Re: [LKP] [rcu] kernel BUG at include/linux/pagemap.h:149!
by Frederic Weisbecker
On Fri, Sep 11, 2015 at 10:19:47AM +0800, Boqun Feng wrote:
> Subject: [PATCH 01/27] rcu: Don't disable preemption for Tiny and Tree RCU
> readers
>
> Because preempt_disable() maps to barrier() for non-debug builds,
> it forces the compiler to spill and reload registers. Because Tree
> RCU and Tiny RCU now only appear in CONFIG_PREEMPT=n builds, these
> barrier() instances generate needless extra code for each instance of
> rcu_read_lock() and rcu_read_unlock(). This extra code slows down Tree
> RCU and bloats Tiny RCU.
>
> This commit therefore removes the preempt_disable() and preempt_enable()
> from the non-preemptible implementations of __rcu_read_lock() and
> __rcu_read_unlock(), respectively.
>
> For debug purposes, preempt_disable() and preempt_enable() are still
> kept if CONFIG_PREEMPT_COUNT=y, which makes the detection of sleeping
> inside atomic sections still work in non-preemptible kernels.
>
> Signed-off-by: Boqun Feng <boqun.feng(a)gmail.com>
> Signed-off-by: Paul E. McKenney <paulmck(a)linux.vnet.ibm.com>
> ---
> include/linux/rcupdate.h | 6 ++++--
> include/linux/rcutiny.h | 1 +
> kernel/rcu/tree.c | 9 +++++++++
> 3 files changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index d63bb77..6c3cece 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -297,12 +297,14 @@ void synchronize_rcu(void);
>
> static inline void __rcu_read_lock(void)
> {
> - preempt_disable();
> + if (IS_ENABLED(CONFIG_PREEMPT_COUNT))
> + preempt_disable();
preempt_disable() is a no-op when !CONFIG_PREEMPT_COUNT, right?
Or rather it's a barrier(), which is anyway implied by rcu_read_lock().
So perhaps we can get rid of the IS_ENABLED() check?
9 months
[lkp] [x86/acpi] dc6db24d24: BUG: unable to handle kernel paging request at 0000116007090008
by kernel test robot
FYI, we noticed the following commit:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
commit dc6db24d2476cd09c0ecf2b8d80313539f737a89 ("x86/acpi: Set persistent cpuid <-> nodeid mapping when booting")
in testcase: vm-scalability
with following parameters:
runtime: 300
thp_enabled: never
thp_defrag: never
nr_task: 1
nr_pmem: 1
test: swap-w-rand
cpufreq_governor: performance
The motivation behind this suite is to exercise functions and regions of the mm/ of the Linux kernel which are of interest to us.
on test machine: 72 threads Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz with 128G memory
caused below changes:
+------------------------------------------------------------------+------------+------------+
| | 8ad893faf2 | dc6db24d24 |
+------------------------------------------------------------------+------------+------------+
| boot_successes | 7 | 0 |
| boot_failures | 9 | 16 |
| invoked_oom-killer:gfp_mask=0x | 6 | 2 |
| Mem-Info | 6 | 2 |
| Out_of_memory:Kill_process | 6 | |
| page_allocation_failure:order:#,mode:#(GFP_KERNEL|__GFP_NORETRY) | 2 | |
| warn_alloc_failed+0x | 2 | |
| BUG:kernel_hang_in_test_stage | 2 | 2 |
| BUG:kernel_reboot-without-warning_in_test_stage | 1 | |
| BUG:unable_to_handle_kernel | 0 | 12 |
| Oops | 0 | 12 |
| RIP:get_partial_node | 0 | 12 |
| calltrace:devtmpfsd | 0 | 12 |
| RIP:_raw_spin_lock_irqsave | 0 | 9 |
| general_protection_fault:#[##]SMP | 0 | 3 |
| RIP:native_queued_spin_lock_slowpath | 0 | 3 |
| Kernel_panic-not_syncing:Hard_LOCKUP | 0 | 3 |
| RIP:load_balance | 0 | 2 |
| Kernel_panic-not_syncing:Fatal_exception_in_interrupt | 0 | 2 |
| WARNING:at_lib/list_debug.c:#__list_add | 0 | 1 |
| calltrace:_do_fork | 0 | 1 |
| RIP:resched_curr | 0 | 1 |
| Kernel_panic-not_syncing:Fatal_exception | 0 | 1 |
| WARNING:at_include/linux/uaccess.h:#__probe_kernel_read | 0 | 5 |
| Kernel_panic-not_syncing:Out_of_memory_and_no_killable_processes | 0 | 2 |
+------------------------------------------------------------------+------------+------------+
[ 9.531507] pci 0000:80:02.2: bridge window [mem 0x387fffd00000-0x387fffefffff 64bit pref]
[ 9.541378] pci_bus 0000:80: on NUMA node 2
[ 9.546734] ACPI: Enabled 4 GPEs in block 00 to 3F
[ 9.586911] BUG: unable to handle kernel paging request at 0000116007090008
[ 9.595109] IP: [<ffffffff811e50fc>] get_partial_node+0x2c/0x1c0
[ 9.602933] PGD 0
[ 9.605503] Oops: 0000 [#1] SMP
[ 9.609264] Modules linked in:
[ 9.613005] CPU: 24 PID: 585 Comm: kdevtmpfs Not tainted 4.8.0-rc1-00300-gdc6db24d #1
[ 9.622193] Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS SE5C610.86B.01.01.0008.021120151325 02/11/2015
[ 9.634299] task: ffff880068040000 task.stack: ffff880068024000
[ 9.641168] RIP: 0010:[<ffffffff811e50fc>] [<ffffffff811e50fc>] get_partial_node+0x2c/0x1c0
[ 9.651890] RSP: 0000:ffff8800680279f0 EFLAGS: 00010006
[ 9.658079] RAX: 0000000000000002 RBX: 0000000000000246 RCX: 0000000002098020
[ 9.666308] RDX: ffff882053b9cfc0 RSI: 0000116007090000 RDI: ffff880076804dc0
[ 9.674535] RBP: ffff880068027a90 R08: ffff882053b9cfb0 R09: 0000000000000000
[ 9.682764] R10: ffff880068027c88 R11: 0000000b00000000 R12: ffff880076804dc0
[ 9.690994] R13: 0000000000000000 R14: ffff880076804dc0 R15: ffff882053b9cfb0
[ 9.699224] FS: 0000000000000000(0000) GS:ffff882053b80000(0000) knlGS:0000000000000000
[ 9.708701] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 9.715373] CR2: 0000116007090008 CR3: 0000000001e06000 CR4: 00000000001406e0
[ 9.723602] Stack:
[ 9.726094] ffff88207ffd4080 0000000200000000 0000000000000000 0000000002281220
[ 9.735086] 0000000000000000 0000000000000000 ffffffff82343f68 ffff880068040000
[ 9.744080] ffff880068027a88 ffffffff811d9de5 ffff880068040000 ffffffff82343f70
[ 9.753072] Call Trace:
[ 9.756056] [<ffffffff811d9de5>] ? alloc_pages_current+0x95/0x140
[ 9.763223] [<ffffffff811e551a>] ___slab_alloc+0x28a/0x4b0
[ 9.769696] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 9.776379] [<ffffffff813e2356>] ? selinux_inode_permission+0xc6/0x180
[ 9.784032] [<ffffffff811e4342>] ? new_slab+0x2d2/0x5a0
[ 9.790208] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 9.796881] [<ffffffff811e5760>] __slab_alloc+0x20/0x40
[ 9.803067] [<ffffffff811e6b7f>] kmem_cache_alloc+0x17f/0x1c0
[ 9.809837] [<ffffffff813dd477>] avc_alloc_node+0x27/0x140
[ 9.816317] [<ffffffff813dd87a>] avc_compute_av+0x8a/0x1e0
[ 9.822801] [<ffffffff8121000a>] ? sget_userns+0x4ca/0x4e0
[ 9.829289] [<ffffffff813de596>] avc_has_perm+0x136/0x190
[ 9.835673] [<ffffffff810a4a69>] ? __might_sleep+0x49/0x80
[ 9.842161] [<ffffffff813e0000>] ? inode_doinit_with_dentry+0x530/0x660
[ 9.849901] [<ffffffff813f4c5d>] ? security_transition_sid+0x2d/0x40
[ 9.857351] [<ffffffff813e1379>] may_create+0xb9/0xe0
[ 9.863334] [<ffffffff813e13e2>] selinux_inode_mknod+0x42/0x80
[ 9.870201] [<ffffffff813da552>] security_inode_mknod+0x52/0x80
[ 9.877165] [<ffffffff812197e1>] vfs_mknod+0x131/0x1e0
[ 9.883255] [<ffffffff815b2e65>] handle_create+0x75/0x1e0
[ 9.889639] [<ffffffff8192da66>] ? __schedule+0x2e6/0x790
[ 9.896027] [<ffffffff815b3104>] devtmpfsd+0x134/0x180
[ 9.902117] [<ffffffff815b2fd0>] ? handle_create+0x1e0/0x1e0
[ 9.908792] [<ffffffff8109ded4>] kthread+0xd4/0xf0
[ 9.914503] [<ffffffff81932cbf>] ret_from_fork+0x1f/0x40
[ 9.920788] [<ffffffff8109de00>] ? kthread_create_on_node+0x180/0x180
[ 9.928335] Code: 1f 44 00 00 55 48 89 e5 41 57 41 56 41 55 41 54 53 48 83 e4 f0 48 83 ec 70 48 85 f6 48 c7 44 24 20 00 00 00 00 0f 84 54 01 00 00 <48> 83 7e 08 00 0f 84 49 01 00 00 48 89 f3 49 89 fd 48 89 f7 89
[ 9.954843] RIP [<ffffffff811e50fc>] get_partial_node+0x2c/0x1c0
[ 9.962756] RSP <ffff8800680279f0>
[ 9.966902] CR2: 0000116007090008
[ 9.970871] BUG: unable to handle kernel paging request at 0000000100000048
[ 9.979058] IP: [<ffffffff819329b9>] _raw_spin_lock_irqsave+0x29/0x50
[ 9.986582] PGD 0
[ 9.989147] Oops: 0002 [#2] SMP
[ 9.992891] Modules linked in:
[ 9.996623] CPU: 24 PID: 585 Comm: kdevtmpfs Tainted: G D 4.8.0-rc1-00300-gdc6db24d #1
[ 10.007173] Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS SE5C610.86B.01.01.0008.021120151325 02/11/2015
[ 10.019279] task: ffff880068040000 task.stack: ffff880068024000
[ 10.026147] RIP: 0010:[<ffffffff819329b9>] [<ffffffff819329b9>] _raw_spin_lock_irqsave+0x29/0x50
[ 10.036577] RSP: 0000:ffff8800680276e0 EFLAGS: 00010046
[ 10.042763] RAX: 0000000000000000 RBX: 0000000000000097 RCX: ffffffff81e5af08
[ 10.050991] RDX: 0000000000000001 RSI: ffff880068027738 RDI: 0000000100000048
[ 10.059221] RBP: ffff8800680276e8 R08: 0000000000000001 R09: 0000000000000001
[ 10.067450] R10: ffff880068027c88 R11: 000000000000048c R12: 0000000100000048
[ 10.075677] R13: 0000000000000008 R14: ffff880068027738 R15: 0000000000000046
[ 10.083906] FS: 0000000000000000(0000) GS:ffff882053b80000(0000) knlGS:0000000000000000
[ 10.093384] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 10.100059] CR2: 0000000100000048 CR3: 0000000001e06000 CR4: 00000000001406e0
[ 10.108288] Stack:
[ 10.110780] 0000000100000000 ffff880068027718 ffffffff81575da0 ffffffff82263b00
[ 10.119773] ffff880068027738 0000000000000008 ffffffff8107e58f ffff880068027728
[ 10.128764] ffffffff81575e4f ffff880068027798 ffffffff8157726f ffff880068027790
[ 10.137756] Call Trace:
[ 10.140741] [<ffffffff81575da0>] _extract_crng+0x40/0xb0
[ 10.151150] [<ffffffff8107e58f>] ? print_oops_end_marker+0x3f/0x60
[ 10.158405] [<ffffffff81575e4f>] extract_crng+0x3f/0x50
[ 10.164591] [<ffffffff8157726f>] get_random_bytes+0x6f/0x1a0
[ 10.171268] [<ffffffff810d811a>] ? console_unlock+0x33a/0x610
[ 10.178048] [<ffffffff8107e58f>] print_oops_end_marker+0x3f/0x60
[ 10.185106] [<ffffffff8107e5cd>] oops_exit+0x1d/0x30
[ 10.191009] [<ffffffff8103091e>] oops_end+0x7e/0xd0
[ 10.196815] [<ffffffff81066592>] no_context+0x112/0x380
[ 10.203002] [<ffffffff81066881>] __bad_area_nosemaphore+0x81/0x1c0
[ 10.210257] [<ffffffff810669d4>] bad_area_nosemaphore+0x14/0x20
[ 10.217219] [<ffffffff81066d6c>] __do_page_fault+0xbc/0x4d0
[ 10.223796] [<ffffffff8146b47d>] ? list_del+0xd/0x30
[ 10.229690] [<ffffffff810671b0>] do_page_fault+0x30/0x80
[ 10.235972] [<ffffffff81933f48>] page_fault+0x28/0x30
[ 10.241965] [<ffffffff811e50fc>] ? get_partial_node+0x2c/0x1c0
[ 10.249610] [<ffffffff811d9de5>] ? alloc_pages_current+0x95/0x140
[ 10.256771] [<ffffffff811e551a>] ___slab_alloc+0x28a/0x4b0
[ 10.263249] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 10.269921] [<ffffffff813e2356>] ? selinux_inode_permission+0xc6/0x180
[ 10.277564] [<ffffffff811e4342>] ? new_slab+0x2d2/0x5a0
[ 10.283749] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 10.290421] [<ffffffff811e5760>] __slab_alloc+0x20/0x40
[ 10.296607] [<ffffffff811e6b7f>] kmem_cache_alloc+0x17f/0x1c0
[ 10.303379] [<ffffffff813dd477>] avc_alloc_node+0x27/0x140
[ 10.309848] [<ffffffff813dd87a>] avc_compute_av+0x8a/0x1e0
[ 10.316326] [<ffffffff8121000a>] ? sget_userns+0x4ca/0x4e0
[ 10.322806] [<ffffffff813de596>] avc_has_perm+0x136/0x190
[ 10.329184] [<ffffffff810a4a69>] ? __might_sleep+0x49/0x80
[ 10.335660] [<ffffffff813e0000>] ? inode_doinit_with_dentry+0x530/0x660
[ 10.343403] [<ffffffff813f4c5d>] ? security_transition_sid+0x2d/0x40
[ 10.350855] [<ffffffff813e1379>] may_create+0xb9/0xe0
[ 10.356849] [<ffffffff813e13e2>] selinux_inode_mknod+0x42/0x80
[ 10.363716] [<ffffffff813da552>] security_inode_mknod+0x52/0x80
[ 10.370680] [<ffffffff812197e1>] vfs_mknod+0x131/0x1e0
[ 10.376770] [<ffffffff815b2e65>] handle_create+0x75/0x1e0
[ 10.383151] [<ffffffff8192da66>] ? __schedule+0x2e6/0x790
[ 10.389533] [<ffffffff815b3104>] devtmpfsd+0x134/0x180
[ 10.395622] [<ffffffff815b2fd0>] ? handle_create+0x1e0/0x1e0
[ 10.402299] [<ffffffff8109ded4>] kthread+0xd4/0xf0
[ 10.408001] [<ffffffff81932cbf>] ret_from_fork+0x1f/0x40
[ 10.414284] [<ffffffff8109de00>] ? kthread_create_on_node+0x180/0x180
[ 10.421829] Code: 00 00 0f 1f 44 00 00 55 48 89 e5 53 9c 58 0f 1f 44 00 00 48 89 c3 fa 66 0f 1f 44 00 00 65 ff 05 9e a8 6d 7e 31 c0 ba 01 00 00 00 <f0> 0f b1 17 85 c0 75 06 48 89 d8 5b 5d c3 89 c6 e8 22 74 79 ff
[ 10.448339] RIP [<ffffffff819329b9>] _raw_spin_lock_irqsave+0x29/0x50
[ 10.455959] RSP <ffff8800680276e0>
[ 10.460101] CR2: 0000000100000048
[ 10.464058] BUG: unable to handle kernel paging request at 0000000100000048
[ 10.472244] IP: [<ffffffff819329b9>] _raw_spin_lock_irqsave+0x29/0x50
[ 10.479768] PGD 0
[ 10.482332] Oops: 0002 [#3] SMP
[ 10.486089] Modules linked in:
[ 10.489822] CPU: 24 PID: 585 Comm: kdevtmpfs Tainted: G D 4.8.0-rc1-00300-gdc6db24d #1
[ 10.500366] Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS SE5C610.86B.01.01.0008.021120151325 02/11/2015
[ 10.512467] task: ffff880068040000 task.stack: ffff880068024000
[ 10.519334] RIP: 0010:[<ffffffff819329b9>] [<ffffffff819329b9>] _raw_spin_lock_irqsave+0x29/0x50
[ 10.529765] RSP: 0000:ffff8800680273d0 EFLAGS: 00010046
[ 10.535952] RAX: 0000000000000000 RBX: 0000000000000097 RCX: ffffffff81e5af08
[ 10.544183] RDX: 0000000000000001 RSI: ffff880068027428 RDI: 0000000100000048
[ 10.552410] RBP: ffff8800680273d8 R08: 0000000000000001 R09: 0000000000000001
[ 10.560641] R10: ffff880068027c88 R11: 00000000000004d1 R12: 0000000100000048
[ 10.568869] R13: 0000000000000008 R14: ffff880068027428 R15: 0000000000000046
[ 10.577097] FS: 0000000000000000(0000) GS:ffff882053b80000(0000) knlGS:0000000000000000
[ 10.586578] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 10.593250] CR2: 0000000100000048 CR3: 0000000001e06000 CR4: 00000000001406e0
[ 10.601479] Stack:
[ 10.603969] 0000000100000000 ffff880068027408 ffffffff81575da0 ffffffff82263b00
[ 10.612968] ffff880068027428 0000000000000008 ffffffff8107e58f ffff880068027418
[ 10.621966] ffffffff81575e4f ffff880068027488 ffffffff8157726f ffff880068027480
[ 10.630963] Call Trace:
[ 10.633942] [<ffffffff81575da0>] _extract_crng+0x40/0xb0
[ 10.640228] [<ffffffff8107e58f>] ? print_oops_end_marker+0x3f/0x60
[ 10.647484] [<ffffffff81575e4f>] extract_crng+0x3f/0x50
[ 10.653670] [<ffffffff8157726f>] get_random_bytes+0x6f/0x1a0
[ 10.660342] [<ffffffff810d811a>] ? console_unlock+0x33a/0x610
[ 10.667113] [<ffffffff8107e58f>] print_oops_end_marker+0x3f/0x60
[ 10.674173] [<ffffffff8107e5cd>] oops_exit+0x1d/0x30
[ 10.680069] [<ffffffff8103091e>] oops_end+0x7e/0xd0
[ 10.685868] [<ffffffff81066592>] no_context+0x112/0x380
[ 10.692059] [<ffffffff81457b18>] ? put_dec+0x18/0xa0
[ 10.697962] [<ffffffff81066881>] __bad_area_nosemaphore+0x81/0x1c0
[ 10.705218] [<ffffffff810669d4>] bad_area_nosemaphore+0x14/0x20
[ 10.712183] [<ffffffff81066d6c>] __do_page_fault+0xbc/0x4d0
[ 10.718756] [<ffffffff810671b0>] do_page_fault+0x30/0x80
[ 10.725040] [<ffffffff8109f061>] ? atomic_notifier_call_chain+0x21/0x30
[ 10.732783] [<ffffffff81933f48>] page_fault+0x28/0x30
[ 10.738777] [<ffffffff819329b9>] ? _raw_spin_lock_irqsave+0x29/0x50
[ 10.746132] [<ffffffff81575da0>] _extract_crng+0x40/0xb0
[ 10.752415] [<ffffffff8107e58f>] ? print_oops_end_marker+0x3f/0x60
[ 10.759671] [<ffffffff81575e4f>] extract_crng+0x3f/0x50
[ 10.765856] [<ffffffff8157726f>] get_random_bytes+0x6f/0x1a0
[ 10.772530] [<ffffffff810d811a>] ? console_unlock+0x33a/0x610
[ 10.779301] [<ffffffff8107e58f>] print_oops_end_marker+0x3f/0x60
[ 10.786364] [<ffffffff8107e5cd>] oops_exit+0x1d/0x30
[ 10.792257] [<ffffffff8103091e>] oops_end+0x7e/0xd0
[ 10.798057] [<ffffffff81066592>] no_context+0x112/0x380
[ 10.804244] [<ffffffff81066881>] __bad_area_nosemaphore+0x81/0x1c0
[ 10.811498] [<ffffffff810669d4>] bad_area_nosemaphore+0x14/0x20
[ 10.818463] [<ffffffff81066d6c>] __do_page_fault+0xbc/0x4d0
[ 10.825037] [<ffffffff8146b47d>] ? list_del+0xd/0x30
[ 10.830933] [<ffffffff810671b0>] do_page_fault+0x30/0x80
[ 10.837216] [<ffffffff81933f48>] page_fault+0x28/0x30
[ 10.843208] [<ffffffff811e50fc>] ? get_partial_node+0x2c/0x1c0
[ 10.850855] [<ffffffff811d9de5>] ? alloc_pages_current+0x95/0x140
[ 10.858015] [<ffffffff811e551a>] ___slab_alloc+0x28a/0x4b0
[ 10.864491] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 10.871163] [<ffffffff813e2356>] ? selinux_inode_permission+0xc6/0x180
[ 10.878809] [<ffffffff811e4342>] ? new_slab+0x2d2/0x5a0
[ 10.884995] [<ffffffff813dd477>] ? avc_alloc_node+0x27/0x140
[ 10.891667] [<ffffffff811e5760>] __slab_alloc+0x20/0x40
[ 10.897853] [<ffffffff811e6b7f>] kmem_cache_alloc+0x17f/0x1c0
[ 10.904623] [<ffffffff813dd477>] avc_alloc_node+0x27/0x140
[ 10.911103] [<ffffffff813dd87a>] avc_compute_av+0x8a/0x1e0
[ 10.917582] [<ffffffff8121000a>] ? sget_userns+0x4ca/0x4e0
[ 10.924061] [<ffffffff813de596>] avc_has_perm+0x136/0x190
[ 10.930443] [<ffffffff810a4a69>] ? __might_sleep+0x49/0x80
[ 10.936924] [<ffffffff813e0000>] ? inode_doinit_with_dentry+0x530/0x660
[ 10.944666] [<ffffffff813f4c5d>] ? security_transition_sid+0x2d/0x40
[ 10.952120] [<ffffffff813e1379>] may_create+0xb9/0xe0
[ 10.958112] [<ffffffff813e13e2>] selinux_inode_mknod+0x42/0x80
[ 10.964979] [<ffffffff813da552>] security_inode_mknod+0x52/0x80
[ 10.971944] [<ffffffff812197e1>] vfs_mknod+0x131/0x1e0
[ 10.978033] [<ffffffff815b2e65>] handle_create+0x75/0x1e0
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
Thanks,
Xiaolong
3 years
[x86/acpi] 04c197c080: BUG: unable to handle kernel paging request at 0000003000000010
by kernel test robot
FYI, we noticed the following commit:
https://github.com/0day-ci/linux Dou-Liyang/Fix-the-local-APIC-id-validation-in-case-of-0xff/20161008-154907
commit 04c197c080f2ed7a022f79701455c6837f4b9573 ("x86/acpi: Fix the local APIC id validation in case of 0xff")
in testcase: will-it-scale
with following parameters:
test: unlink2
cpufreq_governor: performance
Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
on test machine: 72 threads Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz with 128G memory
caused below changes:
+-------------------------------------------------------+------------+------------+
| | 1e1a4b0f54 | 04c197c080 |
+-------------------------------------------------------+------------+------------+
| boot_successes | 2 | 4 |
| boot_failures | 0 | 7 |
| BUG:unable_to_handle_kernel | 0 | 3 |
| Oops | 0 | 3 |
| RIP:check_timer | 0 | 3 |
| calltrace:native_smp_prepare_cpus | 0 | 3 |
| Kernel_panic-not_syncing:Fatal_exception | 0 | 3 |
| PANIC:double_fault | 0 | 2 |
| Bad_pagetable | 0 | 1 |
| RIP:copy_user_enhanced_fast_string | 0 | 1 |
| Kernel_panic-not_syncing:Fatal_exception_in_interrupt | 0 | 1 |
| Kernel_panic-not_syncing:Machine_halted | 0 | 1 |
| RIP:vgacon_scroll | 0 | 1 |
| invoked_oom-killer:gfp_mask=0x | 0 | 4 |
| Mem-Info | 0 | 4 |
+-------------------------------------------------------+------------+------------+
[ 0.492621] ..MP-BIOS bug: 8254 timer not connected to IO-APIC
[ 0.499130] ...trying to set up timer (IRQ0) through the 8259A ...
[ 0.506027] ..... (found apic 2 pin 0) ...
[ 0.510601] BUG: unable to handle kernel paging request at 0000003000000010
[ 0.518391] IP: [<ffffffff8200964b>] check_timer+0x21d/0x61e
[ 0.524722] PGD 0
[ 0.526974] Oops: 0000 [#1] SMP
[ 0.530477] Modules linked in:
[ 0.533901] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.8.0-00989-g04c197c #1
[ 0.541865] Hardware name: Intel Corporation S2600WTT/S2600WTT, BIOS SE5C610.86B.01.01.0008.021120151325 02/11/2015
[ 0.553521] task: ffff882023b00000 task.stack: ffffc9000c468000
[ 0.560129] RIP: 0010:[<ffffffff8200964b>] [<ffffffff8200964b>] check_timer+0x21d/0x61e
[ 0.569170] RSP: 0000:ffffc9000c46bd90 EFLAGS: 00010082
[ 0.575095] RAX: 0000003000000000 RBX: 0000000000000000 RCX: ffffffff81e5cb48
[ 0.583058] RDX: 0000000000000001 RSI: 0000000000000046 RDI: 0000000000000046
[ 0.591031] RBP: ffffc9000c46be08 R08: 0000000000000000 R09: 0000000000000000
[ 0.598994] R10: 0000000000000040 R11: 0000000000000208 R12: 0000000000000002
[ 0.606957] R13: 0000000000000002 R14: 0000000000000002 R15: ffff88103f00ae20
[ 0.614927] FS: 0000000000000000(0000) GS:ffff88103f400000(0000) knlGS:0000000000000000
[ 0.623958] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 0.630368] CR2: 0000003000000010 CR3: 000000207ee06000 CR4: 00000000001406f0
[ 0.638331] Stack:
[ 0.640574] 0000000000000000 0000000000000246 ffffffff00000000 ffff88103f002080
[ 0.648870] ffff88103f002080 0000000000000017 0000000000000001 ffffc9000c46bdd8
[ 0.657165] ffffffff8145869d ffffc9000c46bde8 0000000000000718 0000000000000001
[ 0.665459] Call Trace:
[ 0.668193] [<ffffffff8145869d>] ? radix_tree_lookup+0xd/0x10
[ 0.674710] [<ffffffff8200a1a9>] setup_IO_APIC+0x17d/0x1c5
[ 0.680937] [<ffffffff8200885c>] apic_bsp_setup+0xa1/0xac
[ 0.687059] [<ffffffff820064b5>] native_smp_prepare_cpus+0x297/0x317
[ 0.694259] [<ffffffff81ff1038>] kernel_init_freeable+0xcf/0x225
[ 0.701072] [<ffffffff81929710>] ? rest_init+0x90/0x90
[ 0.706911] [<ffffffff8192971e>] kernel_init+0xe/0x100
[ 0.712744] [<ffffffff81936fc5>] ret_from_fork+0x25/0x30
[ 0.718776] Code: ff 48 c7 c7 50 6d c9 81 e8 31 54 17 ff 89 da 44 89 ee 48 c7 c7 90 6d c9 81 e8 20 54 17 ff 48 8b 45 a8 48 8b 00 48 39 45 a8 74 1a <44> 39 70 10 75 0f 44 39 60 14 75 09 44 89 68 10 89 58 14 eb 26
[ 0.740436] RIP [<ffffffff8200964b>] check_timer+0x21d/0x61e
[ 0.746858] RSP <ffffc9000c46bd90>
[ 0.750749] CR2: 0000003000000010
[ 0.754461] ---[ end trace 3618134a8804dce5 ]---
[ 0.759620] Kernel panic - not syncing: Fatal exception
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
Thanks,
Kernel Test Robot
3 years, 3 months
[lkp] [x86/platform/UV] 71854cb812: will-it-scale.per_thread_ops -2.3% regression
by kernel test robot
FYI, we noticed a -2.3% regression of will-it-scale.per_thread_ops due to commit:
commit 71854cb812ec23bfe5f63d52217e6b9e6cb901f5 ("x86/platform/UV: Fix support for EFI_OLD_MEMMAP after BIOS callback updates")
https://github.com/0day-ci/linux Alex-Thorlton/x86-platform-UV-Fix-support-for-EFI_OLD_MEMMAP-after-BIOS-callback-updates/20161020-095215
in testcase: will-it-scale
on test machine: 12 threads Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz with 6G memory
with following parameters:
test: read2
cpufreq_governor: performance
Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
gcc-6/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/wsm/read2/will-it-scale
commit:
v4.9-rc1
71854cb812 ("x86/platform/UV: Fix support for EFI_OLD_MEMMAP after BIOS callback updates")
v4.9-rc1 71854cb812ec23bfe5f63d5221
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
%stddev %change %stddev
\ | \
1646359 ± 0% -2.3% 1608758 ± 1% will-it-scale.per_thread_ops
981.11 ± 0% +2.3% 1003 ± 0% will-it-scale.time.system_time
81.90 ± 0% -27.5% 59.34 ± 0% will-it-scale.time.user_time
4679 ± 88% -43.4% 2649 ± 7% cpuidle.C1E-NHM.usage
76734 ± 21% -22.4% 59544 ± 4% softirqs.RCU
0.29 ± 2% +32.2% 0.38 ± 2% perf-stat.branch-miss-rate%
2.953e+09 ± 2% +31.1% 3.871e+09 ± 2% perf-stat.branch-misses
183791 ± 10% +15.1% 211493 ± 7% sched_debug.cpu.avg_idle.stddev
0.00 ± 11% +24.6% 0.00 ± 3% sched_debug.cpu.next_balance.stddev
13311 ± 12% +23.7% 16466 ± 1% sched_debug.cpu.ttwu_count.min
will-it-scale.time.user_time
85 ++---------------------------------------------------------------------+
| .*.*.. .*..*. .*..*. .*.. .*..*. .* |
80 *+ *.*..* *..* *..*..* * *..*.*. |
| |
| |
75 ++ |
| |
70 ++ |
| |
65 ++ |
| |
| O O |
60 O+ O O O O O O O O O O O O O O O O O O
| O O O O O O O O |
55 ++---------------------------------------------------------------------+
will-it-scale.time.system_time
1010 ++-------------------------------------------------------------------+
| |
1005 ++ O O O O O O O O O |
O O O O O O O O O O O O O O O O O O
| O O |
1000 ++ |
| |
995 ++ |
| |
990 ++ |
| |
| |
985 ++ |
*. .*..*.*.. .*.*.. .*.*..*. .*.. .*.*..*. |
980 ++*--*---------*-*-------*-*---------*----*-*---------*--------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
3 years, 3 months
Re: [LKP] [lkp] [f2fs] ec795418c4: fsmark.files_per_sec -36.3% regression
by Jaegeuk Kim
On Wed, Aug 24, 2016 at 09:51:11AM -0700, huang ying wrote:
> Hi, Jaegeuk,
>
> On Thu, Aug 11, 2016 at 6:22 PM, Jaegeuk Kim <jaegeuk(a)kernel.org> wrote:
> > On Thu, Aug 11, 2016 at 03:49:41PM -0700, Huang, Ying wrote:
> >> Hi, Kim,
> >>
> >> "Huang, Ying" <ying.huang(a)intel.com> writes:
> >> >>
> >> >> [lkp] [f2fs] 3bdad3c7ee: aim7.jobs-per-min -25.3% regression
> >> >> [lkp] [f2fs] b93f771286: aim7.jobs-per-min -81.2% regression
> >> >>
> >> >> In terms of the above regression, I could check that _reproduce_ procedure
> >> >> includes mounting filesystem only. Is that correct?
> >> >
> >> > Sorry, our test system failed to generate reproduce steps for aim7. We
> >> > will implement it.
> >> >
> >> > - [lkp] [f2fs] 3bdad3c7ee: aim7.jobs-per-min -25.3% regression
> >> >
> >> > The disk is one 48G ram disk. The steps for aim7 is,
> >> >
> >> > cat > workfile <<EOF
> >> > FILESIZE: 1M
> >> > POOLSIZE: 10M
> >> > 10 disk_cp
> >> > EOF
> >> >
> >> > (
> >> > echo $HOSTNAME
> >> > echo disk_cp
> >> >
> >> > echo 1
> >> > echo 3000
> >> > echo 2
> >> > echo 3000
> >> > echo 1
> >> > ) | ./multitask -t &
> >> >
> >> >
> >> > - [lkp] [f2fs] b93f771286: aim7.jobs-per-min -81.2% regression
> >> >
> >> > The disk is 4 12G ram disk, and setup RAID0 on them via mdadm. The
> >> > steps for aim7 is,
> >> >
> >> > cat > workfile <<EOF
> >> > FILESIZE: 1M
> >> > POOLSIZE: 10M
> >> > 10 sync_disk_rw
> >> > EOF
> >> >
> >> > (
> >> > echo $HOSTNAME
> >> > echo sync_disk_rw
> >> >
> >> > echo 1
> >> > echo 600
> >> > echo 2
> >> > echo 600
> >> > echo 1
> >> > ) | ./multitask -t &
> >>
> >> Any update on these 2 regressions? Is the information is enough for you
> >> to reproduce?
> >
> > Sorry, I've had no time to dig this due to business travel now.
> > I'll check that when back to US.
>
> Any update?
Sorry, how can I get multitask binary?
Thanks,
>
> Best Regards,
> Huang, Ying
3 years, 3 months
[sched/core] 0397626b80: WARNING: CPU: 0 PID: 0 at kernel/sched/sched.h:797 assert_clock_updated
by kernel test robot
Greetings,
0day kernel testing robot got the below dmesg and the first bad commit is
https://git.kernel.org/pub/scm/linux/kernel/git/peterz/queue.git sched/debug
commit 0397626b8034bec8a0cf700a6fe8664e08773075
Author: Matt Fleming <matt(a)codeblueprint.co.uk>
AuthorDate: Wed Sep 21 14:38:13 2016 +0100
Commit: Peter Zijlstra <peterz(a)infradead.org>
CommitDate: Tue Oct 25 11:16:57 2016 +0200
sched/core: Add debug code to catch missing update_rq_clock()
There's no diagnostic checks for figuring out when we've accidentally
missed update_rq_clock() calls. Let's add some by piggybacking on the
rq_*pin_lock() wrappers.
The idea behind the diagnostic checks is that upon pining rq lock the
rq clock should be updated, via update_rq_clock(), before anybody
reads the clock with rq_clock() or rq_clock_task().
The exception to this rule is when updates have explicitly been
disabled with the rq_clock_skip_update() optimisation.
There are some functions that only unpin the rq lock in order to grab
some other lock and avoid deadlock. In that case we don't need to
update the clock again and the previous diagnostic state can be
carried over in rq_repin_lock() by saving the state in the rq_flags
context.
Since this patch adds a new clock update flag and some already exist
in rq::clock_skip_update, that field has now been renamed. An attempt
has been made to keep the flag manipulation code small and fast since
it's used in the heart of the __schedule() fast path.
For the !CONFIG_SCHED_DEBUG case the only object code change (other
than addresses) is the following change to reset RQCF_ACT_SKIP inside
of __schedule(),
- c7 83 38 09 00 00 00 movl $0x0,0x938(%rbx)
- 00 00 00
+ 83 a3 38 09 00 00 fc andl $0xfffffffc,0x938(%rbx)
Cc: Yuyang Du <yuyang.du(a)intel.com>
Cc: Ingo Molnar <mingo(a)kernel.org>
Cc: Luca Abeni <luca.abeni(a)unitn.it>
Cc: Wanpeng Li <wanpeng.li(a)hotmail.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work(a)gmail.com>
Cc: Byungchul Park <byungchul.park(a)lge.com>
Cc: Frederic Weisbecker <fweisbec(a)gmail.com>
Cc: Thomas Gleixner <tglx(a)linutronix.de>
Cc: Jan Kara <jack(a)suse.cz>
Cc: Rik van Riel <riel(a)redhat.com>
Cc: Petr Mladek <pmladek(a)suse.com>
Cc: Mel Gorman <mgorman(a)techsingularity.net>
Cc: Mike Galbraith <umgwanakikbuti(a)gmail.com>
Suggested-by: Peter Zijlstra <peterz(a)infradead.org>
Signed-off-by: Matt Fleming <matt(a)codeblueprint.co.uk>
Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org>
Link: http://lkml.kernel.org/r/20160921133813.31976-8-matt@codeblueprint.co.uk
+-------------------------------------------------------+------------+------------+-----------------+
| | 36969d2283 | 0397626b80 | v4.9-rc2_102807 |
+-------------------------------------------------------+------------+------------+-----------------+
| boot_successes | 130 | 0 | 4 |
| boot_failures | 68 | 52 | 9 |
| invoked_oom-killer:gfp_mask=0x | 1 | | |
| Mem-Info | 1 | | |
| BUG:kernel_reboot-without-warning_in_test_stage | 61 | 0 | 6 |
| RIP:arch_local_irq_restore | 6 | | |
| calltrace:rcu_torture_cbflood | 6 | | |
| Kernel_panic-not_syncing:softlockup:hung_tasks | 6 | | |
| WARNING:at_kernel/sched/sched.h:#assert_clock_updated | 0 | 52 | 3 |
| calltrace:_do_fork | 0 | 52 | 3 |
| INFO:possible_circular_locking_dependency_detected | 0 | 0 | 3 |
| calltrace:torture_shuffle | 0 | 0 | 3 |
| calltrace:serio_handle_event | 0 | 0 | 1 |
| calltrace:ret_from_fork | 0 | 0 | 1 |
| calltrace:SyS_exit_group | 0 | 0 | 1 |
| calltrace:power_supply_deferred_register_work | 0 | 0 | 1 |
+-------------------------------------------------------+------------+------------+-----------------+
[ 1.636773] Freeing SMP alternatives memory: 20K (ffffffff8310e000 - ffffffff83113000)
[ 1.646318] ftrace: allocating 31050 entries in 122 pages
[ 1.861833] ------------[ cut here ]------------
[ 1.865815] WARNING: CPU: 0 PID: 0 at kernel/sched/sched.h:797 assert_clock_updated+0x66/0x7c
[ 1.873878] rq->clock_update_flags < RQCF_ACT_SKIP
[ 1.877436] Modules linked in:
[ 1.878944] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.9.0-rc1-00289-g0397626 #1
[ 1.885893] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Debian-1.8.2-1 04/01/2014
[ 1.893364] ffffffff82603cd0 ffffffff816ca9a7 ffffffff82619540 ffffffff82603d38
[ 1.898590] 0000000000000000 ffffffff8237116e ffffffff82603d10 ffffffff810c88a0
[ 1.905988] 0000000982603da8 ffffffff8237145f 0000000000000001 0000000000000200
[ 1.912750] Call Trace:
[ 1.914894] [<ffffffff816ca9a7>] dump_stack+0xf5/0x174
[ 1.918496] [<ffffffff810c88a0>] __warn+0x159/0x179
[ 1.924318] [<ffffffff810c892a>] warn_slowpath_fmt+0x6a/0x73
[ 1.926162] [<ffffffff81134ad7>] ? __lock_is_held+0x3c/0x57
[ 1.931428] [<ffffffff8111891d>] assert_clock_updated+0x66/0x7c
[ 1.933449] [<ffffffff811189a4>] rq_clock_task+0x71/0x7e
[ 1.936802] [<ffffffff8111f0a2>] post_init_entity_util_avg+0x41/0x14d
[ 1.943975] [<ffffffff8110e1d9>] wake_up_new_task+0x74/0x289
[ 1.945831] [<ffffffff810c76cf>] _do_fork+0x435/0x694
[ 1.949712] [<ffffffff816ed4b5>] ? _find_next_bit+0xbf/0xcd
[ 1.957757] [<ffffffff816ed4ef>] ? find_next_bit+0x2c/0x2e
[ 1.961940] [<ffffffff81ca18d6>] ? rest_init+0x1ad/0x1ad
[ 1.969651] [<ffffffff810c7967>] kernel_thread+0x39/0x40
[ 1.972273] [<ffffffff82fa0870>] ? trace_event_define_fields_x86_irq_vector+0x40/0x40
[ 1.983583] [<ffffffff81ca1752>] rest_init+0x29/0x1ad
[ 1.986780] [<ffffffff82fa0870>] ? trace_event_define_fields_x86_irq_vector+0x40/0x40
[ 1.997567] [<ffffffff82f91675>] start_kernel+0x65d/0x66a
[ 1.999358] [<ffffffff82f90120>] ? early_idt_handler_array+0x120/0x120
[ 2.006616] [<ffffffff82f90315>] x86_64_start_reservations+0x40/0x42
[ 2.008848] [<ffffffff82f9044c>] x86_64_start_kernel+0x135/0x144
[ 2.015735] ---[ end trace 42ad9032378b9e6b ]---
[ 2.017923] smpboot: APIC(0) Converting physical 0 to logical package 0
git bisect start d5cf6829ea836d09490fa0ec9cb39dccc0f8c175 07d9a380680d1c0eb51ef87ff2eab5c994949e69 --
git bisect bad 245646129012126a7c2f8027a726b6e95f86b429 # 09:17 5- 9 Merge 'renesas-drivers/clk-renesas-for-v4.10' into devel-hourly-2016102807
git bisect good d51cbbe982a050d17ea7e8783969830c8e9fadd1 # 09:42 47+ 16 Merge 'linux-review/Alex-Goins/include-linux-rtmutex-h-NOOP-rt_mutex_destroy-if-CONFIG_DEBUG_RT_MUTEXES/20161026-134915' into devel-hourly-2016102807
git bisect bad 6b383025cda12d46ce56a89c6bf9b0edcfaa2eaa # 10:01 4- 3 Merge 'linux-review/Christian-Borntraeger/blk-cgroup-use-__GFP_NOWARN-for-NOWAIT-allocations/20161025-214022' into devel-hourly-2016102807
git bisect good bf6ab1edf167ab34edf229b1cd6c30d518c8e417 # 10:16 47+ 17 Merge 'linux-review/Arkadiusz-Hiler/drm-i915-fix-comment-on-I915_-READ-WRITE-_FW/20161027-170646' into devel-hourly-2016102807
git bisect bad b3ebc60730bb1791c068613f691f42e017e091f4 # 10:29 2- 2 Merge 'shawnguo/imx/defconfig' into devel-hourly-2016102807
git bisect good 87067099fb3cd0968bef69bcc10484e189be8734 # 10:53 48+ 20 Merge 'char-misc/char-misc-linus' into devel-hourly-2016102807
git bisect bad 336fff834f86c9cd1f421469b32f47717ef7d13d # 11:10 4- 7 Merge 'linux-review/Sakari-Ailus/v4l-videodev2-Include-linux-time-h-for-timeval-and-timespec-structs/20161028-001855' into devel-hourly-2016102807
git bisect good 25c5c851c5de84770944a00e34a68971360351ac # 11:25 46+ 18 Merge 'leon-rdma/testing/queue-next' into devel-hourly-2016102807
git bisect bad e5710597f1382efa96cc9b0bce9d8fc9115c0134 # 11:44 1- 3 Merge 'peterz-queue/master' into devel-hourly-2016102807
git bisect good 44002ad9d372e1b03de36848a886b4b7c6bbb941 # 12:05 50+ 21 Merge 'peterz-queue/sched/tracepoints' into devel-hourly-2016102807
git bisect good a725331f38ecfd8c567a1e2a5b06e538d3458687 # 12:33 50+ 6 Merge branch 'locking/core'
git bisect bad aac14c92bc1893250ccc9986ccf9be4a40b1f672 # 12:46 1- 9 futex: Use smp_store_release() in mark_wake_futex()
git bisect bad 12ade98c7267a2cc34f4c81f26c82abbb3f52924 # 13:02 3- 5 sched: Add missing update_rq_clock() call for task_hot().
git bisect good 66143550f40698ceac4bcb0504703b0cf7cc031c # 13:17 50+ 22 sched/core: Reset RQCF_ACT_SKIP before unpinning rq->lock
git bisect bad 0397626b8034bec8a0cf700a6fe8664e08773075 # 13:29 0- 5 sched/core: Add debug code to catch missing update_rq_clock()
git bisect good 36969d228368dd55733edcddf89b2ffcf92d48bc # 13:46 50+ 17 sched/fair: Push rq lock pin/unpin into idle_balance()
# first bad commit: [0397626b8034bec8a0cf700a6fe8664e08773075] sched/core: Add debug code to catch missing update_rq_clock()
git bisect good 36969d228368dd55733edcddf89b2ffcf92d48bc # 13:55 148+ 68 sched/fair: Push rq lock pin/unpin into idle_balance()
# extra tests with CONFIG_DEBUG_INFO_REDUCED
git bisect bad 0397626b8034bec8a0cf700a6fe8664e08773075 # 14:09 0- 8 sched/core: Add debug code to catch missing update_rq_clock()
# extra tests on HEAD of linux-devel/devel-hourly-2016102807
git bisect bad d5cf6829ea836d09490fa0ec9cb39dccc0f8c175 # 14:09 0- 9 0day head guard for 'devel-hourly-2016102807'
# extra tests on tree/branch peterz-queue/sched/debug
git bisect bad 8ce323de7cdc74da415f0cc02f964e3e1ebe3156 # 14:30 1- 2 sched: Avoid double update_rq_clock()
# extra tests on tree/branch linus/master
git bisect good 2a26d99b251b8625d27aed14e97fc10707a3a81f # 15:01 138+ 42 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
# extra tests on tree/branch linux-next/master
git bisect good fee425e048137e29a84b762593886a6c038585fc # 15:29 146+ 48 Add linux-next specific files for 20161028
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/lkp Intel Corporation
3 years, 4 months
[lkp] [sched] b3ba75a66d: [No primary change] [will-it-scale] interrupts.CAL:Function_call_interrupts +91.3% increase
by kernel test robot
Greeting,
There is no primary kpi change in this test, below is the data collected through multiple monitors running background just for your
information.
commit b3ba75a66db7919e7a2f782170db8f86e1d47d21 ("sched: move IO scheduling accounting from io_schedule_timeout() to __schedule()")
https://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git review-mutex_lock_io
in testcase: will-it-scale
on test machine: 12 threads Intel(R) Core(TM) i7 CPU X 980 @ 3.33GHz with 6G memory
with following parameters:
test: page_fault1
cpufreq_governor: performance
Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
gcc-6/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/wsm/page_fault1/will-it-scale
commit:
9fe68cad6e ("Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6")
b3ba75a66d ("sched: move IO scheduling accounting from io_schedule_timeout() to __schedule()")
9fe68cad6e74967b b3ba75a66db7919e7a2f782170
---------------- --------------------------
%stddev %change %stddev
\ | \
44221 ± 0% +91.3% 84610 ± 6% interrupts.CAL:Function_call_interrupts
0.00 ± 37% -75.3% 0.00 ±173% sched_debug.rt_rq:/.rt_time.min
3411 ± 1% +8.6% 3705 ± 4% slabinfo.cred_jar.active_objs
3411 ± 1% +8.6% 3705 ± 4% slabinfo.cred_jar.num_objs
0.18 ±173% +735.6% 1.52 ± 53% perf-profile.calltrace.cycles-pp.poll_idle.cpuidle_enter_state.cpuidle_enter.call_cpuidle.cpu_startup_entry
0.26 ±111% +554.9% 1.67 ± 54% perf-profile.children.cycles-pp.poll_idle
0.26 ±111% +554.9% 1.67 ± 54% perf-profile.self.cycles-pp.poll_idle
59.09 ± 0% +1.0% 59.70 ± 0% turbostat.%Busy
2076 ± 0% +1.0% 2097 ± 0% turbostat.Avg_MHz
23.27 ± 0% +32.3% 30.78 ± 5% turbostat.CPU%c1
7.35 ± 0% +29.4% 9.52 ± 17% turbostat.CPU%c3
10.29 ± 0% -100.0% 0.00 ± -1% turbostat.CPU%c6
45306 ±154% -97.0% 1340 ±173% latency_stats.avg.call_rwsem_down_write_failed.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
47219 ±152% -100.0% 0.00 ± -1% latency_stats.avg.rpc_wait_bit_killable.__rpc_wait_for_completion_task._nfs4_proc_open_confirm.[nfsv4].nfs4_do_open.[nfsv4].nfs4_atomic_open.[nfsv4].nfs_atomic_open.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
45306 ±154% -97.0% 1340 ±173% latency_stats.max.call_rwsem_down_write_failed.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
47219 ±152% -100.0% 0.00 ± -1% latency_stats.max.rpc_wait_bit_killable.__rpc_wait_for_completion_task._nfs4_proc_open_confirm.[nfsv4].nfs4_do_open.[nfsv4].nfs4_atomic_open.[nfsv4].nfs_atomic_open.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
45306 ±154% -97.0% 1340 ±173% latency_stats.sum.call_rwsem_down_write_failed.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
47219 ±152% -100.0% 0.00 ± -1% latency_stats.sum.rpc_wait_bit_killable.__rpc_wait_for_completion_task._nfs4_proc_open_confirm.[nfsv4].nfs4_do_open.[nfsv4].nfs4_atomic_open.[nfsv4].nfs_atomic_open.path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath
32876422 ± 2% +1319.7% 4.668e+08 ± 15% cpuidle.C1-NHM.time
2151809 ± 2% +313.9% 8906980 ± 22% cpuidle.C1E-NHM.time
27641 ± 1% +43.7% 39713 ± 12% cpuidle.C1E-NHM.usage
5.155e+08 ± 0% +52.8% 7.878e+08 ± 13% cpuidle.C3-NHM.time
719929 ± 0% +25.0% 899641 ± 12% cpuidle.C3-NHM.usage
9.584e+08 ± 0% -77.3% 2.173e+08 ± 35% cpuidle.C6-NHM.time
992245 ± 0% -77.4% 224124 ± 35% cpuidle.C6-NHM.usage
38924956 ± 14% +62.0% 63065833 ± 20% cpuidle.POLL.time
838185 ± 8% +229.8% 2764308 ± 48% cpuidle.POLL.usage
5.277e+10 ± 2% +10.6% 5.835e+10 ± 5% perf-stat.branch-instructions
0.72 ± 2% -19.9% 0.57 ± 5% perf-stat.branch-miss-rate%
3.772e+08 ± 0% -11.7% 3.332e+08 ± 0% perf-stat.branch-misses
5.243e+10 ± 1% +4.2% 5.462e+10 ± 0% perf-stat.cache-misses
5.457e+10 ± 1% +3.6% 5.652e+10 ± 0% perf-stat.cache-references
7.26e+12 ± 0% +2.9% 7.468e+12 ± 0% perf-stat.cpu-cycles
0.10 ± 2% -39.4% 0.06 ± 3% perf-stat.dTLB-load-miss-rate%
65280587 ± 2% -34.5% 42757526 ± 4% perf-stat.dTLB-load-misses
6.65e+10 ± 2% +8.2% 7.198e+10 ± 4% perf-stat.dTLB-loads
0.13 ± 1% -39.1% 0.08 ± 6% perf-stat.dTLB-store-miss-rate%
49231329 ± 1% -39.5% 29760910 ± 7% perf-stat.dTLB-store-misses
0.02 ± 3% -34.2% 0.01 ± 19% perf-stat.iTLB-load-miss-rate%
47120124 ± 0% -29.0% 33461952 ± 15% perf-stat.iTLB-load-misses
2.523e+11 ± 2% +8.7% 2.743e+11 ± 5% perf-stat.iTLB-loads
2.418e+11 ± 3% +11.8% 2.702e+11 ± 5% perf-stat.instructions
5131 ± 4% +62.5% 8337 ± 20% perf-stat.instructions-per-iTLB-miss
0.03 ± 2% +8.7% 0.04 ± 5% perf-stat.ipc
4.78e+10 ± 3% +9.6% 5.241e+10 ± 2% perf-stat.node-stores
interrupts.CAL:Function_call_interrupts
110000 ++-----------------------------------------------------------------+
| |
100000 ++O O O |
O O O O |
90000 ++ O O O O O |
| O O O O O O O O |
80000 ++ O O O O O |
| |
70000 ++ O O |
| |
60000 ++ |
| |
50000 ++ *. |
*.*.*..*. .*.*..*.*.*.*..*.*.*.*..*.*.*.*. .*.*.*.*.. + *.*..*.*.*
40000 ++-------*--------------------------------*-----------*------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
3 years, 4 months
[lkp] [clocksource] 9995f4f184: will-it-scale.scalability 7.8% improvement
by kernel test robot
Greeting,
FYI, we noticed a 7.8% improvement of will-it-scale.scalability due to commit:
commit 9995f4f184613fb02ee73092b03545520a72b104 ("clocksource: Add J-Core timer/clocksource driver")
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
in testcase: will-it-scale
on test machine: 64 threads Intel(R) Xeon(R) CPU E5-4650 0 @ 2.70GHz with 64G memory
with following parameters:
test: signal1
cpufreq_governor: performance
Will It Scale takes a testcase and runs it from 1 through to n parallel copies to see if the testcase will scale. It builds both a process and threads based test in order to see any differences between the two.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/tbox_group/test/testcase:
gcc-6/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/lkp-sbx04/signal1/will-it-scale
commit:
a2ce092be3 ("of: Add J-Core timer bindings")
9995f4f184 ("clocksource: Add J-Core timer/clocksource driver")
a2ce092be34c4951 9995f4f184613fb02ee73092b0
---------------- --------------------------
%stddev %change %stddev
\ | \
0.04 ± 0% +7.8% 0.05 ± 1% will-it-scale.scalability
121.04 ± 51% -40.4% 72.17 ± 23% sched_debug.cpu.sched_goidle.min
1648 ± 1% -75.1% 411.00 ±173% meminfo.Mlocked
1649 ± 1% -75.1% 411.25 ±173% meminfo.Unevictable
99.00 ± 23% -78.3% 21.50 ±173% numa-vmstat.node2.nr_mlock
99.00 ± 23% -78.3% 21.50 ±173% numa-vmstat.node2.nr_unevictable
99.00 ± 23% -78.3% 21.50 ±173% numa-vmstat.node2.nr_zone_unevictable
411.50 ± 1% -75.0% 102.75 ±173% proc-vmstat.nr_mlock
412.00 ± 1% -75.1% 102.75 ±173% proc-vmstat.nr_unevictable
412.00 ± 1% -75.1% 102.75 ±173% proc-vmstat.nr_zone_unevictable
0.23 ± 0% +1.7% 0.23 ± 0% perf-stat.branch-miss-rate%
2.281e+09 ± 0% +2.1% 2.33e+09 ± 1% perf-stat.branch-misses
2.249e+09 ± 0% -7.3% 2.084e+09 ± 2% perf-stat.cache-misses
7.277e+09 ± 0% -8.0% 6.693e+09 ± 0% perf-stat.cache-references
4.164e+11 ± 0% +1.7% 4.233e+11 ± 1% perf-stat.dTLB-stores
41.33 ± 0% -6.6% 38.62 ± 1% perf-stat.node-load-miss-rate%
7.028e+08 ± 2% -29.1% 4.984e+08 ± 2% perf-stat.node-load-misses
9.977e+08 ± 3% -20.6% 7.921e+08 ± 2% perf-stat.node-loads
perf-stat.cache-references
7.6e+09 ++----------------------------------------------------------------+
7.5e+09 ++ * |
| :: |
7.4e+09 ++ : : * |
7.3e+09 *+ .* * * : :+ : *.*
|+ .*. .*. .*.*.* + + + + +: * : + |
7.2e+09 ++*. .*.* *.*..* *.* *. .*.* *. .*..* * * |
7.1e+09 ++ * * * |
7e+09 ++ |
| |
6.9e+09 ++ |
6.8e+09 ++ |
| O O O |
6.7e+09 ++O O O O O O O O O O |
6.6e+09 O+-------------------------O--------------------------------------+
perf-stat.node-load-misses
8e+08 ++----------------------------------------------------------------+
| * |
7.5e+08 *+ + + * * *.* |
|: *. * *.. + : *. : : *. + + .* .*
7e+08 ++ + *. + .*.*.*.*.*.* : + *. : : + *.. .* * + .* |
| * * * * * * * * |
6.5e+08 ++ |
| |
6e+08 ++ |
| O |
5.5e+08 ++ O |
| O O O O O O |
5e+08 O+O O O O O |
| O |
4.5e+08 ++----------------------------------------------------------------+
will-it-scale.scalability
0.049 ++------------------------------------------------------------------+
| O |
0.048 ++ |
| |
| O O O O |
0.047 O+O O O O O O O O O |
| |
0.046 ++ |
| |
0.045 ++ |
| .*.. |
| .*. .*. .*. .* .*
0.044 *+* *..*. .*. .*. .*.*.* *.*..*.* *.*.* *.*.*.* |
| * *.* *.*..*.* |
0.043 ++------------------------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
3 years, 4 months
[lkp] [x86/stacktrace] 448e122131: [No primary change] unixbench.time.system_time -11.2% decrease
by kernel test robot
Greeting,
There is no primary kpi change in this test, below is the data collected through multiple monitors running background just for your information.
commit 448e122131ad6651f4a0cdd281415160134644a6 ("x86/stacktrace: convert save_stack_trace_*() to use the new unwinder")
https://github.com/jpoimboe/linux unwind-2016-09-14
in testcase: unixbench
on test machine: 8 threads Intel(R) Core(TM) i7 CPU 870 @ 2.93GHz with 6G memory
with following parameters:
runtime: 300s
nr_task: 1
test: context1
UnixBench is the original BYTE UNIX benchmark suite aims to test performance of Unix-like system.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase:
gcc-6/x86_64-rhel-7.2/1/debian-x86_64-2016-08-31.cgz/300s/nhm-white/context1/unixbench
commit:
e1a82ef694 ("perf/x86: convert perf_callchain_kernel() to use the new unwinder")
448e122131 ("x86/stacktrace: convert save_stack_trace_*() to use the new unwinder")
e1a82ef6945c5bfd 448e122131ad6651f4a0cdd281
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
%stddev %change %stddev
\ | \
229.19 ± 0% -11.2% 203.56 ± 0% unixbench.time.system_time
36929 ± 21% -84.4% 5747 ± 28% unixbench.time.involuntary_context_switches
59.00 ± 0% -10.2% 53.00 ± 0% unixbench.time.percent_of_cpu_this_job_got
22769222 ± 0% +46.5% 33353802 ± 0% unixbench.time.voluntary_context_switches
21.50 ± 1% +9.5% 23.54 ± 1% turbostat.%Busy
462.00 ± 1% +10.3% 509.75 ± 1% turbostat.Avg_MHz
248988 ± 0% +43.5% 357408 ± 0% vmstat.system.cs
17734 ± 2% +5.2% 18654 ± 3% vmstat.system.in
2.544e+08 ± 0% -19.2% 2.057e+08 ± 1% cpuidle.C1-NHM.time
47050880 ± 0% +42.8% 67187313 ± 0% cpuidle.C1-NHM.usage
769823 ± 4% -10.8% 686612 ± 4% cpuidle.C1E-NHM.time
19908 ± 4% +17.7% 23433 ± 3% cpuidle.C1E-NHM.usage
1494189 ± 13% +46.2% 2184591 ± 13% cpuidle.POLL.usage
2.419e+11 ± 0% -18.2% 1.978e+11 ± 0% perf-stat.branch-instructions
1.38 ± 1% +19.9% 1.65 ± 0% perf-stat.branch-miss-rate%
3.332e+09 ± 0% -1.9% 3.269e+09 ± 1% perf-stat.branch-misses
0.53 ± 10% -26.0% 0.40 ± 11% perf-stat.cache-miss-rate%
4.843e+09 ± 1% +28.6% 6.23e+09 ± 5% perf-stat.cache-references
97835449 ± 0% +43.6% 1.404e+08 ± 0% perf-stat.context-switches
1.239e+12 ± 2% +10.0% 1.363e+12 ± 3% perf-stat.cpu-cycles
56099 ± 2% +5.3% 59074 ± 1% perf-stat.cpu-migrations
3.595e+11 ± 0% -5.7% 3.389e+11 ± 0% perf-stat.dTLB-loads
1.905e+11 ± 0% -4.0% 1.828e+11 ± 0% perf-stat.dTLB-stores
0.06 ± 1% +47.6% 0.09 ± 1% perf-stat.iTLB-load-miss-rate%
6.141e+08 ± 1% +35.6% 8.33e+08 ± 0% perf-stat.iTLB-load-misses
1.046e+12 ± 1% -8.1% 9.608e+11 ± 0% perf-stat.iTLB-loads
1460 ± 3% -32.6% 984.69 ± 4% perf-stat.instructions-per-iTLB-miss
0.72 ± 1% -16.8% 0.60 ± 1% perf-stat.ipc
27084 ± 0% -10.4% 24270 ± 0% sched_debug.cfs_rq:/.exec_clock.avg
5043 ± 10% -30.7% 3495 ± 6% sched_debug.cfs_rq:/.exec_clock.min
19561 ± 11% -23.4% 14993 ± 6% sched_debug.cfs_rq:/.min_vruntime.min
5865911 ± 0% +42.1% 8333916 ± 0% sched_debug.cpu.nr_switches.avg
11231416 ± 5% +45.0% 16284663 ± 1% sched_debug.cpu.nr_switches.max
4386525 ± 6% +50.5% 6600208 ± 3% sched_debug.cpu.nr_switches.stddev
5863169 ± 0% +42.1% 8331117 ± 0% sched_debug.cpu.sched_count.avg
11227373 ± 5% +45.0% 16281545 ± 1% sched_debug.cpu.sched_count.max
4385756 ± 6% +50.5% 6599487 ± 3% sched_debug.cpu.sched_count.stddev
2919935 ± 0% +42.5% 4161650 ± 0% sched_debug.cpu.sched_goidle.avg
5574368 ± 5% +45.9% 8135631 ± 1% sched_debug.cpu.sched_goidle.max
2181714 ± 6% +51.1% 3297412 ± 3% sched_debug.cpu.sched_goidle.stddev
2934348 ± 0% +42.0% 4167230 ± 0% sched_debug.cpu.ttwu_count.avg
5622746 ± 5% +44.6% 8132326 ± 1% sched_debug.cpu.ttwu_count.max
2189417 ± 6% +50.5% 3294646 ± 3% sched_debug.cpu.ttwu_count.stddev
447301 ± 17% +22.9% 549804 ± 20% sched_debug.cpu.ttwu_local.stddev
10.29 ± 4% -66.8% 3.42 ± 7% perf-profile.calltrace.cycles-pp.__account_scheduler_latency.enqueue_entity.enqueue_task_fair.activate_task.ttwu_do_activate
4.38 ± 4% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.__kernel_text_address.print_context_stack.dump_trace.save_stack_trace_tsk.__account_scheduler_latency
0.65 ± 20% +42.7% 0.93 ± 11% perf-profile.calltrace.cycles-pp.__next_timer_interrupt.get_next_timer_interrupt.tick_nohz_stop_sched_tick.__tick_nohz_idle_enter.tick_nohz_idle_enter
0.00 ± -1% +Inf% 2.52 ± 8% perf-profile.calltrace.cycles-pp.__save_stack_trace.save_stack_trace_tsk.__account_scheduler_latency.enqueue_entity.enqueue_task_fair
3.15 ± 7% +32.0% 4.15 ± 7% perf-profile.calltrace.cycles-pp.__schedule.schedule.pipe_wait.pipe_read.__vfs_read
2.46 ± 10% +29.3% 3.19 ± 8% perf-profile.calltrace.cycles-pp.__tick_nohz_idle_enter.tick_nohz_idle_enter.cpu_startup_entry.start_secondary
6.38 ± 7% +27.3% 8.13 ± 4% perf-profile.calltrace.cycles-pp.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
17.57 ± 5% -28.0% 12.65 ± 4% perf-profile.calltrace.cycles-pp.__vfs_write.vfs_write.sys_write.entry_SYSCALL_64_fastpath
15.08 ± 5% -33.1% 10.08 ± 5% perf-profile.calltrace.cycles-pp.__wake_up_common.__wake_up_sync_key.pipe_write.__vfs_write.vfs_write
15.90 ± 5% -32.2% 10.78 ± 5% perf-profile.calltrace.cycles-pp.__wake_up_sync_key.pipe_write.__vfs_write.vfs_write.sys_write
12.18 ± 5% -50.0% 6.09 ± 4% perf-profile.calltrace.cycles-pp.activate_task.ttwu_do_activate.try_to_wake_up.default_wake_function.autoremove_wake_function
14.88 ± 5% -34.0% 9.83 ± 5% perf-profile.calltrace.cycles-pp.autoremove_wake_function.__wake_up_common.__wake_up_sync_key.pipe_write.__vfs_write
1.15 ± 20% -30.8% 0.80 ± 21% perf-profile.calltrace.cycles-pp.clockevents_program_event.tick_program_event.hrtimer_interrupt.hpet_interrupt_handler.__handle_irq_event_percpu
1.79 ± 12% +26.1% 2.26 ± 8% perf-profile.calltrace.cycles-pp.deactivate_task.__schedule.schedule.pipe_wait.pipe_read
14.83 ± 5% -34.4% 9.73 ± 5% perf-profile.calltrace.cycles-pp.default_wake_function.autoremove_wake_function.__wake_up_common.__wake_up_sync_key.pipe_write
1.63 ± 13% +25.0% 2.04 ± 10% perf-profile.calltrace.cycles-pp.dequeue_task_fair.deactivate_task.__schedule.schedule.pipe_wait
9.72 ± 3% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.dump_trace.save_stack_trace_tsk.__account_scheduler_latency.enqueue_entity.enqueue_task_fair
11.68 ± 4% -54.0% 5.38 ± 4% perf-profile.calltrace.cycles-pp.enqueue_entity.enqueue_task_fair.activate_task.ttwu_do_activate.try_to_wake_up
11.91 ± 5% -52.4% 5.67 ± 4% perf-profile.calltrace.cycles-pp.enqueue_task_fair.activate_task.ttwu_do_activate.try_to_wake_up.default_wake_function
1.06 ± 17% +34.6% 1.42 ± 8% perf-profile.calltrace.cycles-pp.get_next_timer_interrupt.tick_nohz_stop_sched_tick.__tick_nohz_idle_enter.tick_nohz_idle_enter.cpu_startup_entry
1.15 ± 20% -30.8% 0.80 ± 21% perf-profile.calltrace.cycles-pp.hpet_msi_next_event.clockevents_program_event.tick_program_event.hrtimer_interrupt.hpet_interrupt_handler
1.28 ± 8% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.is_ftrace_trampoline.__kernel_text_address.print_context_stack.dump_trace.save_stack_trace_tsk
1.86 ± 3% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.is_module_text_address.__kernel_text_address.print_context_stack.dump_trace.save_stack_trace_tsk
0.92 ± 7% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.is_module_text_address.print_context_stack.dump_trace.save_stack_trace_tsk.__account_scheduler_latency
1.18 ± 6% +25.1% 1.47 ± 7% perf-profile.calltrace.cycles-pp.pick_next_task_fair.__schedule.schedule.schedule_preempt_disabled.cpu_startup_entry
5.93 ± 6% +28.3% 7.60 ± 5% perf-profile.calltrace.cycles-pp.pipe_read.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
4.15 ± 4% +33.9% 5.56 ± 5% perf-profile.calltrace.cycles-pp.pipe_wait.pipe_read.__vfs_read.vfs_read.sys_read
17.08 ± 5% -29.1% 12.11 ± 5% perf-profile.calltrace.cycles-pp.pipe_write.__vfs_write.vfs_write.sys_write.entry_SYSCALL_64_fastpath
8.12 ± 4% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.print_context_stack.dump_trace.save_stack_trace_tsk.__account_scheduler_latency.enqueue_entity
9.77 ± 3% -71.8% 2.75 ± 7% perf-profile.calltrace.cycles-pp.save_stack_trace_tsk.__account_scheduler_latency.enqueue_entity.enqueue_task_fair.activate_task
3.35 ± 7% +31.5% 4.41 ± 6% perf-profile.calltrace.cycles-pp.schedule.pipe_wait.pipe_read.__vfs_read.vfs_read
2.55 ± 7% +16.7% 2.97 ± 9% perf-profile.calltrace.cycles-pp.schedule.schedule_preempt_disabled.cpu_startup_entry.start_secondary
2.67 ± 6% +15.5% 3.09 ± 9% perf-profile.calltrace.cycles-pp.schedule_preempt_disabled.cpu_startup_entry.start_secondary
1.31 ± 11% +42.7% 1.87 ± 6% perf-profile.calltrace.cycles-pp.select_task_rq_fair.try_to_wake_up.default_wake_function.autoremove_wake_function.__wake_up_common
0.73 ± 9% +23.8% 0.91 ± 6% perf-profile.calltrace.cycles-pp.set_next_entity.pick_next_task_fair.__schedule.schedule.schedule_preempt_disabled
7.39 ± 8% +27.9% 9.46 ± 5% perf-profile.calltrace.cycles-pp.sys_read.entry_SYSCALL_64_fastpath
18.75 ± 5% -24.5% 14.15 ± 4% perf-profile.calltrace.cycles-pp.sys_write.entry_SYSCALL_64_fastpath
2.56 ± 10% +30.0% 3.33 ± 9% perf-profile.calltrace.cycles-pp.tick_nohz_idle_enter.cpu_startup_entry.start_secondary
1.50 ± 8% +22.8% 1.84 ± 11% perf-profile.calltrace.cycles-pp.tick_nohz_idle_exit.cpu_startup_entry.start_secondary
2.09 ± 12% +25.1% 2.62 ± 7% perf-profile.calltrace.cycles-pp.tick_nohz_stop_sched_tick.__tick_nohz_idle_enter.tick_nohz_idle_enter.cpu_startup_entry.start_secondary
1.16 ± 20% -31.0% 0.80 ± 22% perf-profile.calltrace.cycles-pp.tick_program_event.hrtimer_interrupt.hpet_interrupt_handler.__handle_irq_event_percpu.handle_irq_event_percpu
14.73 ± 5% -34.7% 9.61 ± 4% perf-profile.calltrace.cycles-pp.try_to_wake_up.default_wake_function.autoremove_wake_function.__wake_up_common.__wake_up_sync_key
12.74 ± 5% -46.0% 6.88 ± 4% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.default_wake_function.autoremove_wake_function.__wake_up_common
7.18 ± 8% +28.1% 9.21 ± 5% perf-profile.calltrace.cycles-pp.vfs_read.sys_read.entry_SYSCALL_64_fastpath
18.49 ± 5% -25.3% 13.80 ± 4% perf-profile.calltrace.cycles-pp.vfs_write.sys_write.entry_SYSCALL_64_fastpath
10.39 ± 4% -66.6% 3.47 ± 7% perf-profile.children.cycles-pp.__account_scheduler_latency
3.12 ± 8% -20.8% 2.47 ± 9% perf-profile.children.cycles-pp.__handle_irq_event_percpu
5.33 ± 3% -99.1% 0.05 ± 58% perf-profile.children.cycles-pp.__kernel_text_address
1.06 ± 3% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.__module_text_address
0.83 ± 19% +44.3% 1.21 ± 8% perf-profile.children.cycles-pp.__next_timer_interrupt
0.00 ± -1% +Inf% 2.55 ± 8% perf-profile.children.cycles-pp.__save_stack_trace
6.06 ± 4% +27.7% 7.74 ± 6% perf-profile.children.cycles-pp.__schedule
3.18 ± 10% +30.5% 4.15 ± 7% perf-profile.children.cycles-pp.__tick_nohz_idle_enter
6.58 ± 7% +25.6% 8.27 ± 4% perf-profile.children.cycles-pp.__vfs_read
17.83 ± 5% -28.3% 12.78 ± 4% perf-profile.children.cycles-pp.__vfs_write
15.22 ± 5% -33.3% 10.15 ± 5% perf-profile.children.cycles-pp.__wake_up_common
16.25 ± 5% -32.0% 11.05 ± 4% perf-profile.children.cycles-pp.__wake_up_sync_key
0.89 ± 8% +32.8% 1.19 ± 9% perf-profile.children.cycles-pp._raw_spin_lock_irqsave
12.28 ± 4% -50.1% 6.12 ± 4% perf-profile.children.cycles-pp.activate_task
15.06 ± 5% -34.1% 9.92 ± 5% perf-profile.children.cycles-pp.autoremove_wake_function
2.89 ± 9% -21.8% 2.26 ± 10% perf-profile.children.cycles-pp.clockevents_program_event
1.82 ± 11% +25.3% 2.29 ± 8% perf-profile.children.cycles-pp.deactivate_task
14.96 ± 5% -34.6% 9.78 ± 5% perf-profile.children.cycles-pp.default_wake_function
3.58 ± 8% -20.3% 2.85 ± 9% perf-profile.children.cycles-pp.do_IRQ
9.79 ± 3% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.dump_trace
11.79 ± 4% -53.9% 5.43 ± 4% perf-profile.children.cycles-pp.enqueue_entity
12.03 ± 4% -52.5% 5.71 ± 4% perf-profile.children.cycles-pp.enqueue_task_fair
1.38 ± 15% +36.7% 1.88 ± 8% perf-profile.children.cycles-pp.get_next_timer_interrupt
3.21 ± 8% -21.1% 2.53 ± 9% perf-profile.children.cycles-pp.handle_edge_irq
3.21 ± 9% -20.8% 2.54 ± 9% perf-profile.children.cycles-pp.handle_irq
3.16 ± 9% -20.8% 2.50 ± 9% perf-profile.children.cycles-pp.handle_irq_event
3.16 ± 8% -20.9% 2.50 ± 9% perf-profile.children.cycles-pp.handle_irq_event_percpu
3.08 ± 9% -20.6% 2.44 ± 9% perf-profile.children.cycles-pp.hpet_interrupt_handler
2.84 ± 9% -22.0% 2.21 ± 10% perf-profile.children.cycles-pp.hpet_msi_next_event
3.32 ± 13% -22.7% 2.57 ± 8% perf-profile.children.cycles-pp.hrtimer_interrupt
1.27 ± 8% +19.1% 1.51 ± 3% perf-profile.children.cycles-pp.hrtimer_start_range_ns
2.20 ± 5% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.is_ftrace_trampoline
2.78 ± 4% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.is_module_text_address
0.76 ± 12% +25.1% 0.95 ± 5% perf-profile.children.cycles-pp.mutex_lock
1.56 ± 2% +33.1% 2.07 ± 4% perf-profile.children.cycles-pp.pick_next_task_fair
6.08 ± 6% +26.7% 7.70 ± 5% perf-profile.children.cycles-pp.pipe_read
4.22 ± 3% +33.0% 5.62 ± 5% perf-profile.children.cycles-pp.pipe_wait
17.30 ± 5% -29.3% 12.23 ± 4% perf-profile.children.cycles-pp.pipe_write
8.19 ± 4% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.print_context_stack
3.59 ± 8% -20.1% 2.87 ± 9% perf-profile.children.cycles-pp.ret_from_intr
1.18 ± 12% +24.5% 1.47 ± 3% perf-profile.children.cycles-pp.rw_verify_area
9.83 ± 3% -71.9% 2.77 ± 7% perf-profile.children.cycles-pp.save_stack_trace_tsk
6.47 ± 4% +28.0% 8.29 ± 6% perf-profile.children.cycles-pp.schedule
3.20 ± 3% +25.2% 4.01 ± 6% perf-profile.children.cycles-pp.schedule_preempt_disabled
1.02 ± 15% +27.3% 1.31 ± 2% perf-profile.children.cycles-pp.security_file_permission
1.34 ± 12% +41.0% 1.89 ± 7% perf-profile.children.cycles-pp.select_task_rq_fair
0.81 ± 13% +23.8% 1.00 ± 4% perf-profile.children.cycles-pp.selinux_file_permission
0.87 ± 5% +34.4% 1.17 ± 4% perf-profile.children.cycles-pp.set_next_entity
7.61 ± 8% +26.5% 9.62 ± 5% perf-profile.children.cycles-pp.sys_read
19.04 ± 5% -24.9% 14.29 ± 4% perf-profile.children.cycles-pp.sys_write
3.14 ± 10% +32.2% 4.15 ± 7% perf-profile.children.cycles-pp.tick_nohz_idle_enter
1.77 ± 6% +30.0% 2.30 ± 7% perf-profile.children.cycles-pp.tick_nohz_idle_exit
0.96 ± 5% +27.2% 1.22 ± 9% perf-profile.children.cycles-pp.tick_nohz_restart
1.24 ± 3% +32.7% 1.64 ± 7% perf-profile.children.cycles-pp.tick_nohz_restart_sched_tick
2.68 ± 10% +27.8% 3.43 ± 7% perf-profile.children.cycles-pp.tick_nohz_stop_sched_tick
2.86 ± 9% -21.9% 2.23 ± 11% perf-profile.children.cycles-pp.tick_program_event
14.89 ± 5% -35.0% 9.68 ± 4% perf-profile.children.cycles-pp.try_to_wake_up
12.86 ± 4% -46.2% 6.91 ± 4% perf-profile.children.cycles-pp.ttwu_do_activate
0.80 ± 10% +38.3% 1.11 ± 8% perf-profile.children.cycles-pp.update_cfs_shares
7.40 ± 8% +26.6% 9.37 ± 5% perf-profile.children.cycles-pp.vfs_read
18.77 ± 5% -25.7% 13.95 ± 4% perf-profile.children.cycles-pp.vfs_write
1.97 ± 3% -97.5% 0.05 ± 58% perf-profile.self.cycles-pp.__kernel_text_address
1.14 ± 6% +22.1% 1.40 ± 9% perf-profile.self.cycles-pp.__schedule
0.89 ± 8% +32.9% 1.18 ± 9% perf-profile.self.cycles-pp._raw_spin_lock_irqsave
2.84 ± 9% -22.0% 2.21 ± 10% perf-profile.self.cycles-pp.hpet_msi_next_event
2.20 ± 5% -100.0% 0.00 ± -1% perf-profile.self.cycles-pp.is_ftrace_trampoline
1.49 ± 4% -100.0% 0.00 ± -1% perf-profile.self.cycles-pp.is_module_text_address
1.56 ± 7% -100.0% 0.00 ± -1% perf-profile.self.cycles-pp.print_context_stack
unixbench.time.system_time
250 ++--------------------------------------------------------------------+
* **.* *.**.**.***.**.**.*** *.** **.* *.** *.***.**.**.**
| :O OOO OO OO O O : : : : : : : : |
200 OO OO O : : OO OO O OOO OO OO OO : : : : : |
| : : : : : : : : : : : |
| : : : : : : : : : : : |
150 ++ : : : : : : : : : : : |
| : : : : : : : : : : : |
100 ++ : : : : :: : : :: |
|: : : : : :: : : :: |
|: : : : : :: : : :: |
50 ++ : : : : : : : : |
|: : : : : : : : : |
|: : : : : : : : : |
0 +*-**-----*----------------------**-*----*-----*-**-----*-------------+
unixbench.time.voluntary_context_switches
3.5e+07 O+-O-O------------------------------------------------------------+
|O O OOO O O OO OOO OOO OOO OOO OOO O |
3e+07 ++ O |
| |
2.5e+07 *+ *.** * *.* .* **.* *. * *.** * |
| : : :* *.***.***.*** : : : : *: : : :*.***.***.**
2e+07 ++ : : : : : : : : : : : |
| : : : : : : : : : : : |
1.5e+07 ++ : : : : : : : : : : : |
|: : :: : : :: : : : : |
1e+07 ++ : :: : : : : : :: |
|: : :: : : : : : :: |
5e+06 ++ : : : : : : : : |
|: : : : : : : : : |
0 +*-**----*---------------------**-*----*----*-**-----*------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
3 years, 4 months
[lkp] [tracing] 37c4b339a5: [No primary change] vm-scalability.time.user_time +8.3% increase
by kernel test robot
Greeting,
There is no primary kpi change in this test, below is the data collected through multiple monitors running background just for your information.
commit 37c4b339a579af3cd5c55015222976fbd842ecf4 ("tracing: add a possibility of exporting function trace to other places instead of ring buffer only")
https://github.com/0day-ci/linux Chunyan-Zhang/Integration-of-function-trace-with-System-Trace-IP-blocks/20161018-162151
in testcase: vm-scalability
on test machine: 4 threads Intel(R) Core(TM) i3-3220 CPU @ 3.30GHz with 8G memory
with following parameters:
runtime: 300s
size: 1T
test: lru-shm
cpufreq_governor: performance
The motivation behind this suite is to exercise functions and regions of the mm/ of the Linux kernel which are of interest to us.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
compiler/cpufreq_governor/kconfig/rootfs/runtime/size/tbox_group/test/testcase:
gcc-6/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/300s/1T/lkp-ivb-d02/lru-shm/vm-scalability
commit:
14155cafea ("btrfs: assign error values to the correct bio structs")
37c4b339a5 ("tracing: add a possibility of exporting function trace to other places instead of ring buffer only")
14155cafeadda946 37c4b339a579af3cd5c5501522
---------------- --------------------------
fail:runs %reproduction fail:runs
| | |
1:4 -25% :4 kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[#]
%stddev %change %stddev
\ | \
468.20 ± 0% +8.3% 507.27 ± 0% vm-scalability.time.user_time
4257865 ± 0% -3.2% 4119842 ± 0% vm-scalability.throughput
378.69 ± 0% +2.7% 388.75 ± 0% vm-scalability.time.elapsed_time
378.69 ± 0% +2.7% 388.75 ± 0% vm-scalability.time.elapsed_time.max
27773 ± 3% +9.4% 30379 ± 2% vmstat.system.cs
15326 ± 0% -1.1% 15150 ± 0% vmstat.system.in
2.369e+09 ± 0% -1.9% 2.324e+09 ± 0% perf-stat.branch-misses
10563347 ± 2% +12.4% 11871366 ± 2% perf-stat.context-switches
4.201e+12 ± 0% +2.7% 4.313e+12 ± 0% perf-stat.cpu-cycles
62.24 ± 3% +9.4% 68.08 ± 4% perf-stat.iTLB-load-miss-rate%
68672833 ± 5% +24.8% 85704905 ± 8% perf-stat.iTLB-load-misses
74221 ± 5% -19.9% 59477 ± 7% perf-stat.instructions-per-iTLB-miss
1.21 ± 0% -3.0% 1.17 ± 0% perf-stat.ipc
1.16 ± 7% -12.5% 1.01 ± 4% perf-profile.calltrace.cycles-pp.alloc_set_pte.handle_mm_fault.__do_page_fault.do_page_fault.page_fault
1.96 ± 5% +6.9% 2.10 ± 6% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_fastpath
0.75 ± 12% +27.2% 0.96 ± 8% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_fastpath.write
4.65 ± 3% -10.0% 4.19 ± 2% perf-profile.calltrace.cycles-pp.radix_tree_next_chunk.filemap_map_pages.handle_mm_fault.__do_page_fault.do_page_fault
0.77 ± 11% +31.7% 1.02 ± 9% perf-profile.calltrace.cycles-pp.write
2.10 ± 3% -11.1% 1.87 ± 2% perf-profile.children.cycles-pp.alloc_set_pte
4.88 ± 2% -8.7% 4.45 ± 2% perf-profile.children.cycles-pp.radix_tree_next_chunk
0.78 ± 11% +31.6% 1.02 ± 9% perf-profile.children.cycles-pp.write
1.57 ± 3% -14.1% 1.35 ± 2% perf-profile.self.cycles-pp.alloc_set_pte
1.16 ± 5% -9.5% 1.05 ± 5% perf-profile.self.cycles-pp.get_page_from_freelist
4.88 ± 2% -8.7% 4.45 ± 2% perf-profile.self.cycles-pp.radix_tree_next_chunk
1614 ±123% -76.7% 376.54 ± 26% sched_debug.cpu.cpu_load[2].max
1525 ±121% -76.2% 362.89 ± 25% sched_debug.cpu.cpu_load[3].max
595.27 ±133% -84.9% 89.73 ± 54% sched_debug.cpu.cpu_load[3].stddev
1286 ±114% -73.5% 341.18 ± 23% sched_debug.cpu.cpu_load[4].max
492.55 ±127% -83.8% 79.79 ± 55% sched_debug.cpu.cpu_load[4].stddev
233516 ± 11% +23.0% 287339 ± 6% sched_debug.cpu.nr_switches.min
-8.21 ± -3% +63.5% -13.43 ±-17% sched_debug.cpu.nr_uninterruptible.min
7.52 ± 22% +39.9% 10.52 ± 7% sched_debug.cpu.nr_uninterruptible.stddev
229135 ± 11% +23.1% 282143 ± 6% sched_debug.cpu.sched_count.min
16629 ± 19% -36.5% 10558 ± 14% sched_debug.cpu.sched_goidle.min
111868 ± 13% +25.2% 140024 ± 6% sched_debug.cpu.ttwu_count.min
94578 ± 14% +34.3% 127059 ± 6% sched_debug.cpu.ttwu_local.min
vm-scalability.time.user_time
600 ++--------------------------------------------------------------------+
| |
500 O+ O O O O O O O O O O O O O O O O |
| *.*..*..*.O..O..O..O.O..O..*.*..*..*.* *.*..*..*..*.*..*..*.*..*
| : : : |
400 ++: : : |
| : : : |
300 ++: : : |
| : : : |
200 ++ : : |
|: : : |
|: : : |
100 ++ : : |
| : |
0 *+-----------------------------------------*--------------------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
3 years, 4 months