| Commit message (Expand) | Author | Age | Files | Lines |
* | MFP4 (with some minor changes): | Alexander Leidinger | 2006-10-15 | 1 | -4/+4 |
* | hide kqueue_register from public view, and replace it w/ kqfd_register... | John-Mark Gurney | 2006-09-24 | 1 | -33/+6 |
* | Remove call to fdfree() for the AIO daemons to prevent kernel panics | Mark Peek | 2006-09-06 | 1 | -6/+0 |
* | - Change process_exec function handlers prototype to include struct | Alexander Leidinger | 2006-08-15 | 1 | -1/+8 |
* | Make lio ident more consistant with aio ident. | Doug Ambrisko | 2006-06-02 | 1 | -1/+1 |
* | Use a dedicated mutex to protect aio queues, the movation is to reduce | David Xu | 2006-05-09 | 1 | -51/+69 |
* | 1. Move code for scanning pending I/O from aio_fsync to aio_aqueue, | David Xu | 2006-03-24 | 1 | -77/+51 |
* | Implement aio_fsync() syscall. | David Xu | 2006-03-23 | 1 | -78/+244 |
* | 1. Remove aio entry from lists earlier in aio_free_entry, | David Xu | 2006-02-26 | 1 | -19/+17 |
* | If block size is zero, use normal file operations to do I/O, | David Xu | 2006-02-22 | 1 | -0/+3 |
* | Just like dofilewrite(), call bwillwrite before fo_write. | David Xu | 2006-01-27 | 1 | -0/+2 |
* | return final error code in aio_return rather than a hardcoded 0. | David Xu | 2006-01-27 | 1 | -1/+0 |
* | in aio_aqueue, store same return code into job->_aiocb_private.error. | David Xu | 2006-01-26 | 1 | -3/+5 |
* | Add locking annotation and comments about socket, pipe, fifo problem. | David Xu | 2006-01-24 | 1 | -125/+126 |
* | Er, rescure a deleted comment line. | David Xu | 2006-01-24 | 1 | -0/+1 |
* | More cleanup for aio code: | David Xu | 2006-01-24 | 1 | -11/+9 |
* | Add bracket. | David Xu | 2006-01-23 | 1 | -1/+1 |
* | Verify all supported notification types. | David Xu | 2006-01-23 | 1 | -3/+18 |
* | 1) Merge _aio_aqueue and aio_aqueue, check quota in aio_aqueue, | David Xu | 2006-01-23 | 1 | -45/+29 |
* | Fix a bogus panic. | David Xu | 2006-01-22 | 1 | -1/+1 |
* | Decrease kaio_active_count first, because user process may go away | David Xu | 2006-01-22 | 1 | -2/+5 |
* | Make aio code MP safe. | David Xu | 2006-01-22 | 1 | -843/+574 |
* | Initialize ki to p->p_aioinfo after we know it's going to be referencing | Christian S.J. Peron | 2006-01-15 | 1 | -2/+2 |
* | Return error from fget_write() rather than hardcoding EBADF now that | John Baldwin | 2006-01-06 | 1 | -1/+1 |
* | In aio_waitcomplete, do not return EAGAIN if no other threads | David Xu | 2005-11-08 | 1 | -1/+1 |
* | Various and sundry cleanups: | John Baldwin | 2005-11-08 | 1 | -80/+84 |
* | Fix name compatible problem with POSIX standard. the sigval_ptr and | David Xu | 2005-11-04 | 1 | -2/+2 |
* | Support sending realtime signal information via signal queue, realtime | David Xu | 2005-11-03 | 1 | -8/+40 |
* | Push down Giant into fdfree() and remove it from two of the callers. | John Baldwin | 2005-11-01 | 1 | -2/+0 |
* | Fix sigevent's POSIX incompatible problem by adding member fields | David Xu | 2005-10-30 | 1 | -9/+63 |
* | Fix tinderbox box by removing incomplete/bad spl usage. Proper giant free | Doug Ambrisko | 2005-10-12 | 1 | -6/+0 |
* | Add in kqueue support to LIO event notification and fix how it handled | Doug Ambrisko | 2005-10-12 | 1 | -121/+198 |
* | Eliminate inconsistency in the setting of the B_DONE flag. Specifically, | Alan Cox | 2005-07-20 | 1 | -0/+1 |
* | Fix the recent panics/LORs/hangs created by my kqueue commit by: | Suleiman Souhlal | 2005-07-01 | 1 | -1/+1 |
* | In lio_listio(2) change jobref from an int to a long so that | Alan Cox | 2005-06-07 | 1 | -1/+2 |
* | Eliminate an unused field from struct aio_liojob. | Alan Cox | 2005-06-05 | 1 | -2/+0 |
* | Eliminate the original method of requesting notification of aio_read(2) and | Alan Cox | 2005-06-04 | 1 | -58/+14 |
* | Synchronize access to the per process aiocb lists in many of the functions. | Alan Cox | 2005-06-03 | 1 | -2/+19 |
* | In aio_waitcomplete() correct two cases of using an aiocb after freeing it. | Alan Cox | 2005-06-02 | 1 | -2/+4 |
* | Synchronize access to aio_freeproc with a mutex. Eliminate related spl | Alan Cox | 2005-05-30 | 1 | -12/+21 |
* | Use the proc mtx to prevent simultaneous changes to p_aioinfo. | Alan Cox | 2005-05-30 | 1 | -16/+21 |
* | Eliminate unnecessary calls to wakeup(); no one sleeps on &aio_freeproc. | Alan Cox | 2005-05-30 | 1 | -12/+1 |
* | Eliminate aio_activeproc; it's unused. | Alan Cox | 2005-05-30 | 1 | -6/+0 |
* | Eliminate aio_bufjobs; it's unused. | Alan Cox | 2005-05-29 | 1 | -5/+0 |
* | - Acquire Giant in AIO's iodone routine. VFS will no longer do it for us | Jeff Roberson | 2005-04-30 | 1 | -0/+2 |
* | fix aio+kq... I've been running ambrisko's test program for much longer | John-Mark Gurney | 2005-03-18 | 1 | -1/+1 |
* | Make a SYSCTL_NODE static | Poul-Henning Kamp | 2005-02-10 | 1 | -1/+1 |
* | /* -> /*- for copyright notices, minor format tweaks as necessary | Warner Losh | 2005-01-06 | 1 | -1/+1 |
* | Remove buf->b_dev field. | Poul-Henning Kamp | 2004-11-04 | 1 | -1/+0 |
* | Give dev_strategy() an explict cdev argument in preparation for removing | Poul-Henning Kamp | 2004-10-29 | 1 | -1/+1 |