)]}' { "log": [ { "commit": "607717a65d92858fd925bec05baae4d142719f27", "tree": "b7faea733fe3426881e63bc7549db9c97c8bdf59", "parents": [ "2ed6dc34f9ed39bb8e4c81ea1056f0ba56315841" ], "author": { "name": "Paul Jackson", "email": "pj@sgi.com", "time": "Tue Oct 16 01:27:43 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:09 2007 -0700" }, "message": "cpuset: remove sched domain hooks from cpusets\n\nRemove the cpuset hooks that defined sched domains depending on the setting\nof the \u0027cpu_exclusive\u0027 flag.\n\nThe cpu_exclusive flag can only be set on a child if it is set on the\nparent.\n\nThis made that flag painfully unsuitable for use as a flag defining a\npartitioning of a system.\n\nIt was entirely unobvious to a cpuset user what partitioning of sched\ndomains they would be causing when they set that one cpu_exclusive bit on\none cpuset, because it depended on what CPUs were in the remainder of that\ncpusets siblings and child cpusets, after subtracting out other\ncpu_exclusive cpusets.\n\nFurthermore, there was no way on production systems to query the\nresult.\n\nUsing the cpu_exclusive flag for this was simply wrong from the get go.\n\nFortunately, it was sufficiently borked that so far as I know, almost no\nsuccessful use has been made of this. One real time group did use it to\naffectively isolate CPUs from any load balancing efforts. They are willing\nto adapt to alternative mechanisms for this, such as someway to manipulate\nthe list of isolated CPUs on a running system. They can do without this\npresent cpu_exclusive based mechanism while we develop an alternative.\n\nThere is a real risk, to the best of my understanding, of users\naccidentally setting up a partitioned scheduler domains, inhibiting desired\nload balancing across all their CPUs, due to the nonobvious (from the\ncpuset perspective) side affects of the cpu_exclusive flag.\n\nFurthermore, since there was no way on a running system to see what one was\ndoing with sched domains, this change will be invisible to any using code.\nUnless they have real insight to the scheduler load balancing choices, they\nwill be unable to detect that this change has been made in the kernel\u0027s\nbehaviour.\n\nInitial discussion on lkml of this patch has generated much comment. My\n(probably controversial) take on that discussion is that it has reached a\nrough concensus that the current cpuset cpu_exclusive mechanism for\ndefining sched domains is borked. There is no concensus on the\nreplacement. But since we can remove this mechanism, and since its\ncontinued presence risks causing unwanted partitioning of the schedulers\nload balancing, we should remove it while we can, as we proceed to work the\nreplacement scheduler domain mechanisms.\n\nSigned-off-by: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Christoph Lameter \u003cclameter@engr.sgi.com\u003e\nCc: Dinakar Guniguntala \u003cdino@in.ibm.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d5a7430ddcdb598261d70f7eb1bf450b5be52085", "tree": "3b94672e0dbc2bff125de3266908f1a47a17b795", "parents": [ "083576112940fda783d716fd5ccc744f81667b2f" ], "author": { "name": "Mike Travis", "email": "travis@sgi.com", "time": "Tue Oct 16 01:24:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:50 2007 -0700" }, "message": "Convert cpu_sibling_map to be a per cpu variable\n\nConvert cpu_sibling_map from a static array sized by NR_CPUS to a per_cpu\nvariable. This saves sizeof(cpumask_t) * NR unused cpus. Access is mostly\nfrom startup and CPU HOTPLUG functions.\n\nSigned-off-by: Mike Travis \u003ctravis@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: \"Siddha, Suresh B\" \u003csuresh.b.siddha@intel.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9c63d9c021f375a2708ad79043d6f4dd1291a085", "tree": "99cf4af567ae79f42cc47d69c59407515539ba1f", "parents": [ "71e20f1873d46e138c26ce83f8fe54b7221f572f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:20 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:20 2007 +0200" }, "message": "sched: sync wakeups preempt too\n\nmake sure sync wakeups preempt too - the scheduler will not\noverschedule as we\u0027ve got various throttles against that.\nAs a result, sync wakeups can be used more widely in the kernel\n(to signal wakeup affinity between tasks), and no arbitrary\nlatencies will be introduced either.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "71e20f1873d46e138c26ce83f8fe54b7221f572f", "tree": "3b5c5083d3ffcf7c9d7ddad81acf30c09197ef99", "parents": [ "d172fcd3ae1ca7ac27ec8904242fd61e0e11d332" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: affine sync wakeups\n\nmake sync wakeups affine for cache-cold tasks: if a cache-cold task\nis woken up by a sync wakeup then use the opportunity to migrate it\nstraight away. (the two tasks are \u0027related\u0027 because they communicate)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "94886b84b1bcdc95f34f70e7fce407efefe472e1", "tree": "fe612688c702061cf04441350f9200a08f1dc28d", "parents": [ "9ac52315d4cf5f561f36dabaf0720c00d3553162" ], "author": { "name": "Laurent Vivier", "email": "Laurent.Vivier@bull.net", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: guest CPU accounting: maintain stats in account_system_time()\n\nmodify account_system_time() to add cputime to cpustat-\u003eguest if we are\nrunning a VCPU. We add this cputime to cpustat-\u003euser instead of\ncpustat-\u003esystem because this part of KVM code is in fact user code\nalthough it is executed in the kernel. We duplicate VCPU time between\nguest and user to allow an unmodified \"top(1)\" to display correct value.\nA modified \"top(1)\" is able to display good cpu user time and cpu guest\ntime by subtracting cpu guest time from cpu user time. Update \"gtime\" in\ntask_struct accordingly.\n\nSigned-off-by: Laurent Vivier \u003cLaurent.Vivier@bull.net\u003e\nAcked-by: Avi Kivity \u003cavi@qumranet.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6323469f9b72530eb90c96ba162cc70f2f4611de", "tree": "4b19d38ecb5f9d21ea5120980abe165fdce0c13a", "parents": [ "ad1cdc1d7883e88f936f7888a092e4e3e6d8c631" ], "author": { "name": "Milton Miller", "email": "miltonm@bga.com", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: domain sysctl fixes: add terminator comment\n\nwe had an incorrect-terminator bug in sd_alloc_ctl_domain_table()\nbefore, so add a comment that documents it.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ad1cdc1d7883e88f936f7888a092e4e3e6d8c631", "tree": "3ef43757e9355a31c61dd57b190f1790c5e3b49f", "parents": [ "6382bc90f5664c450afc1f896e7ddb35ba182af9" ], "author": { "name": "Milton Miller", "email": "miltonm@bga.com", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: domain sysctl fixes: do not crash on allocation failure\n\nNow that we are calling this at runtime, a more relaxed error path is\nsuggested. If an allocation fails, we just register the partial table,\nwhich will show empty directories.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6382bc90f5664c450afc1f896e7ddb35ba182af9", "tree": "01e40b9d5f44bfeed712cf8d394a16aa93598436", "parents": [ "97b6ea7b6369d51a451a7d5747a7939a593fdd9c" ], "author": { "name": "Milton Miller", "email": "miltonm@bga.com", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: domain sysctl fixes: unregister the sysctl table before domains\n\nUnregister and free the sysctl table before destroying domains, then\nrebuild and register after creating the new domains. This prevents the\nsysctl table from pointing to freed memory for root to write.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "97b6ea7b6369d51a451a7d5747a7939a593fdd9c", "tree": "7cc4b183909a1bdcbae6274862552938c180f740", "parents": [ "5cf9f062c8e33d5a09eaa447550330162b2a96ed" ], "author": { "name": "Milton Miller", "email": "miltonm@bga.com", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: domain sysctl fixes: use for_each_online_cpu()\n\ninit_sched_domain_sysctl was walking cpus 0-n and referencing per_cpu\nvariables. If the cpus_possible mask is not contigious this will result\nin a crash referencing unallocated data. If the online mask is not\ncontigious then we would show offline cpus and miss online ones.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5cf9f062c8e33d5a09eaa447550330162b2a96ed", "tree": "93095cd5531605db4084a5189fef41ef4e36d3cb", "parents": [ "0dbee3a6b006dbe814d002cb18e94bf24a216451" ], "author": { "name": "Milton Miller", "email": "miltonm@bga.com", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:19 2007 +0200" }, "message": "sched: domain sysctl fixes: use kcalloc()\n\nkcalloc checks for n * sizeof(element) overflows and it zeros.\n\nSigned-off-by: Milton Miller \u003cmiltonm@bga.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6bc1665ba71de0f207391b01b187b21b2619c15c", "tree": "efb135b9e389046a70816bb59df11bd265f93f53", "parents": [ "cc367732ff0b1c63d0d7bdd11e6d1661794ef6a3" ], "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: allow the immediate migration of cache-cold tasks\n\nallow the immediate migration of cache-cold tasks.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "cc367732ff0b1c63d0d7bdd11e6d1661794ef6a3", "tree": "27c65e05bf19644224937624ca356c876e6d1318", "parents": [ "2d92f22784b7b8879ebe3254e44c92cb8792b0dd" ], "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: debug, improve migration statistics\n\nadd new migration statistics when SCHED_DEBUG and SCHEDSTATS\nis enabled. Available in /proc/\u003cPID\u003e/sched.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "ff56b2f01537aef7237d5ac8bf6bfbb409c1a127", "tree": "52f7a687f8d3e15b17dc8e6a1789cc537e87d6c8", "parents": [ "da84d96176729fb48a8458561e5d8647103168b8" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "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: activate task_hot() only on fair-scheduled tasks\n\nactivate task_hot() only for fair-scheduled tasks (i.e. disable it\nfor RT tasks).\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "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": "178be793485d70d871a0fd46b29e9e3e7da636ad", "tree": "d7542c2e06e649197d4914e7bfe0ad31e072d58c", "parents": [ "1666703af948ae87c87c2bc7121aa34271cc52ab" ], "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 normalize kernel threads via SysRq-N\n\ndo not normalize kernel threads via SysRq-N: the migration threads,\nsoftlockup threads, etc. might be essential for the system to\nfunction properly. So only zap user tasks.\n\npointed out by Andi Kleen.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1666703af948ae87c87c2bc7121aa34271cc52ab", "tree": "9ba5ef0344daa96bd88ddc3d6ad9d3de623c9ff5", "parents": [ "d5036e89dcf7c19b3d03219d7d385bc96965b7fe" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "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: remove stale comment from sched_group_set_shares()\n\nremove stale comment from sched_group_set_shares().\n\nFunction never returns -EINVAL.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d5036e89dcf7c19b3d03219d7d385bc96965b7fe", "tree": "dbb040c61bc645abde2c4ea91605beb43d370607", "parents": [ "3a5e4dc12f23fb96fafd4f5d0f61e6c3070f80a5" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:15 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:15 2007 +0200" }, "message": "sched: clean up is_migration_thread()\n\nclean up is_migration_thread() and turn it into an inline function.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3a5e4dc12f23fb96fafd4f5d0f61e6c3070f80a5", "tree": "e7c0246126f7cf169cdd167555a1db209d5b03ef", "parents": [ "8cbbe86dfcfd68ad69916164bdc838d9e09adca8" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Mon Oct 15 17:00:15 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:15 2007 +0200" }, "message": "sched: cleanup: refactor normalize_rt_tasks\n\nReplace a particularly ugly ifdef with an inline and a new macro.\nAlso split up the function to be easier to read.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8cbbe86dfcfd68ad69916164bdc838d9e09adca8", "tree": "32e949b7a0fac548d7668f01f5d53b727c885502", "parents": [ "3a5c359a58c39801d838c508f127bdb228af28b0" ], "author": { "name": "Andi Kleen", "email": "ak@suse.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: cleanup: refactor common code of sleep_on / wait_for_completion\n\nRefactor common code of sleep_on / wait_for_completion\n\nThese functions were largely cut\u0027n\u0027pasted. This moves\nthe common code into single helpers instead. Advantage\nis about 1k less code on x86-64 and 91 lines of code removed.\nIt adds one function call to the non timeout version of\nthe functions; i don\u0027t expect this to be measurable.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3a5c359a58c39801d838c508f127bdb228af28b0", "tree": "f5eb18d0547404627c65e81b7bcd25ec71198996", "parents": [ "d274a4cee190c880ec25b60501efe50c4435b3d7" ], "author": { "name": "Andi Kleen", "email": "ak@suse.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: cleanup: remove unnecessary gotos\n\nReplace loops implemented with gotos with real loops.\nReplace err \u003d ...; goto x; x: return err; with return ...;\n\nNo functional changes.\n\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\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": "ace8b3d633f93da8535921bf3e3679db3c619578", "tree": "0769cf68ca9c1db2cb1b0369675691a2fe184065", "parents": [ "638e13ac37a1a89473415f407cbffc1688a20fe2" ], "author": { "name": "Zou Nan hai", "email": "nanhai.zou@intel.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: some proc entries are missed in sched_domain sys_ctl debug code\n\ncache_nice_tries and flags entry do not appear in proc fs sched_domain\ndirectory, because ctl_table entry is skipped.\n\nThis patch fixes the issue.\n\nSigned-off-by: Zou Nan hai \u003cnanhai.zou@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "638e13ac37a1a89473415f407cbffc1688a20fe2", "tree": "c39999a223e8b272819c3676684c88d40aa47040", "parents": [ "5cb350baf580017da38199625b7365b1763d7180" ], "author": { "name": "Gautham R Shenoy", "email": "ego@in.ibm.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 rt ptracer monopolizing CPU\n\nyield() in wait_task_inactive(), can cause a high priority thread to be\nscheduled back in, and there by loop forever while it is waiting for some\nlower priority thread which is unfortunately still on the runqueue.\n\nUse schedule_timeout_uninterruptible(1) instead.\n\nSigned-off-by: Gautham R Shenoy \u003cego@in.ibm.com\u003e\nCredit: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5cb350baf580017da38199625b7365b1763d7180", "tree": "3830339798b1c6f19f1580700ea6ba240fb56ef2", "parents": [ "8ca0e14ffb12c257de591571a9e96102acdb1c64" ], "author": { "name": "Dhaval Giani", "email": "dhaval@linux.vnet.ibm.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: group scheduling, sysfs tunables\n\nAdd tunables in sysfs to modify a user\u0027s cpu share.\n\nA directory is created in sysfs for each new user in the system.\n\n\t/sys/kernel/uids/\u003cuid\u003e/cpu_share\n\nReading this file returns the cpu shares granted for the user.\nWriting into this file modifies the cpu share for the user. Only an\nadministrator is allowed to modify a user\u0027s cpu share.\n\nEx:\n\t# cd /sys/kernel/uids/\n\t# cat 512/cpu_share\n\t1024\n\t# echo 2048 \u003e 512/cpu_share\n\t# cat 512/cpu_share\n\t2048\n\t#\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\n" }, { "commit": "a58f6f253d268f7b9712bd13c344a1fd89a3192f", "tree": "e921a48820767f5a1891f9972d13adf35b981fad", "parents": [ "00bf7bfc2eaf775b634774e9ec435d720b6ecee7" ], "author": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.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: export cpu_clock()\n\nexport cpu_clock() - the preferred API instead of sched_clock().\n\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\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": "4cf86d77f5942336e7cd9de874b38b3c83b54d5e", "tree": "a62b0a1b5a71f715257b82c0f65f894153757c84", "parents": [ "06877c33fe9261ccdf143492c28de93c56493079" ], "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: rename task_grp to task_group\n\ncleanup: rename task_grp to task_group. No need to save two characters\nand \u0027grp\u0027 is annoying to read.\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": "a65914b3658043da27c159b8a28c5811bb0a88c9", "tree": "2fc518e91c9a16f7596e1da861bd6c17abf09c07", "parents": [ "8927f49479756c1aff76e8202ad32733c965864f" ], "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: kfree(NULL) is valid\n\nkfree(NULL) is valid.\n\npointed out by checkpatch.pl.\n\nthe fix shrinks the code a bit:\n\n text data bss dec hex filename\n 40024 3842 100 43966 abbe sched.o.before\n 40002 3842 100 43944 aba8 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8927f49479756c1aff76e8202ad32733c965864f", "tree": "b0a50524fd81c693da37645ac63ffbc13424746a", "parents": [ "26797a34a24cfeab9951a6f42f27432c0b2546af" ], "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: style cleanup\n\nfix up __setup() style bug - noticed via checkpatch.pl.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "26797a34a24cfeab9951a6f42f27432c0b2546af", "tree": "9910b5bafd0a443e58450974c55a6106d4998106", "parents": [ "3e9830dcabdeb3656855ec1b678b6bcf3b50261c" ], "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: break out if printing a warning in sched_domain_debug()\n\ncheckpatch.pl and Andy Whitcroft noticed the following bug: we did\nnot break out after printing an error.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3e9830dcabdeb3656855ec1b678b6bcf3b50261c", "tree": "cf6438f4372b3d9fc862a122d9b7fd8b3172e0d9", "parents": [ "af92723262f3e0c431083f668b605a1dcdbe8f3d" ], "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: run sched_domain_debug() if CONFIG_SCHED_DEBUG\u003dy\n\nrun sched_domain_debug() if CONFIG_SCHED_DEBUG\u003dy, instead\nof relying on the hand-crafted SCHED_DOMAIN_DEBUG switch.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a4ec24b48ddef1e93f7578be53270f0b95ad666c", "tree": "cad14ba03ec8647761396e23e693328c5db40991", "parents": [ "a9957449b08ab561a33e1e038df06843b8d8dd9f" ], "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: tidy up SCHED_RR\n\n- make timeslices of SCHED_RR tasks constant and not\ndependent on task\u0027s static_prio [1] ;\n- remove obsolete code (timeslice related bits);\n- make sched_rr_get_interval() return something more\nmeaningful [2] for SCHED_OTHER tasks.\n\n[1] according to the following link, it\u0027s not compliant with SUSv3\n(not sure though, what is the reference for us :-)\nhttp://lkml.org/lkml/2007/3/7/656\n\n[2] the interval is dynamic and can be depicted as follows \"should a\ntask be one of the runnable tasks at this particular moment, it would\nexpect to run for this interval of time before being re-scheduled by the\nscheduler tick\".\n(i.e. it\u0027s more precise if a task is runnable at the moment)\n\nyeah, this seems to require task_rq_lock/unlock() but this is not a hot\npath.\n\nresults:\n\n(SCHED_FIFO)\n\ndimm@earth:~/storage/prog$ sudo chrt -f 10 ./rr_interval \ntime_slice: 0 : 0\n\n(SCHED_RR)\n\ndimm@earth:~/storage/prog$ sudo chrt 10 ./rr_interval \ntime_slice: 0 : 99984800\n\n(SCHED_NORMAL)\n\ndimm@earth:~/storage/prog$ ./rr_interval \ntime_slice: 0 : 19996960\n\n(SCHED_NORMAL + a cpu_hog of similar \u0027weight\u0027 on the same CPU --- so should be a half of the previous result)\n\ndimm@earth:~/storage/prog$ taskset 1 ./rr_interval \ntime_slice: 0 : 9998480\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": "1e819950660e6a811b549422ffb652273257e45e", "tree": "86bd6a49002d97de371c7e89a184a8b44c02b8d7", "parents": [ "08ec3df5109e0555da5b9deb4382fd29733c852c" ], "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: optimize schedule() a bit on SMP\n\noptimize schedule() a bit on SMP, by moving the rq-clock update\noutside the rq lock.\n\ncode size is the same:\n\n text data bss dec hex filename\n 25725 2666 96 28487 6f47 sched.o.before\n 25725 2666 96 28487 6f47 sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "3a2520157234d58abce89526756a32c272824f3f", "tree": "5a6ffe45173a6f6c5df03a66b6d82a53f52f1460", "parents": [ "5522d5d5f70005faeffff3ffc0cfa8eec0155de4" ], "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: whitespace cleanups\n\nmore whitespace cleanups. No code changed:\n\n text data bss dec hex filename\n 26553 2790 288 29631 73bf sched.o.before\n 26553 2790 288 29631 73bf sched.o.after\n\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": "2830cf8c90f37526d401f1999250312df970bfa3", "tree": "9f40ff1f624cba21be3db086d3d87716e0b1f66f", "parents": [ "2d72376b3af1e7d4d4515ebfd0f4383f2e92c343" ], "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 SMP migration fix\n\ngroup scheduler SMP migration fix: use task_cfs_rq(p) to get\nto the relevant fair-scheduling runqueue of a task, rq-\u003ecfs\nis not the right one.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2d72376b3af1e7d4d4515ebfd0f4383f2e92c343", "tree": "a9f36173883f1309640f3a1e58b03a53422262d8", "parents": [ "2b1e315dd2822c99793485f9e53a73459fb399c1" ], "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: clean up schedstats, cnt -\u003e count\n\nrename all \u0027cnt\u0027 fields and variables to the less yucky \u0027count\u0027 name.\n\nyuckage noticed by Andrew Morton.\n\nno change in code, other than the /proc/sched_debug bkl_count string got\na bit larger:\n\n text data bss dec hex filename\n 38236 3506 24 41766 a326 sched.o.before\n 38240 3506 24 41770 a32a sched.o.after\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nReviewed-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "2ddbf952508fb9911036c484a87f6351106b917c", "tree": "73ced0c94ccb2356a08fc84e7b4258e75484789c", "parents": [ "368059a977871def0f88a92eefb6ecc1f7b6132f" ], "author": { "name": "Hiroshi Shimamoto", "email": "h-shimamoto@ct.jp.nec.com", "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: clean up sched_fork()\n\nThe adjusting sched_class is a missing part of the already existing \"do\nnot leak PI boosting priority to the child\" at the sched_fork(). This\npatch moves the adjusting sched_class from wake_up_new_task() to\nsched_fork().\n\nthis also shrinks the code a bit:\n\n text data bss dec hex filename\n 40111 4018 292 44421 ad85 sched.o.before\n 40102 4018 292 44412 ad7c sched.o.after\n\nSigned-off-by: Hiroshi Shimamoto \u003ch-shimamoto@ct.jp.nec.com\u003e\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": "02e4bac2a5b097e23d757bf2953740b3d51b7976", "tree": "11477c89ecec6ffb557d3b2a9d3fcd70c9bc59e0", "parents": [ "b8487b924177385e3932f846f430b73ce8e69bba" ], "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 sched_fork()\n\nfix sched_fork(): large latencies at new task creation time because\nthe -\u003evruntime was not fixed up cross-CPU, if the parent got migrated\nafter the child\u0027s CPU got set up.\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": "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": "785c29ef9573d98b31493c9a68c3589449082108", "tree": "ba4d54cd9f57f5f4de7e0479977d1335b3458b35", "parents": [ "8465e792e82c567b80358e38732164b770ed4b7f" ], "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 condition from set_task_cpu()\n\nremove condition from set_task_cpu(). Now that -\u003evruntime\nis not global anymore, it should (and does) work fine without\nit too.\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": "b8efb56172bc55082b8490778b07ef73eea0b551", "tree": "2d70e91af4cbd470904ebb4e28ad558c29e73092", "parents": [ "de8d585a12aef40676f12ddc63e97daaf7752ba1" ], "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 debug: BKL usage statistics\n\nadd per task and per rq BKL usage statistics.\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": "24e377a83220ef05c9b5bec7e01d65eed6609aa6", "tree": "9303b3d9f91ee39517d379aaac06c0432be8a9b8", "parents": [ "9b5b77512dce239fa168183fa71896712232e95a" ], "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: add fair-user scheduler\n\nEnable user-id based fair group scheduling. This is useful for anyone\nwho wants to test the group scheduler w/o having to enable\nCONFIG_CGROUPS.\n\nA separate scheduling group (i.e struct task_grp) is automatically created for \nevery new user added to the system. Upon uid change for a task, it is made to \nmove to the corresponding scheduling group.\n\nA /proc tunable (/proc/root_user_share) is also provided to tune root\nuser\u0027s quota of cpu bandwidth.\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": "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": "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": "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": "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": "7074badbcb4212d404a243e5c50efeb778ec3fc6", "tree": "ed55ef0139c9477b4b86ea0f115bcd2aabba1495", "parents": [ "d02e5ed8d55e2a2b2735232ea1da40ffbf4c0932" ], "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: add set_curr_task() calls\n\np-\u003esched_class-\u003eset_curr_task() has to be called before \nactivate_task()/enqueue_task() in rt_mutex_setprio(), \nsched_setschedule() and sched_move_task() in order to set up \n\u0027cfs_rq-\u003ecurr\u0027. The logic of enqueueing depends on whether a task to be \ninserted is \u0027current\u0027 or not.\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": "119fe5e06800afc197781ebc8c2d8ca7d03497c8", "tree": "9e2c57360f6d7442b6e6e1e2c15542805f322231", "parents": [ "02e0431a3db554019b816936b597d618256b705d" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "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: fix SMP migration latencies\n\nfix SMP migration latencies: the vruntimes of different CPUs are\nat incompatible offsets so they have to be fixed up when migrating\na task across CPUs.\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\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": "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": "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": "1091985b482fdd577a5c511059b9d7b4467bd15d", "tree": "1ea76f48b0f4c68072eb5eaa5113af6aa7dbd357", "parents": [ "19ccd97a03a026c2341b35af3ed2078a83c4a22b" ], "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: speed up update_load_add/_sub()\n\nspeed up update_load_add/_sub() by not delaying the division - this\nreduces CPU pipeline dependencies.\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": "53df556e06d85245cf6aacedaba8e4da684859c3", "tree": "60095031fd9493b8da74a5ca8813ea48e617f86c", "parents": [ "a25707f3aef9cf68c341eba5960d580f364e4e6f" ], "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 calculations #2\n\ncontinued removal of precise CPU load calculations.\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": "38ad464d410dadceda1563f36bdb0be7fe4c8938", "tree": "32d47a47e3d387792d6d8db6e8ee9ae3e93b8469", "parents": [ "eba1ed4b7e52720e3099325874811c38a5ec1562" ], "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: uniform tunings\n\nuse the same defaults on both UP and SMP.\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": "2e45874c5aabe573b6ab4328f303c765701394f9", "tree": "a779cec221d8f1601f105ad5cf48f8ae4a2a42e8", "parents": [ "bb61c210835db95b0e9fb612a316422e7cc675e3" ], "author": { "name": "Matthias Kaehlcke", "email": "matthias.kaehlcke@gmail.com", "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 list_for_each_entry_safe() in __wake_up_common()\n\nUse list_for_each_entry_safe() instead of list_for_each_safe() in\n__wake_up_common()\n\nSigned-off-by: Matthias Kaehlcke \u003cmatthias.kaehlcke@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": "44142fac3446d08c08c5d717ec11d50a737e8640", "tree": "2d1a97a5512e869416b90b32f4e79b11cdd6acf6", "parents": [ "23fd50450a34f2558070ceabb0bfebc1c9604af5" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:01 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Oct 15 17:00:01 2007 +0200" }, "message": "sched: fix sysctl_sched_child_runs_first flag\n\nfix the sched_child_runs_first flag: always call into -\u003etask_new()\nif we are on the same CPU, as SCHED_OTHER tasks depend on it for\ncorrect initial setup.\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": "f5ff8422bbdd59f8c1f699df248e1b7a11073027", "tree": "cdd0777acc58c0badd2d0ae66f3efc2f7318e776", "parents": [ "3317fedba9446465082bcc6ce1232451ad1d51ce" ], "author": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Sep 21 09:19:54 2007 +0200" }, "committer": { "name": "Jens Axboe", "email": "axboe@carl.home.kernel.dk", "time": "Wed Oct 10 09:25:57 2007 +0200" }, "message": "Fix warnings with !CONFIG_BLOCK\n\nHide everything in blkdev.h with CONFIG_BLOCK isn\u0027t set, and fixup\nthe (few) files that fail to build because they were relying on blkdev.h\npulling in extra includes for them.\n\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "9c95e7319ba98585ebb6d304eca2d56f401ed70c", "tree": "b650a409da9c1e1feb289cfb16ce2fa05c602216", "parents": [ "1799e35d5baab6e06168b46cc78b968e728ea3d1" ], "author": { "name": "Hiroshi Shimamoto", "email": "h-shimamoto@ct.jp.nec.com", "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: fix invalid sched_class use\n\nWhen using rt_mutex, a NULL pointer dereference is occurred at\nenqueue_task_rt. Here is a scenario;\n1) there are two threads, the thread A is fair_sched_class and\n thread B is rt_sched_class.\n2) Thread A is boosted up to rt_sched_class, because the thread A\n has a rt_mutex lock and the thread B is waiting the lock.\n3) At this time, when thread A create a new thread C, the thread\n C has a rt_sched_class.\n4) When doing wake_up_new_task() for the thread C, the priority\n of the thread C is out of the RT priority range, because the\n normal priority of thread A is not the RT priority. It makes\n data corruption by overflowing the rt_prio_array.\nThe new thread C should be fair_sched_class.\n\nThe new thread should be valid scheduler class before queuing.\nThis patch fixes to set the suitable scheduler class.\n\nSigned-off-by: Hiroshi Shimamoto \u003ch-shimamoto@ct.jp.nec.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\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": "cf2ab4696ee42f895eed88c2b6e432fe03dda0db", "tree": "75c58340b1b72e0d060fd3a07142c54b7ac442c8", "parents": [ "2491b2b89d4646e02ab51c90ab7012d124924ddc" ], "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 xtensa build warning\n\nrename RSR to SRR - \u0027RSR\u0027 is already defined on xtensa.\n\nfound by Adrian Bunk.\n\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": "7fd0d2dde929ead79901e389e70dbfb3c6c06986", "tree": "577c4626e1e6f1de79e41deaeea6699261c873aa", "parents": [ "b21010ed6498391c0f359f2a89c907533fe07fec" ], "author": { "name": "Suresh Siddha", "email": "suresh.b.siddha@intel.com", "time": "Wed Sep 05 14:32:48 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Sep 05 14:32:48 2007 +0200" }, "message": "sched: fix MC/HT scheduler optimization, without breaking the FUZZ logic.\n\nFirst fix the check\n\tif (*imbalance + SCHED_LOAD_SCALE_FUZZ \u003c busiest_load_per_task)\nwith this\n\tif (*imbalance \u003c busiest_load_per_task)\n\nAs the current check is always false for nice 0 tasks (as\nSCHED_LOAD_SCALE_FUZZ is same as busiest_load_per_task for nice 0\ntasks).\n\nWith the above change, imbalance was getting reset to 0 in the corner\ncase condition, making the FUZZ logic fail. Fix it by not corrupting the\nimbalance and change the imbalance, only when it finds that the HT/MC\noptimization is needed.\n\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\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": "50c46637aa894f904e2fb39086a3d7732f68bd50", "tree": "d8cceec7806eef62396eed7be95b06aa4b06f8ed", "parents": [ "a3ce8ea66ae9379235334a989ed78a1ea518b0b3" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 25 22:17:19 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sat Aug 25 22:17:19 2007 +0200" }, "message": "sched: s/sched_latency/sched_min_granularity\n\nruntime limit and wakeup granularity used to be a function of\ngranularity and that was incorrect changed to sched_latency.\n\nFix this to make wakeup granularity a function of min-granularity,\nand the runtime limit equal to latency.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\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": "deac4ee65af4befb66b542e4a782e63da93b51a0", "tree": "459381799e2c6fbb07d8a6b669f25f562c24f9d5", "parents": [ "71fd37146385c8255bfd370f33ca81fe8c81e5a5" ], "author": { "name": "Sven-Thorsten Dietrich", "email": "sven@thebigcorporation.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: simplify can_migrate_task()\n\nRemove trivial conditional branch in Linux scheduler\u0027s\ncan_migrate_task() function.\n\n text data bss dec hex filename\n 34770 2998 24 37792 93a0 sched.o.before\n 34757 2998 24 37779 9393 sched.o.after\n\nSigned-off-by: Sven-Thorsten Dietrich \u003csven@thebigcorporation.com\u003e\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": "505c0efd58031923ae01deac16d896607cafa70e", "tree": "cf7255575b341ed7ee2d3683a0378b7c3b167455", "parents": [ "f549da848eca595abca14ebc5e1bf00fd72aa53d" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "message": "sched: tweak the sched_runtime_limit tunable\n\nMichael Gerdau reported reniced task CPU usage weirdnesses.\nSuch symptoms can be caused by limit underruns so double the\nsched_runtime_limit.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f549da848eca595abca14ebc5e1bf00fd72aa53d", "tree": "25069c378b06c23f9f12a9e08c8f670d899f188b", "parents": [ "f8700df7c419781efb34696de7e7f49717f8ede7" ], "author": { "name": "Suresh Siddha", "email": "suresh.b.siddha@intel.com", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "message": "sched: skip updating rq\u0027s next_balance under null SD\n\nWas playing with sched_smt_power_savings/sched_mc_power_savings and\nfound out that while the scheduler domains are reconstructed when sysfs\nsettings change, rebalance_domains() can get triggered with null domain\non other cpus, which is setting next_balance to jiffies + 60*HZ.\nResulting in no idle/busy balancing for 60 seconds.\n\nFix this.\n\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "f8700df7c419781efb34696de7e7f49717f8ede7", "tree": "c3b4c8e563e1caf5e144310817fc1ecdf812ae41", "parents": [ "efe567fc8281661524ffa75477a7c4ca9b466c63" ], "author": { "name": "Suresh Siddha", "email": "suresh.b.siddha@intel.com", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "message": "sched: fix broken SMT/MC optimizations\n\nOn a four package system with HT - HT load balancing optimizations were\nbroken. For example, if two tasks end up running on two logical threads\nof one of the packages, scheduler is not able to pull one of the tasks\nto a completely idle package.\n\nIn this scenario, for nice-0 tasks, imbalance calculated by scheduler\nwill be 512 and find_busiest_queue() will return 0 (as each cpu\u0027s load\nis 1024 \u003e imbalance and has only one task running).\n\nSimilarly MC scheduler optimizations also get fixed with this patch.\n\n[ mingo@elte.hu: restored fair balancing by increasing the fuzz and\n adding it back to the power decision, without the /2\n factor. ]\n\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "c57baf1e1e24b004b57d282267542baab802753c", "tree": "3348374473c2f76abcb57d0785ccd1a2d21ea6a8", "parents": [ "2aa44d0567ed21b47b87d68819415d48194cb923" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "message": "sched: fix sysctl directory permissions\n\nThere are two remaining gotchas:\n\n- The directories have impossible permissions (writeable).\n\n- The ctl_name for the kernel directory is inconsistent with\n everything else. It should be CTL_KERN.\n\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2aa44d0567ed21b47b87d68819415d48194cb923", "tree": "7be2a8a30a23b363e1e2aecd41934e75f581e115", "parents": [ "b377fd3982ad957c796758a90e2988401a884241" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Aug 23 15:18:02 2007 +0200" }, "message": "sched: sched_clock_idle_[sleep|wakeup]_event()\n\nconstruct a more or less wall-clock time out of sched_clock(), by\nusing ACPI-idle\u0027s existing knowledge about how much time we spent\nidling. This allows the rq clock to work around TSC-stops-in-C2,\nTSC-gets-corrupted-in-C3 type of problems.\n\n( Besides the scheduler\u0027s statistics this also benefits blktrace and\n printk-timestamps as well. )\n\nFurthermore, the precise before-C2/C3-sleep and after-C2/C3-wakeup\ncallbacks allow the scheduler to get out the most of the period where\nthe CPU has a reliable TSC. This results in slightly more precise\ntask statistics.\n\nthe ACPI bits were acked by Len.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nAcked-by: Len Brown \u003clen.brown@intel.com\u003e\n" }, { "commit": "de0cf899bbf06b6f64a5dce9c59d74c41b6b4232", "tree": "0bec43e98303fd2459f4e9fdd60aa05b5ee6b8ef", "parents": [ "5d2b3d3695a841231b65b5536a70dc29961c5611" ], "author": { "name": "Oleg Nesterov", "email": "oleg@tv-sign.ru", "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: run_rebalance_domains: s/SCHED_IDLE/CPU_IDLE/\n\nrebalance_domains(SCHED_IDLE) looks strange (typo), change it to CPU_IDLE.\n\nthe effect of this bug was slightly more agressive idle-balancing on\nSMP than intended.\n\nSigned-off-by: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6707de00fdec3e3225192fe3dcd21323a8936b1f", "tree": "cce42f90c916b851de0c7c60b6d98c23191cd49c", "parents": [ "963c6527e0a0e285736ad482b8142d098f9c2288" ], "author": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "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: make global code static\n\nThis patch makes the following needlessly global code static:\n\n- arch_reinit_sched_domains()\n- struct attr_sched_mc_power_savings\n- struct attr_sched_smt_power_savings\n\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "529c77261bccd9d37f110f58b0753d95beaa9fa2", "tree": "fff049581ceaa06591ba07938bb370a0ccee7293", "parents": [ "ac07860264bd2b18834d3fa3be47032115524cea" ], "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: improve rq-clock overflow logic\n\nimprove the rq-clock overflow logic: limit the absolute rq-\u003eclock\ndelta since the last scheduler tick, instead of limiting the delta\nitself.\n\ntested by Arjan van de Ven - whole laptop was misbehaving due to\nan incorrectly calibrated cpu_khz confusing sched_clock().\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\n" }, { "commit": "194081ebfaa8c7d16133e08dd79254910c20c6ff", "tree": "ba4d26c12614c93694fa67dd4003e243fe546e6c", "parents": [ "254753dc321ea2b753ca9bc58ac329557a20efac" ], "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: round a bit better\n\nround a tiny bit better in high-frequency rescheduling scenarios,\nby rounding around zero instead of rounding down.\n\n(this is pretty theoretical though)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "254753dc321ea2b753ca9bc58ac329557a20efac", "tree": "57abb3eeaad1f9c9cc258975bef92567f5a01253", "parents": [ "6e82a3befe91423e501c2124312bd805be0048eb" ], "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: make the multiplication table more accurate\n\ndo small deltas in the weight and multiplication constant table so\nthat the worst-case numeric error is better than 1:100000000. (8 digits)\n\nthe current error table is:\n\n nice mult * inv_mult error\n ------------------------------------------\n -20: 88761 * 48388 -0.0000000065\n -19: 71755 * 59856 -0.0000000037\n -18: 56483 * 76040 0.0000000056\n -17: 46273 * 92818 0.0000000042\n -16: 36291 * 118348 -0.0000000065\n -15: 29154 * 147320 -0.0000000037\n -14: 23254 * 184698 -0.0000000009\n -13: 18705 * 229616 -0.0000000037\n -12: 14949 * 287308 -0.0000000009\n -11: 11916 * 360437 -0.0000000009\n -10: 9548 * 449829 -0.0000000009\n -9: 7620 * 563644 -0.0000000037\n -8: 6100 * 704093 0.0000000009\n -7: 4904 * 875809 0.0000000093\n -6: 3906 * 1099582 -0.0000000009\n -5: 3121 * 1376151 -0.0000000058\n -4: 2501 * 1717300 0.0000000009\n -3: 1991 * 2157191 -0.0000000035\n -2: 1586 * 2708050 0.0000000009\n -1: 1277 * 3363326 0.0000000014\n 0: 1024 * 4194304 0.0000000000\n 1: 820 * 5237765 0.0000000009\n 2: 655 * 6557202 0.0000000033\n 3: 526 * 8165337 -0.0000000079\n 4: 423 * 10153587 0.0000000012\n 5: 335 * 12820798 0.0000000079\n 6: 272 * 15790321 0.0000000037\n 7: 215 * 19976592 -0.0000000037\n 8: 172 * 24970740 -0.0000000037\n 9: 137 * 31350126 -0.0000000079\n 10: 110 * 39045157 -0.0000000061\n 11: 87 * 49367440 -0.0000000037\n 12: 70 * 61356676 0.0000000056\n 13: 56 * 76695844 -0.0000000075\n 14: 45 * 95443717 -0.0000000072\n 15: 36 * 119304647 -0.0000000009\n 16: 29 * 148102320 -0.0000000037\n 17: 23 * 186737708 -0.0000000028\n 18: 18 * 238609294 -0.0000000009\n 19: 15 * 286331153 -0.0000000002\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6e82a3befe91423e501c2124312bd805be0048eb", "tree": "04e179ca9ef5e4efa4ff5814831094569e611bf3", "parents": [ "2daa357705bfe68788132cf9079930ca948a90af" ], "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: optimize update_rq_clock() calls in the load-balancer\n\noptimize update_rq_clock() calls in the load-balancer: update them\nright after locking the runqueue(s) so that the pull functions do\nnot have to call it.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "2daa357705bfe68788132cf9079930ca948a90af", "tree": "c95e7b19e771d8eacecfb9ae9fe66ce23094b252", "parents": [ "c3b64f1e4f772418a649bb8e3b39fcea6c358330" ], "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: optimize activate_task()\n\noptimize activate_task() by removing update_rq_clock() from it.\n(and add update_rq_clock() to all callsites of activate_task() that\ndid not have it before.)\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "546fe3c909b0a4235c7237c210da483eaaac1edc", "tree": "1b81c3f5f7b56f74a708d65b20a34c856b431e49", "parents": [ "a48da48b403319918a587be8b5d46fe1d186c2ac" ], "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: move the __update_rq_clock() call to scheduler_tick()\n\nmove the __update_rq_clock() call from update_cpu_load() to\nscheduler_tick().\n\n( identity transformation that causes no change in functionality. )\n\nthis allows the direct use of rq-\u003eclock in -\u003etask_tick() functions.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "bdd4dfa89c1e3e1379729b9edec1526b3ecc25ec", "tree": "9bf9002699184a1171522735b2be92bead6df02e", "parents": [ "2e1cb74a501c4b1bca5e55dabff24f267349193c" ], "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 the \u0027u64 now\u0027 local variables\n\nfinal step: remove all (now superfluous) \u0027u64 now\u0027 variables.\n\n( identity transformation that causes no change in functionality. )\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" } ], "next": "2e1cb74a501c4b1bca5e55dabff24f267349193c" }