aboutsummaryrefslogtreecommitdiff
path: root/sys/geom/geom_io.c
Commit message (Expand)AuthorAgeFilesLines
* Bring back the geom_bioqueues, they _are_ a good idea.Poul-Henning Kamp2004-01-281-0/+27
* Correct usage of mtx_init() API. This is not a functional change sinceDon Lewis2003-12-071-2/+2
* Forgotten commit: If a provider has zero sectorsize, it is anPoul-Henning Kamp2003-10-221-6/+3
* Remove KASSERT check for negative bio_offsets, add "normal" EIOPoul-Henning Kamp2003-10-191-1/+3
* Allow our bio tools to be used for local bio-chopping by not mandatingPoul-Henning Kamp2003-10-061-2/+7
* Add more KASSERTS().Poul-Henning Kamp2003-09-261-0/+6
* Reorder a couple of KASSERTS to give more sensible messages.Poul-Henning Kamp2003-09-111-2/+2
* In case we encounter a zero sectorsize provider in g_io_check(), failPoul-Henning Kamp2003-08-131-0/+6
* Sleep on "-" in our normal state to simplify debugging.Poul-Henning Kamp2003-06-181-2/+2
* Use __FBSDID().David E. O'Brien2003-06-111-2/+2
* Hide the "ENOMEM" notice messages behind bootverbose. They are stillPoul-Henning Kamp2003-05-071-1/+2
* Use an uma-zone for allocation bio requests.Poul-Henning Kamp2003-05-021-13/+10
* Back out all the stuff that didn't belong in the last commit.Poul-Henning Kamp2003-05-021-7/+1
* Use g_slice_spoiled() rather than g_std_spoiled().Poul-Henning Kamp2003-05-021-1/+7
* Time has run from the "run GEOM in userland" harness, and the new regressionPoul-Henning Kamp2003-04-131-9/+0
* Retire the experimental bio_taskqueue(), it was not quite as usable asPoul-Henning Kamp2003-04-121-27/+0
* Remove all references to BIO_SETATTR. We will not be using it.Poul-Henning Kamp2003-04-031-21/+0
* Fix a bug in the ENOMEM pacing code which probably made it panic systemsPoul-Henning Kamp2003-03-291-4/+4
* Retire the GEOM private statistics code and use devstat instead.Poul-Henning Kamp2003-03-181-61/+7
* Including <sys/stdint.h> is (almost?) universally only to be able to usePoul-Henning Kamp2003-03-181-1/+0
* Don't abuse the statistics counters for detecting if we have outstandingPoul-Henning Kamp2003-03-091-6/+10
* Back out M_* changes, per decision of the TRB.Warner Losh2003-02-191-1/+1
* Implement a bio-taskqueue to reduce number of context switches inPoul-Henning Kamp2003-02-111-11/+56
* Don't short-circuit zero-length requests of they are BIO_[SG]ETATTR.Poul-Henning Kamp2003-02-111-10/+18
* Turn the "updating" flag (back) into two sequence number fields atPoul-Henning Kamp2003-02-111-4/+4
* Update the statistics collection code to track busy time instead ofPoul-Henning Kamp2003-02-091-39/+41
* Move the g_stat struct to its own .h file, we will export it to other code.Poul-Henning Kamp2003-02-081-22/+23
* Commit the correct copy of the g_stat structure.Poul-Henning Kamp2003-02-071-23/+80
* Rename bio_linkage to the more obvious bio_parent.Poul-Henning Kamp2003-02-071-1/+1
* Put the checks we perform on a bio before calling ::start in theirPoul-Henning Kamp2003-02-061-69/+59
* Remove M_TRYWAIT/M_WAITOK/M_WAIT. Callers should use 0.Alfred Perlstein2003-01-211-1/+1
* white-space changesPoul-Henning Kamp2002-12-261-2/+4
* Balk at unaligned requests.Poul-Henning Kamp2002-12-181-0/+10
* malloc(9) with M_NOWAIT seems to return NULL a lot more than I would havePoul-Henning Kamp2002-11-021-0/+14
* Don't track bio allocation in debug output.Poul-Henning Kamp2002-10-201-5/+7
* Add more KASSERTS.Poul-Henning Kamp2002-10-141-1/+7
* Add support g_clone_bio() and g_std_done() to spawn multiple childrenPoul-Henning Kamp2002-10-091-0/+1
* For now, don't wait for drives to stop returning EBUSY. There is tooPoul-Henning Kamp2002-10-081-35/+26
* Put a printf under #ifdef DIAGNOSTIC.Poul-Henning Kamp2002-10-071-0/+2
* Retire g_io_fail() and let g_io_deliver() take an error argument instead.Poul-Henning Kamp2002-09-301-24/+12
* Introduce g_write_data() function.Poul-Henning Kamp2002-09-301-0/+18
* Void functions cannot use return(foo) even if foo is also returning void.Poul-Henning Kamp2002-09-281-14/+28
* Setattr should not retry on EBUSY, we could get EBUSY back becausePoul-Henning Kamp2002-09-271-14/+15
* Allocate bio's with M_NOWAIT and let the caller deal with the problems.Poul-Henning Kamp2002-09-271-7/+9
* Use biowait() rather than DIY.Poul-Henning Kamp2002-09-131-24/+4
* Don't grab Giant around malloc(9) and free(9).Poul-Henning Kamp2002-05-201-6/+0
* Constifixation of attribute argument to g_io_[gs]etattr()Poul-Henning Kamp2002-04-091-2/+2
* Change callers of mtx_init() to pass in an appropriate lock type name. InJohn Baldwin2002-04-041-1/+1
* Centralize EOF handling and improve access controls for bio scheduling.Poul-Henning Kamp2002-04-041-44/+67
* Eliminate some thread pointers which do not make sense anymore.Poul-Henning Kamp2002-03-261-2/+3