- 18 Oct, 2010 13 commits
-
-
Venkatesh Pallipadi authored
Scheduler accounts both softirq and interrupt processing times to the currently running task. This means, if the interrupt processing was for some other task in the system, then the current task ends up being penalized as it gets shorter runtime than otherwise. Change sched task accounting to acoount only actual task time from currently running task. Now update_curr(), modifies the delta_exec to depend on rq->clock_task. Note that this change only handles CONFIG_IRQ_TIME_ACCOUNTING case. We can extend this to CONFIG_VIRT_CPU_ACCOUNTING with minimal effort. But, thats for later. This change will impact scheduling behavior in interrupt heavy conditions. Tested on a 4-way system with eth0 handled by CPU 2 and a network heavy task (nc) running on CPU 3 (and no RSS/RFS). With that I have CPU 2 spending 75%+ of its time in irq processing. CPU 3 spending around 35% time running nc task. Now, if I run another CPU intensive task on CPU 2, without this change /proc/<pid>/schedstat shows 100% of time accounted to this task. With this change, it rightly shows less than 25% accounted to this task as remaining time is actually spent on irq processing. Signed-off-by:
Venkatesh Pallipadi <venki@google.com> Signed-off-by:
Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <1286237003-12406-7-git-send-email-venki@google.com> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
Venkatesh Pallipadi authored
This patch adds IRQ_TIME_ACCOUNTING option on x86 and runtime enables it when TSC is enabled. This change just enables fine grained irq time accounting, isn't used yet. Following patches use it for different purposes. Signed-off-by:
-
Venkatesh Pallipadi authored
s390/powerpc/ia64 have support for CONFIG_VIRT_CPU_ACCOUNTING which does the fine granularity accounting of user, system, hardirq, softirq times. Adding that option on archs like x86 will be challenging however, given the state of TSC reliability on various platforms and also the overhead it will add in syscall entry exit. Instead, add a lighter variant that only does finer accounting of hardirq and softirq times, providing precise irq times (instead of timer tick based samples). This accounting is added with a new config option CONFIG_IRQ_TIME_ACCOUNTING so that there won't be any overhead for users not interested in paying the perf penalty. This accounting is based on sched_clock, with the code being generic. So, other archs may find it useful as well. This patch just adds the core logic and does not enable this logic yet. Signed-off-by:
-
Venkatesh Pallipadi authored
To account softirq time cleanly in scheduler, we need to identify whether softirq is invoked in ksoftirqd context or softirq at hardirq tail context. Add PF_KSOFTIRQD for that purpose. As all PF flag bits are currently taken, create space by moving one of the infrequently used bits (PF_THREAD_BOUND) down in task_struct to be along with some other state fields. Signed-off-by:
-
Venkatesh Pallipadi authored
Just a minor cleanup patch that makes things easier to the following patches. No functionality change in this patch. Signed-off-by:
-
Venkatesh Pallipadi authored
Peter Zijlstra found a bug in the way softirq time is accounted in VIRT_CPU_ACCOUNTING on this thread: http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/01366.html The problem is, softirq processing uses local_bh_disable internally. There is no way, later in the flow, to differentiate between whether softirq is being processed or is it just that bh has been disabled. So, a hardirq when bh is disabled results in time being wrongly accounted as softirq. Looking at the code a bit more, the problem exists in !VIRT_CPU_ACCOUNTING as well. As account_system_time() in normal tick based accouting also uses softirq_count, which will be set even when not in softirq with bh disabled. Peter also suggested solution of using 2*SOFTIRQ_OFFSET as irq count for local_bh_{disable,enable} and using just SOFTIRQ_OFFSET while softirq processing. The patch below does that and adds API in_serving_softirq() which returns whether we are currently processing softirq or not. Also changes one of the usages of softirq_count in net/sched/cls_cgroup.c to in_serving_softirq. Looks like many usages of in_softirq really want in_serving_softirq. Those changes can be made individually on a case by case basis. Signed-off-by:
-
Nikhil Rao authored
When SD_PREFER_SIBLING is set on a sched domain, drop group_capacity to 1 only if the local group has extra capacity. The extra check prevents the case where you always pull from the heaviest group when it is already under-utilized (possible with a large weight task outweighs the tasks on the system). For example, consider a 16-cpu quad-core quad-socket machine with MC and NUMA scheduling domains. Let's say we spawn 15 nice0 tasks and one nice-15 task, and each task is running on one core. In this case, we observe the following events when balancing at the NUMA domain: - find_busiest_group() will always pick the sched group containing the niced task to be the busiest group. - find_busiest_queue() will then always pick one of the cpus running the nice0 task (never picks the cpu with the nice -15 task since weighted_cpuload > imbalance). - The load balancer fails to migrate the task since it is the running task and increments sd->nr_balance_failed. - It repeats the above steps a few more times until sd->nr_balance_failed > 5, at which point it kicks off the active load balancer, wakes up the migration thread and kicks the nice 0 task off the cpu. The load balancer doesn't stop until we kick out all nice 0 tasks from the sched group, leaving you with 3 idle cpus and one cpu running the nice -15 task. When balancing at the NUMA domain, we drop sgs.group_capacity to 1 if the child domain (in this case MC) has SD_PREFER_SIBLING set. Subsequent load checks are not relevant because the niced task has a very large weight. In this patch, we add an extra condition to the "if(prefer_sibling)" check in update_sd_lb_stats(). We drop the capacity of a group only if the local group has extra capacity, ie. nr_running < group_capacity. This patch preserves the original intent of the prefer_siblings check (to spread tasks across the system in low utilization scenarios) and fixes the case above. It helps in the following ways: - In low utilization cases (where nr_tasks << nr_cpus), we still drop group_capacity down to 1 if we prefer siblings. - On very busy systems (where nr_tasks >> nr_cpus), sgs.nr_running will most likely be > sgs.group_capacity. - When balancing large weight tasks, if the local group does not have extra capacity, we do not pick the group with the niced task as the busiest group. This prevents failed balances, active migration and the under-utilization described above. Signed-off-by:
Nikhil Rao <ncrao@google.com> Signed-off-by:
-
Nikhil Rao authored
This patch forces a load balance on a newly idle cpu when the local group has extra capacity and the busiest group does not have any. It improves system utilization when balancing tasks with a large weight differential. Under certain situations, such as a niced down task (i.e. nice = -15) in the presence of nr_cpus NICE0 tasks, the niced task lands on a sched group and kicks away other tasks because of its large weight. This leads to sub-optimal utilization of the machine. Even though the sched group has capacity, it does not pull tasks because sds.this_load >> sds.max_load, and f_b_g() returns NULL. With this patch, if the local group has extra capacity, we shortcut the checks in f_b_g() and try to pull a task over. A sched group has extra capacity if the group capacity is greater than the number of running tasks in that group. Thanks to Mike Galbraith for discussions leading to this patch and for the insight to reuse SD_NEWIDLE_BALANCE. Signed-off-by:
-
Nikhil Rao authored
When cycling through sched groups to determine the busiest group, set group_imb only if the busiest cpu has more than 1 runnable task. This patch fixes the case where two cpus in a group have one runnable task each, but there is a large weight differential between these two tasks. The load balancer is unable to migrate any task from this group, and hence do not consider this group to be imbalanced. Signed-off-by:
-
Nikhil Rao authored
This patch adds a check in task_hot to return if the task has SCHED_IDLE policy. SCHED_IDLE tasks have very low weight, and when run with regular workloads, are typically scheduled many milliseconds apart. There is no need to consider these tasks hot for load balancing. Signed-off-by:
-
Linus Walleij authored
Load weights are for the CFS, they do not belong in the RT task. This makes all RT scheduling classes leave the CFS weights alone. This fixes a real bug as well: I noticed the following phonomena: a process elevated to SCHED_RR forks with SCHED_RESET_ON_FORK set, and the child is indeed SCHED_OTHER, and the niceval is indeed reset to 0. However the weight inserted by set_load_weight() remains at 0, giving the task insignificat priority. With this fix, the weight is reset to what the task had before being elevated to SCHED_RR/SCHED_FIFO. Cc: Lennart Poettering <lennart@poettering.net> Cc: stable@kernel.org Signed-off-by:
Linus Walleij <linus.walleij@stericsson.com> Signed-off-by:
-
Peter Zijlstra authored
In order to separate the stop/migrate work thread from the SCHED_FIFO implementation, create a special class for it that is of higher priority than SCHED_FIFO itself. This currently solves a problem where cpu-hotplug consumes so much cpu-time that the SCHED_FIFO class gets throttled, but has the bandwidth replenishment timer pending on the now dead cpu. It is also required for when we add the planned deadline scheduling class above SCHED_FIFO, as the stop/migrate thread still needs to transcent those tasks. Tested-by:
Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by:
-
Peter Zijlstra authored
Labels should be on column 0. Signed-off-by:
-
- 14 Oct, 2010 2 commits
-
-
Takuya Yoshikawa authored
Targeted preemption latency and minimal preemption granularity for CPU-bound tasks have been changed. This patch updates the comments about these values. Signed-off-by:
Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <20101014160913.eb24fef4.yoshikawa.takuya@oss.ntt.co.jp> Signed-off-by:
-
Ingo Molnar authored
Merge reason: update from -rc5 to -almost-final Signed-off-by:
-
- 13 Oct, 2010 9 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_txLinus Torvalds authored
* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx: ioat2: fix performance regression
-
git://linux-nfs.org/~bfields/linuxLinus Torvalds authored
* 'for-2.6.36' of git://linux-nfs.org/~bfields/linux: nfsd: fix BUG at fs/nfsd/nfsfh.h:199 on unlink
-
Linus Torvalds authored
Merge branch 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: ring-buffer: Fix typo of time extends per page perf, MIPS: Support cross compiling of tools/perf for MIPS perf: Fix incorrect copy_from_user() usage
-
Linus Torvalds authored
* master.kernel.org:/home/rmk/linux-2.6-arm: ARM: relax ioremap prohibition (309caa9c) for -final and -stable ARM: 6440/1: ep93xx: DMA: fix channel_disable cpuimx27: fix i2c bus selection cpuimx27: fix compile when ULPI is selected ARM: 6435/1: Fix HWCAP_TLS flag for ARM11MPCore/Cortex-A9 ARM: 6436/1: AT91: Fix power-saving in idle-mode on 926T processors ARM: fix section mismatch warnings in Versatile Express ARM: 6412/1: kprobes-decode: add support for MOVW instruction ARM: 6419/1: mmu: Fix MT_MEMORY and MT_MEMORY_NONCACHED pte flags ARM: 6416/1: errata: faulty hazard checking in the Store Buffer may lead to data corruption
-
Linus Torvalds authored
Merge branch 'omap-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6 * 'omap-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6: omap: iommu-load cam register before flushing the entry
-
git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6Linus Torvalds authored
* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6: drm/radeon/kms: Silent spurious error message drm/radeon/kms: fix bad cast/shift in evergreen.c drm/radeon/kms: make TV/DFP table info less verbose drm/radeon/kms: leave certain CP int bits enabled drm/radeon/kms: avoid corner case issue with unmappable vram V2
-
Linus Torvalds authored
Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, numa: For each node, register the memory blocks actually used x86, AMD, MCE thresholding: Fix the MCi_MISCj iteration order x86, mce, therm_throt.c: Fix missing curly braces in error handling logic
-
Dan Williams authored
Commit 07934481 "DMAENGINE: generic channel status v2" changed the interface for how dma channel progress is retrieved. It inadvertently exported an internal helper function ioat_tx_status() instead of ioat_dma_tx_status(). The latter polls the hardware to get the latest completion state, while the helper just evaluates the current state without touching hardware. The effect is that we end up waiting for completion timeouts or descriptor allocation errors before the completion state is updated. iperf (before fix): [SUM] 0.0-41.3 sec 364 MBytes 73.9 Mbits/sec iperf (after fix): [SUM] 0.0- 4.5 sec 499 MBytes 940 Mbits/sec This is a regression starting with 2.6.35. Cc: <stable@kernel.org> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Jesse Brandeburg <jesse.brandeburg@intel.com> Cc: Linus Walleij <linus.walleij@stericsson.com> Cc: Maciej Sosnowski <maciej.sosnowski@intel.com> Reported-by:
Richard Scobie <richard@sauce.co.nz> Signed-off-by:
Dan Williams <dan.j.williams@intel.com>
-
J. Bruce Fields authored
As of commit 43a9aa64 "NFSD: Fill in WCC data for REMOVE, RMDIR, MKNOD, and MKDIR", we sometimes call fh_unlock on a filehandle that isn't fully initialized. We should fix up the callers, but as a quick fix it is also sufficient just to remove this assertion. Reported-by:
Marius Tolzmann <tolzmann@molgen.mpg.de> Cc: Chuck Lever <chuck.lever@oracle.com> Signed-off-by:
J. Bruce Fields <bfields@redhat.com>
-
- 12 Oct, 2010 13 commits
-
-
Russell King authored
... but produce a big warning about the problem as encouragement for people to fix their drivers. Signed-off-by:Russell King <rmk+kernel@arm.linux.org.uk>
-
-
Mika Westerberg authored
When channel_disable() is called, it disables per channel interrupts and waits until channels state becomes STATE_STALL, and then disables the channel. Now, if the DMA transfer is disabled while the channel is in STATE_NEXT we will not wait anything and disable the channel immediately. This seems to cause weird data corruption for example in audio transfers. Fix is to wait while we are in STATE_NEXT or STATE_ON and only then disable the channel. Signed-off-by:
Mika Westerberg <mika.westerberg@iki.fi> Acked-by:
Ryan Mallon <ryan@bluewatersys.com> Signed-off-by:
-
git://git.kernel.org/pub/scm/virt/kvm/kvmLinus Torvalds authored
* 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm: KVM: x86: Move TSC reset out of vmcb_init KVM: x86: Fix SVM VMCB reset
-
Steven Rostedt authored
Time stamps for the ring buffer are created by the difference between two events. Each page of the ring buffer holds a full 64 bit timestamp. Each event has a 27 bit delta stamp from the last event. The unit of time is nanoseconds, so 27 bits can hold ~134 milliseconds. If two events happen more than 134 milliseconds apart, a time extend is inserted to add more bits for the delta. The time extend has 59 bits, which is good for ~18 years. Currently the time extend is committed separately from the event. If an event is discarded before it is committed, due to filtering, the time extend still exists. If all events are being filtered, then after ~134 milliseconds a new time extend will be added to the buffer. This can only happen till the end of the page. Since each page holds a full timestamp, there is no reason to add a time extend to the beginning of a page. Time extends can only fill a page that has actual data at the beginning, so there is no fear that time extends will fill more than a page without any data. When reading an event, a loop is made to skip over time extends since they are only used to maintain the time stamp and are never given to the caller. As a paranoid check to prevent the loop running forever, with the knowledge that time extends may only fill a page, a check is made that tests the iteration of the loop, and if the iteration is more than the number of time extends that can fit in a page a warning is printed and the ring buffer is disabled (all of ftrace is also disabled with it). There is another event type that is called a TIMESTAMP which can hold 64 bits of data in the theoretical case that two events happen 18 years apart. This code has not been implemented, but the name of this event exists, as well as the structure for it. The size of a TIMESTAMP is 16 bytes, where as a time extend is only 8 bytes. The macro used to calculate how many time extends can fit on a page used the TIMESTAMP size instead of the time extend size cutting the amount in half. The following test case can easily trigger the warning since we only need to have half the page filled with time extends to trigger the warning: # cd /sys/kernel/debug/tracing/ # echo function > current_tracer # echo 'common_pid < 0' > events/ftrace/function/filter # echo > trace # echo 1 > trace_marker # sleep 120 # cat trace Enabling the function tracer and then setting the filter to only trace functions where the process id is negative (no events), then clearing the trace buffer to ensure that we have nothing in the buffer, then write to trace_marker to add an event to the beginning of a page, sleep for 2 minutes (only 35 seconds is probably needed, but this guarantees the bug), and then finally reading the trace which will trigger the bug. This patch fixes the typo and prevents the false positive of that warning. Reported-by:
Hans J. Koch <hjk@linutronix.de> Tested-by:
Steven Rostedt <rostedt@goodmis.org>
-
Deng-Cheng Zhu authored
Changes: v4: Fix the cosmetic issue of redundant dot-ops v3: Change rmb() to use SYNC v2: Include mips unistd.h and define rmb()/cpu_relax() in tools/perf/perf.h Signed-off-by:
Deng-Cheng Zhu <dengcheng.zhu@gmail.com> Acked-by:
Ralf Baechle <ralf@linux-mips.org> Cc: David Daney <ddaney@caviumnetworks.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by:
-
Jean Delvare authored
I see the following error message in my kernel log from time to time: radeon 0000:07:00.0: ffff88007c334000 reserve failed for wait radeon 0000:07:00.0: ffff88007c334000 reserve failed for wait After investigation, it turns out that there's nothing to be afraid of and everything works as intended. So remove the spurious log message. Signed-off-by:
Jean Delvare <khali@linux-fr.org> Reviewed-by:
Jerome Glisse <jglisse@redhat.com> Signed-off-by:
Dave Airlie <airlied@redhat.com>
-
Alex Deucher authored
Missing parens. fixes: https://bugs.freedesktop.org/show_bug.cgi?id=30718Reported-by:
Dave Gilbert <freedesktop@treblig.org> Signed-off-by:
Alex Deucher <alexdeucher@gmail.com> Reviewed-by:
Matt Turner <mattst88@gmail.com> Cc: stable@kernel.org Signed-off-by:
-
Alex Deucher authored
Make TV standard and DFP table revisions debug only. Signed-off-by:
-
Alex Deucher authored
These bits are used for internal communication and should be left enabled. This may fix s/r issues on some systems. Signed-off-by:
-
Jerome Glisse authored
We should not allocate any object into unmappable vram if we have no means to access them which on all GPU means having the CP running and on newer GPU having the blit utility working. This patch limit the vram allocation to visible vram until we have acceleration up and running. Note that it's more than unlikely that we run into any issue related to that as when acceleration is not woring userspace should allocate any object in vram beside front buffer which should fit in visible vram. V2 use real_vram_size as mc_vram_size could be bigger than the actual amount of vram [airlied: fixup r700_cp_stop case] Signed-off-by:
-
John Blackwood authored
perf events: repair incorrect use of copy_from_user This makes the perf_event_period() return 0 instead of -EFAULT on success. Signed-off-by: John Blackwood<john.blackwood@ccur.com> Signed-off-by:
Joe Korty <joe.korty@ccur.com> Acked-by:
-
Eric Paris authored
This patch disables the fanotify syscalls by just not building them and letting the cond_syscall() statements in kernel/sys_ni.c redirect them to sys_ni_syscall(). It was pointed out by Tvrtko Ursulin that the fanotify interface did not include an explicit prioritization between groups. This is necessary for fanotify to be usable for hierarchical storage management software, as they must get first access to the file, before inotify-like notifiers see the file. This feature can be added in an ABI compatible way in the next release (by using a number of bits in the flags field to carry the info) but it was suggested by Alan that maybe we should just hold off and do it in the next cycle, likely with an (new) explicit argument to the syscall. I don't like this approach best as I know people are already starting to use the current interface, but Alan is all wise and noone on list backed me up with just using what we have. I feel this is needlessly ripping the rug out from under people at the last minute, but if others think it needs to be a new argument it might be the best way forward. Three choices: Go with what we got (and implement the new feature next cycle). Add a new field right now (and implement the new feature next cycle). Wait till next cycle to release the ABI (and implement the new feature next cycle). This is number 3. Signed-off-by:
Eric Paris <eparis@redhat.com> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
- 11 Oct, 2010 3 commits
-
-
Yinghai Lu authored
Russ reported SGI UV is broken recently. He said: | The SRAT table shows that memory range is spread over two nodes. | | SRAT: Node 0 PXM 0 100000000-800000000 | SRAT: Node 1 PXM 1 800000000-1000000000 | SRAT: Node 0 PXM 0 1000000000-1080000000 | |Previously, the kernel early_node_map[] would show three entries |with the proper node. | |[ 0.000000] 0: 0x00100000 -> 0x00800000 |[ 0.000000] 1: 0x00800000 -> 0x01000000 |[ 0.000000] 0: 0x01000000 -> 0x01080000 | |The problem is recent community kernel early_node_map[] shows |only two entries with the node 0 entry overlapping the node 1 |entry. | | 0: 0x00100000 -> 0x01080000 | 1: 0x00800000 -> 0x01000000 After looking at the changelog, Found out that it has been broken for a while by following commit |commit 8716273c |Author: David Rientjes <rientjes@google.com> |Date: Fri Sep 25 15:20:04 2009 -0700 | | x86: Export srat physical topology Before that commit, register_active_regions() is called for every SRAT memory entry right away. Use nodememblk_range[] instead of nodes[] in order to make sure we capture the actual memory blocks registered with each node. nodes[] contains an extended range which spans all memory regions associated with a node, but that does not mean that all the memory in between are included. Reported-by:
Russ Anderson <rja@sgi.com> Tested-by:
Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4CB27BDF.5000800@kernel.org> Acked-by:
David Rientjes <rientjes@google.com> Cc: <stable@kernel.org> 2.6.33 .34 .35 .36 Signed-off-by:
H. Peter Anvin <hpa@linux.intel.com>
-
git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6Linus Torvalds authored
* 'rc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild-2.6: kbuild: fix oldnoconfig to do the right thing kconfig: Temporarily disable dependency warnings kconfig: delay symbol direct dependency initialization
-
Linus Torvalds authored
Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86 * 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mjg59/platform-drivers-x86: IPS driver: Fix limit clamping when reducing CPU power [PATCH 2/2] IPS driver: disable CPU turbo IPS driver: apply BIOS provided CPU limit if different from default intel_ips -- ensure we do not enable gpu turbo mode without driver linkage intel_ips: Print MCP limit exceeded values. IPS driver: verify BIOS provided limits IPS driver: don't toggle CPU turbo on unsupported CPUs NULL pointer might be used in ips_monitor() Release symbol on error-handling path of ips_get_i915_syms() old_cpu_power is wrongly divided by 65535 in ips_monitor() seqno mask of THM_ITV register is 16bit
-
