Messages in this thread |  | | | Date | Fri, 19 Dec 2008 23:27:09 +0100 | | From | Ingo Molnar <> | | Subject | Re: [PATCH v7 4/8] sched: nominate preferred wakeup cpu |
| |
* Andrew Morton <akpm@linux-foundation.org> wrote:
> On Fri, 19 Dec 2008 13:55:08 -0800 > Andrew Morton <akpm@linux-foundation.org> wrote: > > > On Thu, 18 Dec 2008 23:26:22 +0530 > > Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> wrote: > > > > > When the system utilisation is low and more cpus are idle, > > > then the process waking up from sleep should prefer to > > > wakeup an idle cpu from semi-idle cpu package (multi core > > > package) rather than a completely idle cpu package which > > > would waste power. > > > > > > Use the sched_mc balance logic in find_busiest_group() to > > > nominate a preferred wakeup cpu. > > > > > > This info can be sored in appropriate sched_domain, but > > > updating this info in all copies of sched_domain is not > > > practical. Hence this information is stored in root_domain > > > struct which is one copy per partitioned sched domain. > > > The root_domain can be accessed from each cpu's runqueue > > > and there is one copy per partitioned sched domain. > > > > > > > kernel/sched.c: In function 'find_busiest_group': > > kernel/sched.c:3403: warning: passing argument 1 of '__first_cpu' from incompatible pointer type > > > > > > kernel/sched.c: In function 'schedule': > > kernel/sched.c:3679: warning: 'active_balance' may be used uninitialized in this function > > > > I left those unfixed and... > > [ 62.307607] initcall init_nfsd+0x0/0xe2 [nfsd] returned 0 after 251 usecs > [ 62.399426] NFSD: Using /var/lib/nfs/v4recovery as the NFSv4 state recovery directory > [ 74.009934] divide error: 0000 [#1] SMP > [ 74.010085] last sysfs file: /sys/devices/pci0000:00/0000:00:02.0/0000:01:00.0/0000:02:02.0/0000:05:00.1/irq > [ 74.010147] CPU 1 > [ 74.010241] Modules linked in: nfsd auth_rpcgss exportfs lockd nfs_acl autofs4 hidp rfcomm l2cap bluetooth sunrpc ipv6 dm_mirror dm_region_hash dm_log dm_multipath dm_mod rfkill input_polldev sbs sbshc battery ac parport_pc lp parport snd_hda_codec_realtek sg snd_hda_intel floppy snd_hda_codec snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device ide_cd_mod cdrom snd_pcm_oss snd_mixer_oss serio_raw snd_pcm button shpchp snd_timer i2c_i801 i2c_core snd soundcore snd_page_alloc pcspkr ehci_hcd ohci_hcd uhci_hcd > [ 74.012821] Pid: 0, comm: swapper Not tainted 2.6.28-rc9-mm1 #1 > [ 74.012875] RIP: 0010:[<ffffffff802375d8>] [<ffffffff802375d8>] tg_shares_up+0x113/0x1f1 > [ 74.012982] RSP: 0018:ffff88025e057d88 EFLAGS: 00010246 > [ 74.013038] RAX: 0000000000000000 RBX: ffff880028063900 RCX: ffff880028058dc0 > [ 74.013095] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 00000000000000ff > [ 74.013152] RBP: ffff88025e057dd8 R08: 0000000000000000 R09: 0000000000000000 > [ 74.013209] R10: ffff880028067640 R11: 0000000000000022 R12: ffff880028063900 > [ 74.013264] R13: ffffffff802374c5 R14: ffffffff8022c546 R15: ffffffff8079b4a0 > [ 74.013321] FS: 0000000000000000(0000) GS:ffff88025e0385c0(0000) knlGS:0000000000000000 > [ 74.013381] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b > [ 74.013435] CR2: 00007fdb795af8f0 CR3: 0000000000201000 CR4: 00000000000006e0 > [ 74.013489] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > [ 74.013545] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > [ 74.013602] Process swapper (pid: 0, threadinfo ffff88025e050000, task ffff88025e03f870) > [ 74.013661] Stack: > [ 74.013708] 0000000000000000 ffff880028063a00 0000000000000000 0000000000000000 > [ 74.013893] 0000000000000008 ffffffff8079b4a0 ffff880028063900 ffffffff802374c5 > [ 74.013893] ffffffff8022c546 0000000000000030 ffff88025e057e08 ffffffff8022c530 > [ 74.013893] Call Trace: > [ 74.013893] <IRQ> <0> [<ffffffff802374c5>] ? tg_shares_up+0x0/0x1f1 > [ 74.013893] [<ffffffff8022c546>] ? tg_nop+0x0/0x8 > [ 74.013893] [<ffffffff8022c530>] walk_tg_tree+0x5f/0x75 > [ 74.013893] [<ffffffff8022c65c>] update_shares+0x46/0x4a > [ 74.013893] [<ffffffff80235fe4>] run_rebalance_domains+0x192/0x522 > [ 74.013893] [<ffffffff802543eb>] ? getnstimeofday+0x3d/0x9e > [ 74.013893] [<ffffffff8052bd73>] ? _spin_unlock_irq+0x9/0xc > [ 74.013893] [<ffffffff8024057f>] __do_softirq+0xa3/0x164 > [ 74.013893] [<ffffffff8020d0bc>] call_softirq+0x1c/0x28 > [ 74.013893] [<ffffffff8020e19d>] do_softirq+0x31/0x73 > [ 74.013893] [<ffffffff802402ca>] irq_exit+0x3f/0x41 > [ 74.013893] [<ffffffff8021e71d>] smp_apic_timer_interrupt+0x94/0xad > [ 74.013893] [<ffffffff8020caf3>] apic_timer_interrupt+0x13/0x20 > [ 74.013893] <EOI> <0>Code: 8b 47 08 4a 8b 0c 00 48 85 c9 0f 84 c3 00 00 00 49 8b 47 10 4a 8b 04 00 48 8b 80 a8 00 00 00 48 85 c0 74 13 48 0f af 45 c8 31 d2 <48> f7 75 c0 49 89 c6 48 89 c6 eb 16 48 63 55 d0 48 8b 45 c8 45 > [ 74.013893] RIP [<ffffffff802375d8>] tg_shares_up+0x113/0x1f1 > [ 74.013893] RSP <ffff88025e057d88> > [ 74.020022] ---[ end trace 2fc4046e394f2312 ]--- > [ 74.020188] Kernel panic - not syncing: Fatal exception in interrupt > > config: http://userweb.kernel.org/~akpm/config-akpm2.txt > > I'll try hacking some div-by-zero avoidance into update_group_shares_cpu().
hm, weird - Yinghai noticed this crash in -tip and we have that patch zapped from all -*-next branches already.
Ingo
|  |