rand-generator-improvements 
Rand generator improvements
 2019-10-04 09:25:11 +02:00
Robert Baldyga
1525e85805 Add global random seed config 
This is needed to make fuzzy tests work with xdist as each
xdist gateway expects to receive the same set of parameter
values, which for random generators may be achieved only by
providing globally shared seed.

Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-10-03 16:31:05 +02:00
Robert Baldyga
b9b39fdb46 Add more fine-grained fixtures for fuzzy tests 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-10-03 16:31:05 +02:00
Robert Baldyga
ab1df71476 Make random generator API fluent 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-10-03 14:36:31 +02:00
Michal Rakowski
a61664ddd8
Merge pull request #311 from katlapinka/unaligned-tests 
Add new negative io tests and raising error when failed to create io
 2019-10-02 20:50:40 +02:00
Katarzyna Lapinska
219ccf360c Add new negative io tests and raising error when failed to create io 
Signed-off-by: Katarzyna Lapinska <katarzyna.lapinska@intel.com>
 2019-10-02 20:35:25 +02:00
Katarzyna Łapińska
2c56f6eb37
Merge pull request #310 from robertbaldyga/test-sector-alignment 
Test with io aligned to sector size
 2019-10-02 19:53:34 +02:00
Robert Baldyga
58403f2cd4 Test with io aligned to sector size 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-10-02 19:46:28 +02:00
Katarzyna Łapińska
58d33a24e6
Merge pull request #309 from robertbaldyga/update-stats-before-completion 
Update stats before calling completion callback
 2019-10-02 19:46:24 +02:00
Robert Baldyga
f51f7f7e1e Update stats before calling completion callback 
Signed-off-by: Robert Baldyga <robert.baldyga@intel.com>
 2019-10-02 18:49:59 +02:00