aboutsummaryrefslogtreecommitdiff
path: root/sys/ufs/ffs/ffs_softdep.c
Commit message (Expand)AuthorAgeFilesLines
* MFC: Retain generation count when writing zeroes instead of an inode to disk.Tor Egge2005-09-201-3/+35
* MFC ffs_softdep.c 1.182, softdep.h 1.18Stephan Uphoff2005-08-311-0/+19
* MFC: Don't set the COMPLETE flag in an inodedep structure before theTor Egge2005-08-261-1/+1
* fix a deadlock that can occure w/ large files and syncing disks...John-Mark Gurney2004-06-271-1/+1
* softdep_sync_metadata: fix bug introduced in rev. 1.57.2.10:Max Khon2004-03-151-4/+4
* MFC 1.104 - fix bug where spl saved in softupdates lock could get stomped byMatthew Dillon2002-02-051-38/+76
* MFC 1.103. drain_output() must be called prior to checking forMatthew Dillon2002-02-051-8/+10
* MFC 1.88 - free lock in early return. This can occur if we block gettingMatthew Dillon2001-03-021-1/+3
* MFC 1.82, 1.83, 1.84 (convert manual loops to LIST/FOREACH macros)Matthew Dillon2001-02-281-110/+234
* MFC 1.81, fix race between syncer and umount.Matthew Dillon2001-02-021-12/+42
* MFC: Prevent runaway of kernel soft updates memory.Paul Saab2000-12-281-87/+160
* MFC the major low memory deadlock solution. This patch removes most ofMatthew Dillon2000-11-261-17/+19
* MFC 1.75, fixup write-ordering for bitmap blocks.Matthew Dillon2000-11-191-15/+19
* MFC 1.68 - fix softupdates crash when quota exceededMatthew Dillon2000-11-111-1/+2
* MFC 1.73. Cannot do MALLOC while holding ACQUIRE_LOCK.Matthew Dillon2000-11-071-2/+2
* MFC: new bsd-style unrestricted license textPeter Wemm2000-06-221-22/+5
* When writing out bitmap buffers, need to skip over ones that alreadyKirk McKusick2000-01-301-1/+2
* During fastpath processing for removal of a short-lived inode, theKirk McKusick2000-01-181-48/+56
* Need to reorganize the flushing of directory entry (pagedep) dependenciesKirk McKusick2000-01-181-63/+62
* Better bounding on softdep_flushfiles; other minor tweeks to checks.Kirk McKusick2000-01-171-7/+9
* Must track multiple uncommitted renames until one ultimately getsKirk McKusick2000-01-171-22/+65
* Non-operational change, fix compiler warning.Matthew Dillon2000-01-141-1/+1
* Confirming Peter's fix (locking 101: release the lock before you goKirk McKusick2000-01-131-2/+0
* Free the global softupdates lock prior to tsleep() in getdirtybuf().Peter Wemm2000-01-131-0/+2
* Because cylinder group blocks are now written in background,Kirk McKusick2000-01-131-3/+13
* A panic occurs during an fsync when a dirty block associated withKirk McKusick2000-01-131-4/+7
* We cannot proceed to free the blocks of the file until the dependenciesKirk McKusick2000-01-111-29/+32
* Give vn_isdisk() a second argument where it can return a suitable errno.Poul-Henning Kamp2000-01-101-3/+4
* Missing FREE_LOCK call before handle_workitem_freeblocks.Kirk McKusick2000-01-101-3/+5
* Several performance improvements for soft updates have been added:Kirk McKusick2000-01-101-57/+185
* Keep tighter control of removal dependencies by limiting the numberKirk McKusick2000-01-091-20/+22
* Reorganize softdep_fsync so that it only does the inode-is-flushedKirk McKusick2000-01-091-26/+22
* Make static non-exported functions from soft updates.Kirk McKusick2000-01-091-6/+12
* The function request_cleanup() had a tsleep() with PCATCH. It isKirk McKusick1999-12-161-1/+1
* Lock reporting and assertion changes.Eivind Eklund1999-12-111-1/+1
* Convert various pieces of code to use vn_isdisk() rather than checkingPoul-Henning Kamp1999-11-221-4/+4
* struct mountlist and struct mount.mnt_list have no business beingPoul-Henning Kamp1999-11-201-2/+1
* $Id$ -> $FreeBSD$Peter Wemm1999-08-281-1/+1
* Decommision miscfs/specfs/specdev.h. Most of it goes into <sys/conf.h>,Poul-Henning Kamp1999-08-081-2/+2
* No longer need to set B_ASYNC flag since BUF_KERNPROC nowKirk McKusick1999-06-291-2/+1
* Keep the inlines for <sys/buf.h> happy..Peter Wemm1999-06-271-3/+3
* Convert buffer locking from using the B_BUSY and B_WANTED flags to usingKirk McKusick1999-06-261-9/+13
* Add a vnode argument to VOP_BWRITE to get rid of the last vnodeKirk McKusick1999-06-161-12/+14
* Get rid of the global variable rushjob and replace it with a function inKirk McKusick1999-06-151-41/+45
* Cosmetic changes to make it compile without errors in gcc -WallJulian Elischer1999-05-221-10/+17
* Add a hook to ffs_fsync to allow soft updates to get first chance at doingKirk McKusick1999-05-141-28/+97
* Put back changes that might be causing trouble on Alpha.Kirk McKusick1999-05-091-3/+5
* Get rid of random debugging cruft; sync up with latest version.Kirk McKusick1999-05-071-38/+10
* Severe slowdowns have been reported when creating or removing manyKirk McKusick1999-05-071-108/+290
* Reorganize locking to avoid holding the lock during calls to bdwriteKirk McKusick1999-03-021-3/+9