kernel BUG at kernel/sched_rt.c:322!
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=y
and run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
On the off-chance that this is new news...
Thanx, Paul [ 5538.091011] kernel BUG at kernel/sched_rt.c:322! [ 5538.091011] invalid opcode: 0000 [#1] SMP [ 5538.091011] Modules linked in: [ 5538.091011] [ 5538.091011] Pid: 2819, comm: sh Not tainted (2.6.27-rc9-autokern1 #1) [ 5538.091011] EIP: 0060:[<c011c287>] EFLAGS: 00010002 CPU: 7 [ 5538.091011] EIP is at __disable_runtime+0x1c7/0x1d0 [ 5538.091011] EAX: c9056eec EBX: 00000001 ECX: 00000008 EDX: 00006060 [ 5538.091011] ESI: 02faf080 EDI: 00000000 EBP: f6df7cd0 ESP: f6df7ca8 [ 5538.091011] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 5538.091011] Process sh (pid: 2819, ti=f6df6000 task=f6cbdc00 task.ti=f6df6000) [ 5538.091011] Stack: f68c8004 c9056eec f68c8000 c9056b98 00000008 5d353631 c04d0020 c9056b00 [ 5538.091011] c9056b00 c9056b00 f6df7cdc c011d151 c037dfc0 f6df7cec c011aedb f68c8000 [ 5538.091011] c04d2200 f6df7d04 c011f967 00000282 00000000 00000000 00000000 f6df7e48 [ 5538.091011] Call Trace: [ 5538.091011] [<c011d151>] ? rq_offline_rt+0x21/0x60 [ 5538.091011] [<c011aedb>] ? set_rq_offline+0x2b/0x50 [ 5538.091011] [<c011f967>] ? rq_attach_root+0xa7/0xb0 [ 5538.091011] [<c0120bbf>] ? cpu_attach_domain+0x30f/0x490 [ 5538.091011] [<c013dfc1>] ? sched_clock_cpu+0x121/0x170 [ 5538.091011] [<c011b56e>] ? update_curr+0x4e/0x80 [ 5538.091011] [<c013ca8f>] ? hrtimer_run_pending+0x1f/0x90 [ 5538.091011] [<c013c350>] ? enqueue_hrtimer+0x60/0x80 [ 5538.091011] [<c011bc47>] ? __enqueue_entity+0xc7/0x100 [ 5538.091011] [<c01223de>] ? partition_sched_domains+0x1ae/0x220 [ 5538.091011] [<c012008f>] ? wake_up_process+0xf/0x20 [ 5538.091011] [<c0122476>] ? update_sched_domains+0x26/0x40 [ 5538.091011] [<c0374907>] ? notifier_call_chain+0x37/0x80 [ 5538.091011] [<c013d379>] ? __raw_notifier_call_chain+0x19/0x20 [ 5538.091011] [<c013d39a>] ? raw_notifier_call_chain+0x1a/0x20 [ 5538.091011] [<c036e9cf>] ? _cpu_up+0xaf/0x100 [ 5538.091011] [<c037125e>] ? mutex_lock+0xe/0x20 [ 5538.091011] [<c036ea69>] ? cpu_up+0x49/0x70 [ 5538.091011] [<c03619d8>] ? store_online+0x58/0x80 [ 5538.091011] [<c0361980>] ? store_online+0x0/0x80 [ 5538.091011] [<c0266f1c>] ? sysdev_store+0x2c/0x40 [ 5538.091011] [<c01b728d>] ? sysfs_write_file+0x9d/0x100 [ 5538.091011] [<c0175129>] ? vfs_write+0x99/0x130 [ 5538.091011] [<c01b71f0>] ? sysfs_write_file+0x0/0x100 [ 5538.091011] [<c017566d>] ? sys_write+0x3d/0x70 [ 5538.091011] [<c010318e>] ? syscall_call+0x7/0xb [ 5538.091011] [<c0370000>] ? acpi_processor_start+0x630/0x63f [ 5538.091011] ======================= [ 5538.091011] Code: 87 72 ff ff ff 29 b3 4c 03 00 00 19 bb 50 03 00 00 31 f6 31 ff eb 9a 09 fe 0f 95 c0 0f b6 d8 8b 45 dc e8 6d 5f 25 00 85 db 74 a4 <0f> 0b eb fe 90 8d 74 26 00 55 89 d0 89 e5 83 ec 08 83 fa 16 89 [ 5538.091011] EIP: [<c011c287>] __disable_runtime+0x1c7/0x1d0 SS:ESP 0068:f6df7ca8 [ 5538.091011] ---[ end trace 5b3bf11f31634d39 ]---
Quoted 8 lines · Paul E. McKenney
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=yand run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
Is this a regression between 2.6.27-rc8 and -rc9, or did it crop up earlier?
- Steven
Quoted 4 lines · Steven Noonan
Quoted 2 lines · Paul E. McKenney
When I enable:
Quoted 8 lines
Quoted 6 lines
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=yand run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
Is this a regression between 2.6.27-rc8 and -rc9, or did it crop up earlier?
Hello, Steve!
Good question. I will run on older kernels.
Thanx, Paul
Quoted 10 lines · Paul E. McKenney
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=yand run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
On the off-chance that this is new news...
Hmm, yes. I thought I had all those fixed :-(
Quoted 11 lines
[ 5538.091011] kernel BUG at kernel/sched_rt.c:322! [ 5538.091011] invalid opcode: 0000 [#1] SMP [ 5538.091011] Modules linked in: [ 5538.091011] [ 5538.091011] Pid: 2819, comm: sh Not tainted (2.6.27-rc9-autokern1 #1) [ 5538.091011] EIP: 0060:[<c011c287>] EFLAGS: 00010002 CPU: 7 [ 5538.091011] EIP is at __disable_runtime+0x1c7/0x1d0 [ 5538.091011] EAX: c9056eec EBX: 00000001 ECX: 00000008 EDX: 00006060 [ 5538.091011] ESI: 02faf080 EDI: 00000000 EBP: f6df7cd0 ESP: f6df7ca8 [ 5538.091011] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 5538.091011] Process sh (pid: 2819, ti=f6df6000 task=f6cbdc00 task.ti=f6df6000)
Quoted 8 lines
[ 5538.091011] Stack: f68c8004 c9056eec f68c8000 c9056b98 00000008 5d353631 c04d0020 c9056b00 [ 5538.091011] c9056b00 c9056b00 f6df7cdc c011d151 c037dfc0 f6df7cec c011aedb f68c8000 [ 5538.091011] c04d2200 f6df7d04 c011f967 00000282 00000000 00000000 00000000 f6df7e48 [ 5538.091011] Call Trace: [ 5538.091011] [<c011d151>] ? rq_offline_rt+0x21/0x60 [ 5538.091011] [<c011aedb>] ? set_rq_offline+0x2b/0x50 [ 5538.091011] [<c011f967>] ? rq_attach_root+0xa7/0xb0 [ 5538.091011] [<c0120bbf>] ? cpu_attach_domain+0x30f/0x490
At the very least we're doing part of the offline process twice it seems, once through set_rq_offline()/set_rq_online() and once through disable_runtime()/enabled_runtime().
But seeing as we set an offlined cpu's runtime to RUNTIME_INF and skip cpus with RUNTIME_INF runtime that should be harmless.
Modifications to rt_rq->rt_runtime are all done while holding rt_b->rt_runtime_lock and rt_rq->rt_runtime_lock (do_balance_runtime() and __disable_runtime() and __enable_runtime()). Which means its enough to hold either of those locks in order to get a stable reading of the value.
Which leaves me puzzled for the moment...
tip/master has the following commit to clarify the code somewhat:
commit 78333cdd0e472180743d35988e576d6ecc6f6ddb
Author: Peter Zijlstra <[email protected]> Date: Tue Sep 23 15:33:43 2008 +0200
sched: add some comments to the bandwidth code
Hopefully clarify some of this code a little.
kernel/sched_rt.c +42 -0
@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP +/* +* We ran out of runtime, see if we can borrow some from our neighbours. +*/ static int do_balance_runtime (struct rt_rq *rt_rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);
@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)continue ;spin_lock (&iter->rt_runtime_lock); +/* +* Either all rqs have inf runtime and there's nothing to steal +* or __disable_runtime() below sets a specific rq to inf to +* indicate its been disabled and disalow stealing. +*/ if (iter->rt_runtime ==RUNTIME_INF ) goto next; +/* +* From runqueues with spare time, take 1/n part of their +* spare time, but no more than our period. +*/ diff = iter->rt_runtime - iter->rt_time;if (diff >0 ) { diff =div_u64 ((u64 )diff, weight);
@@ -274,6 +286,9 @@ next:return more; } +/* +* Ensure this RQ takes back all the runtime it lend to its neighbours. +*/ static void __disable_runtime (struct rq *rq) {struct root_domain *rd = rq->rd;
@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)spin_lock (&rt_b->rt_runtime_lock);spin_lock (&rt_rq->rt_runtime_lock); +/* +* Either we're all inf and nobody needs to borrow, or we're +* already disabled and thus have nothing to do, or we have +* exactly the right amount of runtime to take out. +*/ if (rt_rq->rt_runtime ==RUNTIME_INF || rt_rq->rt_runtime == rt_b->rt_runtime) goto balanced;spin_unlock (&rt_rq->rt_runtime_lock); +/* +* Calculate the difference between what we started out with +* and what we current have, that's the amount of runtime +* we lend and now have to reclaim. +*/ want = rt_b->rt_runtime - rt_rq->rt_runtime; +/* +* Greedy reclaim, take back as much as we can. +*/ for_each_cpu_mask (i, rd->span) {struct rt_rq *iter =sched_rt_period_rt_rq (rt_b, i);s64 diff; +/* +* Can't reclaim from ourselves or disabled runqueues. +*/ if (iter == rt_rq || iter->rt_runtime ==RUNTIME_INF )continue ;
@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq) }spin_lock (&rt_rq->rt_runtime_lock); +/* +* We cannot be left wanting - that would mean some runtime +* leaked out of the system. +*/ BUG_ON (want); balanced: +/* +* Disable all the borrow logic by pretending we have inf +* runtime - in which case borrowing doesn't make sense. +*/ rt_rq->rt_runtime =RUNTIME_INF ;spin_unlock (&rt_rq->rt_runtime_lock);spin_unlock (&rt_b->rt_runtime_lock);
@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)if (unlikely (!scheduler_running))return ; +/* +* Reset each runqueue's bandwidth settings +*/ for_each_leaf_rt_rq (rt_rq, rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);
Quoted 7 lines · Peter Zijlstra
Quoted 6 lines · Paul E. McKenney
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=y
Quoted 6 lines
Quoted 4 lines
and run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
On the off-chance that this is new news...
Hmm, yes. I thought I had all those fixed :-(
I know that feeling!!! ;-)
Quoted 20 lines
Quoted 11 lines
[ 5538.091011] kernel BUG at kernel/sched_rt.c:322! [ 5538.091011] invalid opcode: 0000 [#1] SMP [ 5538.091011] Modules linked in: [ 5538.091011] [ 5538.091011] Pid: 2819, comm: sh Not tainted (2.6.27-rc9-autokern1 #1) [ 5538.091011] EIP: 0060:[<c011c287>] EFLAGS: 00010002 CPU: 7 [ 5538.091011] EIP is at __disable_runtime+0x1c7/0x1d0 [ 5538.091011] EAX: c9056eec EBX: 00000001 ECX: 00000008 EDX: 00006060 [ 5538.091011] ESI: 02faf080 EDI: 00000000 EBP: f6df7cd0 ESP: f6df7ca8 [ 5538.091011] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 5538.091011] Process sh (pid: 2819, ti=f6df6000 task=f6cbdc00 task.ti=f6df6000)Quoted 8 lines
[ 5538.091011] Stack: f68c8004 c9056eec f68c8000 c9056b98 00000008 5d353631 c04d0020 c9056b00 [ 5538.091011] c9056b00 c9056b00 f6df7cdc c011d151 c037dfc0 f6df7cec c011aedb f68c8000 [ 5538.091011] c04d2200 f6df7d04 c011f967 00000282 00000000 00000000 00000000 f6df7e48 [ 5538.091011] Call Trace: [ 5538.091011] [<c011d151>] ? rq_offline_rt+0x21/0x60 [ 5538.091011] [<c011aedb>] ? set_rq_offline+0x2b/0x50 [ 5538.091011] [<c011f967>] ? rq_attach_root+0xa7/0xb0 [ 5538.091011] [<c0120bbf>] ? cpu_attach_domain+0x30f/0x490
Quoted 6 lines
At the very least we're doing part of the offline process twice it seems, once through set_rq_offline()/set_rq_online() and once through disable_runtime()/enabled_runtime().
But seeing as we set an offlined cpu's runtime to
RUNTIME_INFand skip cpus withRUNTIME_INFruntime that should be harmless.
Would double-processing a non-offlined CPU cause trouble, perhaps setting the runtime to a nonsensical value?
Quoted 7 lines
Modifications to
rt_rq->rt_runtimeare all done while holdingrt_b->rt_runtime_lockandrt_rq->rt_runtime_lock(do_balance_runtime()and__disable_runtime()and__enable_runtime()). Which means its enough to hold either of those locks in order to get a stable reading of the value.Which leaves me puzzled for the moment...
I know that feeling as well...
Quoted 19 lines
tip/master has the following commit to clarify the code somewhat:
commit
78333cdd0e472180743d35988e576d6ecc6f6ddbAuthor: Peter Zijlstra <[email protected]> Date: Tue Sep 23 15:33:43 2008 +0200sched: add some comments to the bandwidth code
Hopefully clarify some of this code a little.
Signed-off-by Peter Zijlstra <[email protected]>Signed-off-by Ingo Molnar <[email protected]>kernel/sched_rt.c +0
-0
kernel/sched_rt.c static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) · line 236
Quoted 6 lines
kernel/sched_rt.c +3
-0@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP +/* +* We ran out of runtime, see if we can borrow some from our neighbours. +*/
Suppose that all CPUs nearby have run out of runtime. Or is that possible?
Thanx, Paul
Quoted 96 lines
kernel/sched_rt.c +39
-0static int do_balance_runtime (struct rt_rq *rt_rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)continue ;spin_lock (&iter->rt_runtime_lock); +/* +* Either all rqs have inf runtime and there's nothing to steal +* or __disable_runtime() below sets a specific rq to inf to +* indicate its been disabled and disalow stealing. +*/ if (iter->rt_runtime ==RUNTIME_INF ) goto next; +/* +* From runqueues with spare time, take 1/n part of their +* spare time, but no more than our period. +*/ diff = iter->rt_runtime - iter->rt_time;if (diff >0 ) { diff =div_u64 ((u64 )diff, weight);@@ -274,6 +286,9 @@ next:return more; } +/* +* Ensure this RQ takes back all the runtime it lend to its neighbours. +*/ static void __disable_runtime (struct rq *rq) {struct root_domain *rd = rq->rd;@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)spin_lock (&rt_b->rt_runtime_lock);spin_lock (&rt_rq->rt_runtime_lock); +/* +* Either we're all inf and nobody needs to borrow, or we're +* already disabled and thus have nothing to do, or we have +* exactly the right amount of runtime to take out. +*/ if (rt_rq->rt_runtime ==RUNTIME_INF || rt_rq->rt_runtime == rt_b->rt_runtime) goto balanced;spin_unlock (&rt_rq->rt_runtime_lock); +/* +* Calculate the difference between what we started out with +* and what we current have, that's the amount of runtime +* we lend and now have to reclaim. +*/ want = rt_b->rt_runtime - rt_rq->rt_runtime; +/* +* Greedy reclaim, take back as much as we can. +*/ for_each_cpu_mask (i, rd->span) {struct rt_rq *iter =sched_rt_period_rt_rq (rt_b, i);s64 diff; +/* +* Can't reclaim from ourselves or disabled runqueues. +*/ if (iter == rt_rq || iter->rt_runtime ==RUNTIME_INF )continue ;@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq) }spin_lock (&rt_rq->rt_runtime_lock); +/* +* We cannot be left wanting - that would mean some runtime +* leaked out of the system. +*/ BUG_ON (want); balanced: +/* +* Disable all the borrow logic by pretending we have inf +* runtime - in which case borrowing doesn't make sense. +*/ rt_rq->rt_runtime =RUNTIME_INF ;spin_unlock (&rt_rq->rt_runtime_lock);spin_unlock (&rt_b->rt_runtime_lock);@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)if (unlikely (!scheduler_running))return ; +/* +* Reset each runqueue's bandwidth settings +*/ for_each_leaf_rt_rq (rt_rq, rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);
Quoted 10 lines · Paul E. McKenney
Quoted 9 lines · Peter Zijlstra
Quoted 8 lines · Paul E. McKenney
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=yand run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
Paul,
Wuld you like to share your scipt? I tested cpu hotplug on my 8-core machine by unplug cpu 2~5 and plug them in a loop for one night and didn't trigger the issue.
Did you set CONFIG_RT_GROUP_SCHED=y?
Quoted 31 lines
Quoted 4 lines
Quoted 2 lines
On the off-chance that this is new news...
Hmm, yes. I thought I had all those fixed :-(
I know that feeling!!! ;-)
Quoted 24 lines
Quoted 11 lines
[ 5538.091011] kernel BUG at kernel/sched_rt.c:322! [ 5538.091011] invalid opcode: 0000 [#1] SMP [ 5538.091011] Modules linked in: [ 5538.091011] [ 5538.091011] Pid: 2819, comm: sh Not tainted (2.6.27-rc9-autokern1 #1) [ 5538.091011] EIP: 0060:[<c011c287>] EFLAGS: 00010002 CPU: 7 [ 5538.091011] EIP is at __disable_runtime+0x1c7/0x1d0 [ 5538.091011] EAX: c9056eec EBX: 00000001 ECX: 00000008 EDX: 00006060 [ 5538.091011] ESI: 02faf080 EDI: 00000000 EBP: f6df7cd0 ESP: f6df7ca8 [ 5538.091011] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 5538.091011] Process sh (pid: 2819, ti=f6df6000 task=f6cbdc00 task.ti=f6df6000)Quoted 8 lines
[ 5538.091011] Stack: f68c8004 c9056eec f68c8000 c9056b98 00000008 5d353631 c04d0020 c9056b00 [ 5538.091011] c9056b00 c9056b00 f6df7cdc c011d151 c037dfc0 f6df7cec c011aedb f68c8000 [ 5538.091011] c04d2200 f6df7d04 c011f967 00000282 00000000 00000000 00000000 f6df7e48 [ 5538.091011] Call Trace: [ 5538.091011] [<c011d151>] ? rq_offline_rt+0x21/0x60 [ 5538.091011] [<c011aedb>] ? set_rq_offline+0x2b/0x50 [ 5538.091011] [<c011f967>] ? rq_attach_root+0xa7/0xb0 [ 5538.091011] [<c0120bbf>] ? cpu_attach_domain+0x30f/0x490At the very least we're doing part of the offline process twice it seems, once through set_rq_offline()/set_rq_online() and once through disable_runtime()/enabled_runtime().
Quoted 11 lines
Quoted 2 lines
But seeing as we set an offlined cpu's runtime to
RUNTIME_INFand skip cpus withRUNTIME_INFruntime that should be harmless.Would double-processing a non-offlined CPU cause trouble, perhaps setting the runtime to a nonsensical value?
Quoted 5 lines
Modifications to
rt_rq->rt_runtimeare all done while holdingrt_b->rt_runtime_lockandrt_rq->rt_runtime_lock(do_balance_runtime()and__disable_runtime()and__enable_runtime()). Which means its enough to hold either of those locks in order to get a stable reading of the value.
These locks, especially rt_b->rt_runtime_lock, prevent the simultaneous changing of rt_runtime. It looks codes are ok.
Anything related to RCU?
Quoted 128 lines
Quoted 2 lines
Which leaves me puzzled for the moment...
I know that feeling as well...
Quoted 19 lines
tip/master has the following commit to clarify the code somewhat:
commit
78333cdd0e472180743d35988e576d6ecc6f6ddbAuthor: Peter Zijlstra <[email protected]> Date: Tue Sep 23 15:33:43 2008 +0200sched: add some comments to the bandwidth code
Hopefully clarify some of this code a little.
Signed-off-by Peter Zijlstra <[email protected]>Signed-off-by Ingo Molnar <[email protected]>kernel/sched_rt.c +0
-0kernel/sched_rt.c static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) · line 236
Quoted 6 lines
kernel/sched_rt.c +3
-0@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP +/* +* We ran out of runtime, see if we can borrow some from our neighbours. +*/ Suppose that all CPUs nearby have run out of runtime. Or is that possible?
Thanx, Paul
Quoted 92 lines
kernel/sched_rt.c +39
-0static int do_balance_runtime (struct rt_rq *rt_rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)continue ;spin_lock (&iter->rt_runtime_lock); +/* +* Either all rqs have inf runtime and there's nothing to steal +* or __disable_runtime() below sets a specific rq to inf to +* indicate its been disabled and disalow stealing. +*/ if (iter->rt_runtime ==RUNTIME_INF ) goto next; +/* +* From runqueues with spare time, take 1/n part of their +* spare time, but no more than our period. +*/ diff = iter->rt_runtime - iter->rt_time;if (diff >0 ) { diff =div_u64 ((u64 )diff, weight);@@ -274,6 +286,9 @@ next:return more; } +/* +* Ensure this RQ takes back all the runtime it lend to its neighbours. +*/ static void __disable_runtime (struct rq *rq) {struct root_domain *rd = rq->rd;@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)spin_lock (&rt_b->rt_runtime_lock);spin_lock (&rt_rq->rt_runtime_lock); +/* +* Either we're all inf and nobody needs to borrow, or we're +* already disabled and thus have nothing to do, or we have +* exactly the right amount of runtime to take out. +*/ if (rt_rq->rt_runtime ==RUNTIME_INF || rt_rq->rt_runtime == rt_b->rt_runtime) goto balanced;spin_unlock (&rt_rq->rt_runtime_lock); +/* +* Calculate the difference between what we started out with +* and what we current have, that's the amount of runtime +* we lend and now have to reclaim. +*/ want = rt_b->rt_runtime - rt_rq->rt_runtime; +/* +* Greedy reclaim, take back as much as we can. +*/ for_each_cpu_mask (i, rd->span) {struct rt_rq *iter =sched_rt_period_rt_rq (rt_b, i);s64 diff; +/* +* Can't reclaim from ourselves or disabled runqueues. +*/ if (iter == rt_rq || iter->rt_runtime ==RUNTIME_INF )continue ;@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq) }spin_lock (&rt_rq->rt_runtime_lock); +/* +* We cannot be left wanting - that would mean some runtime +* leaked out of the system. +*/ BUG_ON (want); balanced: +/* +* Disable all the borrow logic by pretending we have inf +* runtime - in which case borrowing doesn't make sense. +*/ rt_rq->rt_runtime =RUNTIME_INF ;spin_unlock (&rt_rq->rt_runtime_lock);spin_unlock (&rt_b->rt_runtime_lock);@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)if (unlikely (!scheduler_running))return ; +/* +* Reset each runqueue's bandwidth settings +*/ for_each_leaf_rt_rq (rt_rq, rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);
Quoted 10 lines · Yanmin
Quoted 8 lines · Paul E. McKenney
Quoted 7 lines · Peter Zijlstra
Quoted 6 lines · Paul E. McKenney
When I enable:
CONFIG_GROUP_SCHED=y
CONFIG_FAIR_GROUP_SCHED=y
CONFIG_USER_SCHED=y
Quoted 6 lines
Quoted 2 lines
Quoted 2 lines
Quoted 2 lines
and run a bash script onlining and offlining CPUs in an infinite loop on x86 using 2.6.27-rc9, after about 1.5 hours I get the following.
Paul,
Wuld you like to share your scipt? I tested cpu hotplug on my 8-core machine by unplug cpu 2~5 and plug them in a loop for one night and didn't trigger the issue.
See attached! I hand-edit the loop for the machine at hand, so on an 8-CPU x86 machine I would use "for ((i = 1; i < 8; i++))", given that x86 machines tend not to allow you to offline CPU 0.
Quoted 1 line
Did you set
CONFIG_RT_GROUP_SCHED=y?
No, I did not.
Thanx, Paul
Quoted 176 lines
Quoted 30 lines
Quoted 3 lines
Quoted 1 line
On the off-chance that this is new news...
Hmm, yes. I thought I had all those fixed :-(
I know that feeling!!! ;-)
Quoted 24 lines
Quoted 11 lines
[ 5538.091011] kernel BUG at kernel/sched_rt.c:322! [ 5538.091011] invalid opcode: 0000 [#1] SMP [ 5538.091011] Modules linked in: [ 5538.091011] [ 5538.091011] Pid: 2819, comm: sh Not tainted (2.6.27-rc9-autokern1 #1) [ 5538.091011] EIP: 0060:[<c011c287>] EFLAGS: 00010002 CPU: 7 [ 5538.091011] EIP is at __disable_runtime+0x1c7/0x1d0 [ 5538.091011] EAX: c9056eec EBX: 00000001 ECX: 00000008 EDX: 00006060 [ 5538.091011] ESI: 02faf080 EDI: 00000000 EBP: f6df7cd0 ESP: f6df7ca8 [ 5538.091011] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 [ 5538.091011] Process sh (pid: 2819, ti=f6df6000 task=f6cbdc00 task.ti=f6df6000)Quoted 8 lines
[ 5538.091011] Stack: f68c8004 c9056eec f68c8000 c9056b98 00000008 5d353631 c04d0020 c9056b00 [ 5538.091011] c9056b00 c9056b00 f6df7cdc c011d151 c037dfc0 f6df7cec c011aedb f68c8000 [ 5538.091011] c04d2200 f6df7d04 c011f967 00000282 00000000 00000000 00000000 f6df7e48 [ 5538.091011] Call Trace: [ 5538.091011] [<c011d151>] ? rq_offline_rt+0x21/0x60 [ 5538.091011] [<c011aedb>] ? set_rq_offline+0x2b/0x50 [ 5538.091011] [<c011f967>] ? rq_attach_root+0xa7/0xb0 [ 5538.091011] [<c0120bbf>] ? cpu_attach_domain+0x30f/0x490At the very least we're doing part of the offline process twice it seems, once through set_rq_offline()/set_rq_online() and once through disable_runtime()/enabled_runtime().
Quoted 11 lines
Quoted 2 lines
But seeing as we set an offlined cpu's runtime to
RUNTIME_INFand skip cpus withRUNTIME_INFruntime that should be harmless.Would double-processing a non-offlined CPU cause trouble, perhaps setting the runtime to a nonsensical value?
Quoted 5 lines
Modifications to
rt_rq->rt_runtimeare all done while holdingrt_b->rt_runtime_lockandrt_rq->rt_runtime_lock(do_balance_runtime()and__disable_runtime()and__enable_runtime()). Which means its enough to hold either of those locks in order to get a stable reading of the value.These locks, especially rt_b->rt_runtime_lock, prevent the simultaneous changing of rt_runtime. It looks codes are ok.
Anything related to RCU?
Quoted 128 lines
Quoted 2 lines
Which leaves me puzzled for the moment...
I know that feeling as well...
Quoted 19 lines
tip/master has the following commit to clarify the code somewhat:
commit
78333cdd0e472180743d35988e576d6ecc6f6ddbAuthor: Peter Zijlstra <[email protected]> Date: Tue Sep 23 15:33:43 2008 +0200sched: add some comments to the bandwidth code
Hopefully clarify some of this code a little.
Signed-off-by Peter Zijlstra <[email protected]>Signed-off-by Ingo Molnar <[email protected]>kernel/sched_rt.c +0
-0kernel/sched_rt.c static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) · line 236
Quoted 6 lines
kernel/sched_rt.c +3
-0@@ -231,6 +231,9 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP +/* +* We ran out of runtime, see if we can borrow some from our neighbours. +*/ Suppose that all CPUs nearby have run out of runtime. Or is that possible?
Thanx, Paul
Quoted 92 lines
kernel/sched_rt.c +39
-0static int do_balance_runtime (struct rt_rq *rt_rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);@@ -250,9 +253,18 @@ static int do_balance_runtime(struct rt_rq *rt_rq)continue ;spin_lock (&iter->rt_runtime_lock); +/* +* Either all rqs have inf runtime and there's nothing to steal +* or __disable_runtime() below sets a specific rq to inf to +* indicate its been disabled and disalow stealing. +*/ if (iter->rt_runtime ==RUNTIME_INF ) goto next; +/* +* From runqueues with spare time, take 1/n part of their +* spare time, but no more than our period. +*/ diff = iter->rt_runtime - iter->rt_time;if (diff >0 ) { diff =div_u64 ((u64 )diff, weight);@@ -274,6 +286,9 @@ next:return more; } +/* +* Ensure this RQ takes back all the runtime it lend to its neighbours. +*/ static void __disable_runtime (struct rq *rq) {struct root_domain *rd = rq->rd;@@ -289,17 +304,33 @@ static void __disable_runtime(struct rq *rq)spin_lock (&rt_b->rt_runtime_lock);spin_lock (&rt_rq->rt_runtime_lock); +/* +* Either we're all inf and nobody needs to borrow, or we're +* already disabled and thus have nothing to do, or we have +* exactly the right amount of runtime to take out. +*/ if (rt_rq->rt_runtime ==RUNTIME_INF || rt_rq->rt_runtime == rt_b->rt_runtime) goto balanced;spin_unlock (&rt_rq->rt_runtime_lock); +/* +* Calculate the difference between what we started out with +* and what we current have, that's the amount of runtime +* we lend and now have to reclaim. +*/ want = rt_b->rt_runtime - rt_rq->rt_runtime; +/* +* Greedy reclaim, take back as much as we can. +*/ for_each_cpu_mask (i, rd->span) {struct rt_rq *iter =sched_rt_period_rt_rq (rt_b, i);s64 diff; +/* +* Can't reclaim from ourselves or disabled runqueues. +*/ if (iter == rt_rq || iter->rt_runtime ==RUNTIME_INF )continue ;@@ -319,8 +350,16 @@ static void __disable_runtime(struct rq *rq) }spin_lock (&rt_rq->rt_runtime_lock); +/* +* We cannot be left wanting - that would mean some runtime +* leaked out of the system. +*/ BUG_ON (want); balanced: +/* +* Disable all the borrow logic by pretending we have inf +* runtime - in which case borrowing doesn't make sense. +*/ rt_rq->rt_runtime =RUNTIME_INF ;spin_unlock (&rt_rq->rt_runtime_lock);spin_unlock (&rt_b->rt_runtime_lock);@@ -343,6 +382,9 @@ static void __enable_runtime(struct rq *rq)if (unlikely (!scheduler_running))return ; +/* +* Reset each runqueue's bandwidth settings +*/ for_each_leaf_rt_rq (rt_rq, rq) {struct rt_bandwidth *rt_b =sched_rt_bandwidth (rt_rq);