aboutsummaryrefslogtreecommitdiff
path: root/sys/kern/vfs_cluster.c
Commit message (Expand)AuthorAgeFilesLines
* cluster_write(): do not access buffer after it is releasedKonstantin Belousov2021-09-091-3/+8
* Delete dead CLUSTERDEBUG config option.Konstantin Belousov2021-02-281-8/+0
* Make MAXPHYS tunable. Bump MAXPHYS to 1M.Konstantin Belousov2020-11-281-0/+2
* vfs: fix trivial whitespace issues which don't interefere with blameMateusz Guzik2020-07-101-1/+1
* Remove duplicated empty lines from kern/*.cMateusz Guzik2020-01-301-1/+0
* Do not use waitable allocation of pbuf when creating cluster for write.Konstantin Belousov2019-12-231-2/+1
* Currently the breadn_flags() and getblkx() interfaces are passedKirk McKusick2019-12-031-1/+1
* Drop the object lock in vfs_bio and cluster where it is now safe to do so.Jeff Roberson2019-10-291-16/+2
* (4/6) Protect page valid with the busy lock.Jeff Roberson2019-10-151-5/+7
* (1/6) Replace busy checks with acquires where it is trival to do so.Jeff Roberson2019-10-151-9/+9
* The VFS-level clustering code collects together sequential blocksKirk McKusick2019-09-171-2/+20
* Use an atomic reference count for paging in progress so that callers do notJeff Roberson2019-08-191-1/+2
* Allocate pager bufs from UMA instead of 80-ish mutex protected linked list.Gleb Smirnoff2019-01-151-5/+15
* ANSIfy sys/kernEd Maste2018-06-011-2/+1
* Detect and optimize reads from the hole on UFS.Konstantin Belousov2018-05-131-11/+17
* sys: further adoption of SPDX licensing ID tags.Pedro F. Giffuni2017-11-201-0/+2
* Move bogus_page declaration to vm_page.h and initialization to vm_page.c.Gleb Smirnoff2017-01-041-3/+0
* Add BUF_TRACKING and FULL_BUF_TRACKING buffer debuggingConrad Meyer2016-10-311-0/+1
* Renumber license clauses in sys/kern to avoid skipping #3Ed Maste2016-09-151-1/+1
* Remove b_pin_count from struct buf.Mark Johnston2016-08-111-14/+0
* sys/kern: spelling fixes in comments.Pedro F. Giffuni2016-04-291-1/+1
* kern: for pointers replace 0 with NULL.Pedro F. Giffuni2016-04-151-1/+1
* Add four new RCTL resources - readbps, readiops, writebps and writeiops,Edward Tomasz Napierala2016-04-071-0/+15
* The bread() function was inconsistent about whether it would returnKirk McKusick2016-01-271-4/+14
* Refactor unmapped buffer address handling.Jeff Roberson2015-07-231-7/+3
* Remove several write-only variables, all reported by the gcc 4.9Konstantin Belousov2015-05-291-2/+0
* When allocating a pbuf for the cluster write, do not sleep waitingKonstantin Belousov2013-08-271-1/+3
* Fix a whitespace.Jung-uk Kim2013-08-231-1/+1
* Both cluster_rbuild() and cluster_wbuild() sometimes set the pagesKonstantin Belousov2013-08-221-9/+26
* The soft and hard busy mechanism rely on the vm object lock to work.Attilio Rao2013-08-091-3/+3
* - Convert the bufobj lock to rwlock.Jeff Roberson2013-05-311-8/+7
* Add a sysctl vfs.read_min to complement the exiting vfs.read_max. ItScott Long2013-05-071-0/+12
* Implement the concept of the unmapped VMIO buffers, i.e. buffers whichKonstantin Belousov2013-03-191-41/+64
* Some style fixes.Konstantin Belousov2013-03-141-1/+1
* Add currently unused flag argument to the cluster_read(),Konstantin Belousov2013-03-141-16/+8
* Switch the vm_object mutex to be a rwlock. This will enable in theAttilio Rao2013-03-091-12/+12
* Add barrier write capability to the VFS buffer interface. A barrierKirk McKusick2013-02-161-3/+9
* Correct a KASSERT message.Alan Cox2012-08-151-1/+1
* Unbreak detection of the async mode for clustered writes after r231075.Konstantin Belousov2012-02-081-1/+1
* The hardware has caught up; improvements are now observed even at 128,Ivan Voras2011-03-161-1/+1
* Bumping the read-ahead count once more, to value equivalent to 512 KiB onIvan Voras2010-08-091-1/+1
* To help with sequential read UFS performance on modern systems, increaseIvan Voras2010-08-071-1/+1
* Remove a stale comment. The very same revision (r85511) that introducedAlan Cox2009-06-301-3/+0
* Correct a long-standing performance bug in cluster_rbuild(). Specifically,Alan Cox2009-06-271-4/+15
* Eliminate unnecessary obfuscation when testing a page's valid bits.Alan Cox2009-06-071-4/+2
* - Complete part of the unfinished bufobj work by consistently usingJeff Roberson2008-03-221-13/+18
* - Move rusage from being per-process in struct pstats to per-thread inJeff Roberson2007-06-011-2/+2
* Change these descriptions of memory types used in malloc(9), as theirWojciech A. Koszek2007-03-051-1/+1
* Replace PG_BUSY with VPO_BUSY. In other words, changes to the page'sAlan Cox2006-10-221-1/+1
* Add mnt_noasync counter to better handle interleaved calls to nmount(),Tor Egge2006-09-261-1/+1