[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <206d6a81e08cb23a2c97e67335be6017e938bac5.camel@gmx.de>
Date: Mon, 05 Jul 2021 18:00:58 +0200
From: Mike Galbraith <efault@....de>
To: Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Vlastimil Babka <vbabka@...e.cz>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Christoph Lameter <cl@...ux.com>,
David Rientjes <rientjes@...gle.com>,
Pekka Enberg <penberg@...nel.org>,
Joonsoo Kim <iamjoonsoo.kim@....com>,
Thomas Gleixner <tglx@...utronix.de>,
Mel Gorman <mgorman@...hsingularity.net>,
Jesper Dangaard Brouer <brouer@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Jann Horn <jannh@...gle.com>
Subject: Re: [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT
compatible
On Fri, 2021-07-02 at 20:29 +0200, Sebastian Andrzej Siewior wrote:
>
> > The remaining patches to upstream from the RT tree are small ones
> > related to KConfig. The patch that restricts PREEMPT_RT to SLUB
> > (not SLAB or SLOB) makes sense. The patch that disables
> > CONFIG_SLUB_CPU_PARTIAL with PREEMPT_RT could perhaps be re-
> > evaluated as the series also addresses some latency issues with
> > percpu partial slabs.
>
> With that series the PARTIAL slab can be indeed enabled. I have (had)
> a half done series where I had PARTIAL enabled and noticed a slight
> increase in latency so made it "default y on !RT". It wasn't dramatic
> but appeared to be outside of noise.
I'm seeing warnings/explosions while exercising box IFF PARTIAL slab
thingy is enabled. I aborted -PARTIAL after a little over 4 hours,
whereas the longest survival of 4 +PARTIAL runs was 50 minutes, so I'm
fairly confident that PARTIAL really really is the trigger.
My reproducer is a keep box busy loop of parallel kbuild along with
alternating ltp::controllers (sans swap-from-hell bits), ltp::zram and
hackbench.
The warning may or may not trigger before box explodes.
[ 224.232200] ------------[ cut here ]------------
[ 224.232202] WARNING: CPU: 3 PID: 9112 at mm/slub.c:2018 ___slab_alloc.constprop.100+0xb09/0x13a0
[ 224.232210] Modules linked in: sr_mod(E) cdrom(E) zram(E) btrfs(E) blake2b_generic(E) xor(E) raid6_pq(E) xfs(E) libcrc32c(E) af_packet(E) ip6table_mangle(E) ip6table_raw(E) iptable_raw(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) nfnetlink(E) ebtable_filter(E) rfkill(E) ebtables(E) ip6table_filter(E) ip6_tables(E) iptable_filter(E) ip_tables(E) x_tables(E) bpfilter(E) joydev(E) usblp(E) intel_rapl_msr(E) intel_rapl_common(E) nls_iso8859_1(E) nls_cp437(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) kvm(E) snd_hda_codec_realtek(E) snd_hda_codec_generic(E) ledtrig_audio(E) snd_hda_codec_hdmi(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) ghash_clmulni_intel(E) snd_hda_intel(E) aesni_intel(E) snd_intel_dspcfg(E) crypto_simd(E) iTCO_wdt(E) at24(E) intel_pmc_bxt(E) regmap_i2c(E) mei_hdcp(E) iTCO_vendor_support(E) cryptd(E) snd_hda_codec(E) snd_hwdep(E) pcspkr(E) i2c_i801(E) snd_hda_core(E) i2c_smbus(E) r8169(E) snd_pcm(E) realtek(E) snd_timer(E)
[ 224.232253] mei_me(E) mdio_devres(E) lpc_ich(E) snd(E) libphy(E) mei(E) soundcore(E) mfd_core(E) fan(E) thermal(E) nfsd(E) intel_smartconnect(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) sch_fq_codel(E) sunrpc(E) fuse(E) configfs(E) hid_logitech_hidpp(E) hid_logitech_dj(E) uas(E) usb_storage(E) hid_generic(E) usbhid(E) nouveau(E) wmi(E) drm_ttm_helper(E) ttm(E) i2c_algo_bit(E) drm_kms_helper(E) syscopyarea(E) sysfillrect(E) sysimgblt(E) fb_sys_fops(E) cec(E) ahci(E) rc_core(E) xhci_pci(E) ehci_pci(E) libahci(E) xhci_hcd(E) ehci_hcd(E) drm(E) libata(E) usbcore(E) video(E) button(E) sd_mod(E) t10_pi(E) vfat(E) fat(E) virtio_blk(E) virtio_mmio(E) virtio_ring(E) virtio(E) ext4(E) crc32c_intel(E) crc16(E) mbcache(E) jbd2(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) msr(E) autofs4(E)
[ 224.232295] CPU: 3 PID: 9112 Comm: dd Kdump: loaded Tainted: G E 5.13.0.g60ab3ed-tip-rt-slub #25
[ 224.232297] Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.20C 09/23/2013
[ 224.232299] RIP: 0010:___slab_alloc.constprop.100+0xb09/0x13a0
[ 224.232302] Code: 48 8b 7d 88 4c 89 ee 8b 47 28 4c 01 f8 48 89 c2 48 0f ca 48 33 97 b8 00 00 00 48 33 10 e8 cf e5 ff ff e9 b5 00 00 00 4d 89 ce <0f> 0b e9 2d fa ff ff 8b 53 38 8b 05 8f 47 4a 01 48 8b 75 80 83 c2
[ 224.232303] RSP: 0018:ffff8882047e3ba0 EFLAGS: 00010046
[ 224.232305] RAX: ffff888100040f80 RBX: 0000000000000000 RCX: 0000000080190019
[ 224.232307] RDX: ffffea0005d59a08 RSI: 0000000000000000 RDI: ffffffff8177ab54
[ 224.232308] RBP: ffff8882047e3c70 R08: ffffffffffffffff R09: 0000000000000000
[ 224.232309] R10: ffff8882047e3c90 R11: 0000000000000000 R12: ffffea0004d60780
[ 224.232310] R13: 0000000000000019 R14: 0000000000000000 R15: 0000000080190019
[ 224.232311] FS: 00007f88ffa09580(0000) GS:ffff88840ecc0000(0000) knlGS:0000000000000000
[ 224.232312] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 224.232313] CR2: 00007f88ffa4a000 CR3: 000000015606a005 CR4: 00000000001706e0
[ 224.232315] Call Trace:
[ 224.232318] ? __alloc_file+0x26/0xf0
[ 224.232322] ? prep_new_page+0xab/0x100
[ 224.232326] ? __alloc_file+0x26/0xf0
[ 224.232329] ? __slab_alloc.isra.87.constprop.99+0x2e/0x40
[ 224.232331] __slab_alloc.isra.87.constprop.99+0x2e/0x40
[ 224.232333] ? __alloc_file+0x26/0xf0
[ 224.232335] kmem_cache_alloc+0x4d/0x160
[ 224.232338] __alloc_file+0x26/0xf0
[ 224.232340] alloc_empty_file+0x43/0xe0
[ 224.232343] path_openat+0x35/0xe30
[ 224.232345] ? getname_flags+0x32/0x170
[ 224.232347] ? ___slab_alloc.constprop.100+0xbbb/0x13a0
[ 224.232349] ? filemap_map_pages+0xf0/0x3e0
[ 224.232352] do_filp_open+0xa2/0x100
[ 224.232355] ? __slab_alloc.isra.87.constprop.99+0x36/0x40
[ 224.232357] ? __slab_alloc.isra.87.constprop.99+0x36/0x40
[ 224.232359] ? getname_flags+0x32/0x170
[ 224.232361] ? alloc_fd+0xe2/0x1b0
[ 224.232363] ? do_sys_openat2+0x248/0x310
[ 224.232365] do_sys_openat2+0x248/0x310
[ 224.232368] do_sys_open+0x47/0x60
[ 224.232370] do_syscall_64+0x37/0x80
[ 224.232373] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 224.232376] RIP: 0033:0x7f88ff54ab41
[ 224.232378] Code: 41 83 e2 40 48 89 54 24 30 75 3e 89 f0 25 00 00 41 00 3d 00 00 41 00 74 30 89 f2 b8 01 01 00 00 48 89 fe bf 9c ff ff ff 0f 05 <48> 3d 00 f0 ff ff 77 3f 48 8b 4c 24 18 64 48 33 0c 25 28 00 00 00
[ 224.232379] RSP: 002b:00007ffc0916a720 EFLAGS: 00000287 ORIG_RAX: 0000000000000101
[ 224.232381] RAX: ffffffffffffffda RBX: 0000558d793efcf0 RCX: 00007f88ff54ab41
[ 224.232382] RDX: 0000000000080000 RSI: 0000558d793efcb0 RDI: 00000000ffffff9c
[ 224.232383] RBP: 00007ffc0916a860 R08: 0000000000000000 R09: 00007ffc0916a873
[ 224.232384] R10: 0000000000000000 R11: 0000000000000287 R12: 0000558d793efa88
[ 224.232385] R13: 000000000000000b R14: 0000558d793efa60 R15: 000000000000000b
[ 224.232387] ---[ end trace 0000000000000002 ]---
...
[ 2010.420941] general protection fault, maybe for address 0xffffea00054ca398: 0000 [#1] PREEMPT_RT SMP NOPTI
[ 2010.420946] CPU: 4 PID: 17541 Comm: dd Kdump: loaded Tainted: G W E 5.13.0.g60ab3ed-tip-rt-slub #25
[ 2010.420948] Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.20C 09/23/2013
[ 2010.420949] RIP: 0010:___slab_alloc.constprop.100+0x52b/0x13a0
[ 2010.420955] Code: b7 44 24 2a 31 db 66 25 ff 7f 66 89 45 b8 48 8b 45 88 80 4d bb 80 48 8b 4d b8 f6 40 0b 40 0f 84 5b 02 00 00 48 89 f0 4c 89 fa <f0> 49 0f c7 4c 24 20 0f 84 8f 01 00 00 4d 89 ce f3 90 48 8b b5 30
[ 2010.420957] RSP: 0018:ffff888102cf7ba0 EFLAGS: 00010002
[ 2010.420959] RAX: ffff888100047e00 RBX: 0000000000000000 RCX: 0000000080000000
[ 2010.420961] RDX: 0000000000000000 RSI: ffff888100047e00 RDI: ffff888100040f80
[ 2010.420962] RBP: ffff888102cf7c70 R08: ffffffffffffffff R09: 0000000000000000
[ 2010.420963] R10: ffff888102cf7c90 R11: 0000000000000000 R12: ffffea00054ca378
[ 2010.420964] R13: 0000000000000000 R14: 80000000000101f8 R15: 0000000000000000
[ 2010.420966] FS: 00007f9e8edbb580(0000) GS:ffff88840ed00000(0000) knlGS:0000000000000000
[ 2010.420967] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2010.420968] CR2: 00007f9e8edfa000 CR3: 0000000102ede004 CR4: 00000000001706e0
[ 2010.420970] Call Trace:
[ 2010.420973] ? __alloc_file+0x26/0xf0
[ 2010.420977] ? prep_new_page+0xab/0x100
[ 2010.420982] ? vm_area_alloc+0x1a/0x60
[ 2010.420984] ? __alloc_file+0x26/0xf0
[ 2010.420987] ? __slab_alloc.isra.87.constprop.99+0x2e/0x40
[ 2010.420989] __slab_alloc.isra.87.constprop.99+0x2e/0x40
[ 2010.420992] ? __alloc_file+0x26/0xf0
[ 2010.420994] kmem_cache_alloc+0x4d/0x160
[ 2010.420996] __alloc_file+0x26/0xf0
[ 2010.420999] alloc_empty_file+0x43/0xe0
[ 2010.421002] path_openat+0x35/0xe30
[ 2010.421004] ? getname_flags+0x32/0x170
[ 2010.421006] ? ___slab_alloc.constprop.100+0xbbb/0x13a0
[ 2010.421008] ? filemap_map_pages+0xf0/0x3e0
[ 2010.421012] do_filp_open+0xa2/0x100
[ 2010.421015] ? __handle_mm_fault+0x8b8/0xa40
[ 2010.421017] ? __slab_alloc.isra.87.constprop.99+0x36/0x40
[ 2010.421019] ? __slab_alloc.isra.87.constprop.99+0x36/0x40
[ 2010.421021] ? getname_flags+0x32/0x170
[ 2010.421023] ? alloc_fd+0xe2/0x1b0
[ 2010.421026] ? do_sys_openat2+0x248/0x310
[ 2010.421028] do_sys_openat2+0x248/0x310
[ 2010.421030] do_sys_open+0x47/0x60
[ 2010.421033] do_syscall_64+0x37/0x80
[ 2010.421035] entry_SYSCALL_64_after_hwframe+0x44/0xae
[ 2010.421039] RIP: 0033:0x7f9e8e8fcb41
[ 2010.421041] Code: 41 83 e2 40 48 89 54 24 30 75 3e 89 f0 25 00 00 41 00 3d 00 00 41 00 74 30 89 f2 b8 01 01 00 00 48 89 fe bf 9c ff ff ff 0f 05 <48> 3d 00 f0 ff ff 77 3f 48 8b 4c 24 18 64 48 33 0c 25 28 00 00 00
[ 2010.421043] RSP: 002b:00007ffe8964b7b0 EFLAGS: 00000287 ORIG_RAX: 0000000000000101
[ 2010.421044] RAX: ffffffffffffffda RBX: 0000562e1e31b450 RCX: 00007f9e8e8fcb41
[ 2010.421045] RDX: 0000000000080000 RSI: 0000562e1e31b230 RDI: 00000000ffffff9c
[ 2010.421047] RBP: 00007ffe8964b8f0 R08: 0000000000000000 R09: 00007ffe8964b903
[ 2010.421048] R10: 0000000000000000 R11: 0000000000000287 R12: 0000562e1e31b400
[ 2010.421049] R13: 0000000000000009 R14: 0000562e1e31b3e0 R15: 0000000000000009
[ 2010.421051] Modules linked in: zram(E) sr_mod(E) cdrom(E) btrfs(E) blake2b_generic(E) xor(E) raid6_pq(E) xfs(E) libcrc32c(E) af_packet(E) ip6table_mangle(E) ip6table_raw(E) iptable_raw(E) bridge(E) stp(E) llc(E) iscsi_ibft(E) iscsi_boot_sysfs(E) nfnetlink(E) ebtable_filter(E) rfkill(E) ebtables(E) ip6table_filter(E) ip6_tables(E) iptable_filter(E) ip_tables(E) x_tables(E) bpfilter(E) joydev(E) usblp(E) intel_rapl_msr(E) intel_rapl_common(E) nls_iso8859_1(E) nls_cp437(E) x86_pkg_temp_thermal(E) intel_powerclamp(E) coretemp(E) kvm_intel(E) kvm(E) snd_hda_codec_realtek(E) snd_hda_codec_generic(E) ledtrig_audio(E) snd_hda_codec_hdmi(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) ghash_clmulni_intel(E) snd_hda_intel(E) aesni_intel(E) snd_intel_dspcfg(E) crypto_simd(E) iTCO_wdt(E) at24(E) intel_pmc_bxt(E) regmap_i2c(E) mei_hdcp(E) iTCO_vendor_support(E) cryptd(E) snd_hda_codec(E) snd_hwdep(E) pcspkr(E) i2c_i801(E) snd_hda_core(E) i2c_smbus(E) r8169(E) snd_pcm(E) realtek(E) snd_timer(E)
[ 2010.421093] mei_me(E) mdio_devres(E) lpc_ich(E) snd(E) libphy(E) mei(E) soundcore(E) mfd_core(E) fan(E) thermal(E) nfsd(E) intel_smartconnect(E) auth_rpcgss(E) nfs_acl(E) lockd(E) grace(E) sch_fq_codel(E) sunrpc(E) fuse(E) configfs(E) hid_logitech_hidpp(E) hid_logitech_dj(E) uas(E) usb_storage(E) hid_generic(E) usbhid(E) nouveau(E) wmi(E) drm_ttm_helper(E) ttm(E) i2c_algo_bit(E) drm_kms_helper(E) syscopyarea(E) sysfillrect(E) sysimgblt(E) fb_sys_fops(E) cec(E) ahci(E) rc_core(E) xhci_pci(E) ehci_pci(E) libahci(E) xhci_hcd(E) ehci_hcd(E) drm(E) libata(E) usbcore(E) video(E) button(E) sd_mod(E) t10_pi(E) vfat(E) fat(E) virtio_blk(E) virtio_mmio(E) virtio_ring(E) virtio(E) ext4(E) crc32c_intel(E) crc16(E) mbcache(E) jbd2(E) sg(E) dm_multipath(E) dm_mod(E) scsi_dh_rdac(E) scsi_dh_emc(E) scsi_dh_alua(E) scsi_mod(E) msr(E) autofs4(E) [last unloaded: zram]
[ 2010.421138] Dumping ftrace buffer:
[ 2010.421141] (ftrace buffer empty)
Powered by blists - more mailing lists