find_new_ilb() returns nr_cpu_ids on failure - which is the usual
cpumask bitops return pattern, but is weird & unnecessary in this
context: not only is it a global variable, it it is a +1 out of
bounds CPU index and also has different signedness ...
Its only user, kick_ilb(), then checks the return against nr_cpu_ids
to decide to return. There's no other use.
So instead of this, use a standard -1 return on failure to find an
idle CPU, as the argument is signed already.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Link: https://lore.kernel.org/r/20231006102518.2452758-4-mingo@kernel.org
The old pick_eevdf() could fail to find the actual earliest eligible
deadline when it descended to the right looking for min_deadline, but
it turned out that that min_deadline wasn't actually eligible. In that
case we need to go back and search through any left branches we
skipped looking for the actual best _eligible_ min_deadline.
This is more expensive, but still O(log n), and at worst should only
involve descending two branches of the rbtree.
I've run this through a userspace stress test (thank you
tools/lib/rbtree.c), so hopefully this implementation doesn't miss any
corner cases.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/xm261qego72d.fsf_-_@google.com
Marek and Biju reported instances of:
"EEVDF scheduling fail, picking leftmost"
which Mike correlated with cgroup scheduling and the min_deadline heap
getting corrupted; some trace output confirms:
> And yeah, min_deadline is hosed somehow:
>
> validate_cfs_rq: --- /
> __print_se: ffff88845cf48080 w: 1024 ve: -58857638 lag: 870381 vd: -55861854 vmd: -66302085 E (11372/tr)
> __print_se: ffff88810d165800 w: 25 ve: -80323686 lag: 22336429 vd: -41496434 vmd: -66302085 E (-1//autogroup-31)
> __print_se: ffff888108379000 w: 25 ve: 0 lag: -57987257 vd: 114632828 vmd: 114632828 N (-1//autogroup-33)
> validate_cfs_rq: min_deadline: -55861854 avg_vruntime: -62278313462 / 1074 = -57987256
Turns out that reweight_entity(), which tries really hard to be fast,
does not do the normal dequeue+update+enqueue pattern but *does* scale
the deadline.
However, it then fails to propagate the updated deadline value up the
heap.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reported-by: Biju Das <biju.das.jz@bp.renesas.com>
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Biju Das <biju.das.jz@bp.renesas.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Link: https://lkml.kernel.org/r/20231006192445.GE743@noisy.programming.kicks-ass.net
The expectation is that placing a task at avg_vruntime() makes it
eligible. Turns out there is a corner case where this is not the case.
Specifically, avg_vruntime() relies on the fact that integer division
is a flooring function (eg. it discards the remainder). By this
property the value returned is slightly left of the true average.
However! when the average is a negative (relative to min_vruntime) the
effect is flipped and it becomes a ceil, with the result that the
returned value is just right of the average and thus not eligible.
Fixes: af4cf40470 ("sched/fair: Add cfs_rq::avg_vruntime")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tasks that never consume their full slice would not update their slice value.
This means that tasks that are spawned before the sysctl scaling keep their
original (UP) slice length.
Fixes: 147f3efaa2 ("sched/fair: Implement an EEVDF-like scheduling policy")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230915124822.847197830@noisy.programming.kicks-ass.net
It was useful to track feec() placement decision and debug the spare
capacity and optimization issues vs uclamp_max.
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230916232955.2099394-4-qyousef@layalina.io
find_energy_efficient_cpu() bails out early if effective util of the
task is 0 as the delta at this point will be zero and there's nothing
for EAS to do. When uclamp is being used, this could lead to wrong
decisions when uclamp_max is set to 0. In this case the task is capped
to performance point 0, but it is actually running and consuming energy
and we can benefit from EAS energy calculations.
Rework the condition so that it bails out when both util and uclamp_min
are 0.
We can do that without needing to use uclamp_task_util(); remove it.
Fixes: d81304bc61 ("sched/uclamp: Cater for uclamp in find_energy_efficient_cpu()'s early exit condition")
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230916232955.2099394-3-qyousef@layalina.io
When uclamp_max is being used, the util of the task could be higher than
the spare capacity of the CPU, but due to uclamp_max value we force-fit
it there.
The way the condition for checking for max_spare_cap in
find_energy_efficient_cpu() was constructed; it ignored any CPU that has
its spare_cap less than or _equal_ to max_spare_cap. Since we initialize
max_spare_cap to 0; this lead to never setting max_spare_cap_cpu and
hence ending up never performing compute_energy() for this cluster and
missing an opportunity for a better energy efficient placement to honour
uclamp_max setting.
max_spare_cap = 0;
cpu_cap = capacity_of(cpu) - cpu_util(p); // 0 if cpu_util(p) is high
...
util_fits_cpu(...); // will return true if uclamp_max forces it to fit
...
// this logic will fail to update max_spare_cap_cpu if cpu_cap is 0
if (cpu_cap > max_spare_cap) {
max_spare_cap = cpu_cap;
max_spare_cap_cpu = cpu;
}
prev_spare_cap suffers from a similar problem.
Fix the logic by converting the variables into long and treating -1
value as 'not populated' instead of 0 which is a viable and correct
spare capacity value. We need to be careful signed comparison is used
when comparing with cpu_cap in one of the conditions.
Fixes: 1d42509e47 ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230916232955.2099394-2-qyousef@layalina.io
We've observed the following warning being hit in
distribute_cfs_runtime():
SCHED_WARN_ON(cfs_rq->runtime_remaining > 0)
We have the following race:
- CPU 0: running bandwidth distribution (distribute_cfs_runtime).
Inspects the local cfs_rq and makes its runtime_remaining positive.
However, we defer unthrottling the local cfs_rq until after
considering all remote cfs_rq's.
- CPU 1: starts running bandwidth distribution from the slack timer. When
it finds the cfs_rq for CPU 0 on the throttled list, it observers the
that the cfs_rq is throttled, yet is not on the CSD list, and has a
positive runtime_remaining, thus triggering the warning in
distribute_cfs_runtime.
To fix this, we can rework the local unthrottling logic to put the local
cfs_rq on a local list, so that any future bandwidth distributions will
realize that the cfs_rq is about to be unthrottled.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230922230535.296350-2-joshdon@google.com
This makes the following patch cleaner by avoiding extra CONFIG_SMP
conditionals on the availability of rq->throttled_csd_list.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230922230535.296350-1-joshdon@google.com
The name is a bit opaque - make it clear that this is about wakeup
preemption.
Also rename the ->check_preempt_curr() methods similarly.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Other scheduling classes already postfix their similar methods
with the class name.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
When using sysbench to benchmark Postgres in a single docker instance
with sysbench's nr_threads set to nr_cpu, it is observed there are times
update_cfs_group() and update_load_avg() shows noticeable overhead on
a 2sockets/112core/224cpu Intel Sapphire Rapids(SPR):
13.75% 13.74% [kernel.vmlinux] [k] update_cfs_group
10.63% 10.04% [kernel.vmlinux] [k] update_load_avg
Annotate shows the cycles are mostly spent on accessing tg->load_avg
with update_load_avg() being the write side and update_cfs_group() being
the read side. tg->load_avg is per task group and when different tasks
of the same taskgroup running on different CPUs frequently access
tg->load_avg, it can be heavily contended.
E.g. when running postgres_sysbench on a 2sockets/112cores/224cpus Intel
Sappire Rapids, during a 5s window, the wakeup number is 14millions and
migration number is 11millions and with each migration, the task's load
will transfer from src cfs_rq to target cfs_rq and each change involves
an update to tg->load_avg. Since the workload can trigger as many wakeups
and migrations, the access(both read and write) to tg->load_avg can be
unbound. As a result, the two mentioned functions showed noticeable
overhead. With netperf/nr_client=nr_cpu/UDP_RR, the problem is worse:
during a 5s window, wakeup number is 21millions and migration number is
14millions; update_cfs_group() costs ~25% and update_load_avg() costs ~16%.
Reduce the overhead by limiting updates to tg->load_avg to at most once
per ms. The update frequency is a tradeoff between tracking accuracy and
overhead. 1ms is chosen because PELT window is roughly 1ms and it
delivered good results for the tests that I've done. After this change,
the cost of accessing tg->load_avg is greatly reduced and performance
improved. Detailed test results below.
==============================
postgres_sysbench on SPR:
25%
base: 42382±19.8%
patch: 50174±9.5% (noise)
50%
base: 67626±1.3%
patch: 67365±3.1% (noise)
75%
base: 100216±1.2%
patch: 112470±0.1% +12.2%
100%
base: 93671±0.4%
patch: 113563±0.2% +21.2%
==============================
hackbench on ICL:
group=1
base: 114912±5.2%
patch: 117857±2.5% (noise)
group=4
base: 359902±1.6%
patch: 361685±2.7% (noise)
group=8
base: 461070±0.8%
patch: 491713±0.3% +6.6%
group=16
base: 309032±5.0%
patch: 378337±1.3% +22.4%
=============================
hackbench on SPR:
group=1
base: 100768±2.9%
patch: 103134±2.9% (noise)
group=4
base: 413830±12.5%
patch: 378660±16.6% (noise)
group=8
base: 436124±0.6%
patch: 490787±3.2% +12.5%
group=16
base: 457730±3.2%
patch: 680452±1.3% +48.8%
============================
netperf/udp_rr on ICL
25%
base: 114413±0.1%
patch: 115111±0.0% +0.6%
50%
base: 86803±0.5%
patch: 86611±0.0% (noise)
75%
base: 35959±5.3%
patch: 49801±0.6% +38.5%
100%
base: 61951±6.4%
patch: 70224±0.8% +13.4%
===========================
netperf/udp_rr on SPR
25%
base: 104954±1.3%
patch: 107312±2.8% (noise)
50%
base: 55394±4.6%
patch: 54940±7.4% (noise)
75%
base: 13779±3.1%
patch: 36105±1.1% +162%
100%
base: 9703±3.7%
patch: 28011±0.2% +189%
==============================================
netperf/tcp_stream on ICL (all in noise range)
25%
base: 43092±0.1%
patch: 42891±0.5%
50%
base: 19278±14.9%
patch: 22369±7.2%
75%
base: 16822±3.0%
patch: 17086±2.3%
100%
base: 18216±0.6%
patch: 18078±2.9%
===============================================
netperf/tcp_stream on SPR (all in noise range)
25%
base: 34491±0.3%
patch: 34886±0.5%
50%
base: 19278±14.9%
patch: 22369±7.2%
75%
base: 16822±3.0%
patch: 17086±2.3%
100%
base: 18216±0.6%
patch: 18078±2.9%
Reported-by: Nitin Tekchandani <nitin.tekchandani@intel.com>
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: David Vernet <void@manifault.com>
Tested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Tested-by: Swapnil Sapkal <Swapnil.Sapkal@amd.com>
Link: https://lkml.kernel.org/r/20230912065808.2530-2-aaron.lu@intel.com
We don't need to maintain per-queue leaf_cfs_rq_list on !SMP, since
it's used for cfs_rq load tracking & balancing on SMP.
But sched debug interface uses it to print per-cfs_rq stats.
This patch fixes the !SMP version of cfs_rq_is_decayed(), so the
per-queue leaf_cfs_rq_list is also maintained correctly on !SMP,
to fix the warning in assert_list_leaf_cfs_rq().
Fixes: 0a00a35464 ("sched/fair: Delete useless condition in tg_unthrottle_up()")
Reported-by: Leo Yu-Chi Liang <ycliang@andestech.com>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Leo Yu-Chi Liang <ycliang@andestech.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Closes: https://lore.kernel.org/all/ZN87UsqkWcFLDxea@swlinux02/
Link: https://lore.kernel.org/r/20230913132031.2242151-1-chengming.zhou@linux.dev
task_numa_placement() searches for a nearest node to migrate by calling
for_each_node_state(). Now that we have numa_nearest_node(), switch to
using it.
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20230819141239.287290-3-yury.norov@gmail.com
For SMT4, any group with more than 2 tasks will be marked as
group_smt_balance. Retain the behaviour of group_has_spare by marking
the busiest group as the group which has the least number of idle_cpus.
Also, handle rounding effect of adding (ncores_local + ncores_busy) when
the local is fully idle and busy group imbalance is less than 2 tasks.
Local group should try to pull at least 1 task in this case so imbalance
should be set to 2 instead.
Fixes: fee1759e4f ("sched/fair: Determine active load balance for SMT sched groups")
Acked-by: Shrikanth Hegde <sshegde@linux.vnet.ibm.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: http://lkml.kernel.org/r/6cd1633036bb6b651af575c32c2a9608a106702c.camel@linux.intel.com
should_we_balance() is called in load_balance() to find out if the CPU that
is trying to do the load balance is the right one or not.
With commit:
b1bfeab9b002("sched/fair: Consider the idle state of the whole core for load balance")
the code tries to find an idle core to do the load balancing
and falls back on an idle sibling CPU if there is no idle core.
However, on larger SMT systems, it could be needlessly iterating to find a
idle by scanning all the CPUs in an non-idle core. If the core is not idle,
and first SMT sibling which is idle has been found, then its not needed to
check other SMT siblings for idleness
Lets say in SMT4, Core0 has 0,2,4,6 and CPU0 is BUSY and rest are IDLE.
balancing domain is MC/DIE. CPU2 will be set as the first idle_smt and
same process would be repeated for CPU4 and CPU6 but this is unnecessary.
Since calling is_core_idle loops through all CPU's in the SMT mask, effect
is multiplied by weight of smt_mask. For example,when say 1 CPU is busy,
we would skip loop for 2 CPU's and skip iterating over 8CPU's. That
effect would be more in DIE/NUMA domain where there are more cores.
Testing and performance evaluation
==================================
The test has been done on this system which has 12 cores, i.e 24 small
cores with SMT=4:
lscpu
Architecture: ppc64le
Byte Order: Little Endian
CPU(s): 96
On-line CPU(s) list: 0-95
Model name: POWER10 (architected), altivec supported
Thread(s) per core: 8
Used funclatency bcc tool to evaluate the time taken by should_we_balance(). For
base tip/sched/core the time taken is collected by making the
should_we_balance() noinline. time is in nanoseconds. The values are
collected by running the funclatency tracer for 60 seconds. values are
average of 3 such runs. This represents the expected reduced time with
patch.
tip/sched/core was at commit:
2f88c8e802 ("sched/eevdf/doc: Modify the documented knob to base_slice_ns as well")
Results:
------------------------------------------------------------------------------
workload tip/sched/core with_patch(%gain)
------------------------------------------------------------------------------
idle system 809.3 695.0(16.45)
stress ng – 12 threads -l 100 1013.5 893.1(13.49)
stress ng – 24 threads -l 100 1073.5 980.0(9.54)
stress ng – 48 threads -l 100 683.0 641.0(6.55)
stress ng – 96 threads -l 100 2421.0 2300(5.26)
stress ng – 96 threads -l 15 375.5 377.5(-0.53)
stress ng – 96 threads -l 25 635.5 637.5(-0.31)
stress ng – 96 threads -l 35 934.0 891.0(4.83)
Ran schbench(old), hackbench and stress_ng to evaluate the workload
performance between tip/sched/core and with patch.
No modification to tip/sched/core
TL;DR:
Good improvement is seen with schbench. when hackbench and stress_ng
runs for longer good improvement is seen.
------------------------------------------------------------------------------
schbench(old) tip +patch(%gain)
10 iterations sched/core
------------------------------------------------------------------------------
1 Threads
50.0th: 8.00 9.00(-12.50)
75.0th: 9.60 9.00(6.25)
90.0th: 11.80 10.20(13.56)
95.0th: 12.60 10.40(17.46)
99.0th: 13.60 11.90(12.50)
99.5th: 14.10 12.60(10.64)
99.9th: 15.90 14.60(8.18)
2 Threads
50.0th: 9.90 9.20(7.07)
75.0th: 12.60 10.10(19.84)
90.0th: 15.50 12.00(22.58)
95.0th: 17.70 14.00(20.90)
99.0th: 21.20 16.90(20.28)
99.5th: 22.60 17.50(22.57)
99.9th: 30.40 19.40(36.18)
4 Threads
50.0th: 12.50 10.60(15.20)
75.0th: 15.30 12.00(21.57)
90.0th: 18.60 14.10(24.19)
95.0th: 21.30 16.20(23.94)
99.0th: 26.00 20.70(20.38)
99.5th: 27.60 22.50(18.48)
99.9th: 33.90 31.40(7.37)
8 Threads
50.0th: 16.30 14.30(12.27)
75.0th: 20.20 17.40(13.86)
90.0th: 24.50 21.90(10.61)
95.0th: 27.30 24.70(9.52)
99.0th: 35.00 31.20(10.86)
99.5th: 46.40 33.30(28.23)
99.9th: 89.30 57.50(35.61)
16 Threads
50.0th: 22.70 20.70(8.81)
75.0th: 30.10 27.40(8.97)
90.0th: 36.00 32.80(8.89)
95.0th: 39.60 36.40(8.08)
99.0th: 49.20 44.10(10.37)
99.5th: 64.90 50.50(22.19)
99.9th: 143.50 100.60(29.90)
32 Threads
50.0th: 34.60 35.50(-2.60)
75.0th: 48.20 50.50(-4.77)
90.0th: 59.20 62.40(-5.41)
95.0th: 65.20 69.00(-5.83)
99.0th: 80.40 83.80(-4.23)
99.5th: 102.10 98.90(3.13)
99.9th: 727.10 506.80(30.30)
schbench does improve in general. There is some run to run variation with
schbench. Did a validation run to confirm that trend is similar.
------------------------------------------------------------------------------
hackbench tip +patch(%gain)
20 iterations, 50000 loops sched/core
------------------------------------------------------------------------------
Process 10 groups : 11.74 11.70(0.34)
Process 20 groups : 22.73 22.69(0.18)
Process 30 groups : 33.39 33.40(-0.03)
Process 40 groups : 43.73 43.61(0.27)
Process 50 groups : 53.82 54.35(-0.98)
Process 60 groups : 64.16 65.29(-1.76)
thread 10 Time : 12.81 12.79(0.16)
thread 20 Time : 24.63 24.47(0.65)
Process(Pipe) 10 Time : 6.40 6.34(0.94)
Process(Pipe) 20 Time : 10.62 10.63(-0.09)
Process(Pipe) 30 Time : 15.09 14.84(1.66)
Process(Pipe) 40 Time : 19.42 19.01(2.11)
Process(Pipe) 50 Time : 24.04 23.34(2.91)
Process(Pipe) 60 Time : 28.94 27.51(4.94)
thread(Pipe) 10 Time : 6.96 6.87(1.29)
thread(Pipe) 20 Time : 11.74 11.73(0.09)
hackbench shows slight improvement with pipe. Slight degradation in process.
------------------------------------------------------------------------------
stress_ng tip +patch(%gain)
10 iterations 100000 cpu_ops sched/core
------------------------------------------------------------------------------
--cpu=96 -util=100 Time taken : 5.30, 5.01(5.47)
--cpu=48 -util=100 Time taken : 7.94, 6.73(15.24)
--cpu=24 -util=100 Time taken : 11.67, 8.75(25.02)
--cpu=12 -util=100 Time taken : 15.71, 15.02(4.39)
--cpu=96 -util=10 Time taken : 22.71, 22.19(2.29)
--cpu=96 -util=20 Time taken : 12.14, 12.37(-1.89)
--cpu=96 -util=30 Time taken : 8.76, 8.86(-1.14)
--cpu=96 -util=40 Time taken : 7.13, 7.14(-0.14)
--cpu=96 -util=50 Time taken : 6.10, 6.13(-0.49)
--cpu=96 -util=60 Time taken : 5.42, 5.41(0.18)
--cpu=96 -util=70 Time taken : 4.94, 4.94(0.00)
--cpu=96 -util=80 Time taken : 4.56, 4.53(0.66)
--cpu=96 -util=90 Time taken : 4.27, 4.26(0.23)
Good improvement seen with 24 CPUs. In this case only one CPU is busy,
and no core is idle. Decent improvement with 100% utilization case. no
difference in other utilization.
Fixes: b1bfeab9b0 ("sched/fair: Consider the idle state of the whole core for load balance")
Signed-off-by: Shrikanth Hegde <sshegde@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230902081204.232218-1-sshegde@linux.vnet.ibm.com
The following commit deserves special mention:
22dc02f81c Revert "sched/fair: Move unused stub functions to header"
This is in x86/cleanups, because the revert is a re-application of a
number of cleanups that got removed inadvertedly.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=kiAA
-----END PGP SIGNATURE-----
Merge tag 'x86-cleanups-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull misc x86 cleanups from Ingo Molnar:
"The following commit deserves special mention:
22dc02f81c Revert "sched/fair: Move unused stub functions to header"
This is in x86/cleanups, because the revert is a re-application of a
number of cleanups that got removed inadvertedly"
[ This also effectively undoes the amd_check_microcode() microcode
declaration change I had done in my microcode loader merge in commit
42a7f6e3ff ("Merge tag 'x86_microcode_for_v6.6_rc1' [...]").
I picked the declaration change by Arnd from this branch instead,
which put it in <asm/processor.h> instead of <asm/microcode.h> like I
had done in my merge resolution - Linus ]
* tag 'x86-cleanups-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/platform/uv: Refactor code using deprecated strncpy() interface to use strscpy()
x86/hpet: Refactor code using deprecated strncpy() interface to use strscpy()
x86/platform/uv: Refactor code using deprecated strcpy()/strncpy() interfaces to use strscpy()
x86/qspinlock-paravirt: Fix missing-prototype warning
x86/paravirt: Silence unused native_pv_lock_init() function warning
x86/alternative: Add a __alt_reloc_selftest() prototype
x86/purgatory: Include header for warn() declaration
x86/asm: Avoid unneeded __div64_32 function definition
Revert "sched/fair: Move unused stub functions to header"
x86/apic: Hide unused safe_smp_processor_id() on 32-bit UP
x86/cpu: Fix amd_check_microcode() declaration
- The biggest change is introduction of a new iteration of the
SCHED_FAIR interactivity code: the EEVDF ("Earliest Eligible Virtual
Deadline First") scheduler.
EEVDF too is a virtual-time scheduler, with two parameters (weight
and relative deadline), compared to CFS that had weight only.
It completely reworks the base scheduler: placement, preemption,
picking -- everything.
LWN.net, as usual, has a terrific writeup about EEVDF:
https://lwn.net/Articles/925371/
Preemption (both tick and wakeup) is driven by testing against
a fresh pick. Because the tree is now effectively an interval
tree, and the selection is no longer the 'leftmost' task,
over-scheduling is less of a problem. A lot of the CFS
heuristics are removed or replaced by more natural latency-space
parameters & constructs.
In terms of expected performance regressions: we'll and can fix
everything where a 'good' workload misbehaves with the new scheduler,
but EEVDF inevitably changes workload scheduling in a binary fashion,
hopefully for the better in the overwhelming majority of cases,
but in some cases it won't, especially in adversarial loads that
got lucky with the previous code, such as some variants of hackbench.
We are trying hard to err on the side of fixing all performance
regressions, but we expect some inevitable post-release iterations
of that process.
- Improve load-balancing on hybrid x86 systems: enable cluster
scheduling (again).
- Improve & fix bandwidth-scheduling on nohz systems.
- Improve bandwidth-throttling.
- Use lock guards to simplify and de-goto-ify control flow.
- Misc improvements, cleanups and fixes.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----
iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmTtDOgRHG1pbmdvQGtl
cm5lbC5vcmcACgkQEnMQ0APhK1iS4g//b9yewVW9OPxetKoN8zIJA0TjFYuuOVHK
BlCJi5dbzXeCTrtENI65BRA7kPbTQ3AjwLRQ2BallAZ4dJceK0RhlZJvcrMNsm4e
Adcpoch/FbqPKCrtAJQY04Ln1B244n/KyVifYett9220dMgTFQGJJYxrTc2G2+Kp
F44vdUHzRczIE+KeOgBild1CwfKv5Zn5xgaXgtuoPLZtWBE0C1fSSzbK/PTINcUx
bS4NVxK0CpOqSiNjnugV8KsYb71/0U6IgShBVjfHsrlBYigOH2NbVTH5xyjF8f83
WxiGstlhxj+N6Kv4L6FOJIAr2BIggH82j3FaPACmv4c8pzEoBBbvlAJkfinLEgbn
Povg3OF2t6uZ8NoHjeu3WxOjBsphbpkFz7H5nno1ibXSIR/JyUH5MdBPSx93QITB
QoUKQpr/L8zWauWDOEzSaJjEsZbl8rkcIVq5Bk0bR3qn2xkZsIeVte+vCEu3+tBc
b4JOZjq7AuPDqPnsBLvuyiFZ7zwsAfm+pOD5UF3/zbLjPn1N/7wTNQZ29zjc04jl
SifpCZGgF1KlG8m8wNTlSfVvq0ksppCzJt+C6VFuejZ191IGpirQHn4Vp0sluMhC
WRzXhb7v37Bq5JY10GMfeKb/jAiRs68kozhzqVPsBSAPS6I6jJssONgedq+LbQdC
tFsmE9n09do=
=XtCD
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- The biggest change is introduction of a new iteration of the
SCHED_FAIR interactivity code: the EEVDF ("Earliest Eligible Virtual
Deadline First") scheduler
EEVDF too is a virtual-time scheduler, with two parameters (weight
and relative deadline), compared to CFS that had weight only. It
completely reworks the base scheduler: placement, preemption, picking
-- everything
LWN.net, as usual, has a terrific writeup about EEVDF:
https://lwn.net/Articles/925371/
Preemption (both tick and wakeup) is driven by testing against a
fresh pick. Because the tree is now effectively an interval tree, and
the selection is no longer the 'leftmost' task, over-scheduling is
less of a problem. A lot of the CFS heuristics are removed or
replaced by more natural latency-space parameters & constructs
In terms of expected performance regressions: we will and can fix
everything where a 'good' workload misbehaves with the new scheduler,
but EEVDF inevitably changes workload scheduling in a binary fashion,
hopefully for the better in the overwhelming majority of cases, but
in some cases it won't, especially in adversarial loads that got
lucky with the previous code, such as some variants of hackbench. We
are trying hard to err on the side of fixing all performance
regressions, but we expect some inevitable post-release iterations of
that process
- Improve load-balancing on hybrid x86 systems: enable cluster
scheduling (again)
- Improve & fix bandwidth-scheduling on nohz systems
- Improve bandwidth-throttling
- Use lock guards to simplify and de-goto-ify control flow
- Misc improvements, cleanups and fixes
* tag 'sched-core-2023-08-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
sched/eevdf/doc: Modify the documented knob to base_slice_ns as well
sched/eevdf: Curb wakeup-preemption
sched: Simplify sched_core_cpu_{starting,deactivate}()
sched: Simplify try_steal_cookie()
sched: Simplify sched_tick_remote()
sched: Simplify sched_exec()
sched: Simplify ttwu()
sched: Simplify wake_up_if_idle()
sched: Simplify: migrate_swap_stop()
sched: Simplify sysctl_sched_uclamp_handler()
sched: Simplify get_nohz_timer_target()
sched/rt: sysctl_sched_rr_timeslice show default timeslice after reset
sched/rt: Fix sysctl_sched_rr_timeslice intial value
sched/fair: Block nohz tick_stop when cfs bandwidth in use
sched, cgroup: Restore meaning to hierarchical_quota
MAINTAINERS: Add Peter explicitly to the psi section
sched/psi: Select KERNFS as needed
sched/topology: Align group flags when removing degenerate domain
sched/fair: remove util_est boosting
sched/fair: Propagate enqueue flags into place_entity()
...
Mike and others noticed that EEVDF does like to over-schedule quite a
bit -- which does hurt performance of a number of benchmarks /
workloads.
In particular, what seems to cause over-scheduling is that when lag is
of the same order (or larger) than the request / slice then placement
will not only cause the task to be placed left of current, but also
with a smaller deadline than current, which causes immediate
preemption.
[ notably, lag bounds are relative to HZ ]
Mike suggested we stick to picking 'current' for as long as it's
eligible to run, giving it uninterrupted runtime until it reaches
parity with the pack.
Augment Mike's suggestion by only allowing it to exhaust it's initial
request.
One random data point:
echo NO_RUN_TO_PARITY > /debug/sched/features
perf stat -a -e context-switches --repeat 10 -- perf bench sched messaging -g 20 -t -l 5000
3,723,554 context-switches ( +- 0.56% )
9.5136 +- 0.0394 seconds time elapsed ( +- 0.41% )
echo RUN_TO_PARITY > /debug/sched/features
perf stat -a -e context-switches --repeat 10 -- perf bench sched messaging -g 20 -t -l 5000
2,556,535 context-switches ( +- 0.51% )
9.2427 +- 0.0302 seconds time elapsed ( +- 0.33% )
Suggested-by: Mike Galbraith <umgwanakikbuti@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230816134059.GC982867@hirez.programming.kicks-ass.net
Pick up the EEVDF work into the main branch - it's looking good so far.
Conflicts:
kernel/sched/features.h
Signed-off-by: Ingo Molnar <mingo@kernel.org>
CFS bandwidth limits and NOHZ full don't play well together. Tasks
can easily run well past their quotas before a remote tick does
accounting. This leads to long, multi-period stalls before such
tasks can run again. Currently, when presented with these conflicting
requirements the scheduler is favoring nohz_full and letting the tick
be stopped. However, nohz tick stopping is already best-effort, there
are a number of conditions that can prevent it, whereas cfs runtime
bandwidth is expected to be enforced.
Make the scheduler favor bandwidth over stopping the tick by setting
TICK_DEP_BIT_SCHED when the only running task is a cfs task with
runtime limit enabled. We use cfs_b->hierarchical_quota to
determine if the task requires the tick.
Add check in pick_next_task_fair() as well since that is where
we have a handle on the task that is actually going to be running.
Add check in sched_can_stop_tick() to cover some edge cases such
as nr_running going from 2->1 and the 1 remains the running task.
Reviewed-By: Ben Segall <bsegall@google.com>
Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230712133357.381137-3-pauld@redhat.com
In cgroupv2 cfs_b->hierarchical_quota is set to -1 for all task
groups due to the previous fix simply taking the min. It should
reflect a limit imposed at that level or by an ancestor. Even
though cgroupv2 does not require child quota to be less than or
equal to that of its ancestors the task group will still be
constrained by such a quota so this should be shown here. Cgroupv1
continues to set this correctly.
In both cases, add initialization when a new task group is created
based on the current parent's value (or RUNTIME_INF in the case of
root_task_group). Otherwise, the field is wrong until a quota is
changed after creation and __cfs_schedulable() is called.
Fixes: c53593e5cb ("sched, cgroup: Don't reject lower cpu.max on ancestors")
Signed-off-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230714125746.812891-1-pauld@redhat.com
Revert commit 7aa55f2a59 ("sched/fair: Move unused stub functions to
header"), for while it has the right Changelog, the actual patch
content a revert of the previous 4 patches:
f7df852ad6 ("sched: Make task_vruntime_update() prototype visible")
c0bdfd72fb ("sched/fair: Hide unused init_cfs_bandwidth() stub")
378be384e0 ("sched: Add schedule_user() declaration")
d55ebae3f3 ("sched: Hide unused sched_update_scaling()")
So in effect this is a revert of a revert and re-applies those
patches.
Fixes: 7aa55f2a59 ("sched/fair: Move unused stub functions to header")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
There is no need to use runnable_avg when estimating util_est and that
even generates wrong behavior because one includes blocked tasks whereas
the other one doesn't. This can lead to accounting twice the waking task p,
once with the blocked runnable_avg and another one when adding its
util_est.
cpu's runnable_avg is already used when computing util_avg which is then
compared with util_est.
In some situation, feec will not select prev_cpu but another one on the
same performance domain because of higher max_util
Fixes: 7d0583cf9e ("sched/fair, cpufreq: Introduce 'runnable boosting'")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20230706135144.324311-1-vincent.guittot@linaro.org
EEVDF uses this tunable as the base request/slice -- make sure the
name reflects this.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124604.205287511@infradead.org
EEVDF is a better defined scheduling policy, as a result it has less
heuristics/tunables. There is no compelling reason to keep CFS around.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124604.137187212@infradead.org
Using lag is both more correct and simpler when moving between
runqueues.
Notable, min_vruntime() was invented as a cheap approximation of
avg_vruntime() for this very purpose (SMP migration). Since we now
have the real thing; use it.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124604.068911180@infradead.org
Removes the FAIR_SLEEPERS code in favour of the new LAG based
placement.
Specifically, the whole FAIR_SLEEPER thing was a very crude
approximation to make up for the lack of lag based placement,
specifically the 'service owed' part. This is important for things
like 'starve' and 'hackbench'.
One side effect of FAIR_SLEEPER is that it caused 'small' unfairness,
specifically, by always ignoring up-to 'thresh' sleeptime it would
have a 50%/50% time distribution for a 50% sleeper vs a 100% runner,
while strictly speaking this should (of course) result in a 33%/67%
split (as CFS will also do if the sleep period exceeds 'thresh').
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124604.000198861@infradead.org
Where CFS is currently a WFQ based scheduler with only a single knob,
the weight. The addition of a second, latency oriented parameter,
makes something like WF2Q or EEVDF based a much better fit.
Specifically, EEVDF does EDF like scheduling in the left half of the
tree -- those entities that are owed service. Except because this is a
virtual time scheduler, the deadlines are in virtual time as well,
which is what allows over-subscription.
EEVDF has two parameters:
- weight, or time-slope: which is mapped to nice just as before
- request size, or slice length: which is used to compute
the virtual deadline as: vd_i = ve_i + r_i/w_i
Basically, by setting a smaller slice, the deadline will be earlier
and the task will be more eligible and ran earlier.
Tick driven preemption is driven by request/slice completion; while
wakeup preemption is driven by the deadline.
Because the tree is now effectively an interval tree, and the
selection is no longer 'leftmost', over-scheduling is less of a
problem.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124603.931005524@infradead.org
With the introduction of avg_vruntime, it is possible to approximate
lag (the entire purpose of introducing it in fact). Use this to do lag
based placement over sleep+wake.
Specifically, the FAIR_SLEEPERS thing places things too far to the
left and messes up the deadline aspect of EEVDF.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124603.794929315@infradead.org
With the introduction of avg_vruntime() there is no need to use worse
approximations. Take the 0-lag point as starting point for inserting
new tasks.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124603.722361178@infradead.org
In order to move to an eligibility based scheduling policy, we need
to have a better approximation of the ideal scheduler.
Specifically, for a virtual time weighted fair queueing based
scheduler the ideal scheduler will be the weighted average of the
individual virtual runtimes (math in the comment).
As such, compute the weighted average to approximate the ideal
scheduler -- note that the approximation is in the individual task
behaviour, which isn't strictly conformant.
Specifically consider adding a task with a vruntime left of center, in
this case the average will move backwards in time -- something the
ideal scheduler would of course never do.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20230531124603.654144274@infradead.org
Add WF_CURRENT_CPU wake flag that advices the scheduler to
move the wakee to the current CPU. This is useful for fast on-CPU
context switching use cases.
In addition, make ttwu external rather than static so that
the flag could be passed to it from outside of sched/core.c.
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Andrei Vagin <avagin@google.com>
Acked-by: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230308073201.3102738-3-avagin@google.com
Signed-off-by: Kees Cook <keescook@chromium.org>
select_idle_capacity() not only looks for an idle cpu that fits for the
waking task but also for cpu with highest bandwidth when no cpu fits.
Start the loop with target cpu so it will be selected 1st when no cpu fits
but several cpus shared the same bandwidth. Starting with target cpu
prevents the task to migrate between cpus with same bandwidth at every
wakeup when no cpu fits.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230711081359.868862-1-vincent.guittot@linaro.org
should_we_balance() traverses the group_balance_mask (AND'ed with lb_env::
cpus) starting from lower numbered CPUs looking for the first idle CPU.
In hybrid x86 systems, the siblings of SMT cores get CPU numbers, before
non-SMT cores:
[0, 1] [2, 3] [4, 5] 6 7 8 9
b i b i b i b i i i
In the figure above, CPUs in brackets are siblings of an SMT core. The
rest are non-SMT cores. 'b' indicates a busy CPU, 'i' indicates an
idle CPU.
We should let a CPU on a fully idle core get the first chance to idle
load balance as it has more CPU capacity than a CPU on an idle SMT
CPU with busy sibling. So for the figure above, if we are running
should_we_balance() to CPU 1, we should return false to let CPU 7 on
idle core to have a chance first to idle load balance.
A partially busy (i.e., of type group_has_spare) local group with SMT
cores will often have only one SMT sibling busy. If the destination CPU
is a non-SMT core, partially busy, lower-numbered, SMT cores should not
be considered when finding the first idle CPU.
However, in should_we_balance(), when we encounter idle SMT first in partially
busy core, we prematurely break the search for the first idle CPU.
Higher-numbered, non-SMT cores is not given the chance to have
idle balance done on their behalf. Those CPUs will only be considered
for idle balancing by chance via CPU_NEWLY_IDLE.
Instead, consider the idle state of the whole SMT core.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Co-developed-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/807bdd05331378ea3bf5956bda87ded1036ba769.1688770494.git.tim.c.chen@linux.intel.com
In the current prefer sibling load balancing code, there is an implicit
assumption that the busiest sched group and local sched group are
equivalent, hence the tasks to be moved is simply the difference in
number of tasks between the two groups (i.e. imbalance) divided by two.
However, we may have different number of cores between the cluster groups,
say when we take CPU offline or we have hybrid groups. In that case,
we should balance between the two groups such that #tasks/#cores ratio
is the same between the same between both groups. Hence the imbalance
computed will need to reflect this.
Adjust the sibling imbalance computation to take into account of the
above considerations.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/4eacbaa236e680687dae2958378a6173654113df.1688770494.git.tim.c.chen@linux.intel.com
On hybrid CPUs with scheduling cluster enabled, we will need to
consider balancing between SMT CPU cluster, and Atom core cluster.
Below shows such a hybrid x86 CPU with 4 big cores and 8 atom cores.
Each scheduling cluster span a L2 cache.
--L2-- --L2-- --L2-- --L2-- ----L2---- -----L2------
[0, 1] [2, 3] [4, 5] [5, 6] [7 8 9 10] [11 12 13 14]
Big Big Big Big Atom Atom
core core core core Module Module
If the busiest group is a big core with both SMT CPUs busy, we should
active load balance if destination group has idle CPU cores. Such
condition is considered by asym_active_balance() in load balancing but not
considered when looking for busiest group and computing load imbalance.
Add this consideration in find_busiest_group() and calculate_imbalance().
In addition, update the logic determining the busier group when one group
is SMT and the other group is non SMT but both groups are partially busy
with idle CPU. The busier group should be the group with idle cores rather
than the group with one busy SMT CPU. We do not want to make the SMT group
the busiest one to pull the only task off SMT CPU and causing the whole core to
go empty.
Otherwise suppose in the search for the busiest group, we first encounter
an SMT group with 1 task and set it as the busiest. The destination
group is an atom cluster with 1 task and we next encounter an atom
cluster group with 3 tasks, we will not pick this atom cluster over the
SMT group, even though we should. As a result, we do not load balance
the busier Atom cluster (with 3 tasks) towards the local atom cluster
(with 1 task). And it doesn't make sense to pick the 1 task SMT group
as the busier group as we also should not pull task off the SMT towards
the 1 task atom cluster and make the SMT core completely empty.
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/e24f35d142308790f69be65930b82794ef6658a2.1688770494.git.tim.c.chen@linux.intel.com
We currently export the total throttled time for cgroups that are given
a bandwidth limit. This patch extends this accounting to also account
the total time that each children cgroup has been throttled.
This is useful to understand the degree to which children have been
affected by the throttling control. Children which are not runnable
during the entire throttled period, for example, will not show any
self-throttling time during this period.
Expose this in a new interface, 'cpu.stat.local', which is similar to
how non-hierarchical events are accounted in 'memory.events.local'.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230620183247.737942-2-joshdon@google.com
It is easy for a cfs_rq to become throttled even when it has no enqueued
entities (for example, if we have just put_prev()'d the last runnable
task of the cfs_rq, and the cfs_rq is out of quota).
Avoid accounting this time towards total throttle time, since it
otherwise falsely inflates the stats.
Note that the dequeue path is special, since we normally disallow
migrations when a task is in a throttled hierarchy (see
throttled_lb_pair()).
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230620183247.737942-1-joshdon@google.com
When checking whether a recently used CPU can be a potential idle
candidate, recent_used_cpu should be used to test p->cpus_ptr as
p->recent_used_cpu is not equal to recent_used_cpu and candidate
decision is made based on recent_used_cpu here.
Fixes: 89aafd67f2 ("sched/fair: Use prev instead of new target as recent_used_cpu")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20230620080747.359122-1-linmiaohe@huawei.com
After commit 8ad075c2eb ("sched: Async unthrottling for cfs
bandwidth"), we may update the rq clock multiple times in the loop of
__cfsb_csd_unthrottle().
A prior (although less common) instance of this problem exists in
unthrottle_offline_cfs_rqs().
Cure both by ensuring update_rq_clock() is called before the loop and
setting RQCF_ACT_SKIP during the loop, to supress further updates.
The alternative would be pulling update_rq_clock() out of
unthrottle_cfs_rq(), but that gives an even bigger mess.
Fixes: 8ad075c2eb ("sched: Async unthrottling for cfs bandwidth")
Reviewed-By: Ben Segall <bsegall@google.com>
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20230613082012.49615-4-jiahao.os@bytedance.com
cppcheck reports
kernel/sched/fair.c:7436:17: style: Local variable 'cpu_util' shadows outer function [shadowFunction]
unsigned long cpu_util;
^
Clean this up by renaming the variable to eff_util
Signed-off-by: Tom Rix <trix@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20230611122535.183654-1-trix@redhat.com
The responsiveness of the Per Entity Load Tracking (PELT) util_avg in
mobile devices is still considered too low for utilization changes
during task ramp-up.
In Android this manifests in the fact that the first frames of a UI
activity are very prone to be jankframes (a frame which doesn't meet
the required frame rendering time, e.g. 16ms@60Hz) since the CPU
frequency is normally low at this point and has to ramp up quickly.
The beginning of an UI activity is also characterized by the occurrence
of CPU contention, especially on little CPUs. Current little CPUs can
have an original CPU capacity of only ~ 150 which means that the actual
CPU capacity at lower frequency can even be much smaller.
Schedutil maps CPU util_avg into CPU frequency request via:
util = effective_cpu_util(..., cpu_util_cfs(cpu), ...) ->
util = map_util_perf(util) -> freq = map_util_freq(util, ...)
CPU contention for CFS tasks can be detected by 'CPU runnable > CPU
utililization' in cpu_util_cfs_boost() -> cpu_util(..., boost = 1).
Schedutil uses 'runnable boosting' by calling cpu_util_cfs_boost().
To be in sync with schedutil's CPU frequency selection, Energy Aware
Scheduling (EAS) also calls cpu_util(..., boost = 1) during max util
detection.
Moreover, 'runnable boosting' is also used in load-balance for busiest
CPU selection when the migration type is 'migrate_util', i.e. only at
sched domains which don't have the SD_SHARE_PKG_RESOURCES flag set.
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230515115735.296329-3-dietmar.eggemann@arm.com
There is a lot of code duplication in cpu_util_next() & cpu_util_cfs().
Remove this by allowing cpu_util_next() to be called with p = NULL.
Rename cpu_util_next() to cpu_util() since the '_next' suffix is no
longer necessary to distinct cpu utilization related functions.
Implement cpu_util_cfs(cpu) as cpu_util(cpu, p = NULL, -1).
This will allow to code future related cpu util changes only in one
place, namely in cpu_util().
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230515115735.296329-2-dietmar.eggemann@arm.com
We've run into the case that the balancer tries to balance a migration
disabled task and trigger the warning in set_task_cpu() like below:
------------[ cut here ]------------
WARNING: CPU: 7 PID: 0 at kernel/sched/core.c:3115 set_task_cpu+0x188/0x240
Modules linked in: hclgevf xt_CHECKSUM ipt_REJECT nf_reject_ipv4 <...snip>
CPU: 7 PID: 0 Comm: swapper/7 Kdump: loaded Tainted: G O 6.1.0-rc4+ #1
Hardware name: Huawei TaiShan 2280 V2/BC82AMDC, BIOS 2280-V2 CS V5.B221.01 12/09/2021
pstate: 604000c9 (nZCv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : set_task_cpu+0x188/0x240
lr : load_balance+0x5d0/0xc60
sp : ffff80000803bc70
x29: ffff80000803bc70 x28: ffff004089e190e8 x27: ffff004089e19040
x26: ffff007effcabc38 x25: 0000000000000000 x24: 0000000000000001
x23: ffff80000803be84 x22: 000000000000000c x21: ffffb093e79e2a78
x20: 000000000000000c x19: ffff004089e19040 x18: 0000000000000000
x17: 0000000000001fad x16: 0000000000000030 x15: 0000000000000000
x14: 0000000000000003 x13: 0000000000000000 x12: 0000000000000000
x11: 0000000000000001 x10: 0000000000000400 x9 : ffffb093e4cee530
x8 : 00000000fffffffe x7 : 0000000000ce168a x6 : 000000000000013e
x5 : 00000000ffffffe1 x4 : 0000000000000001 x3 : 0000000000000b2a
x2 : 0000000000000b2a x1 : ffffb093e6d6c510 x0 : 0000000000000001
Call trace:
set_task_cpu+0x188/0x240
load_balance+0x5d0/0xc60
rebalance_domains+0x26c/0x380
_nohz_idle_balance.isra.0+0x1e0/0x370
run_rebalance_domains+0x6c/0x80
__do_softirq+0x128/0x3d8
____do_softirq+0x18/0x24
call_on_irq_stack+0x2c/0x38
do_softirq_own_stack+0x24/0x3c
__irq_exit_rcu+0xcc/0xf4
irq_exit_rcu+0x18/0x24
el1_interrupt+0x4c/0xe4
el1h_64_irq_handler+0x18/0x2c
el1h_64_irq+0x74/0x78
arch_cpu_idle+0x18/0x4c
default_idle_call+0x58/0x194
do_idle+0x244/0x2b0
cpu_startup_entry+0x30/0x3c
secondary_start_kernel+0x14c/0x190
__secondary_switched+0xb0/0xb4
---[ end trace 0000000000000000 ]---
Further investigation shows that the warning is superfluous, the migration
disabled task is just going to be migrated to its current running CPU.
This is because that on load balance if the dst_cpu is not allowed by the
task, we'll re-select a new_dst_cpu as a candidate. If no task can be
balanced to dst_cpu we'll try to balance the task to the new_dst_cpu
instead. In this case when the migration disabled task is not on CPU it
only allows to run on its current CPU, load balance will select its
current CPU as new_dst_cpu and later triggers the warning above.
The new_dst_cpu is chosen from the env->dst_grpmask. Currently it
contains CPUs in sched_group_span() and if we have overlapped groups it's
possible to run into this case. This patch makes env->dst_grpmask of
group_balance_mask() which exclude any CPUs from the busiest group and
solve the issue. For balancing in a domain with no overlapped groups
the behaviour keeps same as before.
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230530082507.10444-1-yangyicong@huawei.com
These four functions have a normal definition for CONFIG_FAIR_GROUP_SCHED,
and empty one that is only referenced when FAIR_GROUP_SCHED is disabled
but CGROUP_SCHED is still enabled. If both are turned off, the functions
are still defined but the misisng prototype causes a W=1 warning:
kernel/sched/fair.c:12544:6: error: no previous prototype for 'free_fair_sched_group'
kernel/sched/fair.c:12546:5: error: no previous prototype for 'alloc_fair_sched_group'
kernel/sched/fair.c:12553:6: error: no previous prototype for 'online_fair_sched_group'
kernel/sched/fair.c:12555:6: error: no previous prototype for 'unregister_fair_sched_group'
Move the alternatives into the header as static inline functions with
the correct combination of #ifdef checks to avoid the warning without
adding even more complexity.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230522195021.3456768-6-arnd@kernel.org
init_cfs_bandwidth() is only used when CONFIG_FAIR_GROUP_SCHED is
enabled, and without this causes a W=1 warning for the missing prototype:
kernel/sched/fair.c:6131:6: error: no previous prototype for 'init_cfs_bandwidth'
The normal implementation is only defined for CONFIG_CFS_BANDWIDTH,
so the stub exists when CFS_BANDWIDTH is disabled but FAIR_GROUP_SCHED
is enabled.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230522195021.3456768-4-arnd@kernel.org
This function is only used when CONFIG_SMP is enabled, without that there
is no caller and no prototype:
kernel/sched/fair.c:688:5: error: no previous prototype for 'sched_update_scaling' [-Werror=missing-prototypes
Hide the definition in the same #ifdef check as the declaration.
Fixes: 8a99b6833c ("sched: Move SCHED_DEBUG sysctl to debugfs")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230522195021.3456768-2-arnd@kernel.org
Now that find_busiest_group() triggers load balancing between a fully_
busy SMT2 core and an idle non-SMT core, it is no longer needed to force
balancing via asym_packing. Use asym_packing only as intended: when there
is high-priority CPU that is idle.
After this change, the same logic apply to SMT and non-SMT local groups.
It makes less sense having a separate function to deal specifically with
SMT. Fold the logic in asym_smt_can_pull_tasks() into sched_asym().
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-8-ricardo.neri-calderon@linux.intel.com
The prefer_sibling setting acts on the busiest group to move excess tasks
to the local group. This should be done as per request of the child of the
busiest group's sched domain, not the local group's.
Using the flags of the child domain of the local group works fortuitously
if both groups have child domains.
There are cases, however, in which the busiest group's sched domain has
child but the local group's does not. Consider, for instance a non-SMT
core (or an SMT core with only one online sibling) doing load balance with
an SMT core at the MC level. SD_PREFER_SIBLING of the busiest group's child
domain will not be honored. We are left with a fully busy SMT core and an
idle non-SMT core.
Suggested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-7-ricardo.neri-calderon@linux.intel.com
When comparing two fully_busy scheduling groups, keep the current busiest
group if it represents an SMT core. Tasks in such scheduling group share
CPU resources and need more help than tasks in a non-SMT fully_busy group.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-6-ricardo.neri-calderon@linux.intel.com
Using asym_packing priorities within an SMT core is straightforward. Just
follow the priorities that hardware indicates.
When balancing load from an SMT core, also consider the idle state of its
siblings. Priorities do not reflect that an SMT core divides its throughput
among all its busy siblings. They only makes sense when exactly one sibling
is busy.
Indicate that active balance is needed if the destination CPU has lower
priority than the source CPU but the latter has busy SMT siblings.
Make find_busiest_queue() not skip higher-priority SMT cores with more than
busy sibling.
Suggested-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-5-ricardo.neri-calderon@linux.intel.com
Callers of asym_smt_can_pull_tasks() check the idle state of the
destination CPU and its SMT siblings, if any. No extra checks are needed
in such function.
Since SMT cores divide capacity among its siblings, priorities only really
make sense if only one sibling is active. This is true for SMT2, SMT4,
SMT8, etc. Do not use asym_packing load balance for this case. Instead,
let find_busiest_group() handle imbalances.
When balancing non-SMT cores or at higher scheduling domains (e.g.,
between MC scheduling groups), continue using priorities.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Len Brown <len.brown@intel.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-4-ricardo.neri-calderon@linux.intel.com
When balancing load between cores, all the SMT siblings of the destination
CPU, if any, must be idle. Otherwise, pulling new tasks degrades the
throughput of the busy SMT siblings. The overall throughput of the system
remains the same.
When balancing load within an SMT core this consideration is not relevant.
Follow the priorities that hardware indicates.
Suggested-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-3-ricardo.neri-calderon@linux.intel.com
asym_packing needs this function to determine whether an SMT core is a
suitable destination for load balancing.
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20230406203148.19182-2-ricardo.neri-calderon@linux.intel.com
- Allow unprivileged PSI poll()ing
- Fix performance regression introduced by mm_cid
- Improve livepatch stalls by adding livepatch task switching to cond_resched(),
this resolves livepatching busy-loop stalls with certain CPU-bound kthreads.
- Improve sched_move_task() performance on autogroup configs.
- On core-scheduling CPUs, avoid selecting throttled tasks to run
- Misc cleanups, fixes and improvements.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=Hgci
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Allow unprivileged PSI poll()ing
- Fix performance regression introduced by mm_cid
- Improve livepatch stalls by adding livepatch task switching to
cond_resched(). This resolves livepatching busy-loop stalls with
certain CPU-bound kthreads
- Improve sched_move_task() performance on autogroup configs
- On core-scheduling CPUs, avoid selecting throttled tasks to run
- Misc cleanups, fixes and improvements
* tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/clock: Fix local_clock() before sched_clock_init()
sched/rt: Fix bad task migration for rt tasks
sched: Fix performance regression introduced by mm_cid
sched/core: Make sched_dynamic_mutex static
sched/psi: Allow unprivileged polling of N*2s period
sched/psi: Extract update_triggers side effect
sched/psi: Rename existing poll members in preparation
sched/psi: Rearrange polling code in preparation
sched/fair: Fix inaccurate tally of ttwu_move_affine
vhost: Fix livepatch timeouts in vhost_worker()
livepatch,sched: Add livepatch task switching to cond_resched()
livepatch: Skip task_call_func() for current task
livepatch: Convert stack entries array to percpu
sched: Interleave cfs bandwidth timers for improved single thread performance at low utilization
sched/core: Reduce cost of sched_move_task when config autogroup
sched/core: Avoid selecting the task that is throttled to run when core-sched enable
sched/topology: Make sched_energy_mutex,update static
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page().
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive rather
than exclusive, and has fixed a bunch of errors which were caused by its
unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCZEr3zQAKCRDdBJ7gKXxA
jlLoAP0fpQBipwFxED0Us4SKQfupV6z4caXNJGPeay7Aj11/kQD/aMRC2uPfgr96
eMG3kwn2pqkB9ST2QpkaRbxA//eMbQY=
=J+Dj
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
switching from a user process to a kernel thread.
- More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
Raghav.
- zsmalloc performance improvements from Sergey Senozhatsky.
- Yue Zhao has found and fixed some data race issues around the
alteration of memcg userspace tunables.
- VFS rationalizations from Christoph Hellwig:
- removal of most of the callers of write_one_page()
- make __filemap_get_folio()'s return value more useful
- Luis Chamberlain has changed tmpfs so it no longer requires swap
backing. Use `mount -o noswap'.
- Qi Zheng has made the slab shrinkers operate locklessly, providing
some scalability benefits.
- Keith Busch has improved dmapool's performance, making part of its
operations O(1) rather than O(n).
- Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
permitting userspace to wr-protect anon memory unpopulated ptes.
- Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
rather than exclusive, and has fixed a bunch of errors which were
caused by its unintuitive meaning.
- Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
which causes minor faults to install a write-protected pte.
- Vlastimil Babka has done some maintenance work on vma_merge():
cleanups to the kernel code and improvements to our userspace test
harness.
- Cleanups to do_fault_around() by Lorenzo Stoakes.
- Mike Rapoport has moved a lot of initialization code out of various
mm/ files and into mm/mm_init.c.
- Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
DRM, but DRM doesn't use it any more.
- Lorenzo has also coverted read_kcore() and vread() to use iterators
and has thereby removed the use of bounce buffers in some cases.
- Lorenzo has also contributed further cleanups of vma_merge().
- Chaitanya Prakash provides some fixes to the mmap selftesting code.
- Matthew Wilcox changes xfs and afs so they no longer take sleeping
locks in ->map_page(), a step towards RCUification of pagefaults.
- Suren Baghdasaryan has improved mmap_lock scalability by switching to
per-VMA locking.
- Frederic Weisbecker has reworked the percpu cache draining so that it
no longer causes latency glitches on cpu isolated workloads.
- Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
logic.
- Liu Shixin has changed zswap's initialization so we no longer waste a
chunk of memory if zswap is not being used.
- Yosry Ahmed has improved the performance of memcg statistics
flushing.
- David Stevens has fixed several issues involving khugepaged,
userfaultfd and shmem.
- Christoph Hellwig has provided some cleanup work to zram's IO-related
code paths.
- David Hildenbrand has fixed up some issues in the selftest code's
testing of our pte state changing.
- Pankaj Raghav has made page_endio() unneeded and has removed it.
- Peter Xu contributed some rationalizations of the userfaultfd
selftests.
- Yosry Ahmed has fixed an issue around memcg's page recalim
accounting.
- Chaitanya Prakash has fixed some arm-related issues in the
selftests/mm code.
- Longlong Xia has improved the way in which KSM handles hwpoisoned
pages.
- Peter Xu fixes a few issues with uffd-wp at fork() time.
- Stefan Roesch has changed KSM so that it may now be used on a
per-process and per-cgroup basis.
* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
shmem: restrict noswap option to initial user namespace
mm/khugepaged: fix conflicting mods to collapse_file()
sparse: remove unnecessary 0 values from rc
mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
maple_tree: fix allocation in mas_sparse_area()
mm: do not increment pgfault stats when page fault handler retries
zsmalloc: allow only one active pool compaction context
selftests/mm: add new selftests for KSM
mm: add new KSM process and sysfs knobs
mm: add new api to enable ksm per process
mm: shrinkers: fix debugfs file permissions
mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
migrate_pages_batch: fix statistics for longterm pin retry
userfaultfd: use helper function range_in_vma()
lib/show_mem.c: use for_each_populated_zone() simplify code
mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
fs/buffer: convert create_page_buffers to folio_create_buffers
fs/buffer: add folio_create_empty_buffers helper
...
When local group is fully busy but its average load is above system load,
computing the imbalance will overflow and local group is not the best
target for pulling this load.
Fixes: 0b0695f2b3 ("sched/fair: Rework load_balance()")
Reported-by: Tingjia Cao <tjcao980311@gmail.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Tingjia Cao <tjcao980311@gmail.com>
Link: https://lore.kernel.org/lkml/CABcWv9_DAhVBOq2=W=2ypKE9dKM5s2DvoV8-U0+GDwwuKZ89jQ@mail.gmail.com/T/
before: last 6 bits of PID is used as index to store information about
tasks accessing VMA's.
after: hash_32 is used to take of cases where tasks are created over a
period of time, and thus improve collision probability.
Result:
The patch series overall improves autonuma cost.
Kernbench around more than 5% improvement and system time in mmtest
autonuma showed more than 80% improvement
Link: https://lkml.kernel.org/r/d5a9f75513300caed74e5c8570bba9317b963c2b.1677672277.git.raghavendra.kt@amd.com
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Cc: Bharata B Rao <bharata@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This helps to ensure that only recently accessed PIDs scan the VMAs.
Current implementation: (idea supported by PeterZ)
1. Accessing PID information is maintained in two windows.
access_pids[1] being newest.
2. Reset old access PID info i.e. access_pid[0] every (4 *
sysctl_numa_balancing_scan_delay) interval after initial scan delay
period expires.
The above interval seemed to be experimentally optimum since it avoids
frequent reset of access info as well as helps clearing the old access
info regularly. The reset logic is implemented in scan path.
Link: https://lkml.kernel.org/r/f7a675f66d1442d048b4216b2baf94515012c405.1677672277.git.raghavendra.kt@amd.com
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Suggested-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Bharata B Rao <bharata@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
During Numa scanning make sure only relevant vmas of the tasks are
scanned.
Before:
All the tasks of a process participate in scanning the vma even if they
do not access vma in it's lifespan.
Now:
Except cases of first few unconditional scans, if a process do
not touch vma (exluding false positive cases of PID collisions)
tasks no longer scan all vma
Logic used:
1) 6 bits of PID used to mark active bit in vma numab status during
fault to remember PIDs accessing vma. (Thanks Mel)
2) Subsequently in scan path, vma scanning is skipped if current PID
had not accessed vma.
3) First two times we do allow unconditional scan to preserve earlier
behaviour of scanning.
Acknowledgement to Bharata B Rao <bharata@amd.com> for initial patch to
store pid information and Peter Zijlstra <peterz@infradead.org> (Usage of
test and set bit)
Link: https://lkml.kernel.org/r/092f03105c7c1d3450f4636b1ea350407f07640e.1677672277.git.raghavendra.kt@amd.com
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Suggested-by: Mel Gorman <mgorman@techsingularity.net>
Cc: David Hildenbrand <david@redhat.com>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pach series "sched/numa: Enhance vma scanning", v3.
The patchset proposes one of the enhancements to numa vma scanning
suggested by Mel. This is continuation of [3].
Reposting the rebased patchset to akpm mm-unstable tree (March 1)
Existing mechanism of scan period involves, scan period derived from
per-thread stats. Process Adaptive autoNUMA [1] proposed to gather NUMA
fault stats at per-process level to capture aplication behaviour better.
During that course of discussion, Mel proposed several ideas to enhance
current numa balancing. One of the suggestion was below
Track what threads access a VMA. The suggestion was to use an unsigned
long pid_mask and use the lower bits to tag approximately what threads
access a VMA. Skip VMAs that did not trap a fault. This would be
approximate because of PID collisions but would reduce scanning of areas
the thread is not interested in. The above suggestion intends not to
penalize threads that has no interest in the vma, thus reduce scanning
overhead.
V3 changes are mostly based on PeterZ comments (details below in changes)
Summary of patchset:
Current patchset implements:
1. Delay the vma scanning logic for newly created VMA's so that
additional overhead of scanning is not incurred for short lived tasks
(implementation by Mel)
2. Store the information of tasks accessing VMA in 2 windows. It is
regularly cleared in (4*sysctl_numa_balancing_scan_delay) interval.
The above time is derived from experimenting (Suggested by PeterZ) to
balance between frequent clearing vs obsolete access data
3. hash_32 used to encode task index accessing VMA information
4. VMA's acess information is used to skip scanning for the tasks
which had not accessed VMA
Changes since V2:
patch1:
- Renaming of structure, macro to function,
- Add explanation to heuristics
- Adding more details from result (PeterZ)
Patch2:
- Usage of test and set bit (PeterZ)
- Move storing access PID info to numa_migrate_prep()
- Add a note on fainess among tasks allowed to scan
(PeterZ)
Patch3:
- Maintain two windows of access PID information
(PeterZ supported implementation and Gave idea to extend
to N if needed)
Patch4:
- Apply hash_32 function to track VMA accessing PIDs (PeterZ)
Changes since RFC V1:
- Include Mel's vma scan delay patch
- Change the accessing pid store logic (Thanks Mel)
- Fencing structure / code to NUMA_BALANCING (David, Mel)
- Adding clearing access PID logic (Mel)
- Descriptive change log ( Mike Rapoport)
Things to ponder over:
==========================================
- Improvement to clearing accessing PIDs logic (discussed in-detail in
patch3 itself (Done in this patchset by implementing 2 window history)
- Current scan period is not changed in the patchset, so we do see
frequent tries to scan. Relaxing scan period dynamically could improve
results further.
[1] sched/numa: Process Adaptive autoNUMA
Link: https://lore.kernel.org/lkml/20220128052851.17162-1-bharata@amd.com/T/
[2] RFC V1 Link:
https://lore.kernel.org/all/cover.1673610485.git.raghavendra.kt@amd.com/
[3] V2 Link:
https://lore.kernel.org/lkml/cover.1675159422.git.raghavendra.kt@amd.com/
Results:
Summary: Huge autonuma cost reduction seen in mmtest. Kernbench improvement
is more than 5% and huge system time (80%+) improvement from mmtest autonuma.
(dbench had huge std deviation to post)
kernbench
===========
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Amean user-256 22002.51 ( 0.00%) 22649.95 * -2.94%*
Amean syst-256 10162.78 ( 0.00%) 8214.13 * 19.17%*
Amean elsp-256 160.74 ( 0.00%) 156.92 * 2.38%*
Duration User 66017.43 67959.84
Duration System 30503.15 24657.03
Duration Elapsed 504.61 493.12
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Ops NUMA alloc hit 1738835089.00 1738780310.00
Ops NUMA alloc local 1738834448.00 1738779711.00
Ops NUMA base-page range updates 477310.00 392566.00
Ops NUMA PTE updates 477310.00 392566.00
Ops NUMA hint faults 96817.00 87555.00
Ops NUMA hint local faults % 10150.00 2192.00
Ops NUMA hint local percent 10.48 2.50
Ops NUMA pages migrated 86660.00 85363.00
Ops AutoNUMA cost 489.07 442.14
autonumabench
===============
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Amean syst-NUMA01 399.50 ( 0.00%) 52.05 * 86.97%*
Amean syst-NUMA01_THREADLOCAL 0.21 ( 0.00%) 0.22 * -5.41%*
Amean syst-NUMA02 0.80 ( 0.00%) 0.78 * 2.68%*
Amean syst-NUMA02_SMT 0.65 ( 0.00%) 0.68 * -3.95%*
Amean elsp-NUMA01 313.26 ( 0.00%) 313.11 * 0.05%*
Amean elsp-NUMA01_THREADLOCAL 1.06 ( 0.00%) 1.08 * -1.76%*
Amean elsp-NUMA02 3.19 ( 0.00%) 3.24 * -1.52%*
Amean elsp-NUMA02_SMT 3.72 ( 0.00%) 3.61 * 2.92%*
Duration User 396433.47 324835.96
Duration System 2808.70 376.66
Duration Elapsed 2258.61 2258.12
6.2.0-mmunstable-base 6.2.0-mmunstable-patched
Ops NUMA alloc hit 59921806.00 49623489.00
Ops NUMA alloc miss 0.00 0.00
Ops NUMA interleave hit 0.00 0.00
Ops NUMA alloc local 59920880.00 49622594.00
Ops NUMA base-page range updates 152259275.00 50075.00
Ops NUMA PTE updates 152259275.00 50075.00
Ops NUMA PMD updates 0.00 0.00
Ops NUMA hint faults 154660352.00 39014.00
Ops NUMA hint local faults % 138550501.00 23139.00
Ops NUMA hint local percent 89.58 59.31
Ops NUMA pages migrated 8179067.00 14147.00
Ops AutoNUMA cost 774522.98 195.69
This patch (of 4):
Currently whenever a new task is created we wait for
sysctl_numa_balancing_scan_delay to avoid unnessary scanning overhead.
Extend the same logic to new or very short-lived VMAs.
[raghavendra.kt@amd.com: add initialization in vm_area_dup())]
Link: https://lkml.kernel.org/r/cover.1677672277.git.raghavendra.kt@amd.com
Link: https://lkml.kernel.org/r/7a6fbba87c8b51e67efd3e74285bb4cb311a16ca.1677672277.git.raghavendra.kt@amd.com
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Disha Talreja <dishaa.talreja@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
There are scenarios where non-affine wakeups are incorrectly counted as
affine wakeups by schedstats.
When wake_affine_idle() returns prev_cpu which doesn't equal to
nr_cpumask_bits, it will slip through the check: target == nr_cpumask_bits
in wake_affine() and be counted as if target == this_cpu in schedstats.
Replace target == nr_cpumask_bits with target != this_cpu to make sure
affine wakeups are accurately tallied.
Fixes: 806486c377 (sched/fair: Do not migrate if the prev_cpu is idle)
Suggested-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Libo Chen <libo.chen@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Gautham R. Shenoy <gautham.shenoy@amd.com>
Link: https://lore.kernel.org/r/20220810223313.386614-1-libo.chen@oracle.com
CPU cfs bandwidth controller uses hrtimer. Currently there is no initial
value set. Hence all period timers would align at expiry.
This happens when there are multiple CPU cgroup's.
There is a performance gain that can be achieved here if the timers are
interleaved when the utilization of each CPU cgroup is low and total
utilization of all the CPU cgroup's is less than 50%. If the timers are
interleaved, then the unthrottled cgroup can run freely without many
context switches and can also benefit from SMT Folding. This effect will
be further amplified in SPLPAR environment.
This commit adds a random offset after initializing each hrtimer. This
would result in interleaving the timers at expiry, which helps in achieving
the said performance gain.
This was tested on powerpc platform with 8 core SMT=8. Socket power was
measured when the workload. Benchmarked the stress-ng with power
information. Throughput oriented benchmarks show significant gain up to
25% while power consumption increases up to 15%.
Workload: stress-ng --cpu=32 --cpu-ops=50000.
1CG - 1 cgroup is running.
2CG - 2 cgroups are running together.
Time taken to complete stress-ng in seconds and power is in watts.
each cgroup is throttled at 25% with 100ms as the period value.
6.2-rc6 | with patch
8 core 1CG power 2CG power | 1CG power 2 CG power
27.5 80.6 40 90 | 27.3 82 32.3 104
27.5 81 40.2 91 | 27.5 81 38.7 96
27.7 80 40.1 89 | 27.6 80 29.7 106
27.7 80.1 40.3 94 | 27.6 80 31.5 105
Latency might be affected by this change. That could happen if the CPU was
in a deep idle state which is possible if we interleave the timers. Used
schbench for measuring the latency. Each cgroup is throttled at 25% with
period value is set to 100ms. Numbers are when both the cgroups are
running simultaneously. Latency values don't degrade much. Some
improvement is seen in tail latencies.
6.2-rc6 with patch
Groups: 16
50.0th: 39.5 42.5
75.0th: 924.0 922.0
90.0th: 972.0 968.0
95.0th: 1005.5 994.0
99.0th: 4166.0 2287.0
99.5th: 7314.0 7448.0
99.9th: 15024.0 13600.0
Groups: 32
50.0th: 819.0 463.0
75.0th: 1596.0 918.0
90.0th: 5992.0 1281.5
95.0th: 13184.0 2765.0
99.0th: 21792.0 14240.0
99.5th: 25696.0 18920.0
99.9th: 33280.0 35776.0
Groups: 64
50.0th: 4806.0 3440.0
75.0th: 31136.0 33664.0
90.0th: 54144.0 58752.0
95.0th: 66176.0 67200.0
99.0th: 84736.0 91520.0
99.5th: 97408.0 114048.0
99.9th: 136448.0 140032.0
Initial RFC PATCH, discussions and details on the problem:
Link1: https://lore.kernel.org/lkml/5ae3cb09-8c9a-11e8-75a7-cc774d9bc283@linux.vnet.ibm.com/
Link2: https://lore.kernel.org/lkml/9c57c92c-3e0c-b8c5-4be9-8f4df344a347@linux.vnet.ibm.com/
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Shrikanth Hegde<sshegde@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230223185153.1499710-1-sshegde@linux.vnet.ibm.com
When {rt, cfs}_rq or dl task is throttled, since cookied tasks
are not dequeued from the core tree, So sched_core_find() and
sched_core_next() may return throttled task, which may
cause throttled task to run on the CPU.
So we add checks in sched_core_find() and sched_core_next()
to make sure that the return is a runnable task that is
not throttled.
Co-developed-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Signed-off-by: Cruz Zhao <CruzZhao@linux.alibaba.com>
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230316081806.69544-1-jiahao.os@bytedance.com
Commit 829c1651e9 ("sched/fair: sanitize vruntime of entity being placed")
fixes an overflowing bug, but ignore a case that se->exec_start is reset
after a migration.
For fixing this case, we delay the reset of se->exec_start after
placing the entity which se->exec_start to detect long sleeping task.
In order to take into account a possible divergence between the clock_task
of 2 rqs, we increase the threshold to around 104 days.
Fixes: 829c1651e9 ("sched/fair: sanitize vruntime of entity being placed")
Originally-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Zhang Qiao <zhangqiao22@huawei.com>
Link: https://lore.kernel.org/r/20230317160810.107988-1-vincent.guittot@linaro.org
F_SEAL_EXEC") which permits the setting of the memfd execute bit at
memfd creation time, with the option of sealing the state of the X bit.
- Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
thread-safe for pmd unshare") which addresses a rare race condition
related to PMD unsharing.
- Several folioification patch serieses from Matthew Wilcox, Vishal
Moola, Sidhartha Kumar and Lorenzo Stoakes
- Johannes Weiner has a series ("mm: push down lock_page_memcg()") which
does perform some memcg maintenance and cleanup work.
- SeongJae Park has added DAMOS filtering to DAMON, with the series
"mm/damon/core: implement damos filter". These filters provide users
with finer-grained control over DAMOS's actions. SeongJae has also done
some DAMON cleanup work.
- Kairui Song adds a series ("Clean up and fixes for swap").
- Vernon Yang contributed the series "Clean up and refinement for maple
tree".
- Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
adds to MGLRU an LRU of memcgs, to improve the scalability of global
reclaim.
- David Hildenbrand has added some userfaultfd cleanup work in the
series "mm: uffd-wp + change_protection() cleanups".
- Christoph Hellwig has removed the generic_writepages() library
function in the series "remove generic_writepages".
- Baolin Wang has performed some maintenance on the compaction code in
his series "Some small improvements for compaction".
- Sidhartha Kumar is doing some maintenance work on struct page in his
series "Get rid of tail page fields".
- David Hildenbrand contributed some cleanup, bugfixing and
generalization of pte management and of pte debugging in his series "mm:
support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap
PTEs".
- Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
flag in the series "Discard __GFP_ATOMIC".
- Sergey Senozhatsky has improved zsmalloc's memory utilization with his
series "zsmalloc: make zspage chain size configurable".
- Joey Gouly has added prctl() support for prohibiting the creation of
writeable+executable mappings. The previous BPF-based approach had
shortcomings. See "mm: In-kernel support for memory-deny-write-execute
(MDWE)".
- Waiman Long did some kmemleak cleanup and bugfixing in the series
"mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".
- T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
"mm: multi-gen LRU: improve".
- Jiaqi Yan has provided some enhancements to our memory error
statistics reporting, mainly by presenting the statistics on a per-node
basis. See the series "Introduce per NUMA node memory error
statistics".
- Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
regression in compaction via his series "Fix excessive CPU usage during
compaction".
- Christoph Hellwig does some vmalloc maintenance work in the series
"cleanup vfree and vunmap".
- Christoph Hellwig has removed block_device_operations.rw_page() in ths
series "remove ->rw_page".
- We get some maple_tree improvements and cleanups in Liam Howlett's
series "VMA tree type safety and remove __vma_adjust()".
- Suren Baghdasaryan has done some work on the maintainability of our
vm_flags handling in the series "introduce vm_flags modifier functions".
- Some pagemap cleanup and generalization work in Mike Rapoport's series
"mm, arch: add generic implementation of pfn_valid() for FLATMEM" and
"fixups for generic implementation of pfn_valid()"
- Baoquan He has done some work to make /proc/vmallocinfo and
/proc/kcore better represent the real state of things in his series
"mm/vmalloc.c: allow vread() to read out vm_map_ram areas".
- Jason Gunthorpe rationalized the GUP system's interface to the rest of
the kernel in the series "Simplify the external interface for GUP".
- SeongJae Park wishes to migrate people from DAMON's debugfs interface
over to its sysfs interface. To support this, we'll temporarily be
printing warnings when people use the debugfs interface. See the series
"mm/damon: deprecate DAMON debugfs interface".
- Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
and clean-ups" series.
- Huang Ying has provided a dramatic reduction in migration's TLB flush
IPI rates with the series "migrate_pages(): batch TLB flushing".
- Arnd Bergmann has some objtool fixups in "objtool warning fixes".
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY/PoPQAKCRDdBJ7gKXxA
jlvpAPsFECUBBl20qSue2zCYWnHC7Yk4q9ytTkPB/MMDrFEN9wD/SNKEm2UoK6/K
DmxHkn0LAitGgJRS/W9w81yrgig9tAQ=
=MlGs
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
F_SEAL_EXEC") which permits the setting of the memfd execute bit at
memfd creation time, with the option of sealing the state of the X
bit.
- Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset()
thread-safe for pmd unshare") which addresses a rare race condition
related to PMD unsharing.
- Several folioification patch serieses from Matthew Wilcox, Vishal
Moola, Sidhartha Kumar and Lorenzo Stoakes
- Johannes Weiner has a series ("mm: push down lock_page_memcg()")
which does perform some memcg maintenance and cleanup work.
- SeongJae Park has added DAMOS filtering to DAMON, with the series
"mm/damon/core: implement damos filter".
These filters provide users with finer-grained control over DAMOS's
actions. SeongJae has also done some DAMON cleanup work.
- Kairui Song adds a series ("Clean up and fixes for swap").
- Vernon Yang contributed the series "Clean up and refinement for maple
tree".
- Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It
adds to MGLRU an LRU of memcgs, to improve the scalability of global
reclaim.
- David Hildenbrand has added some userfaultfd cleanup work in the
series "mm: uffd-wp + change_protection() cleanups".
- Christoph Hellwig has removed the generic_writepages() library
function in the series "remove generic_writepages".
- Baolin Wang has performed some maintenance on the compaction code in
his series "Some small improvements for compaction".
- Sidhartha Kumar is doing some maintenance work on struct page in his
series "Get rid of tail page fields".
- David Hildenbrand contributed some cleanup, bugfixing and
generalization of pte management and of pte debugging in his series
"mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with
swap PTEs".
- Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation
flag in the series "Discard __GFP_ATOMIC".
- Sergey Senozhatsky has improved zsmalloc's memory utilization with
his series "zsmalloc: make zspage chain size configurable".
- Joey Gouly has added prctl() support for prohibiting the creation of
writeable+executable mappings.
The previous BPF-based approach had shortcomings. See "mm: In-kernel
support for memory-deny-write-execute (MDWE)".
- Waiman Long did some kmemleak cleanup and bugfixing in the series
"mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF".
- T.J. Alumbaugh has contributed some MGLRU cleanup work in his series
"mm: multi-gen LRU: improve".
- Jiaqi Yan has provided some enhancements to our memory error
statistics reporting, mainly by presenting the statistics on a
per-node basis. See the series "Introduce per NUMA node memory error
statistics".
- Mel Gorman has a second and hopefully final shot at fixing a CPU-hog
regression in compaction via his series "Fix excessive CPU usage
during compaction".
- Christoph Hellwig does some vmalloc maintenance work in the series
"cleanup vfree and vunmap".
- Christoph Hellwig has removed block_device_operations.rw_page() in
ths series "remove ->rw_page".
- We get some maple_tree improvements and cleanups in Liam Howlett's
series "VMA tree type safety and remove __vma_adjust()".
- Suren Baghdasaryan has done some work on the maintainability of our
vm_flags handling in the series "introduce vm_flags modifier
functions".
- Some pagemap cleanup and generalization work in Mike Rapoport's
series "mm, arch: add generic implementation of pfn_valid() for
FLATMEM" and "fixups for generic implementation of pfn_valid()"
- Baoquan He has done some work to make /proc/vmallocinfo and
/proc/kcore better represent the real state of things in his series
"mm/vmalloc.c: allow vread() to read out vm_map_ram areas".
- Jason Gunthorpe rationalized the GUP system's interface to the rest
of the kernel in the series "Simplify the external interface for
GUP".
- SeongJae Park wishes to migrate people from DAMON's debugfs interface
over to its sysfs interface. To support this, we'll temporarily be
printing warnings when people use the debugfs interface. See the
series "mm/damon: deprecate DAMON debugfs interface".
- Andrey Konovalov provided the accurately named "lib/stackdepot: fixes
and clean-ups" series.
- Huang Ying has provided a dramatic reduction in migration's TLB flush
IPI rates with the series "migrate_pages(): batch TLB flushing".
- Arnd Bergmann has some objtool fixups in "objtool warning fixes".
* tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits)
include/linux/migrate.h: remove unneeded externs
mm/memory_hotplug: cleanup return value handing in do_migrate_range()
mm/uffd: fix comment in handling pte markers
mm: change to return bool for isolate_movable_page()
mm: hugetlb: change to return bool for isolate_hugetlb()
mm: change to return bool for isolate_lru_page()
mm: change to return bool for folio_isolate_lru()
objtool: add UACCESS exceptions for __tsan_volatile_read/write
kmsan: disable ftrace in kmsan core code
kasan: mark addr_has_metadata __always_inline
mm: memcontrol: rename memcg_kmem_enabled()
sh: initialize max_mapnr
m68k/nommu: add missing definition of ARCH_PFN_OFFSET
mm: percpu: fix incorrect size in pcpu_obj_full_size()
maple_tree: reduce stack usage with gcc-9 and earlier
mm: page_alloc: call panic() when memoryless node allocation fails
mm: multi-gen LRU: avoid futile retries
migrate_pages: move THP/hugetlb migration support check to simplify code
migrate_pages: batch flushing TLB
migrate_pages: share more code between _unmap and _move
...
When a scheduling entity is placed onto cfs_rq, its vruntime is pulled
to the base level (around cfs_rq->min_vruntime), so that the entity
doesn't gain extra boost when placed backwards.
However, if the entity being placed wasn't executed for a long time, its
vruntime may get too far behind (e.g. while cfs_rq was executing a
low-weight hog), which can inverse the vruntime comparison due to s64
overflow. This results in the entity being placed with its original
vruntime way forwards, so that it will effectively never get to the cpu.
To prevent that, ignore the vruntime of the entity being placed if it
didn't execute for much longer than the characteristic sheduler time
scale.
[rkagan: formatted, adjusted commit log, comments, cutoff value]
Signed-off-by: Zhang Qiao <zhangqiao22@huawei.com>
Co-developed-by: Roman Kagan <rkagan@amazon.de>
Signed-off-by: Roman Kagan <rkagan@amazon.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20230130122216.3555094-1-rkagan@amazon.de
Remove the capacity inversion detection which is now handled by
util_fits_cpu() returning -1 when we need to continue to look for a
potential CPU with better performance.
This ends up almost reverting patches below except for some comments:
commit da07d2f9c1 ("sched/fair: Fixes for capacity inversion detection")
commit aa69c36f31 ("sched/fair: Consider capacity inversion in util_fits_cpu()")
commit 44c7b80bff ("sched/fair: Detect capacity inversion")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230201143628.270912-3-vincent.guittot@linaro.org
By taking into account uclamp_min, the 1:1 relation between task misfit
and cpu overutilized is no more true as a task with a small util_avg may
not fit a high capacity cpu because of uclamp_min constraint.
Add a new state in util_fits_cpu() to reflect the case that task would fit
a CPU except for the uclamp_min hint which is a performance requirement.
Use -1 to reflect that a CPU doesn't fit only because of uclamp_min so we
can use this new value to take additional action to select the best CPU
that doesn't match uclamp_min hint.
When util_fits_cpu() returns -1, we will continue to look for a possible
CPU with better performance, which replaces Capacity Inversion detection
with capacity_orig_of() - thermal_load_avg to detect a capacity inversion.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-and-tested-by: Qais Yousef <qyousef@layalina.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Kajetan Puchalski <kajetan.puchalski@arm.com>
Link: https://lore.kernel.org/r/20230201143628.270912-2-vincent.guittot@linaro.org
Use the vma iterator so that the iterator can be invalidated or updated to
avoid each caller doing so.
Link: https://lkml.kernel.org/r/20230120162650.984577-23-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmPW7E8eHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGf7MIAI0JnHN9WvtEukSZ
E6j6+cEGWxsvD6q0g3GPolaKOCw7hlv0pWcFJFcUAt0jebspMdxV2oUGJ8RYW7Lg
nCcHvEVswGKLAQtQSWw52qotW6fUfMPsNYYB5l31sm1sKH4Cgss0W7l2HxO/1LvG
TSeNHX53vNAZ8pVnFYEWCSXC9bzrmU/VALF2EV00cdICmfvjlgkELGXoLKJJWzUp
s63fBHYGGURSgwIWOKStoO6HNo0j/F/wcSMx8leY8qDUtVKHj4v24EvSgxUSDBER
ch3LiSQ6qf4sw/z7pqruKFthKOrlNmcc0phjiES0xwwGiNhLv0z3rAhc4OM2cgYh
SDc/Y/c=
=zpaD
-----END PGP SIGNATURE-----
Merge tag 'v6.2-rc6' into sched/core, to pick up fixes
Pick up fixes before merging another batch of cpuidle updates.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In presence of a lot of small weight tasks like sched_idle tasks, normal
or high weight tasks can see their ideal runtime (sched_slice) to increase
to hundreds ms whereas it normally stays below sysctl_sched_latency.
2 normal tasks running on a CPU will have a max sched_slice of 12ms
(half of the sched_period). This means that they will make progress
every sysctl_sched_latency period.
If we now add 1000 idle tasks on the CPU, the sched_period becomes
3006 ms and the ideal runtime of the normal tasks becomes 609 ms.
It will even become 1500ms if the idle tasks belongs to an idle cgroup.
This means that the scheduler will look for picking another waiting task
after 609ms running time (1500ms respectively). The idle tasks change
significantly the way the 2 normal tasks interleave their running time
slot whereas they should have a small impact.
Such long sched_slice can delay significantly the release of resources
as the tasks can wait hundreds of ms before the next running slot just
because of idle tasks queued on the rq.
Cap the ideal_runtime to sysctl_sched_latency to make sure that tasks will
regularly make progress and will not be significantly impacted by
idle/background tasks queued on the rq.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20230113133613.257342-1-vincent.guittot@linaro.org
Traversing the Perf Domains requires rcu_read_lock() to be held and is
conditional on sched_energy_enabled(). Ensure right protections applied.
Also skip capacity inversion detection for our own pd; which was an
error.
Fixes: 44c7b80bff ("sched/fair: Detect capacity inversion")
Reported-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Qais Yousef (Google) <qyousef@layalina.io>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20230112122708.330667-3-qyousef@layalina.io
When select_idle_capacity() starts scanning for an idle CPU, it starts
with target CPU that has already been checked in select_idle_sibling().
So we start checking from the next CPU and try the target CPU at the end.
Similarly for task_numa_assign(), we have just checked numa_migrate_on
of dst_cpu, so start from the next CPU. This also works for
steal_cookie_task(), the first scan must fail and start directly
from the next one.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20221216062406.7812-3-jiahao.os@bytedance.com
In update_numa_stats() we try to find an idle cpu on the NUMA node,
preferably an idle core. we can stop looking for the next idle core
or idle cpu after finding an idle core. But we can't stop the
whole loop of scanning the CPU, because we need to calculate
approximate NUMA stats at a point in time. For example,
the src and dst nr_running is needed by task_numa_find_cpu().
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20221216062406.7812-2-jiahao.os@bytedance.com
With a modified container_of() that preserves constness, the compiler
finds some pointers which should have been marked as const. task_of()
also needs to become const-preserving for the !FAIR_GROUP_SCHED case so
that cfs_rq_of() can take a const argument. No change to generated code.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221212144946.2657785-1-willy@infradead.org
CFS bandwidth currently distributes new runtime and unthrottles cfs_rq's
inline in an hrtimer callback. Runtime distribution is a per-cpu
operation, and unthrottling is a per-cgroup operation, since a tg walk
is required. On machines with a large number of cpus and large cgroup
hierarchies, this cpus*cgroups work can be too much to do in a single
hrtimer callback: since IRQ are disabled, hard lockups may easily occur.
Specifically, we've found this scalability issue on configurations with
256 cpus, O(1000) cgroups in the hierarchy being throttled, and high
memory bandwidth usage.
To fix this, we can instead unthrottle cfs_rq's asynchronously via a
CSD. Each cpu is responsible for unthrottling itself, thus sharding the
total work more fairly across the system, and avoiding hard lockups.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221117005418.3499691-1-joshdon@google.com
Only step forward on the sysctl cleanups for this cycle. This
has been on linux-next since September and this time it goes
with a "Yeah, think so, it just moves stuff around a bit" from
Peter Zijlstra.
-----BEGIN PGP SIGNATURE-----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=M48U
-----END PGP SIGNATURE-----
Merge tag 'sysctl-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux
Pull sysctl updates from Luis Chamberlain:
"Only a small step forward on the sysctl cleanups for this cycle"
* tag 'sysctl-6.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux:
sched: Move numa_balancing sysctls to its own file
- A ptrace API cleanup series from Sergey Shtylyov
- Fixes and cleanups for kexec from ye xingchen
- nilfs2 updates from Ryusuke Konishi
- squashfs feature work from Xiaoming Ni: permit configuration of the
filesystem's compression concurrency from the mount command line.
- A series from Akinobu Mita which addresses bound checking errors when
writing to debugfs files.
- A series from Yang Yingliang to address rapido memory leaks
- A series from Zheng Yejian to address possible overflow errors in
encode_comp_t().
- And a whole shower of singleton patches all over the place.
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY5efRgAKCRDdBJ7gKXxA
jgvdAP0al6oFDtaSsshIdNhrzcMwfjt6PfVxxHdLmNhF1hX2dwD/SVluS1bPSP7y
0sZp7Ustu3YTb8aFkMl96Y9m9mY1Nwg=
=ga5B
-----END PGP SIGNATURE-----
Merge tag 'mm-nonmm-stable-2022-12-12' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull non-MM updates from Andrew Morton:
- A ptrace API cleanup series from Sergey Shtylyov
- Fixes and cleanups for kexec from ye xingchen
- nilfs2 updates from Ryusuke Konishi
- squashfs feature work from Xiaoming Ni: permit configuration of the
filesystem's compression concurrency from the mount command line
- A series from Akinobu Mita which addresses bound checking errors when
writing to debugfs files
- A series from Yang Yingliang to address rapidio memory leaks
- A series from Zheng Yejian to address possible overflow errors in
encode_comp_t()
- And a whole shower of singleton patches all over the place
* tag 'mm-nonmm-stable-2022-12-12' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (79 commits)
ipc: fix memory leak in init_mqueue_fs()
hfsplus: fix bug causing custom uid and gid being unable to be assigned with mount
rapidio: devices: fix missing put_device in mport_cdev_open
kcov: fix spelling typos in comments
hfs: Fix OOB Write in hfs_asc2mac
hfs: fix OOB Read in __hfs_brec_find
relay: fix type mismatch when allocating memory in relay_create_buf()
ocfs2: always read both high and low parts of dinode link count
io-mapping: move some code within the include guarded section
kernel: kcsan: kcsan_test: build without structleak plugin
mailmap: update email for Iskren Chernev
eventfd: change int to __u64 in eventfd_signal() ifndef CONFIG_EVENTFD
rapidio: fix possible UAF when kfifo_alloc() fails
relay: use strscpy() is more robust and safer
cpumask: limit visibility of FORCE_NR_CPUS
acct: fix potential integer overflow in encode_comp_t()
acct: fix accuracy loss for input value of encode_comp_t()
linux/init.h: include <linux/build_bug.h> and <linux/stringify.h>
rapidio: rio: fix possible name leak in rio_register_mport()
rapidio: fix possible name leaks when rio_add_device() fails
...
The sysctl_numa_balancing_promote_rate_limit and sysctl_numa_balancing
are part of sched, move them to its own file.
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in
task_numa_work. x86 CMPXCHG instruction returns success in ZF flag, so
this change saves a compare after cmpxchg (and related move instruction in
front of cmpxchg).
No functional change intended.
Link: https://lkml.kernel.org/r/20220822173956.82525-1-ubizjak@gmail.com
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When evaluating the CPU candidates in the perf domain (pd) containing
the previously used CPU (prev_cpu), find_energy_efficient_cpu()
evaluates the energy of the pd:
- without the task (base_energy)
- with the task placed on prev_cpu (if the task fits)
- with the task placed on the CPU with the highest spare capacity,
prev_cpu being excluded from this set
If prev_cpu is already the CPU with the highest spare capacity,
max_spare_cap_cpu will be the CPU with the second highest spare
capacity.
On an Arm64 Juno-r2, with a workload of 10 tasks at a 10% duty cycle,
when prev_cpu and max_spare_cap_cpu are both valid candidates,
prev_spare_cap > max_spare_cap at ~82%.
Thus the energy of the pd when placing the task on max_spare_cap_cpu
is computed with no possible positive outcome 82% most of the time.
Do not consider max_spare_cap_cpu as a valid candidate if
prev_spare_cap > max_spare_cap.
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20221006081052.3862167-2-pierre.gondois@arm.com
We do consider thermal pressure in util_fits_cpu() for uclamp_min only.
With the exception of the biggest cores which by definition are the max
performance point of the system and all tasks by definition should fit.
Even under thermal pressure, the capacity of the biggest CPU is the
highest in the system and should still fit every task. Except when it
reaches capacity inversion point, then this is no longer true.
We can handle this by using the inverted capacity as capacity_orig in
util_fits_cpu(). Which not only addresses the problem above, but also
ensure uclamp_max now considers the inverted capacity. Force fitting
a task when a CPU is in this adverse state will contribute to making the
thermal throttling last longer.
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-10-qais.yousef@arm.com
Check each performance domain to see if thermal pressure is causing its
capacity to be lower than another performance domain.
We assume that each performance domain has CPUs with the same
capacities, which is similar to an assumption made in energy_model.c
We also assume that thermal pressure impacts all CPUs in a performance
domain equally.
If there're multiple performance domains with the same capacity_orig, we
will trigger a capacity inversion if the domain is under thermal
pressure.
The new cpu_in_capacity_inversion() should help users to know when
information about capacity_orig are not reliable and can opt in to use
the inverted capacity as the 'actual' capacity_orig.
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-9-qais.yousef@arm.com
If the utilization of the woken up task is 0, we skip the energy
calculation because it has no impact.
But if the task is boosted (uclamp_min != 0) will have an impact on task
placement and frequency selection. Only skip if the util is truly
0 after applying uclamp values.
Change uclamp_task_cpu() signature to avoid unnecessary additional calls
to uclamp_eff_get(). feec() is the only user now.
Fixes: 732cd75b8c ("sched/fair: Select an energy-efficient CPU on task wake-up")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-8-qais.yousef@arm.com
So that it is now uclamp aware.
This fixes a major problem of busy tasks capped with UCLAMP_MAX keeping
the system in overutilized state which disables EAS and leads to wasting
energy in the long run.
Without this patch running a busy background activity like JIT
compilation on Pixel 6 causes the system to be in overutilized state
74.5% of the time.
With this patch this goes down to 9.79%.
It also fixes another problem when long running tasks that have their
UCLAMP_MIN changed while running such that they need to upmigrate to
honour the new UCLAMP_MIN value. The upmigration doesn't get triggered
because overutilized state never gets set in this state, hence misfit
migration never happens at tick in this case until the task wakes up
again.
Fixes: af24bde8df ("sched/uclamp: Add uclamp support to energy_compute()")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-7-qais.yousef@arm.com
Use the new util_fits_cpu() to ensure migration margin and capacity
pressure are taken into account correctly when uclamp is being used
otherwise we will fail to consider CPUs as fitting in scenarios where
they should.
s/asym_fits_capacity/asym_fits_cpu/ to better reflect what it does now.
Fixes: b4c9c9f156 ("sched/fair: Prefer prev cpu in asymmetric wakeup path")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-6-qais.yousef@arm.com
Use the new util_fits_cpu() to ensure migration margin and capacity
pressure are taken into account correctly when uclamp is being used
otherwise we will fail to consider CPUs as fitting in scenarios where
they should.
Fixes: b4c9c9f156 ("sched/fair: Prefer prev cpu in asymmetric wakeup path")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-5-qais.yousef@arm.com
As reported by Yun Hsiang [1], if a task has its uclamp_min >= 0.8 * 1024,
it'll always pick the previous CPU because fits_capacity() will always
return false in this case.
The new util_fits_cpu() logic should handle this correctly for us beside
more corner cases where similar failures could occur, like when using
UCLAMP_MAX.
We open code uclamp_rq_util_with() except for the clamp() part,
util_fits_cpu() needs the 'raw' values to be passed to it.
Also introduce uclamp_rq_{set, get}() shorthand accessors to get uclamp
value for the rq. Makes the code more readable and ensures the right
rules (use READ_ONCE/WRITE_ONCE) are respected transparently.
[1] https://lists.linaro.org/pipermail/eas-dev/2020-July/001488.html
Fixes: 1d42509e47 ("sched/fair: Make EAS wakeup placement consider uclamp restrictions")
Reported-by: Yun Hsiang <hsiang023167@gmail.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-4-qais.yousef@arm.com
So that the new uclamp rules in regard to migration margin and capacity
pressure are taken into account correctly.
Fixes: a7008c07a5 ("sched/fair: Make task_fits_capacity() consider uclamp restrictions")
Co-developed-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-3-qais.yousef@arm.com
fits_capacity() verifies that a util is within 20% margin of the
capacity of a CPU, which is an attempt to speed up upmigration.
But when uclamp is used, this 20% margin is problematic because for
example if a task is boosted to 1024, then it will not fit on any CPU
according to fits_capacity() logic.
Or if a task is boosted to capacity_orig_of(medium_cpu). The task will
end up on big instead on the desired medium CPU.
Similar corner cases exist for uclamp and usage of capacity_of().
Slightest irq pressure on biggest CPU for example will make a 1024
boosted task look like it can't fit.
What we really want is for uclamp comparisons to ignore the migration
margin and capacity pressure, yet retain them for when checking the
_actual_ util signal.
For example, task p:
p->util_avg = 300
p->uclamp[UCLAMP_MIN] = 1024
Will fit a big CPU. But
p->util_avg = 900
p->uclamp[UCLAMP_MIN] = 1024
will not, this should trigger overutilized state because the big CPU is
now *actually* being saturated.
Similar reasoning applies to capping tasks with UCLAMP_MAX. For example:
p->util_avg = 1024
p->uclamp[UCLAMP_MAX] = capacity_orig_of(medium_cpu)
Should fit the task on medium cpus without triggering overutilized
state.
Inlined comments expand more on desired behavior in more scenarios.
Introduce new util_fits_cpu() function which encapsulates the new logic.
The new function is not used anywhere yet, but will be used to update
various users of fits_capacity() in later patches.
Fixes: af24bde8df ("sched/uclamp: Add uclamp support to energy_compute()")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220804143609.515789-2-qais.yousef@arm.com
linux-next for a couple of months without, to my knowledge, any negative
reports (or any positive ones, come to that).
- Also the Maple Tree from Liam R. Howlett. An overlapping range-based
tree for vmas. It it apparently slight more efficient in its own right,
but is mainly targeted at enabling work to reduce mmap_lock contention.
Liam has identified a number of other tree users in the kernel which
could be beneficially onverted to mapletrees.
Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
(https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com).
This has yet to be addressed due to Liam's unfortunately timed
vacation. He is now back and we'll get this fixed up.
- Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
clang-generated instrumentation to detect used-unintialized bugs down to
the single bit level.
KMSAN keeps finding bugs. New ones, as well as the legacy ones.
- Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
memory into THPs.
- Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to support
file/shmem-backed pages.
- userfaultfd updates from Axel Rasmussen
- zsmalloc cleanups from Alexey Romanov
- cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and memory-failure
- Huang Ying adds enhancements to NUMA balancing memory tiering mode's
page promotion, with a new way of detecting hot pages.
- memcg updates from Shakeel Butt: charging optimizations and reduced
memory consumption.
- memcg cleanups from Kairui Song.
- memcg fixes and cleanups from Johannes Weiner.
- Vishal Moola provides more folio conversions
- Zhang Yi removed ll_rw_block() :(
- migration enhancements from Peter Xu
- migration error-path bugfixes from Huang Ying
- Aneesh Kumar added ability for a device driver to alter the memory
tiering promotion paths. For optimizations by PMEM drivers, DRM
drivers, etc.
- vma merging improvements from Jakub Matěn.
- NUMA hinting cleanups from David Hildenbrand.
- xu xin added aditional userspace visibility into KSM merging activity.
- THP & KSM code consolidation from Qi Zheng.
- more folio work from Matthew Wilcox.
- KASAN updates from Andrey Konovalov.
- DAMON cleanups from Kaixu Xia.
- DAMON work from SeongJae Park: fixes, cleanups.
- hugetlb sysfs cleanups from Muchun Song.
- Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCY0HaPgAKCRDdBJ7gKXxA
joPjAQDZ5LlRCMWZ1oxLP2NOTp6nm63q9PWcGnmY50FjD/dNlwEAnx7OejCLWGWf
bbTuk6U2+TKgJa4X7+pbbejeoqnt5QU=
=xfWx
-----END PGP SIGNATURE-----
Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:
- Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
linux-next for a couple of months without, to my knowledge, any
negative reports (or any positive ones, come to that).
- Also the Maple Tree from Liam Howlett. An overlapping range-based
tree for vmas. It it apparently slightly more efficient in its own
right, but is mainly targeted at enabling work to reduce mmap_lock
contention.
Liam has identified a number of other tree users in the kernel which
could be beneficially onverted to mapletrees.
Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
at [1]. This has yet to be addressed due to Liam's unfortunately
timed vacation. He is now back and we'll get this fixed up.
- Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
clang-generated instrumentation to detect used-unintialized bugs down
to the single bit level.
KMSAN keeps finding bugs. New ones, as well as the legacy ones.
- Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
memory into THPs.
- Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
support file/shmem-backed pages.
- userfaultfd updates from Axel Rasmussen
- zsmalloc cleanups from Alexey Romanov
- cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
memory-failure
- Huang Ying adds enhancements to NUMA balancing memory tiering mode's
page promotion, with a new way of detecting hot pages.
- memcg updates from Shakeel Butt: charging optimizations and reduced
memory consumption.
- memcg cleanups from Kairui Song.
- memcg fixes and cleanups from Johannes Weiner.
- Vishal Moola provides more folio conversions
- Zhang Yi removed ll_rw_block() :(
- migration enhancements from Peter Xu
- migration error-path bugfixes from Huang Ying
- Aneesh Kumar added ability for a device driver to alter the memory
tiering promotion paths. For optimizations by PMEM drivers, DRM
drivers, etc.
- vma merging improvements from Jakub Matěn.
- NUMA hinting cleanups from David Hildenbrand.
- xu xin added aditional userspace visibility into KSM merging
activity.
- THP & KSM code consolidation from Qi Zheng.
- more folio work from Matthew Wilcox.
- KASAN updates from Andrey Konovalov.
- DAMON cleanups from Kaixu Xia.
- DAMON work from SeongJae Park: fixes, cleanups.
- hugetlb sysfs cleanups from Muchun Song.
- Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.
Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]
* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
hugetlb: allocate vma lock for all sharable vmas
hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
hugetlb: fix vma lock handling during split vma and range unmapping
mglru: mm/vmscan.c: fix imprecise comments
mm/mglru: don't sync disk for each aging cycle
mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
mm: memcontrol: use do_memsw_account() in a few more places
mm: memcontrol: deprecate swapaccounting=0 mode
mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
mm/secretmem: remove reduntant return value
mm/hugetlb: add available_huge_pages() func
mm: remove unused inline functions from include/linux/mm_inline.h
selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
selftests/vm: add thp collapse shmem testing
selftests/vm: add thp collapse file and tmpfs testing
selftests/vm: modularize thp collapse memory operations
selftests/vm: dedup THP helpers
mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
mm/madvise: add file and shmem support to MADV_COLLAPSE
...
The linked list is slower than walking the VMAs using the maple tree. We
can't use the VMA iterator here because it doesn't support moving to an
earlier position.
Link: https://lkml.kernel.org/r/20220906194824.2110408-49-Liam.Howlett@oracle.com
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Yu Zhao <yuzhao@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: SeongJae Park <sj@kernel.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With memory tier support we can have memory only NUMA nodes in the top
tier from which we want to avoid promotion tracking NUMA faults. Update
node_is_toptier to work with memory tiers. All NUMA nodes are by default
top tier nodes. With lower(slower) memory tiers added we consider all
memory tiers above a memory tier having CPU NUMA nodes as a top memory
tier
[sj@kernel.org: include missed header file, memory-tiers.h]
Link: https://lkml.kernel.org/r/20220820190720.248704-1-sj@kernel.org
[akpm@linux-foundation.org: mm/memory.c needs linux/memory-tiers.h]
[aneesh.kumar@linux.ibm.com: make toptier_distance inclusive upper bound of toptiers]
Link: https://lkml.kernel.org/r/20220830081457.118960-1-aneesh.kumar@linux.ibm.com
Link: https://lkml.kernel.org/r/20220818131042.113280-10-aneesh.kumar@linux.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Wei Xu <weixugc@google.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Bharata B Rao <bharata@amd.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Hesham Almatary <hesham.almatary@huawei.com>
Cc: Jagdish Gediya <jvgediya.oss@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
sched_nr_migrate_break is set to a fix value and never changes so we can
replace it by a define SCHED_NR_MIGRATE_BREAK.
Also, we adjust SCHED_NR_MIGRATE_BREAK to be aligned with the init value
of sysctl_sched_nr_migrate which can be init to different values.
Then, use SCHED_NR_MIGRATE_BREAK to init sysctl_sched_nr_migrate.
The behavior stays unchanged unless you modify sysctl_sched_nr_migrate
trough debugfs.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220825122726.20819-3-vincent.guittot@linaro.org
During load balance, we try at most env->loop_max time to move a task.
But it can happen that the loop_max LRU tasks (ie tail of
the cfs_tasks list) can't be moved to dst_cpu because of affinity.
In this case, loop in the list until we found at least one.
The maximum of detached tasks remained the same as before.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220825122726.20819-2-vincent.guittot@linaro.org
The promotion hot threshold is workload and system configuration
dependent. So in this patch, a method to adjust the hot threshold
automatically is implemented. The basic idea is to control the number of
the candidate promotion pages to match the promotion rate limit. If the
hint page fault latency of a page is less than the hot threshold, we will
try to promote the page, and the page is called the candidate promotion
page.
If the number of the candidate promotion pages in the statistics interval
is much more than the promotion rate limit, the hot threshold will be
decreased to reduce the number of the candidate promotion pages.
Otherwise, the hot threshold will be increased to increase the number of
the candidate promotion pages.
To make the above method works, in each statistics interval, the total
number of the pages to check (on which the hint page faults occur) and the
hot/cold distribution need to be stable. Because the page tables are
scanned linearly in NUMA balancing, but the hot/cold distribution isn't
uniform along the address usually, the statistics interval should be
larger than the NUMA balancing scan period. So in the patch, the max scan
period is used as statistics interval and it works well in our tests.
Link: https://lkml.kernel.org/r/20220713083954.34196-4-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: osalvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zhong Jiang <zhongjiang-ali@linux.alibaba.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
In NUMA balancing memory tiering mode, if there are hot pages in slow
memory node and cold pages in fast memory node, we need to promote/demote
hot/cold pages between the fast and cold memory nodes.
A choice is to promote/demote as fast as possible. But the CPU cycles and
memory bandwidth consumed by the high promoting/demoting throughput will
hurt the latency of some workload because of accessing inflating and slow
memory bandwidth contention.
A way to resolve this issue is to restrict the max promoting/demoting
throughput. It will take longer to finish the promoting/demoting. But
the workload latency will be better. This is implemented in this patch as
the page promotion rate limit mechanism.
The number of the candidate pages to be promoted to the fast memory node
via NUMA balancing is counted, if the count exceeds the limit specified by
the users, the NUMA balancing promotion will be stopped until the next
second.
A new sysctl knob kernel.numa_balancing_promote_rate_limit_MBps is added
for the users to specify the limit.
Link: https://lkml.kernel.org/r/20220713083954.34196-3-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: osalvador <osalvador@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zhong Jiang <zhongjiang-ali@linux.alibaba.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "memory tiering: hot page selection", v4.
To optimize page placement in a memory tiering system with NUMA balancing,
the hot pages in the slow memory nodes need to be identified.
Essentially, the original NUMA balancing implementation selects the mostly
recently accessed (MRU) pages to promote. But this isn't a perfect
algorithm to identify the hot pages. Because the pages with quite low
access frequency may be accessed eventually given the NUMA balancing page
table scanning period could be quite long (e.g. 60 seconds). So in this
patchset, we implement a new hot page identification algorithm based on
the latency between NUMA balancing page table scanning and hint page
fault. Which is a kind of mostly frequently accessed (MFU) algorithm.
In NUMA balancing memory tiering mode, if there are hot pages in slow
memory node and cold pages in fast memory node, we need to promote/demote
hot/cold pages between the fast and cold memory nodes.
A choice is to promote/demote as fast as possible. But the CPU cycles and
memory bandwidth consumed by the high promoting/demoting throughput will
hurt the latency of some workload because of accessing inflating and slow
memory bandwidth contention.
A way to resolve this issue is to restrict the max promoting/demoting
throughput. It will take longer to finish the promoting/demoting. But
the workload latency will be better. This is implemented in this patchset
as the page promotion rate limit mechanism.
The promotion hot threshold is workload and system configuration
dependent. So in this patchset, a method to adjust the hot threshold
automatically is implemented. The basic idea is to control the number of
the candidate promotion pages to match the promotion rate limit.
We used the pmbench memory accessing benchmark tested the patchset on a
2-socket server system with DRAM and PMEM installed. The test results are
as follows,
pmbench score promote rate
(accesses/s) MB/s
------------- ------------
base 146887704.1 725.6
hot selection 165695601.2 544.0
rate limit 162814569.8 165.2
auto adjustment 170495294.0 136.9
From the results above,
With hot page selection patch [1/3], the pmbench score increases about
12.8%, and promote rate (overhead) decreases about 25.0%, compared with
base kernel.
With rate limit patch [2/3], pmbench score decreases about 1.7%, and
promote rate decreases about 69.6%, compared with hot page selection
patch.
With threshold auto adjustment patch [3/3], pmbench score increases about
4.7%, and promote rate decrease about 17.1%, compared with rate limit
patch.
Baolin helped to test the patchset with MySQL on a machine which contains
1 DRAM node (30G) and 1 PMEM node (126G).
sysbench /usr/share/sysbench/oltp_read_write.lua \
......
--tables=200 \
--table-size=1000000 \
--report-interval=10 \
--threads=16 \
--time=120
The tps can be improved about 5%.
This patch (of 3):
To optimize page placement in a memory tiering system with NUMA balancing,
the hot pages in the slow memory node need to be identified. Essentially,
the original NUMA balancing implementation selects the mostly recently
accessed (MRU) pages to promote. But this isn't a perfect algorithm to
identify the hot pages. Because the pages with quite low access frequency
may be accessed eventually given the NUMA balancing page table scanning
period could be quite long (e.g. 60 seconds). The most frequently
accessed (MFU) algorithm is better.
So, in this patch we implemented a better hot page selection algorithm.
Which is based on NUMA balancing page table scanning and hint page fault
as follows,
- When the page tables of the processes are scanned to change PTE/PMD
to be PROT_NONE, the current time is recorded in struct page as scan
time.
- When the page is accessed, hint page fault will occur. The scan
time is gotten from the struct page. And The hint page fault
latency is defined as
hint page fault time - scan time
The shorter the hint page fault latency of a page is, the higher the
probability of their access frequency to be higher. So the hint page
fault latency is a better estimation of the page hot/cold.
It's hard to find some extra space in struct page to hold the scan time.
Fortunately, we can reuse some bits used by the original NUMA balancing.
NUMA balancing uses some bits in struct page to store the page accessing
CPU and PID (referring to page_cpupid_xchg_last()). Which is used by the
multi-stage node selection algorithm to avoid to migrate pages shared
accessed by the NUMA nodes back and forth. But for pages in the slow
memory node, even if they are shared accessed by multiple NUMA nodes, as
long as the pages are hot, they need to be promoted to the fast memory
node. So the accessing CPU and PID information are unnecessary for the
slow memory pages. We can reuse these bits in struct page to record the
scan time. For the fast memory pages, these bits are used as before.
For the hot threshold, the default value is 1 second, which works well in
our performance test. All pages with hint page fault latency < hot
threshold will be considered hot.
It's hard for users to determine the hot threshold. So we don't provide a
kernel ABI to set it, just provide a debugfs interface for advanced users
to experiment. We will continue to work on a hot threshold automatic
adjustment mechanism.
The downside of the above method is that the response time to the workload
hot spot changing may be much longer. For example,
- A previous cold memory area becomes hot
- The hint page fault will be triggered. But the hint page fault
latency isn't shorter than the hot threshold. So the pages will
not be promoted.
- When the memory area is scanned again, maybe after a scan period,
the hint page fault latency measured will be shorter than the hot
threshold and the pages will be promoted.
To mitigate this, if there are enough free space in the fast memory node,
the hot threshold will not be used, all pages will be promoted upon the
hint page fault for fast response.
Thanks Zhong Jiang reported and tested the fix for a bug when disabling
memory tiering mode dynamically.
Link: https://lkml.kernel.org/r/20220713083954.34196-1-ying.huang@intel.com
Link: https://lkml.kernel.org/r/20220713083954.34196-2-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Wei Xu <weixugc@google.com>
Cc: osalvador <osalvador@suse.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Zhong Jiang <zhongjiang-ali@linux.alibaba.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
There is some ambiguity about task_running() in that it is unrelated
to TASK_RUNNING but instead tests ->on_cpu. As such, rename the thing
task_on_cpu().
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/Yxhkhn55uHZx+NGl@hirez.programming.kicks-ass.net
The sched-domain of this cpu is only used for some heuristics when
SIS_PROP is enabled, and it should be irrelevant whether the local
sd_llc is valid or not, since all we care about is target sd_llc
if !SIS_PROP.
Access the local domain only when there is a need.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lore.kernel.org/r/20220907112000.1854-6-wuyun.abel@bytedance.com
It's uncertain whether idle cores exist or not if shared sched-
domains are not ready, so returning "no idle cores" usually
makes sense.
While __update_idle_core() is an exception, it checks status
of this core and set hint to shared sched-domain if necessary.
So the whole logic of this function depends on the existence
of shared sched-domain, and can certainly bail out early if
it is not available.
It's somehow a little tricky, and as Josh suggested that it
should be transient while the domain isn't ready. So remove
the self-defined default value to make things more clearer.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Don <joshdon@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20220907112000.1854-5-wuyun.abel@bytedance.com
The function select_idle_core() only gets called when has_idle_cores
is true which can be possible only when sched_smt_present is enabled.
This change also aligns select_idle_core() with select_idle_smt() in
the way that the caller do the check if necessary.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20220907112000.1854-4-wuyun.abel@bytedance.com
The prev cpu is checked at the beginning of SIS, and it's unlikely
to be idle before the second check in select_idle_smt(). So we'd
better focus on its SMT siblings.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Don <joshdon@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20220907112000.1854-3-wuyun.abel@bytedance.com
If two cpus share LLC cache, then the two cores they belong to
are also in the same LLC domain.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Don <joshdon@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20220907112000.1854-2-wuyun.abel@bytedance.com
post_init_entity_util_avg() init task util_avg according to the cpu util_avg
at the time of fork, which will decay when switched_to_fair() some time later,
we'd better to not set them at all in the case of !fair task.
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-10-zhouchengming@bytedance.com
When wake_up_new_task(), we use post_init_entity_util_avg() to init
util_avg/runnable_avg based on cpu's util_avg at that time, and
attach task sched_avg to cfs_rq.
Since enqueue_task_fair() -> enqueue_entity() -> update_load_avg()
loop will do attach, we can move this work to update_load_avg().
wake_up_new_task(p)
post_init_entity_util_avg(p)
attach_entity_cfs_rq() --> (1)
activate_task(rq, p)
enqueue_task() := enqueue_task_fair()
enqueue_entity() loop
update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH)
if (!se->avg.last_update_time && (flags & DO_ATTACH))
attach_entity_load_avg() --> (2)
This patch move attach from (1) to (2), update related comments too.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-9-zhouchengming@bytedance.com
commit 7dc603c902 ("sched/fair: Fix PELT integrity for new tasks")
introduce a TASK_NEW state and an unnessary limitation that would fail
when changing cgroup of new forked task.
Because at that time, we can't handle task_change_group_fair() for new
forked fair task which hasn't been woken up by wake_up_new_task(),
which will cause detach on an unattached task sched_avg problem.
This patch delete this unnessary limitation by adding check before do
detach or attach in task_change_group_fair().
So cpu_cgrp_subsys.can_attach() has nothing to do for fair tasks,
only define it in #ifdef CONFIG_RT_GROUP_SCHED.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-8-zhouchengming@bytedance.com
commit 7dc603c902 ("sched/fair: Fix PELT integrity for new tasks")
fixed two load tracking problems for new task, including detach on
unattached new task problem.
There still left another detach on unattached task problem for the task
which has been woken up by try_to_wake_up() and waiting for actually
being woken up by sched_ttwu_pending().
try_to_wake_up(p)
cpu = select_task_rq(p)
if (task_cpu(p) != cpu)
set_task_cpu(p, cpu)
migrate_task_rq_fair()
remove_entity_load_avg() --> unattached
se->avg.last_update_time = 0;
__set_task_cpu()
ttwu_queue(p, cpu)
ttwu_queue_wakelist()
__ttwu_queue_wakelist()
task_change_group_fair()
detach_task_cfs_rq()
detach_entity_cfs_rq()
detach_entity_load_avg() --> detach on unattached task
set_task_rq()
attach_task_cfs_rq()
attach_entity_cfs_rq()
attach_entity_load_avg()
The reason of this problem is similar, we should check in detach_entity_cfs_rq()
that se->avg.last_update_time != 0, before do detach_entity_load_avg().
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-7-zhouchengming@bytedance.com
When we are migrating task out of the CPU, we can combine detach and
propagation into dequeue_entity() to save the detach_entity_cfs_rq()
in migrate_task_rq_fair().
This optimization is like combining DO_ATTACH in the enqueue_entity()
when migrating task to the CPU. So we don't have to traverse the CFS tree
extra time to do the detach_entity_cfs_rq() -> propagate_entity_cfs_rq(),
which wouldn't be called anymore with this patch's change.
detach_task()
deactivate_task()
dequeue_task_fair()
for_each_sched_entity(se)
dequeue_entity()
update_load_avg() /* (1) */
detach_entity_load_avg()
set_task_cpu()
migrate_task_rq_fair()
detach_entity_cfs_rq() /* (2) */
update_load_avg();
detach_entity_load_avg();
propagate_entity_cfs_rq();
for_each_sched_entity()
update_load_avg()
This patch save the detach_entity_cfs_rq() called in (2) by doing
the detach_entity_load_avg() for a CPU migrating task inside (1)
(the task being the first se in the loop)
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-6-zhouchengming@bytedance.com
When reading the sched_avg related code, I found the comments in
enqueue/dequeue_entity() are not updated with the current code.
We don't add/subtract entity's runnable_avg from cfs_rq->runnable_avg
during enqueue/dequeue_entity(), those are done only for attach/detach.
This patch updates the comments to reflect the current code working.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-5-zhouchengming@bytedance.com
set_task_rq() -> set_task_rq_fair() will try to synchronize the blocked
task's sched_avg when migrate, which is not needed for already detached
task.
task_change_group_fair() will detached the task sched_avg from prev cfs_rq
first, so reset sched_avg last_update_time before set_task_rq() to avoid that.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-4-zhouchengming@bytedance.com
We use cpu_cgrp_subsys->fork() to set task group for the new fair task
in cgroup_post_fork().
Since commit b1e8206582 ("sched: Fix yet more sched_fork() races")
has already set_task_rq() for the new fair task in sched_cgroup_fork(),
so cpu_cgrp_subsys->fork() can be removed.
cgroup_can_fork() --> pin parent's sched_task_group
sched_cgroup_fork()
__set_task_cpu()
set_task_rq()
cgroup_post_fork()
ss->fork() := cpu_cgroup_fork()
sched_change_group(..., TASK_SET_GROUP)
task_set_group_fair()
set_task_rq() --> can be removed
After this patch's change, task_change_group_fair() only need to
care about task cgroup migration, make the code much simplier.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220818124805.601-3-zhouchengming@bytedance.com
Previously we only maintain task se depth in task_move_group_fair(),
if a !fair task change task group, its se depth will not be updated,
so commit eb7a59b2c8 ("sched/fair: Reset se-depth when task switched to FAIR")
fix the problem by updating se depth in switched_to_fair() too.
Then commit daa59407b5 ("sched/fair: Unify switched_{from,to}_fair()
and task_move_group_fair()") unified these two functions, moved se.depth
setting to attach_task_cfs_rq(), which further into attach_entity_cfs_rq()
with commit df217913e7 ("sched/fair: Factorize attach/detach entity").
This patch move task se depth maintenance from attach_entity_cfs_rq()
to set_task_rq(), which will be called when CPU/cgroup change, so its
depth will always be correct.
This patch is preparation for the next patch.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-2-zhouchengming@bytedance.com
There's no good reason to crash a user's system with a BUG_ON(),
chances are high that they'll never even see the crash message on
Xorg, and it won't make it into the syslog either.
By using a WARN_ON_ONCE() we at least give the user a chance to report
any bugs triggered here - instead of getting silent hangs.
None of these WARN_ON_ONCE()s are supposed to trigger, ever - so we ignore
cases where a NULL check is done via a BUG_ON() and we let a NULL
pointer through after a WARN_ON_ONCE().
There's one exception: WARN_ON_ONCE() arguments with side-effects,
such as locking - in this case we use the return value of the
WARN_ON_ONCE(), such as in:
- BUG_ON(!lock_task_sighand(p, &flags));
+ if (WARN_ON_ONCE(!lock_task_sighand(p, &flags)))
+ return;
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/YvSsKcAXISmshtHo@gmail.com
The load_balance_mask and select_rq_mask percpu variables are only used in
kernel/sched/fair.c.
Make them static and move their allocation into init_sched_fair_class().
Replace kzalloc_node() with zalloc_cpumask_var_node() to get rid of the
CONFIG_CPUMASK_OFFSTACK #ifdef and to align with per-cpu cpumask
allocation for RT (local_cpu_mask in init_sched_rt_class()) and DL
class (local_cpu_mask_dl in init_sched_dl_class()).
[ mingo: Tidied up changelog & touched up the code. ]
Signed-off-by: Bing Huang <huangbing@kylinos.cn>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220722213609.3901-1-huangbing775@126.com
After commit 7a82e5f52a ("sched/fair: Merge for each idle cpu loop of ILB"),
_nohz_idle_balance()'s 'idle' parameter is not used anymore, so we can remove it.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220803130223.70419-1-jiahao.os@bytedance.com
Create an inline helper for conditional code to be only executed on
asymmetric CPU capacity systems. This makes these (currently ~10 and
future) conditions a lot more readable.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20220729111305.1275158-2-dietmar.eggemann@arm.com
The capacity of the CPU available for CFS tasks can be reduced because of
other activities running on the latter. In such case, it's worth trying to
move CFS tasks on a CPU with more available capacity.
The rework of the load balance has filtered the case when the CPU is
classified to be fully busy but its capacity is reduced.
Check if CPU's capacity is reduced while gathering load balance statistic
and classify it group_misfit_task instead of group_fully_busy so we can
try to move the load on another CPU.
Reported-by: David Chen <david.chen@nutanix.com>
Reported-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: David Chen <david.chen@nutanix.com>
Tested-by: Zhang Qiao <zhangqiao22@huawei.com>
Link: https://lkml.kernel.org/r/20220708154401.21411-1-vincent.guittot@linaro.org
find_energy_efficient_cpu() integrates a margin to protect tasks from
bouncing back and forth from a CPU to another. This margin is set as being
6% of the total current energy estimated on the system. This however does
not work for two reasons:
1. The energy estimation is not a good absolute value:
compute_energy() used in feec() is a good estimation for task placement as
it allows to compare the energy with and without a task. The computed
delta will give a good overview of the cost for a certain task placement.
It, however, doesn't work as an absolute estimation for the total energy
of the system. First it adds the contribution to idle CPUs into the
energy, second it mixes util_avg with util_est values. util_avg contains
the near history for a CPU usage, it doesn't tell at all what the current
utilization is. A system that has been quite busy in the near past will
hold a very high energy and then a high margin preventing any task
migration to a lower capacity CPU, wasting energy. It even creates a
negative feedback loop: by holding the tasks on a less efficient CPU, the
margin contributes in keeping the energy high.
2. The margin handicaps small tasks:
On a system where the workload is composed mostly of small tasks (which is
often the case on Android), the overall energy will be high enough to
create a margin none of those tasks can cross. On a Pixel4, a small
utilization of 5% on all the CPUs creates a global estimated energy of 140
joules, as per the Energy Model declaration of that same device. This
means, after applying the 6% margin that any migration must save more than
8 joules to happen. No task with a utilization lower than 40 would then be
able to migrate away from the biggest CPU of the system.
The 6% of the overall system energy was brought by the following patch:
(eb92692b25 sched/fair: Speed-up energy-aware wake-ups)
It was previously 6% of the prev_cpu energy. Also, the following one
made this margin value conditional on the clusters where the task fits:
(8d4c97c105 sched/fair: Only compute base_energy_pd if necessary)
We could simply revert that margin change to what it was, but the original
version didn't have strong grounds neither and as demonstrated in (1.) the
estimated energy isn't a good absolute value. Instead, removing it
completely. It is indeed, made possible by recent changes that improved
energy estimation comparison fairness (sched/fair: Remove task_util from
effective utilization in feec()) (PM: EM: Increase energy calculation
precision) and task utilization stabilization (sched/fair: Decay task
util_avg during migration)
Without a margin, we could have feared bouncing between CPUs. But running
LISA's eas_behaviour test coverage on three different platforms (Hikey960,
RB-5 and DB-845) showed no issue.
Removing the energy margin enables more energy-optimized placements for a
more energy efficient system.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-8-vdonnefort@google.com
The energy estimation in find_energy_efficient_cpu() (feec()) relies on
the computation of the effective utilization for each CPU of a perf domain
(PD). This effective utilization is then used as an estimation of the busy
time for this pd. The function effective_cpu_util() which gives this value,
scales the utilization relative to IRQ pressure on the CPU to take into
account that the IRQ time is hidden from the task clock. The IRQ scaling is
as follow:
effective_cpu_util = irq + (cpu_cap - irq)/cpu_cap * util
Where util is the sum of CFS/RT/DL utilization, cpu_cap the capacity of
the CPU and irq the IRQ avg time.
If now we take as an example a task placement which doesn't raise the OPP
on the candidate CPU, we can write the energy delta as:
delta = OPPcost/cpu_cap * (effective_cpu_util(cpu_util + task_util) -
effective_cpu_util(cpu_util))
= OPPcost/cpu_cap * (cpu_cap - irq)/cpu_cap * task_util
We end-up with an energy delta depending on the IRQ avg time, which is a
problem: first the time spent on IRQs by a CPU has no effect on the
additional energy that would be consumed by a task. Second, we don't want
to favour a CPU with a higher IRQ avg time value.
Nonetheless, we need to take the IRQ avg time into account. If a task
placement raises the PD's frequency, it will increase the energy cost for
the entire time where the CPU is busy. A solution is to only use
effective_cpu_util() with the CPU contribution part. The task contribution
is added separately and scaled according to prev_cpu's IRQ time.
No change for the FREQUENCY_UTIL component of the energy estimation. We
still want to get the actual frequency that would be selected after the
task placement.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-7-vdonnefort@google.com
The Perf Domain (PD) cpumask (struct em_perf_domain.cpus) stays
invariant after Energy Model creation, i.e. it is not updated after
CPU hotplug operations.
That's why the PD mask is used in conjunction with the cpu_online_mask
(or Sched Domain cpumask). Thereby the cpu_online_mask is fetched
multiple times (in compute_energy()) during a run-queue selection
for a task.
cpu_online_mask may change during this time which can lead to wrong
energy calculations.
To be able to avoid this, use the select_rq_mask per-cpu cpumask to
create a cpumask out of PD cpumask and cpu_online_mask and pass it
through the function calls of the EAS run-queue selection path.
The PD cpumask for max_spare_cap_cpu/compute_prev_delta selection
(find_energy_efficient_cpu()) is now ANDed not only with the SD mask
but also with the cpu_online_mask. This is fine since this cpumask
has to be in syc with the one used for energy computation
(compute_energy()).
An exclusive cpuset setup with at least one asymmetric CPU capacity
island (hence the additional AND with the SD cpumask) is the obvious
exception here.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-6-vdonnefort@google.com
On 21/06/2022 11:04, Vincent Donnefort wrote:
> From: Dietmar Eggemann <dietmar.eggemann@arm.com>
https://lkml.kernel.org/r/202206221253.ZVyGQvPX-lkp@intel.com discovered
that this patch doesn't build anymore (on tip sched/core or linux-next)
because of commit f5b2eeb499 ("sched/fair: Consider CPU affinity when
allowing NUMA imbalance in find_idlest_group()").
New version of [PATCH v11 4/7] sched/fair: Rename select_idle_mask to
select_rq_mask below.
-- >8 --
Decouple the name of the per-cpu cpumask select_idle_mask from its usage
in select_idle_[cpu/capacity]() of the CFS run-queue selection
(select_task_rq_fair()).
This is to support the reuse of this cpumask in the Energy Aware
Scheduling (EAS) path (find_energy_efficient_cpu()) of the CFS run-queue
selection.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/250691c7-0e2b-05ab-bedf-b245c11d9400@arm.com
effective_cpu_util() already has a `int cpu' parameter which allows to
retrieve the CPU capacity scale factor (or maximum CPU capacity) inside
this function via an arch_scale_cpu_capacity(cpu).
A lot of code calling effective_cpu_util() (or the shim
sched_cpu_util()) needs the maximum CPU capacity, i.e. it will call
arch_scale_cpu_capacity() already.
But not having to pass it into effective_cpu_util() will make the EAS
wake-up code easier, especially when the maximum CPU capacity reduced
by the thermal pressure is passed through the EAS wake-up functions.
Due to the asymmetric CPU capacity support of arm/arm64 architectures,
arch_scale_cpu_capacity(int cpu) is a per-CPU variable read access via
per_cpu(cpu_scale, cpu) on such a system.
On all other architectures it is a a compile-time constant
(SCHED_CAPACITY_SCALE).
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-4-vdonnefort@google.com
Before being migrated to a new CPU, a task sees its PELT values
synchronized with rq last_update_time. Once done, that same task will also
have its sched_avg last_update_time reset. This means the time between
the migration and the last clock update will not be accounted for in
util_avg and a discontinuity will appear. This issue is amplified by the
PELT clock scaling. It takes currently one tick after the CPU being idle
to let clock_pelt catching up clock_task.
This is especially problematic for asymmetric CPU capacity systems which
need stable util_avg signals for task placement and energy estimation.
Ideally, this problem would be solved by updating the runqueue clocks
before the migration. But that would require taking the runqueue lock
which is quite expensive [1]. Instead estimate the missing time and update
the task util_avg with that value.
To that end, we need sched_clock_cpu() but it is a costly function. Limit
the usage to the case where the source CPU is idle as we know this is when
the clock is having the biggest risk of being outdated.
See comment in migrate_se_pelt_lag() for more details about how the PELT
value is estimated. Notice though this estimation doesn't take into account
IRQ and Paravirt time.
[1] https://lkml.kernel.org/r/20190709115759.10451-1-chris.redpath@arm.com
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-3-vdonnefort@google.com
Introducing macro helpers u64_u32_{store,load}() to factorize lockless
accesses to u64 variables for 32-bits architectures.
Users are for now cfs_rq.min_vruntime and sched_avg.last_update_time. To
accommodate the later where the copy lies outside of the structure
(cfs_rq.last_udpate_time_copy instead of sched_avg.last_update_time_copy),
use the _copy() version of those helpers.
Those new helpers encapsulate smp_rmb() and smp_wmb() synchronization and
therefore, have a small penalty for 32-bits machines in set_task_rq_fair()
and init_cfs_rq().
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-2-vdonnefort@google.com
[Problem Statement]
select_idle_cpu() might spend too much time searching for an idle CPU,
when the system is overloaded.
The following histogram is the time spent in select_idle_cpu(),
when running 224 instances of netperf on a system with 112 CPUs
per LLC domain:
@usecs:
[0] 533 | |
[1] 5495 | |
[2, 4) 12008 | |
[4, 8) 239252 | |
[8, 16) 4041924 |@@@@@@@@@@@@@@ |
[16, 32) 12357398 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[32, 64) 14820255 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[64, 128) 13047682 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[128, 256) 8235013 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[256, 512) 4507667 |@@@@@@@@@@@@@@@ |
[512, 1K) 2600472 |@@@@@@@@@ |
[1K, 2K) 927912 |@@@ |
[2K, 4K) 218720 | |
[4K, 8K) 98161 | |
[8K, 16K) 37722 | |
[16K, 32K) 6715 | |
[32K, 64K) 477 | |
[64K, 128K) 7 | |
netperf latency usecs:
=======
case load Lat_99th std%
TCP_RR thread-224 257.39 ( 0.21)
The time spent in select_idle_cpu() is visible to netperf and might have a negative
impact.
[Symptom analysis]
The patch [1] from Mel Gorman has been applied to track the efficiency
of select_idle_sibling. Copy the indicators here:
SIS Search Efficiency(se_eff%):
A ratio expressed as a percentage of runqueues scanned versus
idle CPUs found. A 100% efficiency indicates that the target,
prev or recent CPU of a task was idle at wakeup. The lower the
efficiency, the more runqueues were scanned before an idle CPU
was found.
SIS Domain Search Efficiency(dom_eff%):
Similar, except only for the slower SIS
patch.
SIS Fast Success Rate(fast_rate%):
Percentage of SIS that used target, prev or
recent CPUs.
SIS Success rate(success_rate%):
Percentage of scans that found an idle CPU.
The test is based on Aubrey's schedtests tool, including netperf, hackbench,
schbench and tbench.
Test on vanilla kernel:
schedstat_parse.py -f netperf_vanilla.log
case load se_eff% dom_eff% fast_rate% success_rate%
TCP_RR 28 threads 99.978 18.535 99.995 100.000
TCP_RR 56 threads 99.397 5.671 99.964 100.000
TCP_RR 84 threads 21.721 6.818 73.632 100.000
TCP_RR 112 threads 12.500 5.533 59.000 100.000
TCP_RR 140 threads 8.524 4.535 49.020 100.000
TCP_RR 168 threads 6.438 3.945 40.309 99.999
TCP_RR 196 threads 5.397 3.718 32.320 99.982
TCP_RR 224 threads 4.874 3.661 25.775 99.767
UDP_RR 28 threads 99.988 17.704 99.997 100.000
UDP_RR 56 threads 99.528 5.977 99.970 100.000
UDP_RR 84 threads 24.219 6.992 76.479 100.000
UDP_RR 112 threads 13.907 5.706 62.538 100.000
UDP_RR 140 threads 9.408 4.699 52.519 100.000
UDP_RR 168 threads 7.095 4.077 44.352 100.000
UDP_RR 196 threads 5.757 3.775 35.764 99.991
UDP_RR 224 threads 5.124 3.704 28.748 99.860
schedstat_parse.py -f schbench_vanilla.log
(each group has 28 tasks)
case load se_eff% dom_eff% fast_rate% success_rate%
normal 1 mthread 99.152 6.400 99.941 100.000
normal 2 mthreads 97.844 4.003 99.908 100.000
normal 3 mthreads 96.395 2.118 99.917 99.998
normal 4 mthreads 55.288 1.451 98.615 99.804
normal 5 mthreads 7.004 1.870 45.597 61.036
normal 6 mthreads 3.354 1.346 20.777 34.230
normal 7 mthreads 2.183 1.028 11.257 21.055
normal 8 mthreads 1.653 0.825 7.849 15.549
schedstat_parse.py -f hackbench_vanilla.log
(each group has 28 tasks)
case load se_eff% dom_eff% fast_rate% success_rate%
process-pipe 1 group 99.991 7.692 99.999 100.000
process-pipe 2 groups 99.934 4.615 99.997 100.000
process-pipe 3 groups 99.597 3.198 99.987 100.000
process-pipe 4 groups 98.378 2.464 99.958 100.000
process-pipe 5 groups 27.474 3.653 89.811 99.800
process-pipe 6 groups 20.201 4.098 82.763 99.570
process-pipe 7 groups 16.423 4.156 77.398 99.316
process-pipe 8 groups 13.165 3.920 72.232 98.828
process-sockets 1 group 99.977 5.882 99.999 100.000
process-sockets 2 groups 99.927 5.505 99.996 100.000
process-sockets 3 groups 99.397 3.250 99.980 100.000
process-sockets 4 groups 79.680 4.258 98.864 99.998
process-sockets 5 groups 7.673 2.503 63.659 92.115
process-sockets 6 groups 4.642 1.584 58.946 88.048
process-sockets 7 groups 3.493 1.379 49.816 81.164
process-sockets 8 groups 3.015 1.407 40.845 75.500
threads-pipe 1 group 99.997 0.000 100.000 100.000
threads-pipe 2 groups 99.894 2.932 99.997 100.000
threads-pipe 3 groups 99.611 4.117 99.983 100.000
threads-pipe 4 groups 97.703 2.624 99.937 100.000
threads-pipe 5 groups 22.919 3.623 87.150 99.764
threads-pipe 6 groups 18.016 4.038 80.491 99.557
threads-pipe 7 groups 14.663 3.991 75.239 99.247
threads-pipe 8 groups 12.242 3.808 70.651 98.644
threads-sockets 1 group 99.990 6.667 99.999 100.000
threads-sockets 2 groups 99.940 5.114 99.997 100.000
threads-sockets 3 groups 99.469 4.115 99.977 100.000
threads-sockets 4 groups 87.528 4.038 99.400 100.000
threads-sockets 5 groups 6.942 2.398 59.244 88.337
threads-sockets 6 groups 4.359 1.954 49.448 87.860
threads-sockets 7 groups 2.845 1.345 41.198 77.102
threads-sockets 8 groups 2.871 1.404 38.512 74.312
schedstat_parse.py -f tbench_vanilla.log
case load se_eff% dom_eff% fast_rate% success_rate%
loopback 28 threads 99.976 18.369 99.995 100.000
loopback 56 threads 99.222 7.799 99.934 100.000
loopback 84 threads 19.723 6.819 70.215 100.000
loopback 112 threads 11.283 5.371 55.371 99.999
loopback 140 threads 0.000 0.000 0.000 0.000
loopback 168 threads 0.000 0.000 0.000 0.000
loopback 196 threads 0.000 0.000 0.000 0.000
loopback 224 threads 0.000 0.000 0.000 0.000
According to the test above, if the system becomes busy, the
SIS Search Efficiency(se_eff%) drops significantly. Although some
benchmarks would finally find an idle CPU(success_rate% = 100%), it is
doubtful whether it is worth it to search the whole LLC domain.
[Proposal]
It would be ideal to have a crystal ball to answer this question:
How many CPUs must a wakeup path walk down, before it can find an idle
CPU? Many potential metrics could be used to predict the number.
One candidate is the sum of util_avg in this LLC domain. The benefit
of choosing util_avg is that it is a metric of accumulated historic
activity, which seems to be smoother than instantaneous metrics
(such as rq->nr_running). Besides, choosing the sum of util_avg
would help predict the load of the LLC domain more precisely, because
SIS_PROP uses one CPU's idle time to estimate the total LLC domain idle
time.
In summary, the lower the util_avg is, the more select_idle_cpu()
should scan for idle CPU, and vice versa. When the sum of util_avg
in this LLC domain hits 85% or above, the scan stops. The reason to
choose 85% as the threshold is that this is the imbalance_pct(117)
when a LLC sched group is overloaded.
Introduce the quadratic function:
y = SCHED_CAPACITY_SCALE - p * x^2
and y'= y / SCHED_CAPACITY_SCALE
x is the ratio of sum_util compared to the CPU capacity:
x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE)
y' is the ratio of CPUs to be scanned in the LLC domain,
and the number of CPUs to scan is calculated by:
nr_scan = llc_weight * y'
Choosing quadratic function is because:
[1] Compared to the linear function, it scans more aggressively when the
sum_util is low.
[2] Compared to the exponential function, it is easier to calculate.
[3] It seems that there is no accurate mapping between the sum of util_avg
and the number of CPUs to be scanned. Use heuristic scan for now.
For a platform with 112 CPUs per LLC, the number of CPUs to scan is:
sum_util% 0 5 15 25 35 45 55 65 75 85 86 ...
scan_nr 112 111 108 102 93 81 65 47 25 1 0 ...
For a platform with 16 CPUs per LLC, the number of CPUs to scan is:
sum_util% 0 5 15 25 35 45 55 65 75 85 86 ...
scan_nr 16 15 15 14 13 11 9 6 3 0 0 ...
Furthermore, to minimize the overhead of calculating the metrics in
select_idle_cpu(), borrow the statistics from periodic load balance.
As mentioned by Abel, on a platform with 112 CPUs per LLC, the
sum_util calculated by periodic load balance after 112 ms would
decay to about 0.5 * 0.5 * 0.5 * 0.7 = 8.75%, thus bringing a delay
in reflecting the latest utilization. But it is a trade-off.
Checking the util_avg in newidle load balance would be more frequent,
but it brings overhead - multiple CPUs write/read the per-LLC shared
variable and introduces cache contention. Tim also mentioned that,
it is allowed to be non-optimal in terms of scheduling for the
short-term variations, but if there is a long-term trend in the load
behavior, the scheduler can adjust for that.
When SIS_UTIL is enabled, the select_idle_cpu() uses the nr_scan
calculated by SIS_UTIL instead of the one from SIS_PROP. As Peter and
Mel suggested, SIS_UTIL should be enabled by default.
This patch is based on the util_avg, which is very sensitive to the
CPU frequency invariance. There is an issue that, when the max frequency
has been clamp, the util_avg would decay insanely fast when
the CPU is idle. Commit addca28512 ("cpufreq: intel_pstate: Handle no_turbo
in frequency invariance") could be used to mitigate this symptom, by adjusting
the arch_max_freq_ratio when turbo is disabled. But this issue is still
not thoroughly fixed, because the current code is unaware of the user-specified
max CPU frequency.
[Test result]
netperf and tbench were launched with 25% 50% 75% 100% 125% 150%
175% 200% of CPU number respectively. Hackbench and schbench were launched
by 1, 2 ,4, 8 groups. Each test lasts for 100 seconds and repeats 3 times.
The following is the benchmark result comparison between
baseline:vanilla v5.19-rc1 and compare:patched kernel. Positive compare%
indicates better performance.
Each netperf test is a:
netperf -4 -H 127.0.1 -t TCP/UDP_RR -c -C -l 100
netperf.throughput
=======
case load baseline(std%) compare%( std%)
TCP_RR 28 threads 1.00 ( 0.34) -0.16 ( 0.40)
TCP_RR 56 threads 1.00 ( 0.19) -0.02 ( 0.20)
TCP_RR 84 threads 1.00 ( 0.39) -0.47 ( 0.40)
TCP_RR 112 threads 1.00 ( 0.21) -0.66 ( 0.22)
TCP_RR 140 threads 1.00 ( 0.19) -0.69 ( 0.19)
TCP_RR 168 threads 1.00 ( 0.18) -0.48 ( 0.18)
TCP_RR 196 threads 1.00 ( 0.16) +194.70 ( 16.43)
TCP_RR 224 threads 1.00 ( 0.16) +197.30 ( 7.85)
UDP_RR 28 threads 1.00 ( 0.37) +0.35 ( 0.33)
UDP_RR 56 threads 1.00 ( 11.18) -0.32 ( 0.21)
UDP_RR 84 threads 1.00 ( 1.46) -0.98 ( 0.32)
UDP_RR 112 threads 1.00 ( 28.85) -2.48 ( 19.61)
UDP_RR 140 threads 1.00 ( 0.70) -0.71 ( 14.04)
UDP_RR 168 threads 1.00 ( 14.33) -0.26 ( 11.16)
UDP_RR 196 threads 1.00 ( 12.92) +186.92 ( 20.93)
UDP_RR 224 threads 1.00 ( 11.74) +196.79 ( 18.62)
Take the 224 threads as an example, the SIS search metrics changes are
illustrated below:
vanilla patched
4544492 +237.5% 15338634 sched_debug.cpu.sis_domain_search.avg
38539 +39686.8% 15333634 sched_debug.cpu.sis_failed.avg
128300000 -87.9% 15551326 sched_debug.cpu.sis_scanned.avg
5842896 +162.7% 15347978 sched_debug.cpu.sis_search.avg
There is -87.9% less CPU scans after patched, which indicates lower overhead.
Besides, with this patch applied, there is -13% less rq lock contention
in perf-profile.calltrace.cycles-pp._raw_spin_lock.raw_spin_rq_lock_nested
.try_to_wake_up.default_wake_function.woken_wake_function.
This might help explain the performance improvement - Because this patch allows
the waking task to remain on the previous CPU, rather than grabbing other CPUs'
lock.
Each hackbench test is a:
hackbench -g $job --process/threads --pipe/sockets -l 1000000 -s 100
hackbench.throughput
=========
case load baseline(std%) compare%( std%)
process-pipe 1 group 1.00 ( 1.29) +0.57 ( 0.47)
process-pipe 2 groups 1.00 ( 0.27) +0.77 ( 0.81)
process-pipe 4 groups 1.00 ( 0.26) +1.17 ( 0.02)
process-pipe 8 groups 1.00 ( 0.15) -4.79 ( 0.02)
process-sockets 1 group 1.00 ( 0.63) -0.92 ( 0.13)
process-sockets 2 groups 1.00 ( 0.03) -0.83 ( 0.14)
process-sockets 4 groups 1.00 ( 0.40) +5.20 ( 0.26)
process-sockets 8 groups 1.00 ( 0.04) +3.52 ( 0.03)
threads-pipe 1 group 1.00 ( 1.28) +0.07 ( 0.14)
threads-pipe 2 groups 1.00 ( 0.22) -0.49 ( 0.74)
threads-pipe 4 groups 1.00 ( 0.05) +1.88 ( 0.13)
threads-pipe 8 groups 1.00 ( 0.09) -4.90 ( 0.06)
threads-sockets 1 group 1.00 ( 0.25) -0.70 ( 0.53)
threads-sockets 2 groups 1.00 ( 0.10) -0.63 ( 0.26)
threads-sockets 4 groups 1.00 ( 0.19) +11.92 ( 0.24)
threads-sockets 8 groups 1.00 ( 0.08) +4.31 ( 0.11)
Each tbench test is a:
tbench -t 100 $job 127.0.0.1
tbench.throughput
======
case load baseline(std%) compare%( std%)
loopback 28 threads 1.00 ( 0.06) -0.14 ( 0.09)
loopback 56 threads 1.00 ( 0.03) -0.04 ( 0.17)
loopback 84 threads 1.00 ( 0.05) +0.36 ( 0.13)
loopback 112 threads 1.00 ( 0.03) +0.51 ( 0.03)
loopback 140 threads 1.00 ( 0.02) -1.67 ( 0.19)
loopback 168 threads 1.00 ( 0.38) +1.27 ( 0.27)
loopback 196 threads 1.00 ( 0.11) +1.34 ( 0.17)
loopback 224 threads 1.00 ( 0.11) +1.67 ( 0.22)
Each schbench test is a:
schbench -m $job -t 28 -r 100 -s 30000 -c 30000
schbench.latency_90%_us
========
case load baseline(std%) compare%( std%)
normal 1 mthread 1.00 ( 31.22) -7.36 ( 20.25)*
normal 2 mthreads 1.00 ( 2.45) -0.48 ( 1.79)
normal 4 mthreads 1.00 ( 1.69) +0.45 ( 0.64)
normal 8 mthreads 1.00 ( 5.47) +9.81 ( 14.28)
*Consider the Standard Deviation, this -7.36% regression might not be valid.
Also, a OLTP workload with a commercial RDBMS has been tested, and there
is no significant change.
There were concerns that unbalanced tasks among CPUs would cause problems.
For example, suppose the LLC domain is composed of 8 CPUs, and 7 tasks are
bound to CPU0~CPU6, while CPU7 is idle:
CPU0 CPU1 CPU2 CPU3 CPU4 CPU5 CPU6 CPU7
util_avg 1024 1024 1024 1024 1024 1024 1024 0
Since the util_avg ratio is 87.5%( = 7/8 ), which is higher than 85%,
select_idle_cpu() will not scan, thus CPU7 is undetected during scan.
But according to Mel, it is unlikely the CPU7 will be idle all the time
because CPU7 could pull some tasks via CPU_NEWLY_IDLE.
lkp(kernel test robot) has reported a regression on stress-ng.sock on a
very busy system. According to the sched_debug statistics, it might be caused
by SIS_UTIL terminates the scan and chooses a previous CPU earlier, and this
might introduce more context switch, especially involuntary preemption, which
impacts a busy stress-ng. This regression has shown that, not all benchmarks
in every scenario benefit from idle CPU scan limit, and it needs further
investigation.
Besides, there is slight regression in hackbench's 16 groups case when the
LLC domain has 16 CPUs. Prateek mentioned that we should scan aggressively
in an LLC domain with 16 CPUs. Because the cost to search for an idle one
among 16 CPUs is negligible. The current patch aims to propose a generic
solution and only considers the util_avg. Something like the below could
be applied on top of the current patch to fulfill the requirement:
if (llc_weight <= 16)
nr_scan = nr_scan * 32 / llc_weight;
For LLC domain with 16 CPUs, the nr_scan will be expanded to 2 times large.
The smaller the CPU number this LLC domain has, the larger nr_scan will be
expanded. This needs further investigation.
There is also ongoing work[2] from Abel to filter out the busy CPUs during
wakeup, to further speed up the idle CPU scan. And it could be a following-up
optimization on top of this change.
Suggested-by: Tim Chen <tim.c.chen@intel.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Tested-by: Mohini Narkhede <mohini.narkhede@intel.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20220612163428.849378-1-yu.c.chen@intel.com
While doing newidle load balancing, it is possible for new tasks to
arrive, such as with pending wakeups. newidle_balance() already accounts
for this by exiting the sched_domain load_balance() iteration if it
detects these cases. This is very important for minimizing wakeup
latency.
However, if we are already in load_balance(), we may stay there for a
while before returning back to newidle_balance(). This is most
exacerbated if we enter a 'goto redo' loop in the LBF_ALL_PINNED case. A
very straightforward workaround to this is to adjust should_we_balance()
to bail out if we're doing a CPU_NEWLY_IDLE balance and new tasks are
detected.
This was tested with the following reproduction:
- two threads that take turns sleeping and waking each other up are
affined to two cores
- a large number of threads with 100% utilization are pinned to all
other cores
Without this patch, wakeup latency was ~120us for the pair of threads,
almost entirely spent in load_balance(). With this patch, wakeup latency
is ~6us.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220609025515.2086253-1-joshdon@google.com
We notice the rq leaf_cfs_rq_list has two problems when do bugfix
backports and some test profiling.
1. cfs_rqs under throttled subtree could be added to the list, and
make their fully decayed ancestors on the list, even though not needed.
2. #1 also make the leaf_cfs_rq_list management complex and error prone,
this is the list of related bugfix so far:
commit 31bc6aeaab ("sched/fair: Optimize update_blocked_averages()")
commit fe61468b2c ("sched/fair: Fix enqueue_task_fair warning")
commit b34cb07dde ("sched/fair: Fix enqueue_task_fair() warning some more")
commit 39f23ce07b ("sched/fair: Fix unthrottle_cfs_rq() for leaf_cfs_rq list")
commit 0258bdfaff ("sched/fair: Fix unfairness caused by missing load decay")
commit a7b359fc6a ("sched/fair: Correctly insert cfs_rq's to list on unthrottle")
commit fdaba61ef8 ("sched/fair: Ensure that the CFS parent is added after unthrottling")
commit 2630cde267 ("sched/fair: Add ancestors of unthrottled undecayed cfs_rq")
commit 31bc6aeaab ("sched/fair: Optimize update_blocked_averages()")
delete every cfs_rq under throttled subtree from rq->leaf_cfs_rq_list,
and delete the throttled_hierarchy() test in update_blocked_averages(),
which optimized update_blocked_averages().
But those later bugfix add cfs_rqs under throttled subtree back to
rq->leaf_cfs_rq_list again, with their fully decayed ancestors, for
the integrity of rq->leaf_cfs_rq_list.
This patch takes another method, skip all cfs_rqs under throttled
hierarchy when list_add_leaf_cfs_rq(), to completely make cfs_rqs
under throttled subtree off the leaf_cfs_rq_list.
So we don't need to consider throttled related things in
enqueue_entity(), unthrottle_cfs_rq() and enqueue_task_fair(),
which simplify the code a lot. Also optimize update_blocked_averages()
since cfs_rqs under throttled hierarchy and their ancestors
won't be on the leaf_cfs_rq_list.
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220601021848.76943-1-zhouchengming@bytedance.com
In the case of systems containing multiple LLCs per socket, like
AMD Zen systems, users want to spread bandwidth hungry applications
across multiple LLCs. Stream is one such representative workload where
the best performance is obtained by limiting one stream thread per LLC.
To ensure this, users are known to pin the tasks to a specify a subset
of the CPUs consisting of one CPU per LLC while running such bandwidth
hungry tasks.
Suppose we kickstart a multi-threaded task like stream with 8 threads
using taskset or numactl to run on a subset of CPUs on a 2 socket Zen3
server where each socket contains 128 CPUs
(0-63,128-191 in one socket, 64-127,192-255 in another socket)
Eg: numactl -C 0,16,32,48,64,80,96,112 ./stream8
Here each CPU in the list is from a different LLC and 4 of those LLCs
are on one socket, while the other 4 are on another socket.
Ideally we would prefer that each stream thread runs on a different
CPU from the allowed list of CPUs. However, the current heuristics in
find_idlest_group() do not allow this during the initial placement.
Suppose the first socket (0-63,128-191) is our local group from which
we are kickstarting the stream tasks. The first four stream threads
will be placed in this socket. When it comes to placing the 5th
thread, all the allowed CPUs are from the local group (0,16,32,48)
would have been taken.
However, the current scheduler code simply checks if the number of
tasks in the local group is fewer than the allowed numa-imbalance
threshold. This threshold was previously 25% of the NUMA domain span
(in this case threshold = 32) but after the v6 of Mel's patchset
"Adjust NUMA imbalance for multiple LLCs", got merged in sched-tip,
Commit: e496132ebe ("sched/fair: Adjust the allowed NUMA imbalance
when SD_NUMA spans multiple LLCs") it is now equal to number of LLCs
in the NUMA domain, for processors with multiple LLCs.
(in this case threshold = 8).
For this example, the number of tasks will always be within threshold
and thus all the 8 stream threads will be woken up on the first socket
thereby resulting in sub-optimal performance.
The following sched_wakeup_new tracepoint output shows the initial
placement of tasks in the current tip/sched/core on the Zen3 machine:
stream-5313 [016] d..2. 627.005036: sched_wakeup_new: comm=stream pid=5315 prio=120 target_cpu=032
stream-5313 [016] d..2. 627.005086: sched_wakeup_new: comm=stream pid=5316 prio=120 target_cpu=048
stream-5313 [016] d..2. 627.005141: sched_wakeup_new: comm=stream pid=5317 prio=120 target_cpu=000
stream-5313 [016] d..2. 627.005183: sched_wakeup_new: comm=stream pid=5318 prio=120 target_cpu=016
stream-5313 [016] d..2. 627.005218: sched_wakeup_new: comm=stream pid=5319 prio=120 target_cpu=016
stream-5313 [016] d..2. 627.005256: sched_wakeup_new: comm=stream pid=5320 prio=120 target_cpu=016
stream-5313 [016] d..2. 627.005295: sched_wakeup_new: comm=stream pid=5321 prio=120 target_cpu=016
Once the first four threads are distributed among the allowed CPUs of
socket one, the rest of the treads start piling on these same CPUs
when clearly there are CPUs on the second socket that can be used.
Following the initial pile up on a small number of CPUs, though the
load-balancer eventually kicks in, it takes a while to get to {4}{4}
and even {4}{4} isn't stable as we observe a bunch of ping ponging
between {4}{4} to {5}{3} and back before a stable state is reached
much later (1 Stream thread per allowed CPU) and no more migration is
required.
We can detect this piling and avoid it by checking if the number of
allowed CPUs in the local group are fewer than the number of tasks
running in the local group and use this information to spread the
5th task out into the next socket (after all, the goal in this
slowpath is to find the idlest group and the idlest CPU during the
initial placement!).
The following sched_wakeup_new tracepoint output shows the initial
placement of tasks after adding this fix on the Zen3 machine:
stream-4485 [016] d..2. 230.784046: sched_wakeup_new: comm=stream pid=4487 prio=120 target_cpu=032
stream-4485 [016] d..2. 230.784123: sched_wakeup_new: comm=stream pid=4488 prio=120 target_cpu=048
stream-4485 [016] d..2. 230.784167: sched_wakeup_new: comm=stream pid=4489 prio=120 target_cpu=000
stream-4485 [016] d..2. 230.784222: sched_wakeup_new: comm=stream pid=4490 prio=120 target_cpu=112
stream-4485 [016] d..2. 230.784271: sched_wakeup_new: comm=stream pid=4491 prio=120 target_cpu=096
stream-4485 [016] d..2. 230.784322: sched_wakeup_new: comm=stream pid=4492 prio=120 target_cpu=080
stream-4485 [016] d..2. 230.784368: sched_wakeup_new: comm=stream pid=4493 prio=120 target_cpu=064
We see that threads are using all of the allowed CPUs and there is
no pileup.
No output is generated for tracepoint sched_migrate_task with this
patch due to a perfect initial placement which removes the need
for balancing later on - both across NUMA boundaries and within
NUMA boundaries for stream.
Following are the results from running 8 Stream threads with and
without pinning on a dual socket Zen3 Machine (2 x 64C/128T):
During the testing of this patch, the tip sched/core was at
commit: 089c02ae27 "ftrace: Use preemption model accessors for trace
header printout"
Pinning is done using: numactl -C 0,16,32,48,64,80,96,112 ./stream8
5.18.0-rc1 5.18.0-rc1 5.18.0-rc1
tip sched/core tip sched/core tip sched/core
(no pinning) + pinning + this-patch
+ pinning
Copy: 109364.74 (0.00 pct) 94220.50 (-13.84 pct) 158301.28 (44.74 pct)
Scale: 109670.26 (0.00 pct) 90210.59 (-17.74 pct) 149525.64 (36.34 pct)
Add: 129029.01 (0.00 pct) 101906.00 (-21.02 pct) 186658.17 (44.66 pct)
Triad: 127260.05 (0.00 pct) 106051.36 (-16.66 pct) 184327.30 (44.84 pct)
Pinning currently hurts the performance compared to unbound case on
tip/sched/core. With the addition of this patch, we are able to
outperform tip/sched/core by a good margin with pinning.
Following are the results from running 16 Stream threads with and
without pinning on a dual socket IceLake Machine (2 x 32C/64T):
NUMA Topology of Intel Skylake machine:
Node 1: 0,2,4,6 ... 126 (Even numbers)
Node 2: 1,3,5,7 ... 127 (Odd numbers)
Pinning is done using: numactl -C 0-15 ./stream16
5.18.0-rc1 5.18.0-rc1 5.18.0-rc1
tip sched/core tip sched/core tip sched/core
(no pinning) +pinning + this-patch
+ pinning
Copy: 85815.31 (0.00 pct) 149819.21 (74.58 pct) 156807.48 (82.72 pct)
Scale: 64795.60 (0.00 pct) 97595.07 (50.61 pct) 99871.96 (54.13 pct)
Add: 71340.68 (0.00 pct) 111549.10 (56.36 pct) 114598.33 (60.63 pct)
Triad: 68890.97 (0.00 pct) 111635.16 (62.04 pct) 114589.24 (66.33 pct)
In case of Icelake machine, with single LLC per socket, pinning across
the two sockets reduces cache contention, thus showing great
improvement in pinned case which is further benefited by this patch.
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20220407111222.22649-1-kprateek.nayak@amd.com
The imbalance limitations are applied inconsistently at fork time
and at runtime. At fork, a new task can remain local until there are
too many running tasks even if the degree of imbalance is larger than
NUMA_IMBALANCE_MIN which is different to runtime. Secondly, the imbalance
figure used during load balancing is different to the one used at NUMA
placement. Load balancing uses the number of tasks that must move to
restore imbalance where as NUMA balancing uses the total imbalance.
In combination, it is possible for a parallel workload that uses a small
number of CPUs without applying scheduler policies to have very variable
run-to-run performance.
[lkp@intel.com: Fix build breakage for arc-allyesconfig]
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20220520103519.1863-4-mgorman@techsingularity.net
If a destination node has spare capacity but there is an imbalance then
two tasks are selected for swapping. If the tasks have no numa group
or are within the same NUMA group, it's simply shuffling tasks around
without having any impact on the compute imbalance. Instead, it's just
punishing one task to help another.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20220520103519.1863-3-mgorman@techsingularity.net
On clone, numa_migrate_retry is inherited from the parent which means
that the first NUMA placement of a task is non-deterministic. This
affects when load balancing recognises numa tasks and whether to
migrate "regular", "remote" or "all" tasks between NUMA scheduler
domains.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20220520103519.1863-2-mgorman@techsingularity.net
ordinary user mode tasks.
In commit 40966e316f ("kthread: Ensure struct kthread is present for
all kthreads") caused init and the user mode helper threads that call
kernel_execve to have struct kthread allocated for them. This struct
kthread going away during execve in turned made a use after free of
struct kthread possible.
The commit 343f4c49f2 ("kthread: Don't allocate kthread_struct for
init and umh") is enough to fix the use after free and is simple enough
to be backportable.
The rest of the changes pass struct kernel_clone_args to clean things
up and cause the code to make sense.
In making init and the user mode helpers tasks purely user mode tasks
I ran into two complications. The function task_tick_numa was
detecting tasks without an mm by testing for the presence of
PF_KTHREAD. The initramfs code in populate_initrd_image was using
flush_delayed_fput to ensuere the closing of all it's file descriptors
was complete, and flush_delayed_fput does not work in a userspace thread.
I have looked and looked and more complications and in my code review
I have not found any, and neither has anyone else with the code sitting
in linux-next.
Link: https://lkml.kernel.org/r/87mtfu4up3.fsf@email.froward.int.ebiederm.org
Eric W. Biederman (8):
kthread: Don't allocate kthread_struct for init and umh
fork: Pass struct kernel_clone_args into copy_thread
fork: Explicity test for idle tasks in copy_thread
fork: Generalize PF_IO_WORKER handling
init: Deal with the init process being a user mode process
fork: Explicitly set PF_KTHREAD
fork: Stop allowing kthreads to call execve
sched: Update task_tick_numa to ignore tasks without an mm
arch/alpha/kernel/process.c | 13 ++++++------
arch/arc/kernel/process.c | 13 ++++++------
arch/arm/kernel/process.c | 12 ++++++-----
arch/arm64/kernel/process.c | 12 ++++++-----
arch/csky/kernel/process.c | 15 ++++++-------
arch/h8300/kernel/process.c | 10 ++++-----
arch/hexagon/kernel/process.c | 12 ++++++-----
arch/ia64/kernel/process.c | 15 +++++++------
arch/m68k/kernel/process.c | 12 ++++++-----
arch/microblaze/kernel/process.c | 12 ++++++-----
arch/mips/kernel/process.c | 13 ++++++------
arch/nios2/kernel/process.c | 12 ++++++-----
arch/openrisc/kernel/process.c | 12 ++++++-----
arch/parisc/kernel/process.c | 18 +++++++++-------
arch/powerpc/kernel/process.c | 15 +++++++------
arch/riscv/kernel/process.c | 12 ++++++-----
arch/s390/kernel/process.c | 12 ++++++-----
arch/sh/kernel/process_32.c | 12 ++++++-----
arch/sparc/kernel/process_32.c | 12 ++++++-----
arch/sparc/kernel/process_64.c | 12 ++++++-----
arch/um/kernel/process.c | 15 +++++++------
arch/x86/include/asm/fpu/sched.h | 2 +-
arch/x86/include/asm/switch_to.h | 8 +++----
arch/x86/kernel/fpu/core.c | 4 ++--
arch/x86/kernel/process.c | 18 +++++++++-------
arch/xtensa/kernel/process.c | 17 ++++++++-------
fs/exec.c | 8 ++++---
include/linux/sched/task.h | 8 +++++--
init/initramfs.c | 2 ++
init/main.c | 2 +-
kernel/fork.c | 46 +++++++++++++++++++++++++++++++++-------
kernel/sched/fair.c | 2 +-
kernel/umh.c | 6 +++---
33 files changed, 234 insertions(+), 160 deletions(-)
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
-----BEGIN PGP SIGNATURE-----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=x6fy
-----END PGP SIGNATURE-----
Merge tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull kthread updates from Eric Biederman:
"This updates init and user mode helper tasks to be ordinary user mode
tasks.
Commit 40966e316f ("kthread: Ensure struct kthread is present for
all kthreads") caused init and the user mode helper threads that call
kernel_execve to have struct kthread allocated for them. This struct
kthread going away during execve in turned made a use after free of
struct kthread possible.
Here, commit 343f4c49f2 ("kthread: Don't allocate kthread_struct for
init and umh") is enough to fix the use after free and is simple
enough to be backportable.
The rest of the changes pass struct kernel_clone_args to clean things
up and cause the code to make sense.
In making init and the user mode helpers tasks purely user mode tasks
I ran into two complications. The function task_tick_numa was
detecting tasks without an mm by testing for the presence of
PF_KTHREAD. The initramfs code in populate_initrd_image was using
flush_delayed_fput to ensuere the closing of all it's file descriptors
was complete, and flush_delayed_fput does not work in a userspace
thread.
I have looked and looked and more complications and in my code review
I have not found any, and neither has anyone else with the code
sitting in linux-next"
* tag 'kthread-cleanups-for-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
sched: Update task_tick_numa to ignore tasks without an mm
fork: Stop allowing kthreads to call execve
fork: Explicitly set PF_KTHREAD
init: Deal with the init process being a user mode process
fork: Generalize PF_IO_WORKER handling
fork: Explicity test for idle tasks in copy_thread
fork: Pass struct kernel_clone_args into copy_thread
kthread: Don't allocate kthread_struct for init and umh
For two kernel releases now kernel/sysctl.c has been being cleaned up
slowly, since the tables were grossly long, sprinkled with tons of #ifdefs and
all this caused merge conflicts with one susbystem or another.
This tree was put together to help try to avoid conflicts with these cleanups
going on different trees at time. So nothing exciting on this pull request,
just cleanups.
I actually had this sysctl-next tree up since v5.18 but I missed sending a
pull request for it on time during the last merge window. And so these changes
have been being soaking up on sysctl-next and so linux-next for a while.
The last change was merged May 4th.
Most of the compile issues were reported by 0day and fixed.
To help avoid a conflict with bpf folks at Daniel Borkmann's request
I merged bpf-next/pr/bpf-sysctl into sysctl-next to get the effor which
moves the BPF sysctls from kernel/sysctl.c to BPF core.
Possible merge conflicts and known resolutions as per linux-next:
bfp:
https://lkml.kernel.org/r/20220414112812.652190b5@canb.auug.org.au
rcu:
https://lkml.kernel.org/r/20220420153746.4790d532@canb.auug.org.au
powerpc:
https://lkml.kernel.org/r/20220520154055.7f964b76@canb.auug.org.au
-----BEGIN PGP SIGNATURE-----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=btwh
-----END PGP SIGNATURE-----
Merge tag 'sysctl-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux
Pull sysctl updates from Luis Chamberlain:
"For two kernel releases now kernel/sysctl.c has been being cleaned up
slowly, since the tables were grossly long, sprinkled with tons of
#ifdefs and all this caused merge conflicts with one susbystem or
another.
This tree was put together to help try to avoid conflicts with these
cleanups going on different trees at time. So nothing exciting on this
pull request, just cleanups.
Thanks a lot to the Uniontech and Huawei folks for doing some of this
nasty work"
* tag 'sysctl-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: (28 commits)
sched: Fix build warning without CONFIG_SYSCTL
reboot: Fix build warning without CONFIG_SYSCTL
kernel/kexec_core: move kexec_core sysctls into its own file
sysctl: minor cleanup in new_dir()
ftrace: fix building with SYSCTL=y but DYNAMIC_FTRACE=n
fs/proc: Introduce list_for_each_table_entry for proc sysctl
mm: fix unused variable kernel warning when SYSCTL=n
latencytop: move sysctl to its own file
ftrace: fix building with SYSCTL=n but DYNAMIC_FTRACE=y
ftrace: Fix build warning
ftrace: move sysctl_ftrace_enabled to ftrace.c
kernel/do_mount_initrd: move real_root_dev sysctls to its own file
kernel/delayacct: move delayacct sysctls to its own file
kernel/acct: move acct sysctls to its own file
kernel/panic: move panic sysctls to its own file
kernel/lockdep: move lockdep sysctls to its own file
mm: move page-writeback sysctls to their own file
mm: move oom_kill sysctls to their own file
kernel/reboot: move reboot sysctls to its own file
sched: Move energy_aware sysctls to topology.c
...
Qian Cai <quic_qiancai@quicinc.com> wrote:
> Reverting the last 3 commits of the series fixed a boot crash.
>
> 1b2552cbdb fork: Stop allowing kthreads to call execve
> 753550eb0c fork: Explicitly set PF_KTHREAD
> 68d85f0a33 init: Deal with the init process being a user mode process
>
> BUG: KASAN: null-ptr-deref in task_nr_scan_windows.isra.0
> arch_atomic_long_read at ./include/linux/atomic/atomic-long.h:29
> (inlined by) atomic_long_read at ./include/linux/atomic/atomic-instrumented.h:1266
> (inlined by) get_mm_counter at ./include/linux/mm.h:1996
> (inlined by) get_mm_rss at ./include/linux/mm.h:2049
> (inlined by) task_nr_scan_windows at kernel/sched/fair.c:1123
> Read of size 8 at addr 00000000000003d0 by task swapper/0/1
With the change to init and the user mode helper processes to not have
PF_KTHREAD set before they call kernel_execve the PF_KTHREAD test in
task_tick_numa became insufficient to detect all tasks that have
"->mm == NULL". Correct that by testing for "->mm == NULL" directly.
Reported-by: Qian Cai <quic_qiancai@quicinc.com>
Tested-by: Qian Cai <quic_qiancai@quicinc.com>
Fixes: 1b2552cbdb ("fork: Stop allowing kthreads to call execve")
Link: https://lkml.kernel.org/r/87r150ug1l.fsf_-_@email.froward.int.ebiederm.org
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
