mirror of
https://github.com/ukui/kernel.git
synced 2026-03-09 10:07:04 -07:00
ce80098db2439ee44403ec6fccd3a10be21c7aff
83 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Barry Song
|
778c558f49 |
sched: Add cluster scheduler level in core and related Kconfig for ARM64
This patch adds scheduler level for clusters and automatically enables
the load balance among clusters. It will directly benefit a lot of
workload which loves more resources such as memory bandwidth, caches.
Testing has widely been done in two different hardware configurations of
Kunpeng920:
24 cores in one NUMA(6 clusters in each NUMA node);
32 cores in one NUMA(8 clusters in each NUMA node)
Workload is running on either one NUMA node or four NUMA nodes, thus,
this can estimate the effect of cluster spreading w/ and w/o NUMA load
balance.
* Stream benchmark:
4threads stream (on 1NUMA * 24cores = 24cores)
stream stream
w/o patch w/ patch
MB/sec copy 29929.64 ( 0.00%) 32932.68 ( 10.03%)
MB/sec scale 29861.10 ( 0.00%) 32710.58 ( 9.54%)
MB/sec add 27034.42 ( 0.00%) 32400.68 ( 19.85%)
MB/sec triad 27225.26 ( 0.00%) 31965.36 ( 17.41%)
6threads stream (on 1NUMA * 24cores = 24cores)
stream stream
w/o patch w/ patch
MB/sec copy 40330.24 ( 0.00%) 42377.68 ( 5.08%)
MB/sec scale 40196.42 ( 0.00%) 42197.90 ( 4.98%)
MB/sec add 37427.00 ( 0.00%) 41960.78 ( 12.11%)
MB/sec triad 37841.36 ( 0.00%) 42513.64 ( 12.35%)
12threads stream (on 1NUMA * 24cores = 24cores)
stream stream
w/o patch w/ patch
MB/sec copy 52639.82 ( 0.00%) 53818.04 ( 2.24%)
MB/sec scale 52350.30 ( 0.00%) 53253.38 ( 1.73%)
MB/sec add 53607.68 ( 0.00%) 55198.82 ( 2.97%)
MB/sec triad 54776.66 ( 0.00%) 56360.40 ( 2.89%)
Thus, it could help memory-bound workload especially under medium load.
Similar improvement is also seen in lkp-pbzip2:
* lkp-pbzip2 benchmark
2-96 threads (on 4NUMA * 24cores = 96cores)
lkp-pbzip2 lkp-pbzip2
w/o patch w/ patch
Hmean tput-2 11062841.57 ( 0.00%) 11341817.51 * 2.52%*
Hmean tput-5 26815503.70 ( 0.00%) 27412872.65 * 2.23%*
Hmean tput-8 41873782.21 ( 0.00%) 43326212.92 * 3.47%*
Hmean tput-12 61875980.48 ( 0.00%) 64578337.51 * 4.37%*
Hmean tput-21 105814963.07 ( 0.00%) 111381851.01 * 5.26%*
Hmean tput-30 150349470.98 ( 0.00%) 156507070.73 * 4.10%*
Hmean tput-48 237195937.69 ( 0.00%) 242353597.17 * 2.17%*
Hmean tput-79 360252509.37 ( 0.00%) 362635169.23 * 0.66%*
Hmean tput-96 394571737.90 ( 0.00%) 400952978.48 * 1.62%*
2-24 threads (on 1NUMA * 24cores = 24cores)
lkp-pbzip2 lkp-pbzip2
w/o patch w/ patch
Hmean tput-2 11071705.49 ( 0.00%) 11296869.10 * 2.03%*
Hmean tput-4 20782165.19 ( 0.00%) 21949232.15 * 5.62%*
Hmean tput-6 30489565.14 ( 0.00%) 33023026.96 * 8.31%*
Hmean tput-8 40376495.80 ( 0.00%) 42779286.27 * 5.95%*
Hmean tput-12 61264033.85 ( 0.00%) 62995632.78 * 2.83%*
Hmean tput-18 86697139.39 ( 0.00%) 86461545.74 ( -0.27%)
Hmean tput-24 104854637.04 ( 0.00%) 104522649.46 * -0.32%*
In the case of 6 threads and 8 threads, we see the greatest performance
improvement.
Similar improvement can be seen on lkp-pixz though the improvement is
smaller:
* lkp-pixz benchmark
2-24 threads lkp-pixz (on 1NUMA * 24cores = 24cores)
lkp-pixz lkp-pixz
w/o patch w/ patch
Hmean tput-2 6486981.16 ( 0.00%) 6561515.98 * 1.15%*
Hmean tput-4 11645766.38 ( 0.00%) 11614628.43 ( -0.27%)
Hmean tput-6 15429943.96 ( 0.00%) 15957350.76 * 3.42%*
Hmean tput-8 19974087.63 ( 0.00%) 20413746.98 * 2.20%*
Hmean tput-12 28172068.18 ( 0.00%) 28751997.06 * 2.06%*
Hmean tput-18 39413409.54 ( 0.00%) 39896830.55 * 1.23%*
Hmean tput-24 49101815.85 ( 0.00%) 49418141.47 * 0.64%*
* SPECrate benchmark
4,8,16 copies mcf_r(on 1NUMA * 32cores = 32cores)
Base Base
Run Time Rate
------- ---------
4 Copies w/o 580 (w/ 570) w/o 11.1 (w/ 11.3)
8 Copies w/o 647 (w/ 605) w/o 20.0 (w/ 21.4, +7%)
16 Copies w/o 844 (w/ 844) w/o 30.6 (w/ 30.6)
32 Copies(on 4NUMA * 32 cores = 128cores)
[w/o patch]
Base Base Base
Benchmarks Copies Run Time Rate
--------------- ------- --------- ---------
500.perlbench_r 32 584 87.2 *
502.gcc_r 32 503 90.2 *
505.mcf_r 32 745 69.4 *
520.omnetpp_r 32 1031 40.7 *
523.xalancbmk_r 32 597 56.6 *
525.x264_r 1 -- CE
531.deepsjeng_r 32 336 109 *
541.leela_r 32 556 95.4 *
548.exchange2_r 32 513 163 *
557.xz_r 32 530 65.2 *
Est. SPECrate2017_int_base 80.3
[w/ patch]
Base Base Base
Benchmarks Copies Run Time Rate
--------------- ------- --------- ---------
500.perlbench_r 32 580 87.8 (+0.688%) *
502.gcc_r 32 477 95.1 (+5.432%) *
505.mcf_r 32 644 80.3 (+13.574%) *
520.omnetpp_r 32 942 44.6 (+9.58%) *
523.xalancbmk_r 32 560 60.4 (+6.714%%) *
525.x264_r 1 -- CE
531.deepsjeng_r 32 337 109 (+0.000%) *
541.leela_r 32 554 95.6 (+0.210%) *
548.exchange2_r 32 515 163 (+0.000%) *
557.xz_r 32 524 66.0 (+1.227%) *
Est. SPECrate2017_int_base 83.7 (+4.062%)
On the other hand, it is slightly helpful to CPU-bound tasks like
kernbench:
* 24-96 threads kernbench (on 4NUMA * 24cores = 96cores)
kernbench kernbench
w/o cluster w/ cluster
Min user-24 12054.67 ( 0.00%) 12024.19 ( 0.25%)
Min syst-24 1751.51 ( 0.00%) 1731.68 ( 1.13%)
Min elsp-24 600.46 ( 0.00%) 598.64 ( 0.30%)
Min user-48 12361.93 ( 0.00%) 12315.32 ( 0.38%)
Min syst-48 1917.66 ( 0.00%) 1892.73 ( 1.30%)
Min elsp-48 333.96 ( 0.00%) 332.57 ( 0.42%)
Min user-96 12922.40 ( 0.00%) 12921.17 ( 0.01%)
Min syst-96 2143.94 ( 0.00%) 2110.39 ( 1.56%)
Min elsp-96 211.22 ( 0.00%) 210.47 ( 0.36%)
Amean user-24 12063.99 ( 0.00%) 12030.78 * 0.28%*
Amean syst-24 1755.20 ( 0.00%) 1735.53 * 1.12%*
Amean elsp-24 601.60 ( 0.00%) 600.19 ( 0.23%)
Amean user-48 12362.62 ( 0.00%) 12315.56 * 0.38%*
Amean syst-48 1921.59 ( 0.00%) 1894.95 * 1.39%*
Amean elsp-48 334.10 ( 0.00%) 332.82 * 0.38%*
Amean user-96 12925.27 ( 0.00%) 12922.63 ( 0.02%)
Amean syst-96 2146.66 ( 0.00%) 2122.20 * 1.14%*
Amean elsp-96 211.96 ( 0.00%) 211.79 ( 0.08%)
Note this patch isn't an universal win, it might hurt those workload
which can benefit from packing. Though tasks which want to take
advantages of lower communication latency of one cluster won't
necessarily been packed in one cluster while kernel is not aware of
clusters, they have some chance to be randomly packed. But this
patch will make them more likely spread.
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
|
||
Jonathan Cameron
|
c5e22feffd |
topology: Represent clusters of CPUs within a die
Both ACPI and DT provide the ability to describe additional layers of
topology between that of individual cores and higher level constructs
such as the level at which the last level cache is shared.
In ACPI this can be represented in PPTT as a Processor Hierarchy
Node Structure [1] that is the parent of the CPU cores and in turn
has a parent Processor Hierarchy Nodes Structure representing
a higher level of topology.
For example Kunpeng 920 has 6 or 8 clusters in each NUMA node, and each
cluster has 4 cpus. All clusters share L3 cache data, but each cluster
has local L3 tag. On the other hand, each clusters will share some
internal system bus.
+-----------------------------------+ +---------+
| +------+ +------+ +--------------------------+ |
| | CPU0 | | cpu1 | | +-----------+ | |
| +------+ +------+ | | | | |
| +----+ L3 | | |
| +------+ +------+ cluster | | tag | | |
| | CPU2 | | CPU3 | | | | | |
| +------+ +------+ | +-----------+ | |
| | | |
+-----------------------------------+ | |
+-----------------------------------+ | |
| +------+ +------+ +--------------------------+ |
| | | | | | +-----------+ | |
| +------+ +------+ | | | | |
| | | L3 | | |
| +------+ +------+ +----+ tag | | |
| | | | | | | | | |
| +------+ +------+ | +-----------+ | |
| | | |
+-----------------------------------+ | L3 |
| data |
+-----------------------------------+ | |
| +------+ +------+ | +-----------+ | |
| | | | | | | | | |
| +------+ +------+ +----+ L3 | | |
| | | tag | | |
| +------+ +------+ | | | | |
| | | | | | +-----------+ | |
| +------+ +------+ +--------------------------+ |
+-----------------------------------| | |
+-----------------------------------| | |
| +------+ +------+ +--------------------------+ |
| | | | | | +-----------+ | |
| +------+ +------+ | | | | |
| +----+ L3 | | |
| +------+ +------+ | | tag | | |
| | | | | | | | | |
| +------+ +------+ | +-----------+ | |
| | | |
+-----------------------------------+ | |
+-----------------------------------+ | |
| +------+ +------+ +--------------------------+ |
| | | | | | +-----------+ | |
| +------+ +------+ | | | | |
| | | L3 | | |
| +------+ +------+ +---+ tag | | |
| | | | | | | | | |
| +------+ +------+ | +-----------+ | |
| | | |
+-----------------------------------+ | |
+-----------------------------------+ | |
| +------+ +------+ +--------------------------+ |
| | | | | | +-----------+ | |
| +------+ +------+ | | | | |
| | | L3 | | |
| +------+ +------+ +--+ tag | | |
| | | | | | | | | |
| +------+ +------+ | +-----------+ | |
| | +---------+
+-----------------------------------+
That means spreading tasks among clusters will bring more bandwidth
while packing tasks within one cluster will lead to smaller cache
synchronization latency. So both kernel and userspace will have
a chance to leverage this topology to deploy tasks accordingly to
achieve either smaller cache latency within one cluster or an even
distribution of load among clusters for higher throughput.
This patch exposes cluster topology to both kernel and userspace.
Libraried like hwloc will know cluster by cluster_cpus and related
sysfs attributes. PoC of HWLOC support at [2].
Note this patch only handle the ACPI case.
Special consideration is needed for SMT processors, where it is
necessary to move 2 levels up the hierarchy from the leaf nodes
(thus skipping the processor core level).
Note that arm64 / ACPI does not provide any means of identifying
a die level in the topology but that may be unrelate to the cluster
level.
[1] ACPI Specification 6.3 - section 5.2.29.1 processor hierarchy node
structure (Type 0)
[2] https://github.com/hisilicon/hwloc/tree/linux-cluster
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210924085104.44806-2-21cnbao@gmail.com
|
||
Valentin Schneider
|
620a6dc407 |
sched/topology: Make sched_init_numa() use a set for the deduplicating sort
The deduplicating sort in sched_init_numa() assumes that the first line in
the distance table contains all unique values in the entire table. I've
been trying to pen what this exactly means for the topology, but it's not
straightforward. For instance, topology.c uses this example:
node 0 1 2 3
0: 10 20 20 30
1: 20 10 20 20
2: 20 20 10 20
3: 30 20 20 10
0 ----- 1
| / |
| / |
| / |
2 ----- 3
Which works out just fine. However, if we swap nodes 0 and 1:
1 ----- 0
| / |
| / |
| / |
2 ----- 3
we get this distance table:
node 0 1 2 3
0: 10 20 20 20
1: 20 10 20 30
2: 20 20 10 20
3: 20 30 20 10
Which breaks the deduplicating sort (non-representative first line). In
this case this would just be a renumbering exercise, but it so happens that
we can have a deduplicating sort that goes through the whole table in O(n²)
at the extra cost of a temporary memory allocation (i.e. any form of set).
The ACPI spec (SLIT) mentions distances are encoded on 8 bits. Following
this, implement the set as a 256-bits bitmap. Should this not be
satisfactory (i.e. we want to support 32-bit values), then we'll have to go
for some other sparse set implementation.
This has the added benefit of letting us allocate just the right amount of
memory for sched_domains_numa_distance[], rather than an arbitrary
(nr_node_ids + 1).
Note: DT binding equivalent (distance-map) decodes distances as 32-bit
values.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210122123943.1217-2-valentin.schneider@arm.com
|
||
Srikar Dronamraju
|
3babbe447d |
sched/topology: Allow archs to override cpu_smt_mask
cpu_smt_mask tracks topology_sibling_cpumask. This would be good for most architectures. One of the users of cpu_smt_mask(), would be to identify idle-cores. On Power9, a pair of SMT4 cores can be presented by the firmware as a SMT8 core for backward compatibility reasons. powerpc allows LPARs to be live migrated from Power8 to Power9. Do note Power8 had only SMT8 cores. Existing software which has been developed/configured for Power8 would expect to see SMT8 core. Maintaining the illusion of SMT8 core is a requirement to make that work. In order to maintain above userspace backward compatibility with previous versions of processor, Power9 onwards there is option to the firmware to advertise a pair of SMT4 cores as a fused cores aka SMT8 core. On Power9 this pair shares the L2 cache as well. However, from the scheduler's point of view, a core should be determined by SMT4, since its a completely independent unit of compute. Hence allow powerpc architecture to override the default cpu_smt_mask() to point to the SMT4 cores in a SMT8 mode. This will ensure the scheduler is always given the right information. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200807074517.27957-1-srikar@linux.vnet.ibm.com |
||
Vlastimil Babka
|
667c790169 |
revert "topology: add support for node_to_mem_node() to determine the fallback node"
This reverts commit |
||
Linus Torvalds
|
7e67a85999 |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.
As perf and the scheduler is getting bigger and more complex,
document the status quo of current responsibilities and interests,
and spread the review pain^H^H^H^H fun via an increase in the Cc:
linecount generated by scripts/get_maintainer.pl. :-)
- Add another series of patches that brings the -rt (PREEMPT_RT) tree
closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
into a new CONFIG_PREEMPTION category that will allow the eventual
introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
to go though.
- Extend the CPU cgroup controller with uclamp.min and uclamp.max to
allow the finer shaping of CPU bandwidth usage.
- Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).
- Improve the behavior of high CPU count, high thread count
applications running under cpu.cfs_quota_us constraints.
- Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.
- Improve CPU isolation housekeeping CPU allocation NUMA locality.
- Fix deadline scheduler bandwidth calculations and logic when cpusets
rebuilds the topology, or when it gets deadline-throttled while it's
being offlined.
- Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
setscheduler() system calls without creating global serialization.
Add new synchronization between cpuset topology-changing events and
the deadline acceptance tests in setscheduler(), which were broken
before.
- Rework the active_mm state machine to be less confusing and more
optimal.
- Rework (simplify) the pick_next_task() slowpath.
- Improve load-balancing on AMD EPYC systems.
- ... and misc cleanups, smaller fixes and improvements - please see
the Git log for more details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
sched/psi: Correct overly pessimistic size calculation
sched/fair: Speed-up energy-aware wake-ups
sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
sched/uclamp: Update CPU's refcount on TG's clamp changes
sched/uclamp: Use TG's clamps to restrict TASK's clamps
sched/uclamp: Propagate system defaults to the root group
sched/uclamp: Propagate parent clamps
sched/uclamp: Extend CPU's cgroup controller
sched/topology: Improve load balancing on AMD EPYC systems
arch, ia64: Make NUMA select SMP
sched, perf: MAINTAINERS update, add submaintainers and reviewers
sched/fair: Use rq_lock/unlock in online_fair_sched_group
cpufreq: schedutil: fix equation in comment
sched: Rework pick_next_task() slow-path
sched: Allow put_prev_task() to drop rq->lock
sched/fair: Expose newidle_balance()
sched: Add task_struct pointer to sched_class::set_curr_task
sched: Rework CPU hotplug task selection
sched/{rt,deadline}: Fix set_next_task vs pick_next_task
sched: Fix kerneldoc comment for ia64_set_curr_task
...
|
||
Matt Fleming
|
a55c7454a8 |
sched/topology: Improve load balancing on AMD EPYC systems
SD_BALANCE_{FORK,EXEC} and SD_WAKE_AFFINE are stripped in sd_init()
for any sched domains with a NUMA distance greater than 2 hops
(RECLAIM_DISTANCE). The idea being that it's expensive to balance
across domains that far apart.
However, as is rather unfortunately explained in:
commit
|
||
Atish Patra
|
60c1b220d8 |
cpu-topology: Move cpu topology code to common code.
Both RISC-V & ARM64 are using cpu-map device tree to describe their cpu topology. It's better to move the relevant code to a common place instead of duplicate code. To: Will Deacon <will.deacon@arm.com> To: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Atish Patra <atish.patra@wdc.com> [Tested on QDF2400] Tested-by: Jeffrey Hugo <jhugo@codeaurora.org> [Tested on Juno and other embedded platforms.] Tested-by: Sudeep Holla <sudeep.holla@arm.com> Reviewed-by: Sudeep Holla <sudeep.holla@arm.com> Acked-by: Will Deacon <will.deacon@arm.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com> |
||
Len Brown
|
2e4c54dac7 |
topology: Create core_cpus and die_cpus sysfs attributes
Create CPU topology sysfs attributes: "core_cpus" and "core_cpus_list" These attributes represent all of the logical CPUs that share the same core. These attriutes is synonymous with the existing "thread_siblings" and "thread_siblings_list" attribute, which will be deprecated. Create CPU topology sysfs attributes: "die_cpus" and "die_cpus_list". These attributes represent all of the logical CPUs that share the same die. Suggested-by: Brice Goglin <Brice.Goglin@inria.fr> Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/071c23a298cd27ede6ed0b6460cae190d193364f.1557769318.git.len.brown@intel.com |
||
|
Len Brown
|
0e344d8c70 |
cpu/topology: Export die_id
Export die_id in cpu topology, for the benefit of hardware that has multiple-die/package. Signed-off-by: Len Brown <len.brown@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Ingo Molnar <mingo@kernel.org> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: linux-doc@vger.kernel.org Link: https://lkml.kernel.org/r/e7d1caaf4fbd24ee40db6d557ab28d7d83298900.1557769318.git.len.brown@intel.com |
||
Mel Gorman
|
a5f5f91da6 |
mm: convert zone_reclaim to node_reclaim
As reclaim is now per-node based, convert zone_reclaim to be node_reclaim. It is possible that a node will be reclaimed multiple times if it has multiple zones but this is unavoidable without caching all nodes traversed so far. The documentation and interface to userspace is the same from a configuration perspective and will will be similar in behaviour unless the node-local allocation requests were also limited to lower zones. Link: http://lkml.kernel.org/r/1467970510-21195-24-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@surriel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
Chris Metcalf
|
00d27c6336 |
numa: remove stale node_has_online_mem() define
This isn't used anywhere, so delete it.
Looks like the last usage (in x86-specific code) was removed by Tejun
in 2011 in commit
|
||
Bartosz Golaszewski
|
06931e6224 |
sched/topology: Rename topology_thread_cpumask() to topology_sibling_cpumask()
Rename topology_thread_cpumask() to topology_sibling_cpumask() for more consistency with scheduler code. Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Russell King <rmk+kernel@arm.linux.org.uk> Acked-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Benoit Cousson <bcousson@baylibre.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Guenter Roeck <linux@roeck-us.net> Cc: Jean Delvare <jdelvare@suse.de> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Russell King <linux@arm.linux.org.uk> Cc: Viresh Kumar <viresh.kumar@linaro.org> Link: http://lkml.kernel.org/r/1432645896-12588-2-git-send-email-bgolaszewski@baylibre.com Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
Joonsoo Kim
|
ad2c814441 |
topology: add support for node_to_mem_node() to determine the fallback node
Anton noticed (http://www.spinics.net/lists/linux-mm/msg67489.html) that
on ppc LPARs with memoryless nodes, a large amount of memory was consumed
by slabs and was marked unreclaimable. He tracked it down to slab
deactivations in the SLUB core when we allocate remotely, leading to poor
efficiency always when memoryless nodes are present.
After much discussion, Joonsoo provided a few patches that help
significantly. They don't resolve the problem altogether:
- memory hotplug still needs testing, that is when a memoryless node
becomes memory-ful, we want to dtrt
- there are other reasons for going off-node than memoryless nodes,
e.g., fully exhausted local nodes
Neither case is resolved with this series, but I don't think that should
block their acceptance, as they can be explored/resolved with follow-on
patches.
The series consists of:
[1/3] topology: add support for node_to_mem_node() to determine the
fallback node
[2/3] slub: fallback to node_to_mem_node() node if allocating on
memoryless node
- Joonsoo's patches to cache the nearest node with memory for each
NUMA node
[3/3] Partial revert of
|
||
Mel Gorman
|
4f9b16a647 |
mm: disable zone_reclaim_mode by default
When it was introduced, zone_reclaim_mode made sense as NUMA distances punished and workloads were generally partitioned to fit into a NUMA node. NUMA machines are now common but few of the workloads are NUMA-aware and it's routine to see major performance degradation due to zone_reclaim_mode being enabled but relatively few can identify the problem. Those that require zone_reclaim_mode are likely to be able to detect when it needs to be enabled and tune appropriately so lets have a sensible default for the bulk of users. This patch (of 2): zone_reclaim_mode causes processes to prefer reclaiming memory from local node instead of spilling over to other nodes. This made sense initially when NUMA machines were almost exclusively HPC and the workload was partitioned into nodes. The NUMA penalties were sufficiently high to justify reclaiming the memory. On current machines and workloads it is often the case that zone_reclaim_mode destroys performance but not all users know how to detect this. Favour the common case and disable it by default. Users that are sophisticated enough to know they need zone_reclaim_mode will detect it. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Michal Hocko <mhocko@suse.cz> Reviewed-by: Christoph Lameter <cl@linux.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
Vincent Guittot
|
143e1e28cb |
sched: Rework sched_domain topology definition
We replace the old way to configure the scheduler topology with a new method which enables a platform to declare additionnal level (if needed). We still have a default topology table definition that can be used by platform that don't want more level than the SMT, MC, CPU and NUMA ones. This table can be overwritten by an arch which either wants to add new level where a load balance make sense like BOOK or powergating level or wants to change the flags configuration of some levels. For each level, we need a function pointer that returns cpumask for each cpu, a function pointer that returns the flags for the level and a name. Only flags that describe topology, can be set by an architecture. The current topology flags are: SD_SHARE_CPUPOWER SD_SHARE_PKG_RESOURCES SD_NUMA SD_ASYM_PACKING Then, each level must be a subset on the next one. The build sequence of the sched_domain will take care of removing useless levels like those with 1 CPU and those with the same CPU span and no more relevant information for load balancing than its children. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Christoph Lameter <cl@linux.com> Cc: David S. Miller <davem@davemloft.net> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Hanjun Guo <hanjun.guo@linaro.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jason Low <jason.low2@hp.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: linux390@de.ibm.com Cc: linux-ia64@vger.kernel.org Cc: linux-s390@vger.kernel.org Link: http://lkml.kernel.org/r/1397209481-28542-2-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
Christoph Lameter
|
dc322a99d3 |
mm: use raw_cpu ops for determining current NUMA node
With the preempt checking logic for __this_cpu_ops we will get false positives from locations in the code that use numa_node_id. Before the __this_cpu ops where introduced there were no checks for preemption present either. smp_raw_processor_id() was used. See http://www.spinics.net/lists/linux-numa/msg00641.html Therefore we need to use raw_cpu_read here to avoid false postives. Note that this issue has been discussed in prior years. If the process changes nodes after retrieving the current numa node then that is acceptable since most uses of numa_node etc are for optimization and not for correctness. There were suggestions to implement a raw_numa_node_id in order to do preempt checks for numa_node_id as well. But I think we better defer that to another patch since that would mean investigating how numa_node_id() is used throughout the kernel which would increase the scope of this patchset significantly. After all preemption was never checked before when numa_node_id() was used. Some sample traces: __this_cpu_read operation in preemptible [00000000] code: login/1456 caller is __this_cpu_preempt_check+0x2b/0x2d CPU: 0 PID: 1456 Comm: login Not tainted 3.12.0-rc4-cl-00062-g2fe80d3-dirty #185 Call Trace: dump_stack+0x4e/0x82 check_preemption_disabled+0xc5/0xe0 __this_cpu_preempt_check+0x2b/0x2d get_task_policy+0x1d/0x49 get_vma_policy+0x14/0x76 alloc_pages_vma+0x35/0xff handle_mm_fault+0x290/0x73b __do_page_fault+0x3fe/0x44d do_page_fault+0x9/0xc page_fault+0x22/0x30 generic_file_aio_read+0x38e/0x624 do_sync_read+0x54/0x73 vfs_read+0x9d/0x12a SyS_read+0x47/0x7e cstar_dispatch+0x7/0x23 caller is __this_cpu_preempt_check+0x2b/0x2d CPU: 0 PID: 1456 Comm: login Not tainted 3.12.0-rc4-cl-00062-g2fe80d3-dirty #185 Call Trace: dump_stack+0x4e/0x82 check_preemption_disabled+0xc5/0xe0 __this_cpu_preempt_check+0x2b/0x2d alloc_pages_current+0x8f/0xbc __page_cache_alloc+0xb/0xd __do_page_cache_readahead+0xf4/0x219 ra_submit+0x1c/0x20 ondemand_readahead+0x28c/0x2b4 page_cache_sync_readahead+0x38/0x3a generic_file_aio_read+0x261/0x624 do_sync_read+0x54/0x73 vfs_read+0x9d/0x12a SyS_read+0x47/0x7e cstar_dispatch+0x7/0x23 Signed-off-by: Christoph Lameter <cl@linux.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Alex Shi <alex.shi@intel.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> |
||
Jason Low
|
f48627e686 |
sched/balancing: Periodically decay max cost of idle balance
This patch builds on patch 2 and periodically decays that max value to do idle balancing per sched domain by approximately 1% per second. Also decay the rq's max_idle_balance_cost value. Signed-off-by: Jason Low <jason.low2@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1379096813-3032-4-git-send-email-jason.low2@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
|
Jason Low
|
9bd721c55c |
sched/balancing: Consider max cost of idle balance per sched domain
In this patch, we keep track of the max cost we spend doing idle load balancing for each sched domain. If the avg time the CPU remains idle is less then the time we have already spent on idle balancing + the max cost of idle balancing in the sched domain, then we don't continue to attempt the balance. We also keep a per rq variable, max_idle_balance_cost, which keeps track of the max time spent on newidle load balances throughout all its domains so that we can determine the avg_idle's max value. By using the max, we avoid overrunning the average. This further reduces the chance we attempt balancing when the CPU is not idle for longer than the cost to balance. Signed-off-by: Jason Low <jason.low2@hp.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1379096813-3032-3-git-send-email-jason.low2@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org> |
||
Alex Shi
|
f03542a701 |
sched: recover SD_WAKE_AFFINE in select_task_rq_fair and code clean up
Since power saving code was removed from sched now, the implement code is out of service in this function, and even pollute other logical. like, 'want_sd' never has chance to be set '0', that remove the effect of SD_WAKE_AFFINE here. So, clean up the obsolete code, includes SD_PREFER_LOCAL. Signed-off-by: Alex Shi <alex.shi@intel.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/5028F431.6000306@intel.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de> |
||
|
Alex Shi
|
6956dc568f |
sched/numa: Add SD_PERFER_SIBLING to CPU domain
Commit
|
||
|
Linus Torvalds
|
d79ee93de9 |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler changes from Ingo Molnar: "The biggest change is the cleanup/simplification of the load-balancer: instead of the current practice of architectures twiddling scheduler internal data structures and providing the scheduler domains in colorfully inconsistent ways, we now have generic scheduler code in kernel/sched/core.c:sched_init_numa() that looks at the architecture's node_distance() parameters and (while not fully trusting it) deducts a NUMA topology from it. This inevitably changes balancing behavior - hopefully for the better. There are various smaller optimizations, cleanups and fixlets as well" * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: sched: Taint kernel with TAINT_WARN after sleep-in-atomic bug sched: Remove stale power aware scheduling remnants and dysfunctional knobs sched/debug: Fix printing large integers on 32-bit platforms sched/fair: Improve the ->group_imb logic sched/nohz: Fix rq->cpu_load[] calculations sched/numa: Don't scale the imbalance sched/fair: Revert sched-domain iteration breakage sched/x86: Rewrite set_cpu_sibling_map() sched/numa: Fix the new NUMA topology bits sched/numa: Rewrite the CONFIG_NUMA sched domain support sched/fair: Propagate 'struct lb_env' usage into find_busiest_group sched/fair: Add some serialization to the sched_domain load-balance walk sched/fair: Let minimally loaded cpu balance the group sched: Change rq->nr_running to unsigned int x86/numa: Check for nonsensical topologies on real hw as well x86/numa: Hard partition cpu topology masks on node boundaries x86/numa: Allow specifying node_distance() for numa=fake x86/sched: Make mwait_usable() heed to "idle=" kernel parameters properly sched: Update documentation and comments sched_rt: Avoid unnecessary dequeue and enqueue of pushable tasks in set_cpus_allowed_rt() |
||
Peter Zijlstra
|
8e7fbcbc22 |
sched: Remove stale power aware scheduling remnants and dysfunctional knobs
It's been broken forever (i.e. it's not scheduling in a power
aware fashion), as reported by Suresh and others sending
patches, and nobody cares enough to fix it properly ...
so remove it to make space free for something better.
There's various problems with the code as it stands today, first
and foremost the user interface which is bound to topology
levels and has multiple values per level. This results in a
state explosion which the administrator or distro needs to
master and almost nobody does.
Furthermore large configuration state spaces aren't good, it
means the thing doesn't just work right because it's either
under so many impossibe to meet constraints, or even if
there's an achievable state workloads have to be aware of
it precisely and can never meet it for dynamic workloads.
So pushing this kind of decision to user-space was a bad idea
even with a single knob - it's exponentially worse with knobs
on every node of the topology.
There is a proposal to replace the user interface with a single
3 state knob:
sched_balance_policy := { performance, power, auto }
where 'auto' would be the preferred default which looks at things
like Battery/AC mode and possible cpufreq state or whatever the hw
exposes to show us power use expectations - but there's been no
progress on it in the past many months.
Aside from that, the actual implementation of the various knobs
is known to be broken. There have been sporadic attempts at
fixing things but these always stop short of reaching a mergable
state.
Therefore this wholesale removal with the hopes of spurring
people who care to come forward once again and work on a
coherent replacement.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1326104915.2442.53.camel@twins
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
||
|
Alex Shi
|
c6ae41e7d4 |
x86: replace percpu_xxx funcs with this_cpu_xxx
Since percpu_xxx() serial functions are duplicated with this_cpu_xxx(). Removing percpu_xxx() definition and replacing them by this_cpu_xxx() in code. There is no function change in this patch, just preparation for later percpu_xxx serial function removing. On x86 machine the this_cpu_xxx() serial functions are same as __this_cpu_xxx() without no unnecessary premmpt enable/disable. Thanks for Stephen Rothwell, he found and fixed a i386 build error in the patch. Also thanks for Andrew Morton, he kept updating the patchset in Linus' tree. Signed-off-by: Alex Shi <alex.shi@intel.com> Acked-by: Christoph Lameter <cl@gentwo.org> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Tejun Heo <tj@kernel.org> |
||
Peter Zijlstra
|
cb83b629ba |
sched/numa: Rewrite the CONFIG_NUMA sched domain support
The current code groups up to 16 nodes in a level and then puts an ALLNODES domain spanning the entire tree on top of that. This doesn't reflect the numa topology and esp for the smaller not-fully-connected machines out there today this might make a difference. Therefore, build a proper numa topology based on node_distance(). Since there's no fixed numa layers anymore, the static SD_NODE_INIT and SD_ALLNODES_INIT aren't usable anymore, the new code tries to construct something similar and scales some values either on the number of cpus in the domain and/or the node_distance() ratio. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Anton Blanchard <anton@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: linux-alpha@vger.kernel.org Cc: linux-ia64@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-sh@vger.kernel.org Cc: Matt Turner <mattst88@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: sparclinux@vger.kernel.org Cc: Tony Luck <tony.luck@intel.com> Cc: x86@kernel.org Cc: Dimitri Sivanich <sivanich@sgi.com> Cc: Greg Pearson <greg.pearson@hp.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: bob.picco@oracle.com Cc: chris.mason@oracle.com Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Andrew Morton <akpm@linux-foundation.org> Link: http://lkml.kernel.org/n/tip-r74n3n8hhuc2ynbrnp3vt954@git.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org> |