| Age | Commit message (Expand) | Author |
|---|
| 2014-04-03 | massage the preferred path detection to happen when mpath asks for | David Gwynne |
| 2014-04-02 | whitespace fix, no functional change | David Gwynne |
| 2014-04-02 | skey == SKEY_ILLEGAL_REQUEST && ASC_ASCQ(sense) == 0x9401 means | David Gwynne |
| 2014-02-19 | If a disk returns a size of 0, treat it as an error to let the | Martin Pieuchot |
| 2014-02-13 | if an attached sd(4) is readonly, make sure it's noticable in the | Alexander Hall |
| 2014-01-31 | SUNW SUNWGS INT FCBPL can be considered an asym device now we can uniquely | David Gwynne |
| 2014-01-31 | if a device doesnt have device ids or serial numbers, try using node_wwn to | David Gwynne |
| 2014-01-30 | SGI branded seagate disks work fine | David Gwynne |
| 2014-01-27 | poison the io "allocated" by the default pool allocator so any attempt to | David Gwynne |
| 2014-01-18 | rename scsi_ioh_runqueue to scsi_iopool_run, and make it available | David Gwynne |
| 2013-12-06 | Add a DVACT_WAKEUP op to the *_activate() API. This is called after the | Theo de Raadt |
| 2013-11-26 | 1 << 31 cleanup. Eitan Adler pointed out that there has been a | Theo de Raadt |
| 2013-11-23 | fix format string; OK deraadt@ | Gleydson Soares |
| 2013-11-01 | Sprinkle (long long) casts where %lld is being used to print daddr_t | Kenneth R Westerback |
| 2013-10-07 | typo | Miod Vallat |
| 2013-10-03 | Print daddr_t variables with %lld, u_int64_t variables with %llu. | Kenneth R Westerback |
| 2013-10-02 | Use u_int64_t instead of daddr_t parameters to sd_cmd_rw*() functions. | Kenneth R Westerback |
| 2013-09-27 | scsi_size() is now used only by cd(4). So move it from scsi_base.c | Kenneth R Westerback |
| 2013-09-19 | Tweak types to keep daddr_t address and sector address separate. | Kenneth R Westerback |
| 2013-09-15 | cddump() takes a daddr_t parameter. Call that parameter 'blkno' and not | Kenneth R Westerback |
| 2013-09-15 | Use DL_SECTOBLK() and DL_BLKTOSEC() to clarify code and remove | Kenneth R Westerback |
| 2013-09-08 | fix next path selection so if the current path is NULL (which can occur if | David Gwynne |
| 2013-09-03 | DELL MD3060e works | David Gwynne |
| 2013-08-29 | rename scsi_sem_{enter,leave} to scsi_pending_{start,finish}. these are | David Gwynne |
| 2013-08-27 | make path driver match routes return 8 so they will definitely be higher | David Gwynne |
| 2013-08-27 | get rid of the different path scheduler types, which simplifies the | David Gwynne |
| 2013-08-27 | these were forgotten in the change from pointing paths to groups instead | David Gwynne |
| 2013-08-27 | make scsi_sem_leave only run again once, no matter how many times | David Gwynne |
| 2013-08-26 | implement handling of group failover. | David Gwynne |
| 2013-08-26 | feng shui | David Gwynne |
| 2013-08-26 | all paths are considered active, not in some unknown state. | David Gwynne |
| 2013-08-26 | all FUJITSU MA disks ive found seem ok with being behind mpath. | David Gwynne |
| 2013-08-26 | pull rdac_c9 apart and use its guts to implement the status check | David Gwynne |
| 2013-08-26 | rename rdac_c8 to rdac_extdevid and use less magic numbers in the process. | David Gwynne |
| 2013-08-26 | when i first imagined how paths on mpath worked, i thought the | David Gwynne |
| 2013-08-26 | my DELL MD3000i seems to return skey illegal request + asc 0x94 + | David Gwynne |
| 2013-08-26 | checksense handlers in path drivers can return MPATH_SENSE_DECLINED | David Gwynne |
| 2013-08-26 | free the dev slot on group allocation failure if we're building a new dev. | David Gwynne |
| 2013-08-26 | introduce the idea of groups of paths. mpath had stuff to managed | David Gwynne |
| 2013-08-26 | rdac_groupid queries which controller the path is attached to, which we'll | David Gwynne |
| 2013-08-26 | now that mpath is attached before any hardware, we can simplify the code. | David Gwynne |
| 2013-08-26 | make scsi_{xsh,ioh}_{add,del} return whether they moved something | David Gwynne |
| 2013-08-25 | move the prototypes of scsi_sem_{enter,leave} into a header so things | David Gwynne |
| 2013-07-05 | Tweak calculations of resid to avoid unsigned vs signed comparison and | Kenneth R Westerback |
| 2013-06-11 | final removal of daddr64_t. daddr_t has been 64 bit for a long enough | Theo de Raadt |
| 2013-06-10 | spelling in comment fix (for real, there's no code change here). | David Gwynne |
| 2013-06-10 | we dont need mpath ccbs if all theyre used for is storing xfers on a list. | David Gwynne |
| 2013-06-10 | toshiba disks in an md1220 work fine | David Gwynne |
| 2013-06-06 | Fix EOM handling. Makes Bacula much happier by allowing the use of | Kenneth R Westerback |
| 2013-05-30 | typo: thing -> thin provisioning | Ted Unangst |
