| Message ID | 20231102032330.1036151-7-chengming.zhou@linux.dev (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | slub: Delay freezing of CPU partial slabs | expand |
Hello,
kernel test robot noticed a 34.2% improvement of stress-ng.rawudp.ops_per_sec on:
commit: b73583016198aecef1dea07033a808da7875ede1 ("[PATCH v5 6/9] slub: Delay freezing of partial slabs")
url: https://github.com/intel-lab-lkp/linux/commits/chengming-zhou-linux-dev/slub-Reflow-___slab_alloc/20231102-112748
base: git://git.kernel.org/cgit/linux/kernel/git/vbabka/slab.git for-next
patch link: https://lore.kernel.org/all/20231102032330.1036151-7-chengming.zhou@linux.dev/
patch subject: [PATCH v5 6/9] slub: Delay freezing of partial slabs
testcase: stress-ng
test machine: 64 threads 2 sockets Intel(R) Xeon(R) Gold 6346 CPU @ 3.10GHz (Ice Lake) with 256G memory
parameters:
nr_threads: 100%
testtime: 60s
class: network
test: rawudp
cpufreq_governor: performance
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20231114/202311141204.e918dbda-oliver.sang@intel.com
=========================================================================================
class/compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime:
network/gcc-12/performance/x86_64-rhel-8.3/100%/debian-11.1-x86_64-20220510.cgz/lkp-icl-2sp8/rawudp/stress-ng/60s
commit:
fae950af3a ("slub: Introduce freeze_slab()")
b735830161 ("slub: Delay freezing of partial slabs")
fae950af3a484ec4 b73583016198aecef1dea07033a
---------------- ---------------------------
%stddev %change %stddev
\ | \
0.51 ± 15% +0.1 0.66 ± 3% mpstat.cpu.all.usr%
30758 ± 11% +41.0% 43361 ± 4% vmstat.system.cs
14033150 +13.1% 15877158 numa-numastat.node0.local_node
14069328 +13.1% 15912745 numa-numastat.node0.numa_hit
14246260 +11.6% 15894273 numa-numastat.node1.local_node
14274705 +11.6% 15927700 numa-numastat.node1.numa_hit
14069250 +13.1% 15912955 numa-vmstat.node0.numa_hit
14033072 +13.1% 15877368 numa-vmstat.node0.numa_local
14274619 +11.6% 15927488 numa-vmstat.node1.numa_hit
14246174 +11.6% 15894061 numa-vmstat.node1.numa_local
0.30 ± 19% +38.5% 0.42 ± 7% sched_debug.cfs_rq:/.nr_running.stddev
2434 ± 4% -10.6% 2176 ± 6% sched_debug.cpu.curr->pid.avg
1079 ± 20% +36.7% 1474 ± 10% sched_debug.cpu.curr->pid.stddev
18781 ± 2% +28.4% 24113 ± 2% sched_debug.cpu.nr_switches.avg
11540 ± 4% +41.8% 16360 ± 5% sched_debug.cpu.nr_switches.min
0.03 +33.3% 0.04 stress-ng.rawudp.MB_recv'd_per_sec
4064768 +34.2% 5456370 stress-ng.rawudp.ops
67734 +34.2% 90929 stress-ng.rawudp.ops_per_sec
757287 ± 2% +31.6% 996382 stress-ng.time.involuntary_context_switches
1112941 ± 2% +40.5% 1564161 ± 2% stress-ng.time.voluntary_context_switches
28346406 +12.3% 31843356 proc-vmstat.numa_hit
28281784 +12.3% 31774341 proc-vmstat.numa_local
103553 ± 2% +6.3% 110100 ± 3% proc-vmstat.numa_pte_updates
128452 +10.1% 141426 ± 2% proc-vmstat.pgactivate
70199954 +10.8% 77804409 proc-vmstat.pgalloc_normal
70032258 +10.8% 77627740 proc-vmstat.pgfree
81626657 ± 11% +20.5% 98326255 ± 3% perf-stat.i.branch-misses
8.365e+08 ± 11% +16.8% 9.77e+08 ± 3% perf-stat.i.cache-references
31476 ± 12% +42.8% 44947 ± 4% perf-stat.i.context-switches
2.46 ± 2% -5.3% 2.33 perf-stat.i.cpi
7610 ± 11% +51.7% 11547 ± 3% perf-stat.i.cpu-migrations
1807 ± 6% -35.8% 1160 ± 9% perf-stat.i.metric.K/sec
67795798 ± 11% +17.2% 79489592 ± 3% perf-stat.i.node-load-misses
42.11 ± 5% +2.2 44.32 perf-stat.i.node-store-miss-rate%
53640005 ± 11% +16.1% 62254015 ± 3% perf-stat.i.node-store-misses
4.42 +3.9% 4.59 perf-stat.overall.MPKI
0.53 +0.0 0.57 perf-stat.overall.branch-miss-rate%
2.46 -4.0% 2.36 perf-stat.overall.cpi
556.40 -7.6% 513.88 perf-stat.overall.cycles-between-cache-misses
0.41 +4.2% 0.42 perf-stat.overall.ipc
59.01 +0.9 59.88 perf-stat.overall.node-load-miss-rate%
80834242 ± 10% +19.7% 96751983 ± 2% perf-stat.ps.branch-misses
3.595e+08 ± 10% +14.6% 4.121e+08 ± 3% perf-stat.ps.cache-misses
8.308e+08 ± 10% +16.1% 9.643e+08 ± 3% perf-stat.ps.cache-references
31157 ± 10% +42.0% 44245 ± 3% perf-stat.ps.context-switches
7566 ± 10% +50.5% 11389 ± 3% perf-stat.ps.cpu-migrations
67342566 ± 10% +16.5% 78472343 ± 2% perf-stat.ps.node-load-misses
53274045 ± 10% +15.4% 61453717 ± 2% perf-stat.ps.node-store-misses
66741521 ± 10% +13.4% 75684953 ± 2% perf-stat.ps.node-stores
5.522e+12 +4.0% 5.742e+12 perf-stat.total.instructions
0.40 ± 5% -28.4% 0.29 ± 8% perf-sched.sch_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
0.58 ± 5% -9.2% 0.53 ± 4% perf-sched.sch_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_datagram.skb_recv_datagram
0.37 ± 11% -38.4% 0.22 ± 16% perf-sched.sch_delay.avg.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread
128.50 ± 19% -30.6% 89.17 ± 18% perf-sched.sch_delay.max.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
0.52 ± 3% -13.8% 0.45 ± 4% perf-sched.total_sch_delay.average.ms
9.51 ± 5% -24.7% 7.16 ± 5% perf-sched.total_wait_and_delay.average.ms
150858 ± 3% +33.8% 201844 ± 6% perf-sched.total_wait_and_delay.count.ms
8.99 ± 5% -25.3% 6.71 ± 5% perf-sched.total_wait_time.average.ms
4.32 ± 4% -34.8% 2.81 ± 7% perf-sched.wait_and_delay.avg.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
3.22 ± 8% -34.3% 2.12 ± 8% perf-sched.wait_and_delay.avg.ms.__cond_resched.slab_pre_alloc_hook.constprop.0.kmem_cache_alloc_lru
47.40 ± 6% -13.9% 40.79 ± 11% perf-sched.wait_and_delay.avg.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
4.93 ± 4% -29.4% 3.48 ± 7% perf-sched.wait_and_delay.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
2.14 ± 5% -16.3% 1.79 ± 4% perf-sched.wait_and_delay.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_datagram.skb_recv_datagram
508.50 ± 7% +39.9% 711.50 ± 9% perf-sched.wait_and_delay.count.__cond_resched.aa_sk_perm.security_socket_recvmsg.sock_recvmsg.__sys_recvfrom
1533 ± 6% +22.0% 1871 ± 6% perf-sched.wait_and_delay.count.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
1003 ± 4% +28.4% 1288 ± 6% perf-sched.wait_and_delay.count.__cond_resched.slab_pre_alloc_hook.constprop.0.kmem_cache_alloc_lru
48937 ± 3% +28.2% 62737 ± 5% perf-sched.wait_and_delay.count.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
86063 ± 4% +39.4% 120002 ± 7% perf-sched.wait_and_delay.count.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_datagram.skb_recv_datagram
6201 ± 3% +14.1% 7077 ± 11% perf-sched.wait_and_delay.count.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
85.45 ±120% +384.6% 414.09 ± 82% perf-sched.wait_and_delay.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
22.16 ±105% +162.1% 58.07 ± 36% perf-sched.wait_and_delay.max.ms.__cond_resched.stop_one_cpu.sched_exec.bprm_execve.part
1.37 ± 17% -38.1% 0.85 ± 26% perf-sched.wait_time.avg.ms.__cond_resched.__kmem_cache_alloc_node.kmalloc_trace.apparmor_sk_alloc_security.security_sk_alloc
2.32 ± 14% -48.3% 1.20 ± 33% perf-sched.wait_time.avg.ms.__cond_resched.aa_sk_perm.security_socket_sendmsg.sock_sendmsg.__sys_sendto
4.31 ± 4% -34.9% 2.81 ± 7% perf-sched.wait_time.avg.ms.__cond_resched.dput.__fput.__x64_sys_close.do_syscall_64
2.24 ± 11% -36.7% 1.42 ± 24% perf-sched.wait_time.avg.ms.__cond_resched.kmem_cache_alloc_node.__alloc_skb.alloc_skb_with_frags.sock_alloc_send_pskb
3.89 ± 41% -57.2% 1.67 ± 36% perf-sched.wait_time.avg.ms.__cond_resched.lock_sock_nested.raw_destroy.sk_common_release.inet_release
3.22 ± 8% -34.2% 2.12 ± 8% perf-sched.wait_time.avg.ms.__cond_resched.slab_pre_alloc_hook.constprop.0.kmem_cache_alloc_lru
47.20 ± 6% -14.0% 40.58 ± 11% perf-sched.wait_time.avg.ms.__cond_resched.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
4.52 ± 4% -29.5% 3.19 ± 7% perf-sched.wait_time.avg.ms.exit_to_user_mode_loop.exit_to_user_mode_prepare.syscall_exit_to_user_mode.do_syscall_64
5.84 ± 24% -45.9% 3.16 ± 40% perf-sched.wait_time.avg.ms.schedule_preempt_disabled.__mutex_lock.constprop.0.ip_ra_control
1.56 ± 5% -19.0% 1.26 ± 4% perf-sched.wait_time.avg.ms.schedule_timeout.__skb_wait_for_more_packets.__skb_recv_datagram.skb_recv_datagram
107.91 ± 77% +281.4% 411.55 ± 82% perf-sched.wait_time.max.ms.__cond_resched.mutex_lock.perf_poll.do_poll.constprop
7.19 -2.9 4.31 ± 4% perf-profile.calltrace.cycles-pp.get_partial_node.___slab_alloc.kmem_cache_alloc.skb_clone.raw_v4_input
10.26 -2.8 7.48 ± 3% perf-profile.calltrace.cycles-pp.___slab_alloc.kmem_cache_alloc.skb_clone.raw_v4_input.ip_protocol_deliver_rcu
12.04 -2.7 9.31 ± 2% perf-profile.calltrace.cycles-pp.kmem_cache_alloc.skb_clone.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish
6.51 -2.7 3.79 ± 5% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.kmem_cache_alloc.skb_clone
12.55 -2.7 9.83 ± 2% perf-profile.calltrace.cycles-pp.skb_clone.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
6.37 -2.7 3.67 ± 5% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.get_partial_node.___slab_alloc.kmem_cache_alloc
6.44 ± 2% -2.1 4.34 ± 5% perf-profile.calltrace.cycles-pp.__unfreeze_partials.raw_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
3.03 ± 4% -2.0 0.99 ± 28% perf-profile.calltrace.cycles-pp.__unfreeze_partials.inet_sock_destruct.__sk_destruct.rcu_do_batch.rcu_core
5.59 ± 2% -1.9 3.67 ± 6% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__unfreeze_partials.raw_recvmsg.inet_recvmsg
2.81 ± 4% -1.9 0.92 ± 29% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__unfreeze_partials.inet_sock_destruct.__sk_destruct.rcu_do_batch
2.69 ± 4% -1.9 0.82 ± 30% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__unfreeze_partials.inet_sock_destruct.__sk_destruct
5.88 ± 2% -1.8 4.07 ± 5% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__unfreeze_partials.raw_recvmsg.inet_recvmsg.sock_recvmsg
15.12 -1.3 13.86 ± 2% perf-profile.calltrace.cycles-pp.inet_sock_destruct.__sk_destruct.rcu_do_batch.rcu_core.__do_softirq
12.74 -1.1 11.66 ± 2% perf-profile.calltrace.cycles-pp.__sk_destruct.rcu_do_batch.rcu_core.__do_softirq.run_ksoftirqd
13.45 -1.1 12.39 ± 2% perf-profile.calltrace.cycles-pp.rcu_do_batch.rcu_core.__do_softirq.run_ksoftirqd.smpboot_thread_fn
13.46 -1.1 12.40 ± 2% perf-profile.calltrace.cycles-pp.rcu_core.__do_softirq.run_ksoftirqd.smpboot_thread_fn.kthread
13.48 -1.1 12.42 ± 2% perf-profile.calltrace.cycles-pp.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
13.49 -1.1 12.43 ± 2% perf-profile.calltrace.cycles-pp.ret_from_fork_asm
13.49 -1.1 12.43 ± 2% perf-profile.calltrace.cycles-pp.ret_from_fork.ret_from_fork_asm
13.49 -1.1 12.43 ± 2% perf-profile.calltrace.cycles-pp.kthread.ret_from_fork.ret_from_fork_asm
13.46 -1.1 12.40 ± 2% perf-profile.calltrace.cycles-pp.__do_softirq.run_ksoftirqd.smpboot_thread_fn.kthread.ret_from_fork
13.46 -1.1 12.40 ± 2% perf-profile.calltrace.cycles-pp.run_ksoftirqd.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm
11.50 -0.6 10.88 ± 2% perf-profile.calltrace.cycles-pp.raw_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom
11.54 -0.6 10.93 ± 2% perf-profile.calltrace.cycles-pp.inet_recvmsg.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64
11.72 -0.5 11.18 ± 2% perf-profile.calltrace.cycles-pp.sock_recvmsg.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe
1.18 ± 3% -0.5 0.71 ± 4% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.get_partial_node.get_any_partial.___slab_alloc.kmem_cache_alloc
1.15 ± 3% -0.5 0.68 ± 4% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.get_partial_node.get_any_partial.___slab_alloc
1.23 ± 3% -0.5 0.77 ± 3% perf-profile.calltrace.cycles-pp.get_partial_node.get_any_partial.___slab_alloc.kmem_cache_alloc.skb_clone
12.05 -0.4 11.61 ± 2% perf-profile.calltrace.cycles-pp.__sys_recvfrom.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recv
12.07 -0.4 11.64 ± 2% perf-profile.calltrace.cycles-pp.__x64_sys_recvfrom.do_syscall_64.entry_SYSCALL_64_after_hwframe.recv
1.38 ± 3% -0.4 0.94 ± 3% perf-profile.calltrace.cycles-pp.get_any_partial.___slab_alloc.kmem_cache_alloc.skb_clone.raw_v4_input
1.84 ± 2% -0.3 1.56 ± 6% perf-profile.calltrace.cycles-pp.__slab_free.inet_sock_destruct.__sk_destruct.rcu_do_batch.rcu_core
0.78 ± 7% -0.1 0.66 ± 5% perf-profile.calltrace.cycles-pp.__do_softirq.do_softirq.__local_bh_enable_ip.sk_common_release.inet_release
0.78 ± 7% -0.1 0.66 ± 5% perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.sk_common_release.inet_release.__sock_release
0.78 ± 7% -0.1 0.66 ± 5% perf-profile.calltrace.cycles-pp.rcu_core.__do_softirq.do_softirq.__local_bh_enable_ip.sk_common_release
0.78 ± 7% -0.1 0.67 ± 5% perf-profile.calltrace.cycles-pp.__local_bh_enable_ip.sk_common_release.inet_release.__sock_release.sock_close
0.52 +0.0 0.55 perf-profile.calltrace.cycles-pp.icmp_route_lookup.__icmp_send.__udp4_lib_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish
0.56 +0.0 0.60 ± 2% perf-profile.calltrace.cycles-pp.new_inode_pseudo.sock_alloc.__sock_create.__sys_socket.__x64_sys_socket
0.57 +0.0 0.61 ± 2% perf-profile.calltrace.cycles-pp.sock_alloc.__sock_create.__sys_socket.__x64_sys_socket.do_syscall_64
0.52 +0.0 0.57 ± 2% perf-profile.calltrace.cycles-pp.alloc_file.alloc_file_pseudo.sock_alloc_file.__sys_socket.__x64_sys_socket
0.73 +0.1 0.78 perf-profile.calltrace.cycles-pp.sock_alloc_file.__sys_socket.__x64_sys_socket.do_syscall_64.entry_SYSCALL_64_after_hwframe
0.72 +0.1 0.78 ± 2% perf-profile.calltrace.cycles-pp.alloc_file_pseudo.sock_alloc_file.__sys_socket.__x64_sys_socket.do_syscall_64
1.03 ± 3% +0.1 1.10 ± 3% perf-profile.calltrace.cycles-pp.sk_filter_trim_cap.sock_queue_rcv_skb_reason.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu
0.59 ± 3% +0.1 0.68 ± 2% perf-profile.calltrace.cycles-pp.allocate_slab.___slab_alloc.kmem_cache_alloc.skb_clone.raw_v4_input
1.14 +0.1 1.22 perf-profile.calltrace.cycles-pp.dst_release.ipv4_pktinfo_prepare.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu
1.96 +0.1 2.05 perf-profile.calltrace.cycles-pp.skb_release_data.kfree_skb_reason.inet_sock_destruct.__sk_destruct.rcu_do_batch
1.64 +0.1 1.75 ± 2% perf-profile.calltrace.cycles-pp.ipv4_pktinfo_prepare.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish
0.42 ± 44% +0.1 0.55 ± 2% perf-profile.calltrace.cycles-pp.alloc_empty_file.alloc_file.alloc_file_pseudo.sock_alloc_file.__sys_socket
2.42 ± 3% +0.1 2.55 ± 3% perf-profile.calltrace.cycles-pp.icmp_socket_deliver.icmp_unreach.icmp_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish
2.41 ± 3% +0.1 2.54 ± 3% perf-profile.calltrace.cycles-pp.raw_icmp_error.icmp_socket_deliver.icmp_unreach.icmp_rcv.ip_protocol_deliver_rcu
2.47 ± 3% +0.1 2.60 ± 3% perf-profile.calltrace.cycles-pp.icmp_unreach.icmp_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
0.66 +0.1 0.80 perf-profile.calltrace.cycles-pp.copyout._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.raw_recvmsg
2.70 ± 2% +0.2 2.84 ± 3% perf-profile.calltrace.cycles-pp.icmp_rcv.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog
0.70 +0.2 0.88 perf-profile.calltrace.cycles-pp._copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.raw_recvmsg.inet_recvmsg
0.62 ± 7% +0.2 0.79 ± 11% perf-profile.calltrace.cycles-pp.free_unref_page.inet_sock_destruct.__sk_destruct.rcu_do_batch.rcu_core
0.66 ± 2% +0.2 0.85 ± 2% perf-profile.calltrace.cycles-pp.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.raw_recvmsg
0.66 +0.2 0.84 perf-profile.calltrace.cycles-pp.skb_release_data.consume_skb.raw_recvmsg.inet_recvmsg.sock_recvmsg
0.70 ± 2% +0.2 0.90 ± 2% perf-profile.calltrace.cycles-pp.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter.raw_recvmsg.inet_recvmsg
0.94 +0.3 1.24 perf-profile.calltrace.cycles-pp.consume_skb.raw_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
0.81 +0.3 1.14 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__skb_try_recv_datagram.__skb_recv_datagram.skb_recv_datagram.raw_recvmsg
0.99 +0.4 1.37 ± 3% perf-profile.calltrace.cycles-pp.__skb_try_recv_datagram.__skb_recv_datagram.skb_recv_datagram.raw_recvmsg.inet_recvmsg
1.53 +0.4 1.94 ± 2% perf-profile.calltrace.cycles-pp.__skb_datagram_iter.skb_copy_datagram_iter.raw_recvmsg.inet_recvmsg.sock_recvmsg
1.55 ± 2% +0.4 1.97 ± 2% perf-profile.calltrace.cycles-pp.skb_copy_datagram_iter.raw_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
1.10 ± 2% +0.4 1.52 ± 3% perf-profile.calltrace.cycles-pp.__skb_recv_datagram.skb_recv_datagram.raw_recvmsg.inet_recvmsg.sock_recvmsg
1.12 ± 2% +0.4 1.54 ± 3% perf-profile.calltrace.cycles-pp.skb_recv_datagram.raw_recvmsg.inet_recvmsg.sock_recvmsg.__sys_recvfrom
0.00 +0.5 0.53 ± 2% perf-profile.calltrace.cycles-pp.alloc_inode.new_inode_pseudo.sock_alloc.__sock_create.__sys_socket
4.85 +0.6 5.40 perf-profile.calltrace.cycles-pp.__copy_skb_header.__skb_clone.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish
7.74 +0.6 8.32 perf-profile.calltrace.cycles-pp.kfree_skb_reason.inet_sock_destruct.__sk_destruct.rcu_do_batch.rcu_core
0.00 +0.6 0.61 ± 2% perf-profile.calltrace.cycles-pp.check_heap_object.__check_object_size.simple_copy_to_iter.__skb_datagram_iter.skb_copy_datagram_iter
0.00 +0.7 0.65 ± 3% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__skb_try_recv_datagram.__skb_recv_datagram.skb_recv_datagram
4.56 +0.7 5.25 perf-profile.calltrace.cycles-pp.sock_def_readable.__sock_queue_rcv_skb.sock_queue_rcv_skb_reason.raw_rcv.raw_v4_input
7.56 +0.7 8.31 perf-profile.calltrace.cycles-pp.__skb_clone.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
50.71 +0.8 51.47 perf-profile.calltrace.cycles-pp.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog
3.67 +0.9 4.59 ± 2% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.__sock_queue_rcv_skb.sock_queue_rcv_skb_reason.raw_rcv
55.46 +1.0 56.43 perf-profile.calltrace.cycles-pp.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action
55.45 +1.0 56.42 perf-profile.calltrace.cycles-pp.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core.process_backlog.__napi_poll
58.02 +1.0 59.01 perf-profile.calltrace.cycles-pp.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.raw_send_hdrinc.raw_sendmsg
57.99 +1.0 58.98 perf-profile.calltrace.cycles-pp.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2
58.01 +1.0 59.00 perf-profile.calltrace.cycles-pp.do_softirq.__local_bh_enable_ip.__dev_queue_xmit.ip_finish_output2.raw_send_hdrinc
55.61 +1.0 56.60 perf-profile.calltrace.cycles-pp.__netif_receive_skb_one_core.process_backlog.__napi_poll.net_rx_action.__do_softirq
58.10 +1.0 59.10 perf-profile.calltrace.cycles-pp.ip_finish_output2.raw_send_hdrinc.raw_sendmsg.sock_sendmsg.__sys_sendto
58.09 +1.0 59.09 perf-profile.calltrace.cycles-pp.__dev_queue_xmit.ip_finish_output2.raw_send_hdrinc.raw_sendmsg.sock_sendmsg
55.68 +1.0 56.68 perf-profile.calltrace.cycles-pp.process_backlog.__napi_poll.net_rx_action.__do_softirq.do_softirq
55.70 +1.0 56.70 perf-profile.calltrace.cycles-pp.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip.__dev_queue_xmit
55.68 +1.0 56.68 perf-profile.calltrace.cycles-pp.__napi_poll.net_rx_action.__do_softirq.do_softirq.__local_bh_enable_ip
59.51 +1.0 60.54 perf-profile.calltrace.cycles-pp.raw_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64
59.58 +1.0 60.61 perf-profile.calltrace.cycles-pp.sock_sendmsg.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe
58.64 +1.0 59.68 perf-profile.calltrace.cycles-pp.raw_send_hdrinc.raw_sendmsg.sock_sendmsg.__sys_sendto.__x64_sys_sendto
59.70 +1.0 60.74 perf-profile.calltrace.cycles-pp.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto
59.69 +1.0 60.73 perf-profile.calltrace.cycles-pp.__sys_sendto.__x64_sys_sendto.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto
4.97 +1.0 6.02 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.__sock_queue_rcv_skb.sock_queue_rcv_skb_reason.raw_rcv.raw_v4_input
59.76 +1.0 60.81 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.sendto
59.78 +1.1 60.84 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.sendto
59.85 +1.1 60.91 perf-profile.calltrace.cycles-pp.sendto
22.21 +2.3 24.51 perf-profile.calltrace.cycles-pp.__sock_queue_rcv_skb.sock_queue_rcv_skb_reason.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu
23.65 +2.4 26.03 perf-profile.calltrace.cycles-pp.sock_queue_rcv_skb_reason.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish
29.20 +2.7 31.86 perf-profile.calltrace.cycles-pp.raw_rcv.raw_v4_input.ip_protocol_deliver_rcu.ip_local_deliver_finish.__netif_receive_skb_one_core
28.65 -5.8 22.86 ± 2% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
24.32 -5.6 18.77 ± 2% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
10.24 ± 2% -4.1 6.14 ± 5% perf-profile.children.cycles-pp.__unfreeze_partials
8.45 -3.3 5.11 ± 4% perf-profile.children.cycles-pp.get_partial_node
10.66 -2.8 7.90 ± 3% perf-profile.children.cycles-pp.___slab_alloc
12.63 -2.7 9.92 ± 2% perf-profile.children.cycles-pp.skb_clone
12.72 -2.7 10.02 ± 2% perf-profile.children.cycles-pp.kmem_cache_alloc
17.07 -1.4 15.72 ± 2% perf-profile.children.cycles-pp.inet_sock_destruct
17.58 -1.3 16.26 ± 2% perf-profile.children.cycles-pp.__sk_destruct
18.54 -1.3 17.26 ± 2% perf-profile.children.cycles-pp.rcu_do_batch
18.54 -1.3 17.27 ± 2% perf-profile.children.cycles-pp.rcu_core
13.48 -1.1 12.42 ± 2% perf-profile.children.cycles-pp.smpboot_thread_fn
13.49 -1.1 12.43 ± 2% perf-profile.children.cycles-pp.ret_from_fork_asm
13.49 -1.1 12.43 ± 2% perf-profile.children.cycles-pp.ret_from_fork
13.49 -1.1 12.43 ± 2% perf-profile.children.cycles-pp.kthread
13.46 -1.1 12.40 ± 2% perf-profile.children.cycles-pp.run_ksoftirqd
11.51 -0.6 10.89 ± 2% perf-profile.children.cycles-pp.raw_recvmsg
11.55 -0.6 10.94 ± 2% perf-profile.children.cycles-pp.inet_recvmsg
11.73 -0.5 11.19 ± 2% perf-profile.children.cycles-pp.sock_recvmsg
12.06 -0.4 11.63 ± 2% perf-profile.children.cycles-pp.__sys_recvfrom
12.08 -0.4 11.65 ± 2% perf-profile.children.cycles-pp.__x64_sys_recvfrom
1.39 ± 3% -0.4 0.96 ± 3% perf-profile.children.cycles-pp.get_any_partial
3.16 -0.2 3.00 ± 3% perf-profile.children.cycles-pp.__slab_free
0.05 +0.0 0.06 ± 6% perf-profile.children.cycles-pp.syscall_return_via_sysret
0.13 ± 2% +0.0 0.14 ± 3% perf-profile.children.cycles-pp.apparmor_capable
0.12 ± 3% +0.0 0.14 ± 5% perf-profile.children.cycles-pp.apparmor_file_alloc_security
0.05 ± 7% +0.0 0.07 ± 7% perf-profile.children.cycles-pp.__wake_up_common
0.15 +0.0 0.16 ± 3% perf-profile.children.cycles-pp._raw_spin_trylock
0.34 ± 2% +0.0 0.36 perf-profile.children.cycles-pp.ip_route_output_key_hash
0.11 ± 6% +0.0 0.13 ± 2% perf-profile.children.cycles-pp.rmqueue
0.12 ± 3% +0.0 0.14 ± 4% perf-profile.children.cycles-pp.release_sock
0.05 +0.0 0.07 ± 10% perf-profile.children.cycles-pp.schedule_timeout
0.05 +0.0 0.07 ± 10% perf-profile.children.cycles-pp.try_to_wake_up
0.08 ± 6% +0.0 0.09 ± 5% perf-profile.children.cycles-pp.__virt_addr_valid
0.16 ± 2% +0.0 0.18 ± 2% perf-profile.children.cycles-pp.__free_one_page
0.07 ± 6% +0.0 0.09 ± 5% perf-profile.children.cycles-pp.exit_to_user_mode_prepare
0.16 ± 5% +0.0 0.18 ± 3% perf-profile.children.cycles-pp.get_page_from_freelist
0.32 ± 2% +0.0 0.34 perf-profile.children.cycles-pp.security_socket_post_create
0.06 ± 7% +0.0 0.09 ± 5% perf-profile.children.cycles-pp.stress_rawudp_server
0.24 +0.0 0.26 perf-profile.children.cycles-pp._raw_spin_lock_bh
0.06 ± 6% +0.0 0.08 ± 8% perf-profile.children.cycles-pp.__skb_wait_for_more_packets
0.04 ± 44% +0.0 0.06 ± 7% perf-profile.children.cycles-pp.__netif_receive_skb_core
0.24 +0.0 0.26 ± 2% perf-profile.children.cycles-pp.init_file
0.18 ± 4% +0.0 0.21 ± 2% perf-profile.children.cycles-pp.__alloc_pages
0.33 +0.0 0.36 ± 3% perf-profile.children.cycles-pp.sock_alloc_inode
0.11 ± 8% +0.0 0.14 ± 5% perf-profile.children.cycles-pp.__fget_light
0.15 ± 2% +0.0 0.18 ± 2% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore
0.44 +0.0 0.47 perf-profile.children.cycles-pp.kmem_cache_alloc_lru
0.29 ± 4% +0.0 0.32 ± 2% perf-profile.children.cycles-pp.__sysvec_apic_timer_interrupt
0.14 ± 2% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.put_cpu_partial
0.23 ± 6% +0.0 0.26 ± 5% perf-profile.children.cycles-pp.tick_sched_timer
0.32 ± 3% +0.0 0.35 ± 3% perf-profile.children.cycles-pp.setsockopt
0.08 ± 5% +0.0 0.12 ± 6% perf-profile.children.cycles-pp.__schedule
0.07 ± 6% +0.0 0.10 ± 7% perf-profile.children.cycles-pp.schedule
0.16 ± 2% +0.0 0.19 ± 2% perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack
0.14 ± 6% +0.0 0.17 ± 4% perf-profile.children.cycles-pp.sockfd_lookup_light
0.29 +0.0 0.32 ± 4% perf-profile.children.cycles-pp.setup_object
0.28 ± 4% +0.0 0.32 ± 3% perf-profile.children.cycles-pp.hrtimer_interrupt
0.52 +0.0 0.56 perf-profile.children.cycles-pp.icmp_route_lookup
0.49 +0.0 0.53 ± 2% perf-profile.children.cycles-pp.alloc_inode
0.13 ± 4% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.syscall_exit_to_user_mode
0.51 +0.0 0.55 ± 2% perf-profile.children.cycles-pp.alloc_empty_file
0.22 ± 2% +0.0 0.26 ± 3% perf-profile.children.cycles-pp.__entry_text_start
0.57 +0.0 0.61 perf-profile.children.cycles-pp.sock_alloc
0.44 +0.0 0.48 perf-profile.children.cycles-pp.__list_del_entry_valid_or_report
0.56 +0.0 0.61 perf-profile.children.cycles-pp.new_inode_pseudo
0.52 +0.0 0.57 ± 2% perf-profile.children.cycles-pp.alloc_file
0.00 +0.1 0.05 perf-profile.children.cycles-pp.__ip_finish_output
0.72 ± 2% +0.1 0.78 ± 2% perf-profile.children.cycles-pp.alloc_file_pseudo
0.15 ± 3% +0.1 0.20 ± 2% perf-profile.children.cycles-pp.is_vmalloc_addr
0.01 ±223% +0.1 0.06 ± 6% perf-profile.children.cycles-pp.autoremove_wake_function
0.73 +0.1 0.78 perf-profile.children.cycles-pp.sock_alloc_file
0.16 ± 3% +0.1 0.22 ± 3% perf-profile.children.cycles-pp.security_socket_recvmsg
0.20 ± 2% +0.1 0.27 ± 3% perf-profile.children.cycles-pp.aa_sk_perm
1.12 ± 3% +0.1 1.19 ± 3% perf-profile.children.cycles-pp.sk_filter_trim_cap
0.14 ± 3% +0.1 0.21 ± 5% perf-profile.children.cycles-pp.__wake_up_common_lock
0.67 +0.1 0.75 perf-profile.children.cycles-pp.shuffle_freelist
0.12 ± 4% +0.1 0.20 ± 4% perf-profile.children.cycles-pp.__list_add_valid_or_report
1.24 +0.1 1.33 perf-profile.children.cycles-pp.dst_release
2.12 +0.1 2.22 perf-profile.children.cycles-pp.kmem_cache_free
0.89 ± 2% +0.1 1.00 perf-profile.children.cycles-pp.allocate_slab
1.72 +0.1 1.84 perf-profile.children.cycles-pp.ipv4_pktinfo_prepare
2.42 ± 2% +0.1 2.55 ± 3% perf-profile.children.cycles-pp.icmp_socket_deliver
2.41 ± 3% +0.1 2.54 ± 3% perf-profile.children.cycles-pp.raw_icmp_error
2.47 ± 3% +0.1 2.60 ± 3% perf-profile.children.cycles-pp.icmp_unreach
2.70 ± 2% +0.1 2.85 ± 3% perf-profile.children.cycles-pp.icmp_rcv
0.67 ± 2% +0.2 0.83 perf-profile.children.cycles-pp.copyout
0.60 ± 2% +0.2 0.77 ± 2% perf-profile.children.cycles-pp.check_heap_object
0.71 ± 2% +0.2 0.88 perf-profile.children.cycles-pp._copy_to_iter
0.73 ± 2% +0.2 0.93 ± 2% perf-profile.children.cycles-pp.__check_object_size
0.71 ± 2% +0.2 0.91 ± 2% perf-profile.children.cycles-pp.simple_copy_to_iter
0.82 ± 7% +0.2 1.03 ± 10% perf-profile.children.cycles-pp.free_unref_page
2.39 +0.2 2.63 perf-profile.children.cycles-pp.sock_rfree
2.99 +0.3 3.28 perf-profile.children.cycles-pp.skb_release_head_state
1.01 +0.3 1.31 perf-profile.children.cycles-pp.consume_skb
4.47 +0.4 4.85 perf-profile.children.cycles-pp.skb_release_data
1.01 +0.4 1.39 ± 3% perf-profile.children.cycles-pp.__skb_try_recv_datagram
1.54 +0.4 1.95 ± 2% perf-profile.children.cycles-pp.__skb_datagram_iter
1.56 ± 2% +0.4 1.97 ± 2% perf-profile.children.cycles-pp.skb_copy_datagram_iter
1.11 ± 2% +0.4 1.53 ± 3% perf-profile.children.cycles-pp.__skb_recv_datagram
1.12 ± 2% +0.4 1.55 ± 3% perf-profile.children.cycles-pp.skb_recv_datagram
4.89 +0.6 5.45 perf-profile.children.cycles-pp.__copy_skb_header
4.58 +0.7 5.27 perf-profile.children.cycles-pp.sock_def_readable
10.70 +0.7 11.42 perf-profile.children.cycles-pp.kfree_skb_reason
7.65 +0.8 8.40 perf-profile.children.cycles-pp.__skb_clone
50.92 +0.8 51.69 perf-profile.children.cycles-pp.raw_v4_input
59.46 +0.8 60.25 perf-profile.children.cycles-pp.do_softirq
59.48 +0.8 60.28 perf-profile.children.cycles-pp.__local_bh_enable_ip
85.69 +0.9 86.58 perf-profile.children.cycles-pp.do_syscall_64
85.79 +0.9 86.70 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe
55.46 +1.0 56.44 perf-profile.children.cycles-pp.ip_local_deliver_finish
55.45 +1.0 56.43 perf-profile.children.cycles-pp.ip_protocol_deliver_rcu
55.61 +1.0 56.61 perf-profile.children.cycles-pp.__netif_receive_skb_one_core
55.68 +1.0 56.68 perf-profile.children.cycles-pp.__napi_poll
55.71 +1.0 56.71 perf-profile.children.cycles-pp.net_rx_action
55.68 +1.0 56.68 perf-profile.children.cycles-pp.process_backlog
58.22 +1.0 59.22 perf-profile.children.cycles-pp.__dev_queue_xmit
58.26 +1.0 59.26 perf-profile.children.cycles-pp.ip_finish_output2
59.52 +1.0 60.54 perf-profile.children.cycles-pp.raw_sendmsg
58.65 +1.0 59.68 perf-profile.children.cycles-pp.raw_send_hdrinc
59.58 +1.0 60.61 perf-profile.children.cycles-pp.sock_sendmsg
59.71 +1.0 60.75 perf-profile.children.cycles-pp.__x64_sys_sendto
59.69 +1.0 60.74 perf-profile.children.cycles-pp.__sys_sendto
59.87 +1.1 60.93 perf-profile.children.cycles-pp.sendto
22.30 +2.3 24.61 perf-profile.children.cycles-pp.__sock_queue_rcv_skb
23.78 +2.4 26.16 perf-profile.children.cycles-pp.sock_queue_rcv_skb_reason
29.56 +2.7 32.22 perf-profile.children.cycles-pp.raw_rcv
28.12 -5.9 22.26 ± 2% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
0.64 -0.5 0.12 ± 3% perf-profile.self.cycles-pp.__unfreeze_partials
0.45 -0.2 0.26 ± 3% perf-profile.self.cycles-pp.get_partial_node
0.05 +0.0 0.06 perf-profile.self.cycles-pp.__dev_queue_xmit
0.05 +0.0 0.06 perf-profile.self.cycles-pp.__cond_resched
0.05 +0.0 0.06 perf-profile.self.cycles-pp.syscall_return_via_sysret
0.06 ± 6% +0.0 0.07 perf-profile.self.cycles-pp.__check_object_size
0.13 +0.0 0.14 ± 2% perf-profile.self.cycles-pp.apparmor_capable
0.10 ± 3% +0.0 0.12 ± 4% perf-profile.self.cycles-pp.__sk_destruct
0.37 +0.0 0.39 perf-profile.self.cycles-pp.sock_queue_rcv_skb_reason
0.15 ± 2% +0.0 0.16 ± 2% perf-profile.self.cycles-pp._raw_spin_trylock
0.06 ± 7% +0.0 0.08 perf-profile.self.cycles-pp.__virt_addr_valid
0.43 +0.0 0.44 perf-profile.self.cycles-pp.memcg_slab_post_alloc_hook
0.19 ± 3% +0.0 0.21 perf-profile.self.cycles-pp.ip_route_output_key_hash_rcu
0.10 ± 4% +0.0 0.12 ± 3% perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe
0.06 ± 9% +0.0 0.07 ± 5% perf-profile.self.cycles-pp.is_vmalloc_addr
0.12 ± 3% +0.0 0.14 perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore
0.30 +0.0 0.32 ± 2% perf-profile.self.cycles-pp.apparmor_socket_post_create
0.06 ± 9% +0.0 0.08 ± 6% perf-profile.self.cycles-pp.stress_rawudp_server
0.41 +0.0 0.43 perf-profile.self.cycles-pp.skb_clone
0.24 +0.0 0.26 perf-profile.self.cycles-pp._raw_spin_lock_bh
0.07 ± 5% +0.0 0.10 ± 5% perf-profile.self.cycles-pp.__skb_try_recv_datagram
0.45 +0.0 0.48 ± 2% perf-profile.self.cycles-pp._raw_spin_lock
0.36 ± 2% +0.0 0.38 perf-profile.self.cycles-pp.inet_sock_destruct
0.10 ± 8% +0.0 0.12 ± 6% perf-profile.self.cycles-pp.__fget_light
0.14 ± 3% +0.0 0.16 ± 2% perf-profile.self.cycles-pp.put_cpu_partial
0.69 +0.0 0.72 perf-profile.self.cycles-pp.raw_rcv
0.03 ± 70% +0.0 0.06 ± 6% perf-profile.self.cycles-pp.__netif_receive_skb_core
0.15 ± 2% +0.0 0.18 ± 4% perf-profile.self.cycles-pp.get_any_partial
0.11 ± 3% +0.0 0.15 ± 3% perf-profile.self.cycles-pp.recv
0.16 ± 3% +0.0 0.19 ± 4% perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack
0.12 ± 5% +0.0 0.16 ± 3% perf-profile.self.cycles-pp.__skb_datagram_iter
0.47 +0.0 0.51 perf-profile.self.cycles-pp.skb_release_head_state
0.43 +0.0 0.47 ± 2% perf-profile.self.cycles-pp.__list_del_entry_valid_or_report
0.00 +0.1 0.05 perf-profile.self.cycles-pp._copy_to_iter
0.00 +0.1 0.05 ± 7% perf-profile.self.cycles-pp.__skb_recv_datagram
0.45 ± 2% +0.1 0.51 ± 2% perf-profile.self.cycles-pp.shuffle_freelist
1.12 ± 3% +0.1 1.18 ± 5% perf-profile.self.cycles-pp.raw_v4_input
0.16 ± 2% +0.1 0.22 ± 2% perf-profile.self.cycles-pp.aa_sk_perm
0.20 ± 2% +0.1 0.26 ± 3% perf-profile.self.cycles-pp.__sys_recvfrom
0.11 ± 5% +0.1 0.19 ± 3% perf-profile.self.cycles-pp.__list_add_valid_or_report
1.18 +0.1 1.26 perf-profile.self.cycles-pp.dst_release
1.91 +0.1 2.00 perf-profile.self.cycles-pp.kmem_cache_free
0.44 +0.1 0.57 ± 2% perf-profile.self.cycles-pp.check_heap_object
2.40 ± 3% +0.1 2.53 ± 3% perf-profile.self.cycles-pp.raw_icmp_error
0.64 ± 2% +0.2 0.79 perf-profile.self.cycles-pp.copyout
2.25 +0.2 2.42 perf-profile.self.cycles-pp.__slab_free
0.60 ± 2% +0.2 0.78 ± 3% perf-profile.self.cycles-pp.raw_recvmsg
2.75 +0.2 2.94 perf-profile.self.cycles-pp.__skb_clone
2.36 +0.2 2.60 perf-profile.self.cycles-pp.sock_rfree
4.24 +0.4 4.59 perf-profile.self.cycles-pp.kfree_skb_reason
4.24 +0.4 4.60 perf-profile.self.cycles-pp.skb_release_data
2.52 +0.4 2.91 perf-profile.self.cycles-pp._raw_spin_lock_irqsave
12.54 +0.6 13.09 perf-profile.self.cycles-pp.__sock_queue_rcv_skb
4.83 +0.6 5.38 perf-profile.self.cycles-pp.__copy_skb_header
4.40 +0.6 5.03 perf-profile.self.cycles-pp.sock_def_readable
0.91 +0.7 1.60 perf-profile.self.cycles-pp.___slab_alloc
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: > From: Chengming Zhou <zhouchengming@bytedance.com> > > Now we will freeze slabs when moving them out of node partial list to > cpu partial list, this method needs two cmpxchg_double operations: > > 1. freeze slab (acquire_slab()) under the node list_lock > 2. get_freelist() when pick used in ___slab_alloc() Recently -next has been failing to boot on a Raspberry Pi 3 with an arm multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having introduced the issue. I've included the full bisect log below. When we see problems we see RCU stalls while logging in, for example: debian-testing-armhf login: root (automatic login) Linux debian-testing-armhf 6.7.0-rc1-00006-gc8d312e03903 #1 SMP @1699864348 armv7l The programs included with the Debian GNU/Linux system are free software; the exact distribution terms for each program are described in the individual files in /usr/share/doc/*/copyright. Debian GNU/Linux comes with ABSOLUTELY NO WARRANTY, to the extent permitted by applicable law. [ 46.453323] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: [ 46.459361] rcu: 3-...0: (1 GPs behind) idle=def4/1/0x40000000 softirq=1304/1304 fqs=951 [ 46.467669] rcu: (detected by 0, t=2103 jiffies, g=1161, q=499 ncpus=4) [ 46.474472] Sending NMI from CPU 0 to CPUs 3: [ 56.478894] rcu: rcu_sched kthread timer wakeup didn't happen for 1002 jiffies! g1161 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 [ 56.490195] rcu: Possible timer handling issue on cpu=0 timer-softirq=1650 [ 56.497259] rcu: rcu_sched kthread starved for 1005 jiffies! g1161 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=0 [ 56.507589] rcu: Unless rcu_sched kthread gets sufficient CPU time, OOM is now expected behavior. [ 56.516681] rcu: RCU grace-period kthread stack dump: [ 56.521803] task:rcu_sched state:I stack:0 pid:13 tgid:13 ppid:2 flags:0x00000000 [ 56.531267] __schedule from schedule+0x20/0xe8 [ 56.535883] schedule from schedule_timeout+0xa0/0x158 [ 56.541111] schedule_timeout from rcu_gp_fqs_loop+0x104/0x594 [ 56.547048] rcu_gp_fqs_loop from rcu_gp_kthread+0x14c/0x1c0 [ 56.552801] rcu_gp_kthread from kthread+0xe0/0xfc [ 56.557674] kthread from ret_from_fork+0x14/0x28 [ 56.562457] Exception stack(0xf084dfb0 to 0xf084dff8) [ 56.567584] dfa0: 00000000 00000000 00000000 00000000 [ 56.575886] dfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 [ 56.584191] dfe0: 00000000 00000000 00000000 00000000 00000013 00000000 [ 56.590907] rcu: Stack dump where RCU GP kthread last ran: [ 56.596474] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.7.0-rc1-00006-gc8d312e03903 #1 [ 56.604515] Hardware name: BCM2835 [ 56.607965] PC is at default_idle_call+0x1c/0xb0 [ 56.612654] LR is at ct_kernel_enter.constprop.0+0x48/0x11c [ 56.618311] pc : [<c1197054>] lr : [<c1195c98>] psr: 60010013 [ 56.624672] sp : c1b01f70 ip : c1d5af7c fp : 00000000 [ 56.629974] r10: c19cda60 r9 : 00000000 r8 : 00000000 [ 56.635277] r7 : c1b04d50 r6 : c1b04d18 r5 : c1d5b684 r4 : c1b09740 [ 56.641902] r3 : 00000000 r2 : 00000000 r1 : 00000001 r0 : 002a3114 [ 56.648528] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none [ 56.655774] Control: 10c5383d Table: 0237406a DAC: 00000051 [ 56.661605] default_idle_call from do_idle+0x208/0x290 [ 56.666920] do_idle from cpu_startup_entry+0x28/0x2c [ 56.672059] cpu_startup_entry from rest_init+0xac/0xb0 [ 56.677371] rest_init from arch_post_acpi_subsys_init+0x0/0x8 Login ti A full log for that run can be seen at: https://validation.linaro.org/scheduler/job/4017095 Boots to initramfs with the same kernel image seem fine. Other systems, including other 32 bit arm ones, don't seem to be having similar issues with this userspace. I've not investigated beyond running the bisect, the log for which is below: git bisect start # good: [64e6d94bfb47ed0732ad06aedf8ec6af5dd2ab84] Merge branch 'for-linux-next-fixes' of git://anongit.freedesktop.org/drm/drm-misc git bisect good 64e6d94bfb47ed0732ad06aedf8ec6af5dd2ab84 # bad: [5a82d69d48c82e89aef44483d2a129f869f3506a] Add linux-next specific files for 20231120 git bisect bad 5a82d69d48c82e89aef44483d2a129f869f3506a # good: [ce252a92a867da8a6622463bff637e5f7b904a46] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git git bisect good ce252a92a867da8a6622463bff637e5f7b904a46 # good: [c22e026efad504e3b056d4436920d173a09c580e] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator.git git bisect good c22e026efad504e3b056d4436920d173a09c580e # good: [b7fc58ffb105470cb339163cc2b04e3f59387a45] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/fpga/linux-fpga.git git bisect good b7fc58ffb105470cb339163cc2b04e3f59387a45 # good: [26f89f0614f03e4016578a992fc2e86b048a5cb4] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git git bisect good 26f89f0614f03e4016578a992fc2e86b048a5cb4 # good: [602bf18307981f3bfd9ebf19921791a4256d3fd1] Merge branch 'for-6.7' into for-next git bisect good 602bf18307981f3bfd9ebf19921791a4256d3fd1 # good: [9f16a68069822b1df6bfb8a9ef7258a1e32b25e7] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching git bisect good 9f16a68069822b1df6bfb8a9ef7258a1e32b25e7 # good: [3ff57db6f6569ebc2cc333437e7e949749e59424] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/krisman/unicode.git git bisect good 3ff57db6f6569ebc2cc333437e7e949749e59424 # bad: [dd374e220ba492f95344a638b1efe5b2744fdd73] slub: Update frozen slabs documentations in the source git bisect bad dd374e220ba492f95344a638b1efe5b2744fdd73 # good: [a3058965bb35490454953aa2c87ea51004839f2f] slub: Prepare __slab_free() for unfrozen partial slab out of node partial list git bisect good a3058965bb35490454953aa2c87ea51004839f2f # bad: [c8d312e039030edab25836a326bcaeb2a3d4db14] slub: Delay freezing of partial slabs git bisect bad c8d312e039030edab25836a326bcaeb2a3d4db14 # good: [00b15a19ee543f0117cb217fcbab8b7b3fd50677] slub: Introduce freeze_slab() git bisect good 00b15a19ee543f0117cb217fcbab8b7b3fd50677 # first bad commit: [c8d312e039030edab25836a326bcaeb2a3d4db14] slub: Delay freezing of partial slabs
On 2023/11/21 02:49, Mark Brown wrote: > On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >> From: Chengming Zhou <zhouchengming@bytedance.com> >> >> Now we will freeze slabs when moving them out of node partial list to >> cpu partial list, this method needs two cmpxchg_double operations: >> >> 1. freeze slab (acquire_slab()) under the node list_lock >> 2. get_freelist() when pick used in ___slab_alloc() > > Recently -next has been failing to boot on a Raspberry Pi 3 with an arm > multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this > patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having > introduced the issue. I've included the full bisect log below. > > When we see problems we see RCU stalls while logging in, for example: > > debian-testing-armhf login: root (automatic login) > Linux debian-testing-armhf 6.7.0-rc1-00006-gc8d312e03903 #1 SMP @1699864348 armv7l > The programs included with the Debian GNU/Linux system are free software; > the exact distribution terms for each program are described in the > individual files in /usr/share/doc/*/copyright. > Debian GNU/Linux comes with ABSOLUTELY NO WARRANTY, to the extent > permitted by applicable law. > [ 46.453323] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: > [ 46.459361] rcu: 3-...0: (1 GPs behind) idle=def4/1/0x40000000 softirq=1304/1304 fqs=951 > [ 46.467669] rcu: (detected by 0, t=2103 jiffies, g=1161, q=499 ncpus=4) > [ 46.474472] Sending NMI from CPU 0 to CPUs 3: IIUC, here should print the backtrace of CPU 3, right? It looks like CPU 3 is the cause, but we couldn't see what it's doing from the log. Thanks! > [ 56.478894] rcu: rcu_sched kthread timer wakeup didn't happen for 1002 jiffies! g1161 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 > [ 56.490195] rcu: Possible timer handling issue on cpu=0 timer-softirq=1650 > [ 56.497259] rcu: rcu_sched kthread starved for 1005 jiffies! g1161 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=0 > [ 56.507589] rcu: Unless rcu_sched kthread gets sufficient CPU time, OOM is now expected behavior. > [ 56.516681] rcu: RCU grace-period kthread stack dump: > [ 56.521803] task:rcu_sched state:I stack:0 pid:13 tgid:13 ppid:2 flags:0x00000000 > [ 56.531267] __schedule from schedule+0x20/0xe8 > [ 56.535883] schedule from schedule_timeout+0xa0/0x158 > [ 56.541111] schedule_timeout from rcu_gp_fqs_loop+0x104/0x594 > [ 56.547048] rcu_gp_fqs_loop from rcu_gp_kthread+0x14c/0x1c0 > [ 56.552801] rcu_gp_kthread from kthread+0xe0/0xfc > [ 56.557674] kthread from ret_from_fork+0x14/0x28 > [ 56.562457] Exception stack(0xf084dfb0 to 0xf084dff8) > [ 56.567584] dfa0: 00000000 00000000 00000000 00000000 > [ 56.575886] dfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 > [ 56.584191] dfe0: 00000000 00000000 00000000 00000000 00000013 00000000 > [ 56.590907] rcu: Stack dump where RCU GP kthread last ran: > [ 56.596474] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 6.7.0-rc1-00006-gc8d312e03903 #1 > [ 56.604515] Hardware name: BCM2835 > [ 56.607965] PC is at default_idle_call+0x1c/0xb0 > [ 56.612654] LR is at ct_kernel_enter.constprop.0+0x48/0x11c > [ 56.618311] pc : [<c1197054>] lr : [<c1195c98>] psr: 60010013 > [ 56.624672] sp : c1b01f70 ip : c1d5af7c fp : 00000000 > [ 56.629974] r10: c19cda60 r9 : 00000000 r8 : 00000000 > [ 56.635277] r7 : c1b04d50 r6 : c1b04d18 r5 : c1d5b684 r4 : c1b09740 > [ 56.641902] r3 : 00000000 r2 : 00000000 r1 : 00000001 r0 : 002a3114 > [ 56.648528] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none > [ 56.655774] Control: 10c5383d Table: 0237406a DAC: 00000051 > [ 56.661605] default_idle_call from do_idle+0x208/0x290 > [ 56.666920] do_idle from cpu_startup_entry+0x28/0x2c > [ 56.672059] cpu_startup_entry from rest_init+0xac/0xb0 > [ 56.677371] rest_init from arch_post_acpi_subsys_init+0x0/0x8 > Login ti > > A full log for that run can be seen at: > > https://validation.linaro.org/scheduler/job/4017095 > > Boots to initramfs with the same kernel image seem fine. Other systems, > including other 32 bit arm ones, don't seem to be having similar issues > with this userspace. I've not investigated beyond running the bisect, > the log for which is below: > > git bisect start > # good: [64e6d94bfb47ed0732ad06aedf8ec6af5dd2ab84] Merge branch 'for-linux-next-fixes' of git://anongit.freedesktop.org/drm/drm-misc > git bisect good 64e6d94bfb47ed0732ad06aedf8ec6af5dd2ab84 > # bad: [5a82d69d48c82e89aef44483d2a129f869f3506a] Add linux-next specific files for 20231120 > git bisect bad 5a82d69d48c82e89aef44483d2a129f869f3506a > # good: [ce252a92a867da8a6622463bff637e5f7b904a46] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git > git bisect good ce252a92a867da8a6622463bff637e5f7b904a46 > # good: [c22e026efad504e3b056d4436920d173a09c580e] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator.git > git bisect good c22e026efad504e3b056d4436920d173a09c580e > # good: [b7fc58ffb105470cb339163cc2b04e3f59387a45] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/fpga/linux-fpga.git > git bisect good b7fc58ffb105470cb339163cc2b04e3f59387a45 > # good: [26f89f0614f03e4016578a992fc2e86b048a5cb4] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git > git bisect good 26f89f0614f03e4016578a992fc2e86b048a5cb4 > # good: [602bf18307981f3bfd9ebf19921791a4256d3fd1] Merge branch 'for-6.7' into for-next > git bisect good 602bf18307981f3bfd9ebf19921791a4256d3fd1 > # good: [9f16a68069822b1df6bfb8a9ef7258a1e32b25e7] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/livepatching/livepatching > git bisect good 9f16a68069822b1df6bfb8a9ef7258a1e32b25e7 > # good: [3ff57db6f6569ebc2cc333437e7e949749e59424] Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/krisman/unicode.git > git bisect good 3ff57db6f6569ebc2cc333437e7e949749e59424 > # bad: [dd374e220ba492f95344a638b1efe5b2744fdd73] slub: Update frozen slabs documentations in the source > git bisect bad dd374e220ba492f95344a638b1efe5b2744fdd73 > # good: [a3058965bb35490454953aa2c87ea51004839f2f] slub: Prepare __slab_free() for unfrozen partial slab out of node partial list > git bisect good a3058965bb35490454953aa2c87ea51004839f2f > # bad: [c8d312e039030edab25836a326bcaeb2a3d4db14] slub: Delay freezing of partial slabs > git bisect bad c8d312e039030edab25836a326bcaeb2a3d4db14 > # good: [00b15a19ee543f0117cb217fcbab8b7b3fd50677] slub: Introduce freeze_slab() > git bisect good 00b15a19ee543f0117cb217fcbab8b7b3fd50677 > # first bad commit: [c8d312e039030edab25836a326bcaeb2a3d4db14] slub: Delay freezing of partial slabs
On Tue, Nov 21, 2023 at 08:58:40AM +0800, Chengming Zhou wrote: > On 2023/11/21 02:49, Mark Brown wrote: > > On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: > > When we see problems we see RCU stalls while logging in, for example: > > [ 46.453323] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: > > [ 46.459361] rcu: 3-...0: (1 GPs behind) idle=def4/1/0x40000000 softirq=1304/1304 fqs=951 > > [ 46.467669] rcu: (detected by 0, t=2103 jiffies, g=1161, q=499 ncpus=4) > > [ 46.474472] Sending NMI from CPU 0 to CPUs 3: > IIUC, here should print the backtrace of CPU 3, right? It looks like CPU 3 is the cause, > but we couldn't see what it's doing from the log. AIUI yes, but it looks like we've just completely lost the CPU - there's more attempts to talk to it visible in the log: > > A full log for that run can be seen at: > > > > https://validation.linaro.org/scheduler/job/4017095 but none of them appear to cause CPU 3 to respond. Note that 32 bit ARM is just using a regular IPI rather than something that's actually a NMI so this isn't hugely out of the ordinary, I'd guess it's stuck with interrupts masked.
On 2023/11/21 09:29, Mark Brown wrote: > On Tue, Nov 21, 2023 at 08:58:40AM +0800, Chengming Zhou wrote: >> On 2023/11/21 02:49, Mark Brown wrote: >>> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: > >>> When we see problems we see RCU stalls while logging in, for example: > >>> [ 46.453323] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: >>> [ 46.459361] rcu: 3-...0: (1 GPs behind) idle=def4/1/0x40000000 softirq=1304/1304 fqs=951 >>> [ 46.467669] rcu: (detected by 0, t=2103 jiffies, g=1161, q=499 ncpus=4) >>> [ 46.474472] Sending NMI from CPU 0 to CPUs 3: > >> IIUC, here should print the backtrace of CPU 3, right? It looks like CPU 3 is the cause, >> but we couldn't see what it's doing from the log. > > AIUI yes, but it looks like we've just completely lost the CPU - there's > more attempts to talk to it visible in the log: > >>> A full log for that run can be seen at: >>> >>> https://validation.linaro.org/scheduler/job/4017095 > > but none of them appear to cause CPU 3 to respond. Note that 32 bit ARM > is just using a regular IPI rather than something that's actually a NMI > so this isn't hugely out of the ordinary, I'd guess it's stuck with > interrupts masked. Ah yes, there is no NMI on ARM, so CPU 3 maybe running somewhere with interrupts disabled. I searched the full log, but still haven't a clue. And there is no any WARNING or BUG related to SLUB in the log. I wonder how to reproduce it locally with a Qemu VM since I don't have the ARM machine. Thanks!
On Tue, Nov 21, 2023 at 11:47:26PM +0800, Chengming Zhou wrote: > Ah yes, there is no NMI on ARM, so CPU 3 maybe running somewhere with > interrupts disabled. I searched the full log, but still haven't a clue. > And there is no any WARNING or BUG related to SLUB in the log. Yeah, nor anything else particularly. I tried turning on some debug options: CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_PREEMPT=y CONFIG_DEBUG_LOCKING=y CONFIG_DEBUG_ATOMIC_SLEEP=y https://validation.linaro.org/scheduler/job/4017828 which has some additional warnings related to clock changes but AFAICT those come from today's -next rather than the debug stuff: https://validation.linaro.org/scheduler/job/4017823 so that's not super helpful. > I wonder how to reproduce it locally with a Qemu VM since I don't have > the ARM machine. There's sample qemu jobs available from for example KernelCI: https://storage.kernelci.org/next/master/next-20231120/arm/multi_v7_defconfig/gcc-10/lab-baylibre/baseline-qemu_arm-virt-gicv3.html (includes the command line, though it's not using Debian testing like my test was). Note that I'm testing a bunch of platforms with the same kernel/rootfs combination and it was only the Raspberry Pi 3 which blew up. It is a bit tight for memory which might have some influence? I'm really suspecting this may have made some underlying platform bug more obvious :/
On 11/21/23 19:21, Mark Brown wrote: > On Tue, Nov 21, 2023 at 11:47:26PM +0800, Chengming Zhou wrote: > >> Ah yes, there is no NMI on ARM, so CPU 3 maybe running somewhere with >> interrupts disabled. I searched the full log, but still haven't a clue. >> And there is no any WARNING or BUG related to SLUB in the log. > > Yeah, nor anything else particularly. I tried turning on some debug > options: > > CONFIG_SOFTLOCKUP_DETECTOR=y > CONFIG_DETECT_HUNG_TASK=y > CONFIG_WQ_WATCHDOG=y > CONFIG_DEBUG_PREEMPT=y > CONFIG_DEBUG_LOCKING=y > CONFIG_DEBUG_ATOMIC_SLEEP=y > > https://validation.linaro.org/scheduler/job/4017828 > > which has some additional warnings related to clock changes but AFAICT > those come from today's -next rather than the debug stuff: > > https://validation.linaro.org/scheduler/job/4017823 > > so that's not super helpful. For the record (and to help debugging focus) on IRC we discussed that with CONFIG_SLUB_CPU_PARTIAL=n the problem persists: https://validation.linaro.org/scheduler/job/4017863 Which limits the scope of where to look so that's good :) >> I wonder how to reproduce it locally with a Qemu VM since I don't have >> the ARM machine. > > There's sample qemu jobs available from for example KernelCI: > > https://storage.kernelci.org/next/master/next-20231120/arm/multi_v7_defconfig/gcc-10/lab-baylibre/baseline-qemu_arm-virt-gicv3.html > > (includes the command line, though it's not using Debian testing like my > test was). Note that I'm testing a bunch of platforms with the same > kernel/rootfs combination and it was only the Raspberry Pi 3 which blew > up. It is a bit tight for memory which might have some influence? > > I'm really suspecting this may have made some underlying platform bug > more obvious :/
On 11/20/23 19:49, Mark Brown wrote: > On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >> From: Chengming Zhou <zhouchengming@bytedance.com> >> >> Now we will freeze slabs when moving them out of node partial list to >> cpu partial list, this method needs two cmpxchg_double operations: >> >> 1. freeze slab (acquire_slab()) under the node list_lock >> 2. get_freelist() when pick used in ___slab_alloc() > > Recently -next has been failing to boot on a Raspberry Pi 3 with an arm > multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this > patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having > introduced the issue. I've included the full bisect log below. > > When we see problems we see RCU stalls while logging in, for example: Can you try this, please? ----8<---- From 000030c1ff055ef6a2ca624d0142f08f3ef19d51 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka <vbabka@suse.cz> Date: Wed, 22 Nov 2023 10:32:41 +0100 Subject: [PATCH] mm/slub: try to fix hangs without cmpxchg64/128 If we don't have cmpxchg64/128 and resort to slab_lock()/slab_unlock() which uses PG_locked, we can get RMW with the newly introduced slab_set/clear_node_partial() operation that modify PG_workingset so all the operations have to be atomic now. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> --- mm/slub.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index bcb5b2c4e213..f2cdb81ab02e 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -522,7 +522,7 @@ static __always_inline void slab_unlock(struct slab *slab) struct page *page = slab_page(slab); VM_BUG_ON_PAGE(PageTail(page), page); - __bit_spin_unlock(PG_locked, &page->flags); + bit_spin_unlock(PG_locked, &page->flags); } static inline bool @@ -2127,12 +2127,12 @@ static inline bool slab_test_node_partial(const struct slab *slab) static inline void slab_set_node_partial(struct slab *slab) { - __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); } static inline void slab_clear_node_partial(struct slab *slab) { - __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); } /*
On Wed, Nov 22, 2023 at 10:37:39AM +0100, Vlastimil Babka wrote: > Can you try this, please? > Subject: [PATCH] mm/slub: try to fix hangs without cmpxchg64/128 > > If we don't have cmpxchg64/128 and resort to slab_lock()/slab_unlock() > which uses PG_locked, we can get RMW with the newly introduced > slab_set/clear_node_partial() operation that modify PG_workingset so all > the operations have to be atomic now. That seems to resolve the issue: https://validation.linaro.org/scheduler/job/4018096 Tested-by: Mark Brown <broonie@kernel.org> Thanks!
On 2023/11/22 17:37, Vlastimil Babka wrote: > On 11/20/23 19:49, Mark Brown wrote: >> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >>> From: Chengming Zhou <zhouchengming@bytedance.com> >>> >>> Now we will freeze slabs when moving them out of node partial list to >>> cpu partial list, this method needs two cmpxchg_double operations: >>> >>> 1. freeze slab (acquire_slab()) under the node list_lock >>> 2. get_freelist() when pick used in ___slab_alloc() >> >> Recently -next has been failing to boot on a Raspberry Pi 3 with an arm >> multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this >> patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having >> introduced the issue. I've included the full bisect log below. >> >> When we see problems we see RCU stalls while logging in, for example: > > Can you try this, please? > Great! I manually disabled __CMPXCHG_DOUBLE to reproduce the problem, and this patch can solve the machine hang problem. BTW, I also did the performance testcase on the machine with 128 CPUs. stress-ng --rawpkt 128 --rawpkt-ops 100000000 base patched 2.22s 2.35s 2.21s 3.14s 2.19s 4.75s Found this atomic version performance numbers are not stable. Should I change back to reuse the slab->__unused (mapcount) field? Or should we check "s->flags & __CMPXCHG_DOUBLE" in slab_set/clear_node_partial() to avoid using the atomic version? Thanks! > ----8<---- > From 000030c1ff055ef6a2ca624d0142f08f3ef19d51 Mon Sep 17 00:00:00 2001 > From: Vlastimil Babka <vbabka@suse.cz> > Date: Wed, 22 Nov 2023 10:32:41 +0100 > Subject: [PATCH] mm/slub: try to fix hangs without cmpxchg64/128 > > If we don't have cmpxchg64/128 and resort to slab_lock()/slab_unlock() > which uses PG_locked, we can get RMW with the newly introduced > slab_set/clear_node_partial() operation that modify PG_workingset so all > the operations have to be atomic now. > > Signed-off-by: Vlastimil Babka <vbabka@suse.cz> > --- > mm/slub.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > diff --git a/mm/slub.c b/mm/slub.c > index bcb5b2c4e213..f2cdb81ab02e 100644 > --- a/mm/slub.c > +++ b/mm/slub.c > @@ -522,7 +522,7 @@ static __always_inline void slab_unlock(struct slab *slab) > struct page *page = slab_page(slab); > > VM_BUG_ON_PAGE(PageTail(page), page); > - __bit_spin_unlock(PG_locked, &page->flags); > + bit_spin_unlock(PG_locked, &page->flags); > } > > static inline bool > @@ -2127,12 +2127,12 @@ static inline bool slab_test_node_partial(const struct slab *slab) > > static inline void slab_set_node_partial(struct slab *slab) > { > - __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > } > > static inline void slab_clear_node_partial(struct slab *slab) > { > - __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > } > > /*
On 11/22/23 12:35, Chengming Zhou wrote: > On 2023/11/22 17:37, Vlastimil Babka wrote: >> On 11/20/23 19:49, Mark Brown wrote: >>> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >>>> From: Chengming Zhou <zhouchengming@bytedance.com> >>>> >>>> Now we will freeze slabs when moving them out of node partial list to >>>> cpu partial list, this method needs two cmpxchg_double operations: >>>> >>>> 1. freeze slab (acquire_slab()) under the node list_lock >>>> 2. get_freelist() when pick used in ___slab_alloc() >>> >>> Recently -next has been failing to boot on a Raspberry Pi 3 with an arm >>> multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this >>> patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having >>> introduced the issue. I've included the full bisect log below. >>> >>> When we see problems we see RCU stalls while logging in, for example: >> >> Can you try this, please? >> > > Great! I manually disabled __CMPXCHG_DOUBLE to reproduce the problem, > and this patch can solve the machine hang problem. > > BTW, I also did the performance testcase on the machine with 128 CPUs. > > stress-ng --rawpkt 128 --rawpkt-ops 100000000 > > base patched > 2.22s 2.35s > 2.21s 3.14s > 2.19s 4.75s > > Found this atomic version performance numbers are not stable. That's weirdly too bad. Is that measured also with __CMPXCHG_DOUBLE disabled, or just the patch? The PG_workingset flag change should be uncontended as we are doing it under list_lock, and with __CMPXCHG_DOUBLE there should be no interfering PG_locked interference.
On 2023/11/22 19:40, Vlastimil Babka wrote: > On 11/22/23 12:35, Chengming Zhou wrote: >> On 2023/11/22 17:37, Vlastimil Babka wrote: >>> On 11/20/23 19:49, Mark Brown wrote: >>>> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >>>>> From: Chengming Zhou <zhouchengming@bytedance.com> >>>>> >>>>> Now we will freeze slabs when moving them out of node partial list to >>>>> cpu partial list, this method needs two cmpxchg_double operations: >>>>> >>>>> 1. freeze slab (acquire_slab()) under the node list_lock >>>>> 2. get_freelist() when pick used in ___slab_alloc() >>>> >>>> Recently -next has been failing to boot on a Raspberry Pi 3 with an arm >>>> multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this >>>> patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having >>>> introduced the issue. I've included the full bisect log below. >>>> >>>> When we see problems we see RCU stalls while logging in, for example: >>> >>> Can you try this, please? >>> >> >> Great! I manually disabled __CMPXCHG_DOUBLE to reproduce the problem, >> and this patch can solve the machine hang problem. >> >> BTW, I also did the performance testcase on the machine with 128 CPUs. >> >> stress-ng --rawpkt 128 --rawpkt-ops 100000000 >> >> base patched >> 2.22s 2.35s >> 2.21s 3.14s >> 2.19s 4.75s >> >> Found this atomic version performance numbers are not stable. > > That's weirdly too bad. Is that measured also with __CMPXCHG_DOUBLE > disabled, or just the patch? The PG_workingset flag change should be The performance test is just the patch. > uncontended as we are doing it under list_lock, and with __CMPXCHG_DOUBLE > there should be no interfering PG_locked interference. > Yes, I don't know. Maybe it's related with my kernel config, making the atomic operation much expensive? Will look again.. And I also tested the atomic-optional version like below, found the performance numbers are much stable. diff --git a/mm/slub.c b/mm/slub.c index a307d319e82c..e11d34d51a14 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -531,7 +531,7 @@ static __always_inline void slab_unlock(struct slab *slab) struct page *page = slab_page(slab); VM_BUG_ON_PAGE(PageTail(page), page); - __bit_spin_unlock(PG_locked, &page->flags); + bit_spin_unlock(PG_locked, &page->flags); } static inline bool @@ -2136,12 +2136,18 @@ static inline bool slab_test_node_partial(const struct slab *slab) static inline void slab_set_node_partial(struct slab *slab) { - __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + if (slab->slab_cache->flags & __CMPXCHG_DOUBLE) + __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + else + set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); } static inline void slab_clear_node_partial(struct slab *slab) { - __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + if (slab->slab_cache->flags & __CMPXCHG_DOUBLE) + __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); + else + clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); }
On 11/22/23 12:54, Chengming Zhou wrote: > On 2023/11/22 19:40, Vlastimil Babka wrote: >> On 11/22/23 12:35, Chengming Zhou wrote: >>> On 2023/11/22 17:37, Vlastimil Babka wrote: >>>> On 11/20/23 19:49, Mark Brown wrote: >>>>> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >>>>>> From: Chengming Zhou <zhouchengming@bytedance.com> >>>>>> >>>>>> Now we will freeze slabs when moving them out of node partial list to >>>>>> cpu partial list, this method needs two cmpxchg_double operations: >>>>>> >>>>>> 1. freeze slab (acquire_slab()) under the node list_lock >>>>>> 2. get_freelist() when pick used in ___slab_alloc() >>>>> >>>>> Recently -next has been failing to boot on a Raspberry Pi 3 with an arm >>>>> multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this >>>>> patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having >>>>> introduced the issue. I've included the full bisect log below. >>>>> >>>>> When we see problems we see RCU stalls while logging in, for example: >>>> >>>> Can you try this, please? >>>> >>> >>> Great! I manually disabled __CMPXCHG_DOUBLE to reproduce the problem, >>> and this patch can solve the machine hang problem. >>> >>> BTW, I also did the performance testcase on the machine with 128 CPUs. >>> >>> stress-ng --rawpkt 128 --rawpkt-ops 100000000 >>> >>> base patched >>> 2.22s 2.35s >>> 2.21s 3.14s >>> 2.19s 4.75s >>> >>> Found this atomic version performance numbers are not stable. >> >> That's weirdly too bad. Is that measured also with __CMPXCHG_DOUBLE >> disabled, or just the patch? The PG_workingset flag change should be > > The performance test is just the patch. > >> uncontended as we are doing it under list_lock, and with __CMPXCHG_DOUBLE >> there should be no interfering PG_locked interference. >> > > Yes, I don't know. Maybe it's related with my kernel config, making the > atomic operation much expensive? Will look again.. I doubt it can explain going from 2.19s to 4.75s, must have been some interference on the machine? > And I also tested the atomic-optional version like below, found the > performance numbers are much stable. This gets rather ugly and fragile so I'd maybe rather go back to the __unused field approach :/ > diff --git a/mm/slub.c b/mm/slub.c > index a307d319e82c..e11d34d51a14 100644 > --- a/mm/slub.c > +++ b/mm/slub.c > @@ -531,7 +531,7 @@ static __always_inline void slab_unlock(struct slab *slab) > struct page *page = slab_page(slab); > > VM_BUG_ON_PAGE(PageTail(page), page); > - __bit_spin_unlock(PG_locked, &page->flags); > + bit_spin_unlock(PG_locked, &page->flags); > } > > static inline bool > @@ -2136,12 +2136,18 @@ static inline bool slab_test_node_partial(const struct slab *slab) > > static inline void slab_set_node_partial(struct slab *slab) > { > - __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + if (slab->slab_cache->flags & __CMPXCHG_DOUBLE) > + __set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + else > + set_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > } > > static inline void slab_clear_node_partial(struct slab *slab) > { > - __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + if (slab->slab_cache->flags & __CMPXCHG_DOUBLE) > + __clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > + else > + clear_bit(PG_workingset, folio_flags(slab_folio(slab), 0)); > }
On 2023/11/22 21:19, Vlastimil Babka wrote: > On 11/22/23 12:54, Chengming Zhou wrote: >> On 2023/11/22 19:40, Vlastimil Babka wrote: >>> On 11/22/23 12:35, Chengming Zhou wrote: >>>> On 2023/11/22 17:37, Vlastimil Babka wrote: >>>>> On 11/20/23 19:49, Mark Brown wrote: >>>>>> On Thu, Nov 02, 2023 at 03:23:27AM +0000, chengming.zhou@linux.dev wrote: >>>>>>> From: Chengming Zhou <zhouchengming@bytedance.com> >>>>>>> >>>>>>> Now we will freeze slabs when moving them out of node partial list to >>>>>>> cpu partial list, this method needs two cmpxchg_double operations: >>>>>>> >>>>>>> 1. freeze slab (acquire_slab()) under the node list_lock >>>>>>> 2. get_freelist() when pick used in ___slab_alloc() >>>>>> >>>>>> Recently -next has been failing to boot on a Raspberry Pi 3 with an arm >>>>>> multi_v7_defconfig and a NFS rootfs, a bisect appears to point to this >>>>>> patch (in -next as c8d312e039030edab25836a326bcaeb2a3d4db14) as having >>>>>> introduced the issue. I've included the full bisect log below. >>>>>> >>>>>> When we see problems we see RCU stalls while logging in, for example: >>>>> >>>>> Can you try this, please? >>>>> >>>> >>>> Great! I manually disabled __CMPXCHG_DOUBLE to reproduce the problem, >>>> and this patch can solve the machine hang problem. >>>> >>>> BTW, I also did the performance testcase on the machine with 128 CPUs. >>>> >>>> stress-ng --rawpkt 128 --rawpkt-ops 100000000 >>>> >>>> base patched >>>> 2.22s 2.35s >>>> 2.21s 3.14s >>>> 2.19s 4.75s >>>> >>>> Found this atomic version performance numbers are not stable. >>> >>> That's weirdly too bad. Is that measured also with __CMPXCHG_DOUBLE >>> disabled, or just the patch? The PG_workingset flag change should be >> >> The performance test is just the patch. >> >>> uncontended as we are doing it under list_lock, and with __CMPXCHG_DOUBLE >>> there should be no interfering PG_locked interference. >>> >> >> Yes, I don't know. Maybe it's related with my kernel config, making the >> atomic operation much expensive? Will look again.. > > I doubt it can explain going from 2.19s to 4.75s, must have been some > interference on the machine? > Yes, it looks so. There are some background services on the 128 CPUs machine. Although "stress-ng --rawpkt 128 --rawpkt-ops 100000000" has so much regression, I tried other less contented testcases: 1. stress-ng --rawpkt 64 --rawpkt-ops 100000000 2. perf bench sched messaging -g 5 -t -l 100000 The performance numbers of this atomic version are pretty much the same. So this atomic version should be good in most cases IMHO. >> And I also tested the atomic-optional version like below, found the >> performance numbers are much stable. > > This gets rather ugly and fragile so I'd maybe rather go back to the > __unused field approach :/ > Agree. If we don't want this atomic version, the __unused field approach seems better. Thanks!
On 11/22/23 15:28, Chengming Zhou wrote: > > Yes, it looks so. There are some background services on the 128 CPUs machine. > Although "stress-ng --rawpkt 128 --rawpkt-ops 100000000" has so much regression, > I tried other less contented testcases: > > 1. stress-ng --rawpkt 64 --rawpkt-ops 100000000 > 2. perf bench sched messaging -g 5 -t -l 100000 > > The performance numbers of this atomic version are pretty much the same. > > So this atomic version should be good in most cases IMHO. OK will fold the fix using full atomic version. >>> And I also tested the atomic-optional version like below, found the >>> performance numbers are much stable. >> >> This gets rather ugly and fragile so I'd maybe rather go back to the >> __unused field approach :/ >> > > Agree. If we don't want this atomic version, the __unused field approach > seems better. > > Thanks! >
On Thu, Nov 2, 2023 at 12:25 PM <chengming.zhou@linux.dev> wrote: > > From: Chengming Zhou <zhouchengming@bytedance.com> > > Now we will freeze slabs when moving them out of node partial list to > cpu partial list, this method needs two cmpxchg_double operations: > > 1. freeze slab (acquire_slab()) under the node list_lock > 2. get_freelist() when pick used in ___slab_alloc() > > Actually we don't need to freeze when moving slabs out of node partial > list, we can delay freezing to when use slab freelist in ___slab_alloc(), > so we can save one cmpxchg_double(). > > And there are other good points: > - The moving of slabs between node partial list and cpu partial list > becomes simpler, since we don't need to freeze or unfreeze at all. > > - The node list_lock contention would be less, since we don't need to > freeze any slab under the node list_lock. > > We can achieve this because there is no concurrent path would manipulate > the partial slab list except the __slab_free() path, which is now > serialized by slab_test_node_partial() under the list_lock. > > Since the slab returned by get_partial() interfaces is not frozen anymore > and no freelist is returned in the partial_context, so we need to use the > introduced freeze_slab() to freeze it and get its freelist. > > Similarly, the slabs on the CPU partial list are not frozen anymore, > we need to freeze_slab() on it before use. > > We can now delete acquire_slab() as it became unused. > > Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> > Reviewed-by: Vlastimil Babka <vbabka@suse.cz> > Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> > --- > mm/slub.c | 113 +++++++++++------------------------------------------- > 1 file changed, 23 insertions(+), 90 deletions(-) > > diff --git a/mm/slub.c b/mm/slub.c > index edf567971679..bcb5b2c4e213 100644 > --- a/mm/slub.c > +++ b/mm/slub.c > @@ -2234,51 +2234,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, > return object; > } > > -/* > - * Remove slab from the partial list, freeze it and > - * return the pointer to the freelist. > - * > - * Returns a list of objects or NULL if it fails. > - */ > -static inline void *acquire_slab(struct kmem_cache *s, > - struct kmem_cache_node *n, struct slab *slab, > - int mode) Nit: alloc_single_from_partial()'s comment still refers to acquire_slab(). > -{ > - void *freelist; > - unsigned long counters; > - struct slab new; > - > - lockdep_assert_held(&n->list_lock); > - > - /* > - * Zap the freelist and set the frozen bit. > - * The old freelist is the list of objects for the > - * per cpu allocation list. > - */ > - freelist = slab->freelist; > - counters = slab->counters; > - new.counters = counters; > - if (mode) { > - new.inuse = slab->objects; > - new.freelist = NULL; > - } else { > - new.freelist = freelist; > - } > - > - VM_BUG_ON(new.frozen); > - new.frozen = 1; > - > - if (!__slab_update_freelist(s, slab, > - freelist, counters, > - new.freelist, new.counters, > - "acquire_slab")) > - return NULL; > - > - remove_partial(n, slab); > - WARN_ON(!freelist); > - return freelist; > -} > - > #ifdef CONFIG_SLUB_CPU_PARTIAL > static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain); > #else > @@ -2295,7 +2250,6 @@ static struct slab *get_partial_node(struct kmem_cache *s, > struct partial_context *pc) > { > struct slab *slab, *slab2, *partial = NULL; > - void *object = NULL; > unsigned long flags; > unsigned int partial_slabs = 0; > > @@ -2314,7 +2268,7 @@ static struct slab *get_partial_node(struct kmem_cache *s, > continue; > > if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) { > - object = alloc_single_from_partial(s, n, slab, > + void *object = alloc_single_from_partial(s, n, slab, > pc->orig_size); > if (object) { > partial = slab; > @@ -2324,13 +2278,10 @@ static struct slab *get_partial_node(struct kmem_cache *s, > continue; > } > > - object = acquire_slab(s, n, slab, object == NULL); > - if (!object) > - break; > + remove_partial(n, slab); > > if (!partial) { > partial = slab; > - pc->object = object; > stat(s, ALLOC_FROM_PARTIAL); > } else { > put_cpu_partial(s, slab, 0); > @@ -2629,9 +2580,6 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) > unsigned long flags = 0; > > while (partial_slab) { > - struct slab new; > - struct slab old; > - > slab = partial_slab; > partial_slab = slab->next; > > @@ -2644,23 +2592,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) > spin_lock_irqsave(&n->list_lock, flags); > } > > - do { > - > - old.freelist = slab->freelist; > - old.counters = slab->counters; > - VM_BUG_ON(!old.frozen); > - > - new.counters = old.counters; > - new.freelist = old.freelist; > - > - new.frozen = 0; > - > - } while (!__slab_update_freelist(s, slab, > - old.freelist, old.counters, > - new.freelist, new.counters, > - "unfreezing slab")); > - > - if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { > + if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) { > slab->next = slab_to_discard; > slab_to_discard = slab; > } else { > @@ -3167,7 +3099,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > node = NUMA_NO_NODE; > goto new_slab; > } > -redo: > > if (unlikely(!node_match(slab, node))) { > /* > @@ -3243,7 +3174,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > > new_slab: > > - if (slub_percpu_partial(c)) { > +#ifdef CONFIG_SLUB_CPU_PARTIAL > + while (slub_percpu_partial(c)) { > local_lock_irqsave(&s->cpu_slab->lock, flags); > if (unlikely(c->slab)) { > local_unlock_irqrestore(&s->cpu_slab->lock, flags); > @@ -3255,12 +3187,22 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > goto new_objects; > } > > - slab = c->slab = slub_percpu_partial(c); > + slab = slub_percpu_partial(c); > slub_set_percpu_partial(c, slab); > local_unlock_irqrestore(&s->cpu_slab->lock, flags); > stat(s, CPU_PARTIAL_ALLOC); > - goto redo; > + > + if (unlikely(!node_match(slab, node) || > + !pfmemalloc_match(slab, gfpflags))) { > + slab->next = NULL; > + __unfreeze_partials(s, slab); > + continue; > + } > + > + freelist = freeze_slab(s, slab); > + goto retry_load_slab; > } > +#endif > > new_objects: > > @@ -3268,8 +3210,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > pc.orig_size = orig_size; > slab = get_partial(s, node, &pc); > if (slab) { > - freelist = pc.object; > if (kmem_cache_debug(s)) { > + freelist = pc.object; > /* > * For debug caches here we had to go through > * alloc_single_from_partial() so just store the > @@ -3281,6 +3223,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, > return freelist; > } > > + freelist = freeze_slab(s, slab); > goto retry_load_slab; > } > > @@ -3682,18 +3625,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, > was_frozen = new.frozen; > new.inuse -= cnt; > if ((!new.inuse || !prior) && !was_frozen) { > - > - if (kmem_cache_has_cpu_partial(s) && !prior) { > - > - /* > - * Slab was on no list before and will be > - * partially empty > - * We can defer the list move and instead > - * freeze it. > - */ > - new.frozen = 1; > - > - } else { /* Needs to be taken off a list */ > + /* Needs to be taken off a list */ > + if (!kmem_cache_has_cpu_partial(s) || prior) { > > n = get_node(s, slab_nid(slab)); > /* > @@ -3723,9 +3656,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, > * activity can be necessary. > */ > stat(s, FREE_FROZEN); > - } else if (new.frozen) { > + } else if (kmem_cache_has_cpu_partial(s) && !prior) { > /* > - * If we just froze the slab then put it onto the > + * If we started with a full slab then put it onto the > * per cpu partial list. > */ > put_cpu_partial(s, slab, 1); > -- Looks good to me, Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Thanks! > 2.20.1 >
On 2023/12/3 14:53, Hyeonggon Yoo wrote: > On Thu, Nov 2, 2023 at 12:25 PM <chengming.zhou@linux.dev> wrote: >> >> From: Chengming Zhou <zhouchengming@bytedance.com> >> >> Now we will freeze slabs when moving them out of node partial list to >> cpu partial list, this method needs two cmpxchg_double operations: >> >> 1. freeze slab (acquire_slab()) under the node list_lock >> 2. get_freelist() when pick used in ___slab_alloc() >> >> Actually we don't need to freeze when moving slabs out of node partial >> list, we can delay freezing to when use slab freelist in ___slab_alloc(), >> so we can save one cmpxchg_double(). >> >> And there are other good points: >> - The moving of slabs between node partial list and cpu partial list >> becomes simpler, since we don't need to freeze or unfreeze at all. >> >> - The node list_lock contention would be less, since we don't need to >> freeze any slab under the node list_lock. >> >> We can achieve this because there is no concurrent path would manipulate >> the partial slab list except the __slab_free() path, which is now >> serialized by slab_test_node_partial() under the list_lock. >> >> Since the slab returned by get_partial() interfaces is not frozen anymore >> and no freelist is returned in the partial_context, so we need to use the >> introduced freeze_slab() to freeze it and get its freelist. >> >> Similarly, the slabs on the CPU partial list are not frozen anymore, >> we need to freeze_slab() on it before use. >> >> We can now delete acquire_slab() as it became unused. >> >> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> >> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> >> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> >> --- >> mm/slub.c | 113 +++++++++++------------------------------------------- >> 1 file changed, 23 insertions(+), 90 deletions(-) >> >> diff --git a/mm/slub.c b/mm/slub.c >> index edf567971679..bcb5b2c4e213 100644 >> --- a/mm/slub.c >> +++ b/mm/slub.c >> @@ -2234,51 +2234,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, >> return object; >> } >> >> -/* >> - * Remove slab from the partial list, freeze it and >> - * return the pointer to the freelist. >> - * >> - * Returns a list of objects or NULL if it fails. >> - */ >> -static inline void *acquire_slab(struct kmem_cache *s, >> - struct kmem_cache_node *n, struct slab *slab, >> - int mode) > > Nit: alloc_single_from_partial()'s comment still refers to acquire_slab(). > Ah, right! It should be changed to remove_partial(). diff --git a/mm/slub.c b/mm/slub.c index 437485a2408d..623c17a4cdd6 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2463,7 +2463,7 @@ static inline void remove_partial(struct kmem_cache_node *n, } /* - * Called only for kmem_cache_debug() caches instead of acquire_slab(), with a + * Called only for kmem_cache_debug() caches instead of remove_partial(), with a * slab from the n->partial list. Remove only a single object from the slab, do * the alloc_debug_processing() checks and leave the slab on the list, or move * it to full list if it was the last free object. Hi Vlastimil, could you please help to fold it? Thanks! >> -{ >> - void *freelist; >> - unsigned long counters; >> - struct slab new; >> - >> - lockdep_assert_held(&n->list_lock); >> - >> - /* >> - * Zap the freelist and set the frozen bit. >> - * The old freelist is the list of objects for the >> - * per cpu allocation list. >> - */ >> - freelist = slab->freelist; >> - counters = slab->counters; >> - new.counters = counters; >> - if (mode) { >> - new.inuse = slab->objects; >> - new.freelist = NULL; >> - } else { >> - new.freelist = freelist; >> - } >> - >> - VM_BUG_ON(new.frozen); >> - new.frozen = 1; >> - >> - if (!__slab_update_freelist(s, slab, >> - freelist, counters, >> - new.freelist, new.counters, >> - "acquire_slab")) >> - return NULL; >> - >> - remove_partial(n, slab); >> - WARN_ON(!freelist); >> - return freelist; >> -} >> - >> #ifdef CONFIG_SLUB_CPU_PARTIAL >> static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain); >> #else >> @@ -2295,7 +2250,6 @@ static struct slab *get_partial_node(struct kmem_cache *s, >> struct partial_context *pc) >> { >> struct slab *slab, *slab2, *partial = NULL; >> - void *object = NULL; >> unsigned long flags; >> unsigned int partial_slabs = 0; >> >> @@ -2314,7 +2268,7 @@ static struct slab *get_partial_node(struct kmem_cache *s, >> continue; >> >> if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) { >> - object = alloc_single_from_partial(s, n, slab, >> + void *object = alloc_single_from_partial(s, n, slab, >> pc->orig_size); >> if (object) { >> partial = slab; >> @@ -2324,13 +2278,10 @@ static struct slab *get_partial_node(struct kmem_cache *s, >> continue; >> } >> >> - object = acquire_slab(s, n, slab, object == NULL); >> - if (!object) >> - break; >> + remove_partial(n, slab); >> >> if (!partial) { >> partial = slab; >> - pc->object = object; >> stat(s, ALLOC_FROM_PARTIAL); >> } else { >> put_cpu_partial(s, slab, 0); >> @@ -2629,9 +2580,6 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) >> unsigned long flags = 0; >> >> while (partial_slab) { >> - struct slab new; >> - struct slab old; >> - >> slab = partial_slab; >> partial_slab = slab->next; >> >> @@ -2644,23 +2592,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) >> spin_lock_irqsave(&n->list_lock, flags); >> } >> >> - do { >> - >> - old.freelist = slab->freelist; >> - old.counters = slab->counters; >> - VM_BUG_ON(!old.frozen); >> - >> - new.counters = old.counters; >> - new.freelist = old.freelist; >> - >> - new.frozen = 0; >> - >> - } while (!__slab_update_freelist(s, slab, >> - old.freelist, old.counters, >> - new.freelist, new.counters, >> - "unfreezing slab")); >> - >> - if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { >> + if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) { >> slab->next = slab_to_discard; >> slab_to_discard = slab; >> } else { >> @@ -3167,7 +3099,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, >> node = NUMA_NO_NODE; >> goto new_slab; >> } >> -redo: >> >> if (unlikely(!node_match(slab, node))) { >> /* >> @@ -3243,7 +3174,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, >> >> new_slab: >> >> - if (slub_percpu_partial(c)) { >> +#ifdef CONFIG_SLUB_CPU_PARTIAL >> + while (slub_percpu_partial(c)) { >> local_lock_irqsave(&s->cpu_slab->lock, flags); >> if (unlikely(c->slab)) { >> local_unlock_irqrestore(&s->cpu_slab->lock, flags); >> @@ -3255,12 +3187,22 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, >> goto new_objects; >> } >> >> - slab = c->slab = slub_percpu_partial(c); >> + slab = slub_percpu_partial(c); >> slub_set_percpu_partial(c, slab); >> local_unlock_irqrestore(&s->cpu_slab->lock, flags); >> stat(s, CPU_PARTIAL_ALLOC); >> - goto redo; >> + >> + if (unlikely(!node_match(slab, node) || >> + !pfmemalloc_match(slab, gfpflags))) { >> + slab->next = NULL; >> + __unfreeze_partials(s, slab); >> + continue; >> + } >> + >> + freelist = freeze_slab(s, slab); >> + goto retry_load_slab; >> } >> +#endif >> >> new_objects: >> >> @@ -3268,8 +3210,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, >> pc.orig_size = orig_size; >> slab = get_partial(s, node, &pc); >> if (slab) { >> - freelist = pc.object; >> if (kmem_cache_debug(s)) { >> + freelist = pc.object; >> /* >> * For debug caches here we had to go through >> * alloc_single_from_partial() so just store the >> @@ -3281,6 +3223,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, >> return freelist; >> } >> >> + freelist = freeze_slab(s, slab); >> goto retry_load_slab; >> } >> >> @@ -3682,18 +3625,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, >> was_frozen = new.frozen; >> new.inuse -= cnt; >> if ((!new.inuse || !prior) && !was_frozen) { >> - >> - if (kmem_cache_has_cpu_partial(s) && !prior) { >> - >> - /* >> - * Slab was on no list before and will be >> - * partially empty >> - * We can defer the list move and instead >> - * freeze it. >> - */ >> - new.frozen = 1; >> - >> - } else { /* Needs to be taken off a list */ >> + /* Needs to be taken off a list */ >> + if (!kmem_cache_has_cpu_partial(s) || prior) { >> >> n = get_node(s, slab_nid(slab)); >> /* >> @@ -3723,9 +3656,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, >> * activity can be necessary. >> */ >> stat(s, FREE_FROZEN); >> - } else if (new.frozen) { >> + } else if (kmem_cache_has_cpu_partial(s) && !prior) { >> /* >> - * If we just froze the slab then put it onto the >> + * If we started with a full slab then put it onto the >> * per cpu partial list. >> */ >> put_cpu_partial(s, slab, 1); >> -- > > Looks good to me, > Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> > > Thanks! > >> 2.20.1 >>
On 12/3/23 11:15, Chengming Zhou wrote: > On 2023/12/3 14:53, Hyeonggon Yoo wrote: >> On Thu, Nov 2, 2023 at 12:25 PM <chengming.zhou@linux.dev> wrote: >>> >>> From: Chengming Zhou <zhouchengming@bytedance.com> >>> >>> Now we will freeze slabs when moving them out of node partial list to >>> cpu partial list, this method needs two cmpxchg_double operations: >>> >>> 1. freeze slab (acquire_slab()) under the node list_lock >>> 2. get_freelist() when pick used in ___slab_alloc() >>> >>> Actually we don't need to freeze when moving slabs out of node partial >>> list, we can delay freezing to when use slab freelist in ___slab_alloc(), >>> so we can save one cmpxchg_double(). >>> >>> And there are other good points: >>> - The moving of slabs between node partial list and cpu partial list >>> becomes simpler, since we don't need to freeze or unfreeze at all. >>> >>> - The node list_lock contention would be less, since we don't need to >>> freeze any slab under the node list_lock. >>> >>> We can achieve this because there is no concurrent path would manipulate >>> the partial slab list except the __slab_free() path, which is now >>> serialized by slab_test_node_partial() under the list_lock. >>> >>> Since the slab returned by get_partial() interfaces is not frozen anymore >>> and no freelist is returned in the partial_context, so we need to use the >>> introduced freeze_slab() to freeze it and get its freelist. >>> >>> Similarly, the slabs on the CPU partial list are not frozen anymore, >>> we need to freeze_slab() on it before use. >>> >>> We can now delete acquire_slab() as it became unused. >>> >>> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> >>> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> >>> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> >>> --- >>> mm/slub.c | 113 +++++++++++------------------------------------------- >>> 1 file changed, 23 insertions(+), 90 deletions(-) >>> >>> diff --git a/mm/slub.c b/mm/slub.c >>> index edf567971679..bcb5b2c4e213 100644 >>> --- a/mm/slub.c >>> +++ b/mm/slub.c >>> @@ -2234,51 +2234,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, >>> return object; >>> } >>> >>> -/* >>> - * Remove slab from the partial list, freeze it and >>> - * return the pointer to the freelist. >>> - * >>> - * Returns a list of objects or NULL if it fails. >>> - */ >>> -static inline void *acquire_slab(struct kmem_cache *s, >>> - struct kmem_cache_node *n, struct slab *slab, >>> - int mode) >> >> Nit: alloc_single_from_partial()'s comment still refers to acquire_slab(). >> > > Ah, right! It should be changed to remove_partial(). > > diff --git a/mm/slub.c b/mm/slub.c > index 437485a2408d..623c17a4cdd6 100644 > --- a/mm/slub.c > +++ b/mm/slub.c > @@ -2463,7 +2463,7 @@ static inline void remove_partial(struct kmem_cache_node *n, > } > > /* > - * Called only for kmem_cache_debug() caches instead of acquire_slab(), with a > + * Called only for kmem_cache_debug() caches instead of remove_partial(), with a > * slab from the n->partial list. Remove only a single object from the slab, do > * the alloc_debug_processing() checks and leave the slab on the list, or move > * it to full list if it was the last free object. > > Hi Vlastimil, could you please help to fold it? Done, thanks.
diff --git a/mm/slub.c b/mm/slub.c index edf567971679..bcb5b2c4e213 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2234,51 +2234,6 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, return object; } -/* - * Remove slab from the partial list, freeze it and - * return the pointer to the freelist. - * - * Returns a list of objects or NULL if it fails. - */ -static inline void *acquire_slab(struct kmem_cache *s, - struct kmem_cache_node *n, struct slab *slab, - int mode) -{ - void *freelist; - unsigned long counters; - struct slab new; - - lockdep_assert_held(&n->list_lock); - - /* - * Zap the freelist and set the frozen bit. - * The old freelist is the list of objects for the - * per cpu allocation list. - */ - freelist = slab->freelist; - counters = slab->counters; - new.counters = counters; - if (mode) { - new.inuse = slab->objects; - new.freelist = NULL; - } else { - new.freelist = freelist; - } - - VM_BUG_ON(new.frozen); - new.frozen = 1; - - if (!__slab_update_freelist(s, slab, - freelist, counters, - new.freelist, new.counters, - "acquire_slab")) - return NULL; - - remove_partial(n, slab); - WARN_ON(!freelist); - return freelist; -} - #ifdef CONFIG_SLUB_CPU_PARTIAL static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain); #else @@ -2295,7 +2250,6 @@ static struct slab *get_partial_node(struct kmem_cache *s, struct partial_context *pc) { struct slab *slab, *slab2, *partial = NULL; - void *object = NULL; unsigned long flags; unsigned int partial_slabs = 0; @@ -2314,7 +2268,7 @@ static struct slab *get_partial_node(struct kmem_cache *s, continue; if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) { - object = alloc_single_from_partial(s, n, slab, + void *object = alloc_single_from_partial(s, n, slab, pc->orig_size); if (object) { partial = slab; @@ -2324,13 +2278,10 @@ static struct slab *get_partial_node(struct kmem_cache *s, continue; } - object = acquire_slab(s, n, slab, object == NULL); - if (!object) - break; + remove_partial(n, slab); if (!partial) { partial = slab; - pc->object = object; stat(s, ALLOC_FROM_PARTIAL); } else { put_cpu_partial(s, slab, 0); @@ -2629,9 +2580,6 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) unsigned long flags = 0; while (partial_slab) { - struct slab new; - struct slab old; - slab = partial_slab; partial_slab = slab->next; @@ -2644,23 +2592,7 @@ static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) spin_lock_irqsave(&n->list_lock, flags); } - do { - - old.freelist = slab->freelist; - old.counters = slab->counters; - VM_BUG_ON(!old.frozen); - - new.counters = old.counters; - new.freelist = old.freelist; - - new.frozen = 0; - - } while (!__slab_update_freelist(s, slab, - old.freelist, old.counters, - new.freelist, new.counters, - "unfreezing slab")); - - if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { + if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial)) { slab->next = slab_to_discard; slab_to_discard = slab; } else { @@ -3167,7 +3099,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, node = NUMA_NO_NODE; goto new_slab; } -redo: if (unlikely(!node_match(slab, node))) { /* @@ -3243,7 +3174,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, new_slab: - if (slub_percpu_partial(c)) { +#ifdef CONFIG_SLUB_CPU_PARTIAL + while (slub_percpu_partial(c)) { local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(c->slab)) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); @@ -3255,12 +3187,22 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, goto new_objects; } - slab = c->slab = slub_percpu_partial(c); + slab = slub_percpu_partial(c); slub_set_percpu_partial(c, slab); local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, CPU_PARTIAL_ALLOC); - goto redo; + + if (unlikely(!node_match(slab, node) || + !pfmemalloc_match(slab, gfpflags))) { + slab->next = NULL; + __unfreeze_partials(s, slab); + continue; + } + + freelist = freeze_slab(s, slab); + goto retry_load_slab; } +#endif new_objects: @@ -3268,8 +3210,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, pc.orig_size = orig_size; slab = get_partial(s, node, &pc); if (slab) { - freelist = pc.object; if (kmem_cache_debug(s)) { + freelist = pc.object; /* * For debug caches here we had to go through * alloc_single_from_partial() so just store the @@ -3281,6 +3223,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, return freelist; } + freelist = freeze_slab(s, slab); goto retry_load_slab; } @@ -3682,18 +3625,8 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, was_frozen = new.frozen; new.inuse -= cnt; if ((!new.inuse || !prior) && !was_frozen) { - - if (kmem_cache_has_cpu_partial(s) && !prior) { - - /* - * Slab was on no list before and will be - * partially empty - * We can defer the list move and instead - * freeze it. - */ - new.frozen = 1; - - } else { /* Needs to be taken off a list */ + /* Needs to be taken off a list */ + if (!kmem_cache_has_cpu_partial(s) || prior) { n = get_node(s, slab_nid(slab)); /* @@ -3723,9 +3656,9 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, * activity can be necessary. */ stat(s, FREE_FROZEN); - } else if (new.frozen) { + } else if (kmem_cache_has_cpu_partial(s) && !prior) { /* - * If we just froze the slab then put it onto the + * If we started with a full slab then put it onto the * per cpu partial list. */ put_cpu_partial(s, slab, 1);