)]}' { "log": [ { "commit": "da84d96176729fb48a8458561e5d8647103168b8", "tree": "24c952d956178faa9ac8b5c505513c93a87f4f6b", "parents": [ "e5f32a3856caabe745381279f7f32e3b581b59dc" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "message": "sched: reintroduce cache-hot affinity\n\nreintroduce a simplified version of cache-hot/cold scheduling\naffinity. This improves performance with certain SMP workloads,\nsuch as sysbench.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e5f32a3856caabe745381279f7f32e3b581b59dc", "tree": "5448c1116966ba96096915e9022241638e5ab7f4", "parents": [ "91c234b4e3419c786cac2d5b7a7b96443e512e3a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "message": "sched: speed up context-switches a bit\n\nspeed up context-switches a bit by not clearing p-\u003eexec_start.\n\n(as a side-effect, this also makes p-\u003eexec_start a universal timestamp\navailable to cache-hot estimations.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "91c234b4e3419c786cac2d5b7a7b96443e512e3a", "tree": "4d8d04c685147d8f05d5687550f1ad0862258d2f", "parents": [ "fb7dde37ece82e13de383afd7042c45df67a9d17" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:18 2007 +0200" }, "message": "sched: do not wakeup-preempt with SCHED_BATCH tasks\n\ndo not wakeup-preempt with SCHED_BATCH tasks, their preemption\nis batched too, driven by the tick.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d274a4cee190c880ec25b60501efe50c4435b3d7", "tree": "583be6dd4e33681b3c792280ac94e1e484a2da66", "parents": [ "95938a35c5562afa7af7252821e44132391a3db8" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: update comment\n\nupdate comment: clarify time-slices and remove obsolete tuning detail.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "95938a35c5562afa7af7252821e44132391a3db8", "tree": "548cda134d007105f3a819a438ab384ab9f04e27", "parents": [ "ce6c131131df442f0d49d064129ecc52d9fe8ca9" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: prevent wakeup over-scheduling\n\nPrevent wakeup over-scheduling. Once a task has been preempted by a\ntask of the same or lower priority, it becomes ineligible for repeated\npreemption by same until it has been ticked, or slept. Instead, the\ntask is marked for preemption at the next tick. Tasks of higher\npriority still preempt immediately.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ce6c131131df442f0d49d064129ecc52d9fe8ca9", "tree": "14b93a32144e7270dd821901ff247f506270a3a3", "parents": [ "e62dd02ed0af35631c6ca473e50758c9594773cf" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: disable forced preemption by default\n\nImplement feature bit to disable forced preemption. This way\nit can be checked whether a workload is overscheduling or not.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e62dd02ed0af35631c6ca473e50758c9594773cf", "tree": "5bc942a91fac6e48d046997bef8dbfcb9c3a8d3b", "parents": [ "ace8b3d633f93da8535921bf3e3679db3c619578" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: fix group scheduling for SCHED_BATCH\n\nThe following patch (sched: disable sleeper_fairness on SCHED_BATCH)\nseems to break GROUP_SCHED. Although, it may be \u0027oops\u0027-less due to the\npossibility of \u0027p\u0027 being always a valid address.\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8ca0e14ffb12c257de591571a9e96102acdb1c64", "tree": "21258bb0bacb051f3a4b11e89efe4821b5320c60", "parents": [ "810e95ccd58d91369191aa4ecc9e6d4a10d8d0c8" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: disable sleeper_fairness on SCHED_BATCH\n\ndisable sleeper fairness for batch tasks - they are about\nbatch processing after all.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "810e95ccd58d91369191aa4ecc9e6d4a10d8d0c8", "tree": "48e2204da284c2136fe40f89eca0c212fb976807", "parents": [ "a58f6f253d268f7b9712bd13c344a1fd89a3192f" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: another wakeup_granularity fix\n\nunit mis-match: wakeup_gran was used against a vruntime\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "00bf7bfc2eaf775b634774e9ec435d720b6ecee7", "tree": "1f816516361276a56b9dee6b39e90361dc3468be", "parents": [ "0702e3ebc1e42576a04d29f8adacf13be825b800" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: fix: move the CPU check into -\u003etask_new_fair()\n\nnoticed by Peter Zijlstra:\n\nfix: move the CPU check into -\u003etask_new_fair(), this way we\ncan call place_entity() and get child -\u003evruntime right at\ninitial wakeup time.\n\n(without this there can be large latencies)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "0702e3ebc1e42576a04d29f8adacf13be825b800", "tree": "039feaa1007234c971ab3fb0c12fee70856f5597", "parents": [ "4cf86d77f5942336e7cd9de874b38b3c83b54d5e" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:14 2007 +0200" }, "message": "sched: cleanup: function prototype cleanups\n\nnoticed by Thomas Gleixner:\n\ncleanup: function prototype cleanups - move into single line\nwherever possible.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "06877c33fe9261ccdf143492c28de93c56493079", "tree": "e7781b8029068751251c956d891a4b73ef0d6979", "parents": [ "a65914b3658043da27c159b8a28c5811bb0a88c9" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: cleanup: rename SCHED_FEAT_USE_TREE_AVG to SCHED_FEAT_TREE_AVG\n\ncleanup: rename SCHED_FEAT_USE_TREE_AVG to SCHED_FEAT_TREE_AVG, to\nmake SCHED_FEAT_ names more consistent.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a2a2d680735ad7c3b5250704b3863abf54ff4020", "tree": "4c30e26d4474dd0bf4e2ff5a7bac76d44d0653d3", "parents": [ "a03c9061d93822f66eb6287f8e9cf5833a12b49c" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: cleanup, make dequeue_entity() and update_stats_wait_end() similar\n\nmake dequeue_entity() / enqueue_entity() and update_stats_dequeue() /\nupdate_stats_enqueue() look similar, structure-wise.\n\nzero effect, functionality-wise:\n\n text data bss dec hex filename\n 34550 3026 100 37676 932c sched.o.before\n 34550 3026 100 37676 932c sched.o.after\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a03c9061d93822f66eb6287f8e9cf5833a12b49c", "tree": "6f9114291361f90788e95cbeca77e22f73989e74", "parents": [ "a4ec24b48ddef1e93f7578be53270f0b95ad666c" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: cleanup, remove calc_weighted()\n\nremove obsolete code -- calc_weighted()\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a9957449b08ab561a33e1e038df06843b8d8dd9f", "tree": "066272181b3d563f8029c99c8c5587d04597ffda", "parents": [ "155bb293ae8387526e6e07d42b1691104e55d9a2" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@sw.ru", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: uninline scheduler\n\n* save ~300 bytes\n* activate_idle_task() was moved to avoid a warning\n\nbloat-o-meter output:\n\nadd/remove: 6/0 grow/shrink: 0/16 up/down: 438/-733 (-295)\t\t\u003c\u003d\u003d\u003d\nfunction old new delta\n__enqueue_entity - 165 +165\nfinish_task_switch - 110 +110\nupdate_curr_rt - 79 +79\n__load_balance_iterator - 32 +32\n__task_rq_unlock - 28 +28\nfind_process_by_pid - 24 +24\ndo_sched_setscheduler 133 123 -10\nsys_sched_rr_get_interval 176 165 -11\nsys_sched_getparam 156 145 -11\nnormalize_rt_tasks 482 470 -12\nsched_getaffinity 112 99 -13\nsys_sched_getscheduler 86 72 -14\nsched_setaffinity 226 212 -14\nsched_setscheduler 666 642 -24\nload_balance_start_fair 33 9 -24\nload_balance_next_fair 33 9 -24\ndequeue_task_rt 133 67 -66\nput_prev_task_rt 97 28 -69\nschedule_tail 133 50 -83\nschedule 682 594 -88\nenqueue_entity 499 366 -133\ntask_new_fair 317 180 -137\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@sw.ru\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "155bb293ae8387526e6e07d42b1691104e55d9a2", "tree": "defc638aae11c729d4ffe53b7a56d242bd54ff80", "parents": [ "1e819950660e6a811b549422ffb652273257e45e" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: tweak wakeup granularity\n\ntweak wakeup granularity.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "08ec3df5109e0555da5b9deb4382fd29733c852c", "tree": "4739cd8a9b37b9d5482f88db3c8cdc78b07a8a98", "parents": [ "647e7cac2d215fb8890f79252d7eaee3d6743d66" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: fix __pick_next_entity()\n\nThe thing is that __pick_next_entity() must never be called when\nfirst_fair(cfs_rq) \u003d\u003d NULL. It wouldn\u0027t be a problem, should \u0027run_node\u0027\nbe the very first field of \u0027struct sched_entity\u0027 (and it\u0027s the second).\n\nThe \u0027nr_running !\u003d 0\u0027 check is _not_ enough, due to the fact that\n\u0027current\u0027 is not within the tree. Generic paths are ok (e.g. schedule()\nas put_prev_task() is called previously)... I\u0027m more worried about e.g.\nmigration_call() -\u003e CPU_DEAD_FROZEN -\u003e migrate_dead_tasks()... if\n\u0027current\u0027 \u003d\u003d rq-\u003eidle, no problems.. if it\u0027s one of the SCHED_NORMAL\ntasks (or imagine, some other use-cases in the future -- i.e. we should\nnot make outer world dependent on internal details of sched_fair class)\n-- it may be \"Houston, we\u0027ve got a problem\" case.\n\nit\u0027s +16 bytes to the \".text\". Another variant is to make \u0027run_node\u0027 the\nfirst data member of \u0027struct sched_entity\u0027 but an additional check (se !\n\u003d NULL) is still needed in pick_next_entity().\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "647e7cac2d215fb8890f79252d7eaee3d6743d66", "tree": "22ca4b4d3f218107935f0a128a7114a3ceba19f5", "parents": [ "3a2520157234d58abce89526756a32c272824f3f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:13 2007 +0200" }, "message": "sched: vslice fixups for non-0 nice levels\n\nMake vslice accurate wrt nice levels, and add some comments\nwhile we\u0027re at it.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "5522d5d5f70005faeffff3ffc0cfa8eec0155de4", "tree": "d05fc41d19b8a70102a0ad3ad7ed8f6fd2d1cf7d", "parents": [ "b9fa3df33f9166daf81bfa8253d339f5a7726122" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: mark scheduling classes as const\n\nmark scheduling classes as const. The speeds up the code\na bit and shrinks it:\n\n text data bss dec hex filename\n 40027 4018 292 44337 ad31 sched.o.before\n 40190 3842 292 44324 ad24 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "b9fa3df33f9166daf81bfa8253d339f5a7726122", "tree": "72e5c3b9ede48fbbb6c0dbbe94c123a4cb75f7a6", "parents": [ "fad095a7b963d9e914e0cdb73e27355c47709441" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: group scheduler, fix latency\n\nThere is a possibility that because of task of a group moving from one\ncpu to another, it may gain more cpu time that desired. See \nhttp://marc.info/?l\u003dlinux-kernel\u0026m\u003d119073197730334 for details.\n\nThis is an attempt to fix that problem. Basically it simulates dequeue\nof higher level entities as if they are going to sleep. Similarly it\nsimulate wakeup of higher level entities as if they are waking up from\nsleep.\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "fad095a7b963d9e914e0cdb73e27355c47709441", "tree": "afb9056ce0416a48d3f62b1f1e85f3d5627de913", "parents": [ "fb615581c78efee25e4d04f1145e8fa8ec705dc3" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: group scheduler, fix bloat\n\nRecent fix to check_preempt_wakeup() to check for preemption at higher\nlevels caused a size bloat for !CONFIG_FAIR_GROUP_SCHED.\n\nFix the problem.\n\n 42277 10598 320 53195 cfcb kernel/sched.o-before_this_patch\n 42216 10598 320 53134 cf8e kernel/sched.o-after_this_patch\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "b39c5dd7f938775fd0a1df5b4b1c26f854d15231", "tree": "a6ebcc600cb54484fc9a0c605ced80d0410100ca", "parents": [ "5f6d858ecca78f71755859a346d845e302973cd1" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: cleanup, remove stale comment\n\ncleanup, remove stale comment.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "5f6d858ecca78f71755859a346d845e302973cd1", "tree": "5422f6ff9aa7ffab4c708432de84a79e52e503d9", "parents": [ "b0ffd246ea947a037746e725bd461bb7e809a4b3" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: speed up and simplify vslice calculations\n\nspeed up and simplify vslice calculations.\n\n[ From: Mike Galbraith \u003cefault@gmx.de\u003e: build fix ]\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b0ffd246ea947a037746e725bd461bb7e809a4b3", "tree": "62ec34bb1fbb98be646084b74732ec9209e5f39f", "parents": [ "2830cf8c90f37526d401f1999250312df970bfa3" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: clean up min_vruntime use\n\nclean up min_vruntime use.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2b1e315dd2822c99793485f9e53a73459fb399c1", "tree": "a24cc75606f9416e19bf6662949b880b6b20873a", "parents": [ "8651a86c342ab79a956afec0c5971acaad38d3a1" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: yield fix\n\nfix yield bugs due to the current-not-in-rbtree changes: the task is\nnot in the rbtree so rbtree-removal is a no-no.\n\n[ From: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e: build fix. ]\n\nalso, nice code size reduction:\n\nkernel/sched.o:\n text data bss dec hex filename\n 38323 3506 24 41853 a37d sched.o.before\n 38236 3506 24 41766 a326 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "8651a86c342ab79a956afec0c5971acaad38d3a1", "tree": "b83e5ba4a69ce150d857892a12ba13641e995672", "parents": [ "57cb499df26d80ec11cd49e56d20835334ac4ab9" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:12 2007 +0200" }, "message": "sched: group scheduler wakeup latency fix\n\ngroup scheduler wakeup latency fix: when checking for preemption\nwe must check cross-group too, not just intra-group.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "57cb499df26d80ec11cd49e56d20835334ac4ab9", "tree": "1affcb6b68f5428e7c96121fec806d1074b0c1a2", "parents": [ "2ddbf952508fb9911036c484a87f6351106b917c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: remove set_leftmost()\n\nLee Schermerhorn noticed that set_leftmost() contains dead code,\nremove this.\n\nReported-by: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "368059a977871def0f88a92eefb6ecc1f7b6132f", "tree": "79103803ff9a7dbc9873d8fd018e6afd95cb9ff3", "parents": [ "02e4bac2a5b097e23d757bf2953740b3d51b7976" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: max_vruntime() simplification\n\nmax_vruntime() simplification.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "b8487b924177385e3932f846f430b73ce8e69bba", "tree": "c3686b03306ca0eff6bc0387fefac2c248e337d4", "parents": [ "94359f05cb7e1fed0deccc83ebc30a1175a9ae16" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: fix sign check error in place_entity()\n\nfix sign check error in place_entity() - we\u0027d get excessive\nlatencies due to negatives being converted to large u64\u0027s.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "94359f05cb7e1fed0deccc83ebc30a1175a9ae16", "tree": "b187343db9950f9396f832318d061106a9592d41", "parents": [ "dc1f31c90cfa067af6f7000db7a5383c7667ccba" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: undo some of the recent changes\n\nundo some of the recent changes that are not needed after all,\nsuch as last_min_vruntime.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "dc1f31c90cfa067af6f7000db7a5383c7667ccba", "tree": "e5636c8fb549f2a71649596d3cfe95147c35c8bc", "parents": [ "785c29ef9573d98b31493c9a68c3589449082108" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: remove last_min_vruntime effect\n\nremove last_min_vruntime use - prepare to remove it.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "8465e792e82c567b80358e38732164b770ed4b7f", "tree": "f03ba121f3feb3bdd3e88d09775091f17b539476", "parents": [ "ddc972975091ba5f839bf24d0f9ef54fe90ee741" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:11 2007 +0200" }, "message": "sched: entity_key() fix\n\nentity_key() fix - we\u0027d occasionally end up with a 0 vruntime\nin the !initial case.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "ddc972975091ba5f839bf24d0f9ef54fe90ee741", "tree": "438406a2930bdcb36c8a1bc6778aab49e1fba36d", "parents": [ "d822cecedad88b69a7d68aa8d49e1f238aa320c7" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "message": "sched debug: check spread\n\ndebug feature: check how well we schedule within a reasonable\nvruntime \u0027spread\u0027 range. (note that CPU overload can increase\nthe spread, so this is not a hard condition, but normal loads\nshould be within the spread.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "67e9fb2a39a1d454218d50383094940982be138f", "tree": "3b981b8d43d6c23f070df73033d731a6f00f0b0b", "parents": [ "1aa4731eff7dab7bd01747b46f654f449f1cfc2c" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "message": "sched: add vslice\n\nadd vslice: the load-dependent \"virtual slice\" a task should\nrun ideally, so that the observed latency stays within the\nsched_latency window.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "c18b8a7cbcbac46497ee1ce656b0e68197c7581d", "tree": "6af79ba2c13900c4eda6593b110129b00cec3098", "parents": [ "fdd71d132badad542a9ab99ab4a9c3c08fa6412f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:10 2007 +0200" }, "message": "sched: remove unneeded tunables\n\nremove unneeded tunables.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "9b5b77512dce239fa168183fa71896712232e95a", "tree": "2a95cf9151b4b6bd745236858f5b73b639dbc0d9", "parents": [ "75c28ace9f2b2f403674e045939424a77c95b47c" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:09 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:09 2007 +0200" }, "message": "sched: clean up code under CONFIG_FAIR_GROUP_SCHED\n\nWith the view of supporting user-id based fair scheduling (and not just\ncontainer-based fair scheduling), this patch renames several functions\nand makes them independent of whether they are being used for container\nor user-id based fair scheduling.\n\nAlso fix a problem reported by KAMEZAWA Hiroyuki (wrt allocating\nless-sized array for tg-\u003ecfs_rq[] and tf-\u003ese[]).\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Dhaval Giani \u003cdhaval@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "75c28ace9f2b2f403674e045939424a77c95b47c", "tree": "036fcf799d75a08d4913d7d25ef5602fe3c62260", "parents": [ "545f3b18152355acbb8da59873506fcf66c7c60e" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:09 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:09 2007 +0200" }, "message": "sched: print \u0026rq-\u003ecfs stats\n\n- Print \u0026rq-\u003ecfs statistics as well (useful for group scheduling)\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Dhaval Giani \u003cdhaval@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "72ea22f8fbc893425faefa60641f45a4cdef2261", "tree": "9c805c28bd2051feb9a9eac280ae824c4f7fedc8", "parents": [ "83b699ed20f5218580a1b7042064082e2e05f8c5" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: fix minor bug in yield\n\n- fix a minor bug in yield (seen for CONFIG_FAIR_GROUP_SCHED),\n group scheduling would skew when yield was called.\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Dhaval Giani \u003cdhaval@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "83b699ed20f5218580a1b7042064082e2e05f8c5", "tree": "544c42283f41065f22e96e02af0badb7ed70a371", "parents": [ "edcb60a309769a5f6e7c9e76d7c98b34d1757448" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: revert recent removal of set_curr_task()\n\nRevert removal of set_curr_task.\nUse put_prev_task/set_curr_task when changing groups/policies\n\nSigned-off-by: Srivatsa Vaddagiri \u003c vatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Dhaval Giani \u003cdhaval@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "edcb60a309769a5f6e7c9e76d7c98b34d1757448", "tree": "ef288782a4d37739d9747fdcb1ae85d0ac7e5a94", "parents": [ "c86da3a3d40f6e7a032edfaea191fb51e9626c8f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: kernel/sched_fair.c whitespace cleanups\n\nsome trivial whitespace cleanups.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "f6b53205e17c8ca481c69ed579a35a650a4b481a", "tree": "d7820281757e3a2c7cfff7e38275261dcd077eab", "parents": [ "4530d7ab0fb8d5056b68c376949e2d5c4db7817e" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: rework enqueue/dequeue_entity() to get rid of set_curr_task()\n\nrework enqueue/dequeue_entity() to get rid of \nsched_class::set_curr_task(). This simplifies sched_setscheduler(), \nrt_mutex_setprio() and sched_move_tasks().\n\n text data bss dec hex filename\n 24330 2734 20 27084 69cc sched.o.before\n 24233 2730 20 26983 6967 sched.o.after\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "4530d7ab0fb8d5056b68c376949e2d5c4db7817e", "tree": "e5ba2d7fde1d56948c5517442a7e90815f96ef82", "parents": [ "87fefa381ef27f46c1182622ea01eb9504cd2e24" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: simplify sched_class::yield_task()\n\nthe \u0027p\u0027 (task_struct) parameter in the sched_class :: yield_task() is\nredundant as the caller is always the \u0027current\u0027. Get rid of it.\n\n text data bss dec hex filename\n 24341 2734 20 27095 69d7 sched.o.before\n 24330 2734 20 27084 69cc sched.o.after\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "87fefa381ef27f46c1182622ea01eb9504cd2e24", "tree": "036336afad61898307bd3699ecdc3bcbdc3850b6", "parents": [ "75d4ef16a6aa84f708188bada182315f80aab6fa" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:08 2007 +0200" }, "message": "sched: optimize task_new_fair()\n\ndue to the fact that we no longer keep the \u0027current\u0027 within the tree, \ndequeue/enqueue_entity() is useless for the \u0027current\u0027 in \ntask_new_fair(). We are about to reschedule and \nsched_class-\u003eput_prev_task() will put the \u0027current\u0027 back into the tree, \nbased on its new key.\n\n text data bss dec hex filename\n 24388 2734 20 27142 6a06 sched.o.before\n 24341 2734 20 27095 69d7 sched.o.after\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "30cfdcfc5f180fc21a3dad6ae3b7b2a9ee112186", "tree": "7178cde2a1d2b924cc0b66031f4eb02482fe54c2", "parents": [ "7074badbcb4212d404a243e5c50efeb778ec3fc6" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "message": "sched: do not keep current in the tree and get rid of sched_entity::fair_key\n\nGet rid of \u0027sched_entity::fair_key\u0027.\n\nAs a side effect, \u0027current\u0027 is not kept withing the tree for \nSCHED_NORMAL/BATCH tasks anymore. This simplifies some parts of code \n(e.g. entity_tick() and yield_task_fair()) and also somewhat optimizes \nthem (e.g. a single update_curr() now vs. dequeue/enqueue() before in \nentity_tick()).\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "d02e5ed8d55e2a2b2735232ea1da40ffbf4c0932", "tree": "de972b3b1318deb834f61b6dba967ad32845c229", "parents": [ "29f59db3a74b0bdf78a1f5b53ef773caa82692dc" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "message": "sched: sched_setscheduler() fix\n\nFix a problem in the \u0027sched-group\u0027 patch for !CONFIG_FAIR_GROUP_SCHED.\n\ndescription:\n\nsched_setscheduler()\n{\n...\nif (task_running()) p-\u003esched_class-\u003eput_prev_entity();\n\n[ this one sets up cfs_rq-\u003ecurr to NULL ]\n\n...\n\nif (task_running) p-\u003esched_class-\u003eset_curr_task();\n\n[ and this one is a _NOP_ (empty) for !CONFIG_FAIR_GROUP_SCHED ]\n\nAs a result, the task continues to run with cfs_rq-\u003ecurr \u003d\u003d NULL... no \ncrashes (due to checks for !NULL in place) but e.g. update_curr() \neffectively becomes a NOP... i.e. runtime statistics for this task is \nnot accounted untill it\u0027s rescheduled anew.\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "29f59db3a74b0bdf78a1f5b53ef773caa82692dc", "tree": "5ac877639bac41d3749d08b7f624bd13052e5ec6", "parents": [ "119fe5e06800afc197781ebc8c2d8ca7d03497c8" ], "author": { "name": "Srivatsa Vaddagiri", "email": "vatsa@linux.vnet.ibm.com", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "message": "sched: group-scheduler core\n\nAdd interface to control cpu bandwidth allocation to task-groups.\n\n(not yet configurable, due to missing CONFIG_CONTAINERS)\n\nSigned-off-by: Srivatsa Vaddagiri \u003cvatsa@linux.vnet.ibm.com\u003e\nSigned-off-by: Dhaval Giani \u003cdhaval@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "02e0431a3db554019b816936b597d618256b705d", "tree": "2d3d9c5d95e9a2ccc248d78a3ffe950be0e77b3b", "parents": [ "35a6ff5417bf94c9e19b6b55a9eb6eea14cc7be7" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:07 2007 +0200" }, "message": "sched: better min_vruntime tracking\n\nBetter min_vruntime tracking: update it every time \u0027curr\u0027 is\nupdated - not just when a task is enqueued into the tree.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "db36cc7d6d9e538481e60fae7f56646b92557526", "tree": "7c106154128106983b11b4552210e537cfaf7f2e", "parents": [ "bbdba7c0e1161934ae881ad00e4db49830f5ef59" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "message": "sched: clean up schedstat block in dequeue_entity()\n\nBetter placement of #ifdef CONFIG_SCHEDSTAT block in dequeue_entity().\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "bbdba7c0e1161934ae881ad00e4db49830f5ef59", "tree": "1c5c5e9c9c0c6d6cb72b843121e7a38f2768356a", "parents": [ "e22f5bbf86d8cce710d5c8ba5bf57832e73aab8c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "message": "sched: remove wait_runtime fields and features\n\nremove wait_runtime based fields and features, now that the CFS\nmath has been changed over to the vruntime metric.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "e22f5bbf86d8cce710d5c8ba5bf57832e73aab8c", "tree": "9e6240455f123da6249fe0a88ba51459488f2e87", "parents": [ "495eca494aa6006df55e3a04e105462c5940ca17" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "message": "sched: remove wait_runtime limit\n\nremove the wait_runtime-limit fields and the code depending on it, now\nthat the math has been changed over to rely on the vruntime metric.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "495eca494aa6006df55e3a04e105462c5940ca17", "tree": "c7ca67c748ccb5f8fd559f5ac17ca1a1dfc7e25c", "parents": [ "7a62eabc4d60980eb39fff659f168d903b55c6d7" ], "author": { "name": "Dmitry Adamushko", "email": "dmitry.adamushko@gmail.com", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "message": "sched: clean up struct load_stat\n\n\u0027struct load_stat\u0027 is redundant now so let\u0027s get rid of it.\n\nSigned-off-by: Dmitry Adamushko \u003cdmitry.adamushko@gmail.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "7a62eabc4d60980eb39fff659f168d903b55c6d7", "tree": "d7ac8019f7ed2f863040952ec7139c18ebd2c554", "parents": [ "86d9560cb6bd85986e98b4c63705daec94406bd4" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:06 2007 +0200" }, "message": "sched: debug: update exec_clock only when SCHED_DEBUG\n\nmicro-optimization: update cfs_rq-\u003eexec_clock only if\nCONFIG_SCHED_DEBUG\u003dy.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "9014623c0e3545be58a7f19f55793f6517bdc274", "tree": "064267aecedeacb8154282c6475d67f4e34f41e3", "parents": [ "94dfb5e75ef59068a8cf68fa6e18f25ebdcd20b9" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: handle vruntime 64-bit overflow\n\nHandle vruntime overflow by centering the key space around min_vruntime.\n\n( otherwise we could overflow 64-bit vruntime in a few days with SCHED_IDLE\n tasks - or in a few years with nice +19. )\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "94dfb5e75ef59068a8cf68fa6e18f25ebdcd20b9", "tree": "3ff5c162ffbc0e796db250f8a0562292118829f3", "parents": [ "28a1f6fa2f7ecec7e5da28b03a24abbecbd2e864" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: add tree based averages\n\nadd support for tree based vruntime averages.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "28a1f6fa2f7ecec7e5da28b03a24abbecbd2e864", "tree": "8129969f8a7ba69acf12f84cefcd1d633bd7ce7a", "parents": [ "67e12eac328b276dca7e61640632ed996ff1a93a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: remove SCHED_FEAT_SKIP_INITIAL\n\nremove SCHED_FEAT_SKIP_INITIAL - it was off by default and even\nwhen enabled it never made any real difference.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "aeb73b040399f94698b4f64dd058cae39187e18d", "tree": "72ffe7e64b414df2157d19073b92406cbf436535", "parents": [ "2e09bf556fbe1a4cd8d837a3e6607de55f7cf4fd" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: clean up new task placement\n\nclean up new task placement.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "2e09bf556fbe1a4cd8d837a3e6607de55f7cf4fd", "tree": "e73fc7738893ec5c50c3b2e626d4b2ed0809ddbe", "parents": [ "5c6b5964a0629bd39fbf4e5648a8aca32de5bcaf" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: wakeup granularity increase\n\nincrease wakeup granularity - we were overscheduling a bit.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "5c6b5964a0629bd39fbf4e5648a8aca32de5bcaf", "tree": "1b23300ecea76fb8a4bf9dd3942a1a0e5ceeda00", "parents": [ "6d0f0ebd063e36cd0ebae9be15973b02c4245a99" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: simplify check_preempt() methods\n\nsimplify the check_preempt() methods.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "6d0f0ebd063e36cd0ebae9be15973b02c4245a99", "tree": "007ce4f7942afd92cd21d82f89033b38dcb2de59", "parents": [ "4d78e7b656aa6440c337302fe065338ce840a64e" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:05 2007 +0200" }, "message": "sched: simplify adaptive latency\n\nsimplify adaptive latency.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "4d78e7b656aa6440c337302fe065338ce840a64e", "tree": "3013b8b4971ba9b6e3e250d36404c89d7a7c107f", "parents": [ "6cb58195143b55d4c427d92f8425bec2b0d9c56c" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: new task placement for vruntime\n\nadd proper new task placement for the vruntime based math too.\n\n( note: introduces a swap() macro, but the swap token is too\n widely used in the kernel namespace for a generic version\n to be added without changing non-scheduler code - so this\n cleanup will be done separately. )\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "6cb58195143b55d4c427d92f8425bec2b0d9c56c", "tree": "80727312684fe2be27c2c6202a42fff1915f9599", "parents": [ "bf5c91ba8c629b84413c761f529627195fd0a935" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: optimize vruntime based scheduling\n\noptimize vruntime based scheduling.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "bf5c91ba8c629b84413c761f529627195fd0a935", "tree": "8a795d6861ba4e13b90d2597a7306e1adb30bee8", "parents": [ "e9acbff6484df51fd880e0f5fe0224e8be34c17b" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: move sched_feat() definitions\n\nmove sched_feat() definitions so that it can be used sooner by generic\ncode too.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "e9acbff6484df51fd880e0f5fe0224e8be34c17b", "tree": "9ac0275ae7dcd13fb8b628971bf038e9f7318d1e", "parents": [ "08e2388aa1e40cb06f7d04ac621e2ae94e1d8fdc" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: introduce se-\u003evruntime\n\nintroduce se-\u003evruntime as a sum of weighted delta-exec\u0027s, and use that\nas the key into the tree.\n\nthe idea to use absolute virtual time as the basic metric of scheduling\nhas been first raised by William Lee Irwin, advanced by Tong Li and first\nprototyped by Roman Zippel in the \"Really Fair Scheduler\" (RFS) patchset.\n\nalso see:\n\n http://lkml.org/lkml/2007/9/2/76\n\nfor a simpler variant of this patch.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "08e2388aa1e40cb06f7d04ac621e2ae94e1d8fdc", "tree": "07ef79ec5f60879471bfcdef1da7e1d37cbddb4e", "parents": [ "1091985b482fdd577a5c511059b9d7b4467bd15d" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: clean up calc_weighted()\n\nclean up calc_weighted() - we always use the normalized shift so\nit\u0027s not needed to pass that in. Also, push the non-nice0 branch\ninto the function.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "19ccd97a03a026c2341b35af3ed2078a83c4a22b", "tree": "7d522fe6be9d261b630cbceee54717c6148a003d", "parents": [ "e59c80c5bbc0d3d6b0772edb347ce2dd303121b3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:04 2007 +0200" }, "message": "sched: uninline __enqueue_entity()/__dequeue_entity()\n\nsuggested by Roman Zippel: uninline __enqueue_entity() and\n__dequeue_entity().\n\nthis reduces code size:\n\n text data bss dec hex filename\n 25385 2386 16 27787 6c8b sched.o.before\n 25257 2386 16 27659 6c0b sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "e59c80c5bbc0d3d6b0772edb347ce2dd303121b3", "tree": "4c8f2553ae73f4a5d2777933801369b429828f66", "parents": [ "429d43bcc026b92b9dfaccd3577fec290f6a67ce" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "message": "sched: simplify SCHED_FEAT_* code\n\nPeter Zijlstra suggested to simplify SCHED_FEAT_* checks via the\nsched_feat(x) macro.\n\nNo code changed:\n\n text data bss dec hex filename\n 38895 3550 24 42469 a5e5 sched.o.before\n 38895 3550 24 42469 a5e5 sched.o.after\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "429d43bcc026b92b9dfaccd3577fec290f6a67ce", "tree": "d457d48080ce35566463f807e253edec95ddebd9", "parents": [ "62160e3f4a06d948ec89665d29f1173e551deedc" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "message": "sched: cleanup: simplify cfs_rq_curr() methods\n\ncleanup: simplify cfs_rq_curr() methods - now that the cfs_rq-\u003ecurr\npointer is unconditionally present, remove the wrappers.\n\n kernel/sched.o:\n text data bss dec hex filename\n 11784 224 2012 14020 36c4 sched.o.before\n 11784 224 2012 14020 36c4 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "62160e3f4a06d948ec89665d29f1173e551deedc", "tree": "b86bfddf913ea3b22837fb3dcbbdf8c2fb567ed1", "parents": [ "53df556e06d85245cf6aacedaba8e4da684859c3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "message": "sched: track cfs_rq-\u003ecurr on !group-scheduling too\n\nNoticed by Roman Zippel: use cfs_rq-\u003ecurr in the !group-scheduling\ncase too. Small micro-optimization and cleanup effect:\n\n text data bss dec hex filename\n 36269 3482 24 39775 9b5f sched.o.before\n 36177 3486 24 39687 9b07 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "a25707f3aef9cf68c341eba5960d580f364e4e6f", "tree": "77f13a0d32f68217cf6be32b1ab755bf7c1c0665", "parents": [ "8ebc91d93669af39dbed50914d7daf457eeb43be" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "message": "sched: remove precise CPU load\n\nCPU load calculations are statistical anyway, and there\u0027s little benefit\nfrom having it calculated on every scheduling event. So remove this code,\nit gets rid of a divide from the scheduler wakeup and context-switch\nfastpath.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "8ebc91d93669af39dbed50914d7daf457eeb43be", "tree": "c7ab6dfce3ea737db57599c8e42a41ddac51464c", "parents": [ "2bd8e6d422a4f44c0994f909317eba80b0fe08a1" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:03 2007 +0200" }, "message": "sched: remove stat_gran\n\nremove the stat_gran code - it was disabled by default and it causes\nunnecessary overhead.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "2bd8e6d422a4f44c0994f909317eba80b0fe08a1", "tree": "3548dd01c056e3f7c3c04fd85cc4726b95677c15", "parents": [ "38ad464d410dadceda1563f36bdb0be7fe4c8938" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "message": "sched: use constants if !CONFIG_SCHED_DEBUG\n\nuse constants if !CONFIG_SCHED_DEBUG.\n\nthis speeds up the code and reduces code-size:\n\n text data bss dec hex filename\n 27464 3014 16 30494 771e sched.o.before\n 26929 3010 20 29959 7507 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "eba1ed4b7e52720e3099325874811c38a5ec1562", "tree": "4ce145dd10b6cc248a2bc3463822dff23f9dd3c5", "parents": [ "a4b29ba2f72673aaa60ba11ced74d579771dd578" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "message": "sched: debug: track maximum \u0027slice\u0027\n\ntrack the maximum amount of time a task has executed while\nthe CPU load was at least 2x. (i.e. at least two nice-0\ntasks were runnable)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "bb61c210835db95b0e9fb612a316422e7cc675e3", "tree": "47415f8860a4e112fb4158c8724ee52786d0c928", "parents": [ "44142fac3446d08c08c5d717ec11d50a737e8640" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:02 2007 +0200" }, "message": "sched: resched task in task_new_fair()\n\nto get full child-runs-first semantics make sure the parent is\nrescheduled.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "30084fbd1caa4b2e1a336fcdef60b68129d1d8f8", "tree": "379ed73cbe0dc469ccacb148937594f39d35f46c", "parents": [ "3146b39c185f8a436d430132457e84fa1d8f8208" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Oct 02 14:13:08 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Oct 02 14:13:08 2007 +0200" }, "message": "sched: fix profile\u003dsleep\n\nfix sleep profiling - we lost this chunk in the CFS merge.\n\nFound-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1799e35d5baab6e06168b46cc78b968e728ea3d1", "tree": "cccf64a62fa9106aa18253371b675925c0582bab", "parents": [ "a88a8eff1e6e32d3288986a9d36c6a449c032d3a" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 19 23:34:46 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 19 23:34:46 2007 +0200" }, "message": "sched: add /proc/sys/kernel/sched_compat_yield\n\nadd /proc/sys/kernel/sched_compat_yield to make sys_sched_yield()\nmore agressive, by moving the yielding task to the last position\nin the rbtree.\n\nwith sched_compat_yield\u003d0:\n\n PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND\n 2539 mingo 20 0 1576 252 204 R 50 0.0 0:02.03 loop_yield\n 2541 mingo 20 0 1576 244 196 R 50 0.0 0:02.05 loop\n\nwith sched_compat_yield\u003d1:\n\n PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND\n 2584 mingo 20 0 1576 248 196 R 99 0.0 0:52.45 loop\n 2582 mingo 20 0 1576 256 204 R 0 0.0 0:00.00 loop_yield\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "1169783085adb9ac969d21103a6885e8435f7ed3", "tree": "8d5313ef18ba821436aa838cb6f03f065049ef21", "parents": [ "4a55b45036a677fac43fe81ddf7fdcd007aaaee7" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "message": "sched: fix ideal_runtime calculations for reniced tasks\n\nfix ideal_runtime:\n\n - do not scale it using niced_granularity()\n it is against sum_exec_delta, so its wall-time, not fair-time.\n\n - move the whole check into __check_preempt_curr_fair()\n so that wakeup preemption can also benefit from the new logic.\n\nthis also results in code size reduction:\n\n text data bss dec hex filename\n 13391 228 1204 14823 39e7 sched.o.before\n 13369 228 1204 14801 39d1 sched.o.after\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "4a55b45036a677fac43fe81ddf7fdcd007aaaee7", "tree": "86558fa9997e28194d84b997011ed91cde49746c", "parents": [ "7c92e54f6f9601cfa9d8894ee248abcf62ed9a1c" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "message": "sched: improve prev_sum_exec_runtime setting\n\nSecond preparatory patch for fix-ideal runtime:\n\nMark prev_sum_exec_runtime at the beginning of our run, the same spot\nthat adds our wait period to wait_runtime. This seems a more natural\nlocation to do this, and it also reduces the code a bit:\n\n text data bss dec hex filename\n 13397 228 1204 14829 39ed sched.o.before\n 13391 228 1204 14823 39e7 sched.o.after\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7c92e54f6f9601cfa9d8894ee248abcf62ed9a1c", "tree": "5678cf7f582ca8e8568ba610dac77161a6a49881", "parents": [ "cf2ab4696ee42f895eed88c2b6e432fe03dda0db" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "message": "sched: simplify __check_preempt_curr_fair()\n\nPreparatory patch for fix-ideal-runtime:\n\nsimplify __check_preempt_curr_fair(): get rid of the integer return.\n\n text data bss dec hex filename\n 13404 228 1204 14836 39f4 sched.o.before\n 13393 228 1204 14825 39e9 sched.o.after\n\nfunctionality is unchanged.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a206c07213cf6372289f189c3774c4c3255a7ae1", "tree": "a13c33021cc7e7b656305cf20f96205c5f5745a9", "parents": [ "a0dc72601d48b171b4870dfdd0824901a2b2b1a9" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "message": "sched: debug: fix cfs_rq-\u003ewait_runtime accounting\n\nthe cfs_rq-\u003ewait_runtime debug/statistics counter was not maintained\nproperly - fix this.\n\nthis also removes some code:\n\n text data bss dec hex filename\n 13420 228 1204 14852 3a04 sched.o.before\n 13404 228 1204 14836 39f4 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "a0dc72601d48b171b4870dfdd0824901a2b2b1a9", "tree": "25a8ee03d5d85f8138af5c6df558646989357376", "parents": [ "7fd0d2dde929ead79901e389e70dbfb3c6c06986" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:49 2007 +0200" }, "message": "sched: fix niced_granularity() shift\n\nfix niced_granularity(). This resulted in under-scheduling for\nCPU-bound negative nice level tasks (and this in turn caused\nhigher than necessary latencies in nice-0 tasks).\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9f508f8258e18e9333f18daf1f0860df48d49ed2", "tree": "6784a82e1bdc2206233f3fd388f68be22f9254fa", "parents": [ "213c8af67f21c1dc0d50940b159d9521c95f3c89" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: clean up task_new_fair()\n\ncleanup: we have the \u0027se\u0027 and \u0027curr\u0027 entity-pointers already,\nno need to use p-\u003ese and current-\u003ese.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "213c8af67f21c1dc0d50940b159d9521c95f3c89", "tree": "b3f594889a460bcec385192d8675b428616d31b7", "parents": [ "b77d69db9f4ba03b2ed17e383c2d73ca89f5ab14" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: small schedstat fix\n\nsmall schedstat fix: the cfs_rq-\u003ewait_runtime \u0027sum of all runtimes\u0027\nstatistics counters missed newly forked tasks and thus had a constant\nnegative skew. Fix this.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "b77d69db9f4ba03b2ed17e383c2d73ca89f5ab14", "tree": "6ef528381357a030d19493aaceb4632813b2ca9e", "parents": [ "7109c4429af3640f79a638f177fc5d05b9807149" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: fix wait_start_fair condition in update_stats_wait_end()\n\nPeter Zijlstra noticed the following bug in SCHED_FEAT_SKIP_INITIAL (which\nis disabled by default at the moment): it relies on se.wait_start_fair\nbeing 0 while update_stats_wait_end() did not recognize a 0 value,\nso instead of \u0027skipping\u0027 the initial interval we gave the new child\na maximum boost of +runtime-limit ...\n\n(No impact on the default kernel, but nice to fix for completeness.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "7109c4429af3640f79a638f177fc5d05b9807149", "tree": "8ea42387ba3fe5d9bc966e3b488699f4f8af322f", "parents": [ "f6cf891c4d7128f9f91243fc0b9ce99e10fa1586" ], "author": { "name": "Ting Yang", "email": "tingy@cs.umass.edu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: call update_curr() in task_tick_fair()\n\nupdate the fair-clock before using it for the key value.\n\n[ mingo@elte.hu: small cleanups. ]\n\nSigned-off-by: Ting Yang \u003ctingy@cs.umass.edu\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "f6cf891c4d7128f9f91243fc0b9ce99e10fa1586", "tree": "ab26a8e708756c3fbafbb15ce48acea4f80ced08", "parents": [ "5f01d519e60a6ca1a7d9be9f2d73c5f521383992" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: make the scheduler converge to the ideal latency\n\nde-HZ-ification of the granularity defaults unearthed a pre-existing\nproperty of CFS: while it correctly converges to the granularity goal,\nit does not prevent run-time fluctuations in the range of\n[-gran ... 0 ... +gran].\n\nWith the increase of the granularity due to the removal of HZ\ndependencies, this becomes visible in chew-max output (with 5 tasks\nrunning):\n\n out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40\n out: 27 . 27. 32 | flu: 0 . 0 | ran: 17 . 13 | per: 44 . 40\n out: 27 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 36 . 40\n out: 29 . 27. 32 | flu: 2 . 0 | ran: 17 . 13 | per: 46 . 40\n out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40\n out: 29 . 27. 32 | flu: 0 . 0 | ran: 18 . 13 | per: 47 . 40\n out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40\n\naverage slice is the ideal 13 msecs and the period is picture-perfect 40\nmsecs. But the \u0027ran\u0027 field fluctuates around 13.33 msecs and there\u0027s no\nmechanism in CFS to keep that from happening: it\u0027s a perfectly valid\nsolution that CFS finds.\n\nto fix this we add a granularity/preemption rule that knows about\nthe \"target latency\", which makes tasks that run longer than the ideal\nlatency run a bit less. The simplest approach is to simply decrease the\npreemption granularity when a task overruns its ideal latency. For this\nwe have to track how much the task executed since its last preemption.\n\n( this adds a new field to task_struct, but we can eliminate that\n overhead in 2.6.24 by putting all the scheduler timestamps into an\n anonymous union. )\n\nwith this change in place, chew-max output is fluctuation-less all\naround:\n\n out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40\n out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40\n out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40\n out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40\n out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40\n out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40\n\nthis patch has no impact on any fastpath or on any globally observable\nscheduling property. (unless you have sharp enough eyes to see\nmillisecond-level ruckles in glxgears smoothness :-)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\n" }, { "commit": "5f01d519e60a6ca1a7d9be9f2d73c5f521383992", "tree": "f5a1b17bc4f0a0fb97d89a7124c440ebefb685f1", "parents": [ "b07d68b5ca4d55a16fab223d63d5fb36f89ff42f" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Aug 28 12:53:24 2007 +0200" }, "message": "sched: fix sleeper bonus limit\n\nThere is an Amarok song switch time increase (regression) under\nhefty load.\n\nWhat is happening is that sleeper_bonus is never consumed, and only\nrarely goes below runtime_limit, so for the most part, Amarok isn\u0027t\ngetting any bonus at all. We\u0027re keeping sleeper_bonus right at\nruntime_limit (sched_latency \u003d\u003d sched_runtime_limit \u003d\u003d 40ms) forever, ie\nwe don\u0027t consume if we\u0027re lower that that, and don\u0027t add if we\u0027re above\nit. One Amarok thread waking (or anybody else) will push us past the\nthreshold, so the next thread waking gets nada, but will reap pain from\nthe previous thread waking until we drop back to runtime_limit. It\nlooks to me like under load, some random task gets a bonus, and\neverybody else pays, whether deserving or not.\n\nThis diff fixed the regression for me at any load rate.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "172ac3dbb7d3e528ac53d08a34df88d1ac53c534", "tree": "f17de2a4a7a562792fd85a14bb1c278bb8c40804", "parents": [ "218050855ece4e923106ab614ac65afa0f618df3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 25 18:41:53 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 25 18:41:53 2007 +0200" }, "message": "sched: cleanup, sched_granularity -\u003e sched_min_granularity\n\ndue to adaptive granularity scheduling the role of sched_granularity\nhas changed to \"minimum granularity\", so rename the variable (and the\ntunable) accordingly.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\n" }, { "commit": "218050855ece4e923106ab614ac65afa0f618df3", "tree": "f7b1234ce9e8ad0bc5d5af949949251240ec6a2c", "parents": [ "1fc84aaae3bae9646dd4c7798b8c0ff934338909" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Sat Aug 25 18:41:53 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 25 18:41:53 2007 +0200" }, "message": "sched: adaptive scheduler granularity\n\nInstead of specifying the preemption granularity, specify the wanted\nlatency. By fixing the granlarity to a constany the wakeup latency\nit a function of the number of running tasks on the rq.\n\nInvert this relation.\n\nsysctl_sched_granularity becomes a minimum for the dynamic granularity\ncomputed from the new sysctl_sched_latency.\n\nThen use this latency to do more intelligent granularity decisions: if\nthere are fewer tasks running then we can schedule coarser. This helps\nperformance while still always keeping the latency target.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "095e56c7036fe97bc3ebcd80ed6e121be0847656", "tree": "f911a303a427ca6286dd61a2f2f82b92fc3daa28", "parents": [ "ea0aa3b23a193d1fc5c982286edecd071af67d94" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: fix startup penalty calculation\n\nfix task startup penalty miscalculation: sysctl_sched_granularity is\nunsigned int and wait_runtime is long so we first have to convert it\nto long before turning it negative ...\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ea0aa3b23a193d1fc5c982286edecd071af67d94", "tree": "f0eaf77186b1d6056a34e9a87ab326f0847bdb1f", "parents": [ "a6f2994042cc2db9e507dc702ed0b5e2cc5890fe" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: simplify bonus calculation #2\n\ncurrent code:\n\n delta \u003d calc_delta_mine(delta_exec, curr-\u003eload.weight, lw);\n delta \u003d min((u64)delta, cfs_rq-\u003esleeper_bonus);\n\nNotice that this calc_delta_mine() line is exactly delta_mine, which\ngives:\n\n delta \u003d min((u64)delta_mine, cfs_rq-\u003esleeper_bonus);\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a6f2994042cc2db9e507dc702ed0b5e2cc5890fe", "tree": "2fcfab62367e086e50f3561a7dbcae6a63ef952b", "parents": [ "b2133c8b1e270b4a7c36f70e29be8738d09e850b" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: simplify bonus calculation #1\n\ncurrent code:\n\n delta \u003d min(cfs_rq-\u003esleeper_bonus, (u64)delta_exec);\n delta \u003d calc_delta_mine(delta, curr-\u003eload.weight, lw);\n delta \u003d min((u64)delta, cfs_rq-\u003esleeper_bonus);\n\ndrop the first min(), because we clip against sleeper_bonus in the 3rd line\nagain. That gives:\n\n delta \u003d calc_delta_mine(delta_exec, curr-\u003eload.weight, lw);\n delta \u003d min((u64)delta, cfs_rq-\u003esleeper_bonus);\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "b2133c8b1e270b4a7c36f70e29be8738d09e850b", "tree": "9075055664141cc1b91a0b3eac915e6241e38801", "parents": [ "98fbc798533339be802c6dcd48c2293c712e87db" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: tidy up and simplify the bonus balance\n\nmake the bonus balance more consistent: do not hand out a bonus if\nthere\u0027s too much in flight already, and only deduct as much from a\nrunner as it has the capacity. This makes the bonus engine a zero-sum\ngame (as intended).\n\nthis also simplifies the code:\n\n text data bss dec hex filename\n 34770 2998 24 37792 93a0 sched.o.before\n 34749 2998 24 37771 938b sched.o.after\n\nand it also avoids overscheduling in sleep-happy workloads like\nhackbench.c.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "71fd37146385c8255bfd370f33ca81fe8c81e5a5", "tree": "63ef23a5290202c5619d7e3f3f9428d29d5b7db1", "parents": [ "7c6c16f354cde4a48bd305b2587fc78257bcb936" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: remove HZ dependency from the granularity default\n\nremove HZ dependency from the granularity default. Use 10 msec for\nthe base granularity, 1 msec for wakeup granularity and 25 msec for\nbatch wakeup granularity. (These defaults are close to the values\nthat the default HZ\u003d250 setting got previously, and thus it\u0027s the\nmost common setting.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7c6c16f354cde4a48bd305b2587fc78257bcb936", "tree": "027af5f5baceb2c1b9c11720c6cae6cc3df44c48", "parents": [ "1a8f46100b657f533ce677e79bc27c6794c91c46" ], "author": { "name": "Bruce Ashfield", "email": "bruce.ashfield@windriver.com", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 24 20:39:10 2007 +0200" }, "message": "sched: CONFIG_SCHED_GROUP_FAIR\u003dy fixlet\n\nwhen I built with CONFIG_FAIR_GROUP_SCHED\u003dy, I need the following change\nto make things right.\n\n[ From: mingo@elte.hu ]\n\nthis config option is not upstream-configurable right now but lets fix\nthis for completeness.\n\nSigned-off-by: Bruce Ashfield \u003cbruce.ashfield@windriver.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5d2b3d3695a841231b65b5536a70dc29961c5611", "tree": "eac6ed4b85734714b308f7f8b70ace62efb631ac", "parents": [ "6707de00fdec3e3225192fe3dcd21323a8936b1f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 12 18:08:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Aug 12 18:08:19 2007 +0200" }, "message": "sched: fix sleeper bonus\n\nPeter Ziljstra noticed that the sleeper bonus deduction code\nwas not properly rate-limited: a task that scheduled more\nfrequently would get a disproportionately large deduction.\nSo limit the deduction to delta_exec.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "e56f31aad9d8c0102bc074cdab4e3ee76b38600d", "tree": "3ff937cbd564cc57249f736c2a58ae477e4fbef5", "parents": [ "529c77261bccd9d37f110f58b0753d95beaa9fa2" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 10 23:05:11 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Aug 10 23:05:11 2007 +0200" }, "message": "sched: fix typo in the FAIR_GROUP_SCHED branch\n\nwhile there\u0027s no in-tree way to turn group scheduling at the moment,\nfix a typo in it nevertheless.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "7cff8cf61cac15fa29a1ca802826d2bcbca66152", "tree": "86fa25bbf7d8cd3b23f7230fb821cdb04990ebfc", "parents": [ "a69edb55605117cc0f20aa36c49c20b96590774d" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:52 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:52 2007 +0200" }, "message": "sched: refine negative nice level granularity\n\nrefine the granularity of negative nice level tasks: let them\nreschedule more often to offset the effect of them consuming\ntheir wait_runtime proportionately slower. (This makes nice-0\ntask scheduling smoother in the presence of negatively\nreniced tasks.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a69edb55605117cc0f20aa36c49c20b96590774d", "tree": "7e06cd9abce45d450ae9ee365dab3901e7193c01", "parents": [ "194081ebfaa8c7d16133e08dd79254910c20c6ff" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:52 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:52 2007 +0200" }, "message": "sched: fix update_stats_enqueue() reniced codepath\n\nthe key has to be rescaled to /weight even if it has a positive value.\n\n(this change only affects the scheduling of reniced tasks)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c3b64f1e4f772418a649bb8e3b39fcea6c358330", "tree": "e5ffd815cfe4d69a40928c6dbe24e33a1e44f658", "parents": [ "d9e0e6aa6d72df21ff190962c842e027fca0e009" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:51 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:51 2007 +0200" }, "message": "sched: clean up set_curr_task_fair()\n\nclean up set_curr_task_fair().\n\n( identity transformation that causes no change in functionality. )\n\n text data bss dec hex filename\n 39170 3750 36 42956 a7cc sched.o.before\n 39170 3750 36 42956 a7cc sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d9e0e6aa6d72df21ff190962c842e027fca0e009", "tree": "f8ec9765f264fecd47449ef933585f03f80254cc", "parents": [ "546fe3c909b0a4235c7237c210da483eaaac1edc" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:51 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 09 11:16:51 2007 +0200" }, "message": "sched: remove __update_rq_clock() call from entity_tick()\n\nremove __update_rq_clock() call from entity_tick().\n\nno change in functionality because scheduler_tick() already calls\n__update_rq_clock().\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" } ], "next": "bdd4dfa89c1e3e1379729b9edec1526b3ecc25ec" }