aboutsummaryrefslogtreecommitdiff
path: root/sys/kern/kern_racct.c
Commit message (Expand)AuthorAgeFilesLines
* kern_racct: Fix a typo in a source code commentGordon Bergling2022-02-091-1/+1
* Drop "All rights reserved" from all my stuff. This includesEdward Tomasz Napierala2020-10-281-1/+0
* Move racct/rctl throttling from userret() to ast(). There's no reasonEdward Tomasz Napierala2020-09-141-0/+2
* kern: clean up empty lines in .c and .h filesMateusz Guzik2020-09-011-1/+1
* Mark more nodes as CTLFLAG_MPSAFE or CTLFLAG_NEEDGIANT (17 of many)Pawel Biernacki2020-02-261-1/+2
* proc: eliminate the zombproc listMateusz Guzik2019-08-281-8/+2
* racct: add RACCT_ENABLED macro and racct_set_unlockedMateusz Guzik2018-12-071-0/+12
* Convert racct_enable to bool and annotate as __read_frequentlyMateusz Guzik2018-11-291-3/+3
* Deinline racct throttling out of syscall exit path.Mateusz Guzik2018-11-291-0/+16
* proc: create a dedicated lock for zombproc to ligthen the load on allproc_lockMateusz Guzik2018-11-291-0/+2
* fork: remove avoidable proc lock/unlock pairMateusz Guzik2018-11-221-2/+2
* call racct_proc_ucred_changed() under the proc lockAndriy Gapon2018-04-201-5/+1
* sys/kern: adoption of SPDX licensing ID tags.Pedro F. Giffuni2017-11-271-0/+2
* try to fix RACCT_RSS accountingAndriy Gapon2017-02-141-1/+4
* Remove redundant KASSERT.Edward Tomasz Napierala2017-01-221-5/+1
* Get rid of rctl_lock; use racct_lock where appropriate. The fast pathsEdward Tomasz Napierala2016-04-211-27/+45
* Allocate RACCT/RCTL zones without UMA_ZONE_NOFREE; no idea why it was thereEdward Tomasz Napierala2016-04-151-1/+1
* Sort variable declarations.Edward Tomasz Napierala2016-04-151-8/+5
* Add four new RCTL resources - readbps, readiops, writebps and writeiops,Edward Tomasz Napierala2016-04-071-11/+66
* Use proper locking macros in RACCT in RCTL.Edward Tomasz Napierala2016-04-051-37/+39
* Fix mismerge.Edward Tomasz Napierala2016-04-011-1/+1
* Drop the 'resource' argument to racct_decay(); it wouldn't make senseEdward Tomasz Napierala2016-04-011-13/+11
* Call rctl_enforce() in all cases the resource usage goes up, even when calledEdward Tomasz Napierala2016-04-011-8/+6
* Reorder the functions; no functional changes.Edward Tomasz Napierala2016-04-011-32/+32
* Reduce code duplication.Edward Tomasz Napierala2016-04-011-17/+13
* Reduce code duplication. There should be no (intended) functional changes.Edward Tomasz Napierala2016-04-011-64/+27
* Rename P_KTHREAD struct proc p_flag to P_KPROC.Konstantin Belousov2016-02-091-1/+1
* fork: plug a use after free of the returned processMateusz Guzik2016-02-041-2/+1
* Fix style issues around existing SDT probes.Mark Johnston2015-12-161-33/+34
* Tweak comments.Edward Tomasz Napierala2015-12-131-2/+2
* Actually make the 'amount' argument to racct_adjust_resource() signed,Edward Tomasz Napierala2015-12-131-1/+1
* Avoid useless relocking.Edward Tomasz Napierala2015-12-131-1/+1
* Speed up rctl operation with large rulesets, by holding the lockEdward Tomasz Napierala2015-11-151-4/+20
* Fix a bug in the CPU % limiting codeJosh Paetzel2015-11-101-8/+8
* save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBEAndriy Gapon2015-09-281-15/+13
* nit: Rename racct_alloc_resource to racct_adjust_resource.Jeremie Le Hen2015-06-141-12/+12
* Build GENERIC with RACCT/RCTL support by default. Note that it stillEdward Tomasz Napierala2015-05-141-1/+1
* Add kern.racct.enable tunable and RACCT_DISABLED config option.Edward Tomasz Napierala2015-04-291-1/+97
* The process spin lock currently has the following distinct uses:Konstantin Belousov2014-11-261-2/+2
* Convert racct stubs to inline functions.Mateusz Guzik2014-10-061-84/+0
* dtrace sdt: remove the ugly sname parameter of SDT_PROBE_DEFINEAndriy Gapon2013-11-261-18/+18
* - For kernel compiled only with KDTRACE_HOOKS and not any lock debuggingAttilio Rao2013-11-251-1/+0
* Accessing td_state requires thread lock to be held.Edward Tomasz Napierala2013-03-141-4/+2
* Improve KASSERT messages in racct, to make it clear which resourceEdward Tomasz Napierala2012-11-151-12/+17
* Fix kassert that's not really valid for %CPU accounting. The problemEdward Tomasz Napierala2012-11-151-2/+3
* Don't divide by zero.Edward Tomasz Napierala2012-11-131-6/+12
* Add CPU percentage limit enforcement to RCTL. The resouce name is "pcpu".Edward Tomasz Napierala2012-10-261-29/+468
* Fix panic with RACCT that could occur in low memory (or out of swap)Edward Tomasz Napierala2012-05-221-0/+3
* Stop treating system processes as special. This fixes panicsEdward Tomasz Napierala2012-04-171-23/+0
* Cast wallclock.tv_sec to uint64_t to avoid overflow in the calculation.Jaakko Heinonen2012-03-181-1/+2
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-26 21:04:55 +0000