From: Dave Anderson <anderson@xxxxxxxxxx>
Subject: Re: [PATCH] runq: search current task's runqueue explicitly
Date: Thu, 05 Jan 2012 15:32:12 -0500 (EST)
>
>
> ----- Original Message -----
>> Currently, runq sub-command doesn't consider CFS runqueue's current
>> task removed from CFS runqueue. Due to this, the remaining CFS
>> runqueus that follow the current task's is not displayed. This patch
>> fixes this by making runq sub-command search current task's runqueue
>> explicitly.
>>
>> Note that CFS runqueue exists for each task group, and so does CFS
>> runqueue's current task, and the above search needs to be done
>> recursively.
>>
>> Test
>> ====
>>
>> On vmcore I made 7 task groups:
>>
>> root group --- A --- AA --- AAA
>> + +- AAB
>> |
>> +- AB --- ABA
>> +- ABB
>>
>> and then I ran three CPU bound tasks, which is exactly the same as
>>
>> int main(void) { for (;;) continue; return 0; }
>>
>> for each task group, including root group; so total 24 tasks. For
>> readability, I annotated each task name with its belonging group name.
>> For example, loop.ABA belongs to task group ABA.
>>
>> Look at CPU0 collumn below. [before] lacks 8 tasks and [after]
>> successfully shows all tasks on the runqueue, which is identical to
>> the result of [sched debug] that is expected to ouput correct result.
>>
>> I'll send this vmcore later.
>>
>> [before]
>>
>> crash> runq | cat
>> CPU 0 RUNQUEUE: ffff88000a215f80
>> CURRENT: PID: 28263 TASK: ffff880037aaa040 COMMAND: "loop.ABA"
>> RT PRIO_ARRAY: ffff88000a216098
>> [no tasks queued]
>> CFS RB_ROOT: ffff88000a216010
>> [120] PID: 28262 TASK: ffff880037cc40c0 COMMAND: "loop.ABA"
>>
>> <cut>
>>
>> [after]
>>
>> crash_fix> runq
>> CPU 0 RUNQUEUE: ffff88000a215f80
>> CURRENT: PID: 28263 TASK: ffff880037aaa040 COMMAND: "loop.ABA"
>> RT PRIO_ARRAY: ffff88000a216098
>> [no tasks queued]
>> CFS RB_ROOT: ffff88000a216010
>> [120] PID: 28262 TASK: ffff880037cc40c0 COMMAND: "loop.ABA"
>> [120] PID: 28271 TASK: ffff8800787a8b40 COMMAND: "loop.ABB"
>> [120] PID: 28272 TASK: ffff880037afd580 COMMAND: "loop.ABB"
>> [120] PID: 28245 TASK: ffff8800785e8b00 COMMAND: "loop.AB"
>> [120] PID: 28246 TASK: ffff880078628ac0 COMMAND: "loop.AB"
>> [120] PID: 28241 TASK: ffff880078616b40 COMMAND: "loop.AA"
>> [120] PID: 28239 TASK: ffff8800785774c0 COMMAND: "loop.AA"
>> [120] PID: 28240 TASK: ffff880078617580 COMMAND: "loop.AA"
>> [120] PID: 28232 TASK: ffff880079b5d4c0 COMMAND: "loop.A"
>> <cut>
>>
>> [sched debug]
>>
>> crash> runq -d
>> CPU 0
>> [120] PID: 28232 TASK: ffff880079b5d4c0 COMMAND: "loop.A"
>> [120] PID: 28239 TASK: ffff8800785774c0 COMMAND: "loop.AA"
>> [120] PID: 28240 TASK: ffff880078617580 COMMAND: "loop.AA"
>> [120] PID: 28241 TASK: ffff880078616b40 COMMAND: "loop.AA"
>> [120] PID: 28245 TASK: ffff8800785e8b00 COMMAND: "loop.AB"
>> [120] PID: 28246 TASK: ffff880078628ac0 COMMAND: "loop.AB"
>> [120] PID: 28262 TASK: ffff880037cc40c0 COMMAND: "loop.ABA"
>> [120] PID: 28263 TASK: ffff880037aaa040 COMMAND: "loop.ABA"
>> [120] PID: 28271 TASK: ffff8800787a8b40 COMMAND: "loop.ABB"
>> [120] PID: 28272 TASK: ffff880037afd580 COMMAND: "loop.ABB"
>> <cut>
>>
>> Diff stat
>> =========
>>
>> defs.h | 1 +
>> task.c | 37 +++++++++++++++++--------------------
>> 2 files changed, 18 insertions(+), 20 deletions(-)
>>
>> Thanks.
>> HATAYAMA, Daisuke
>
> Hello Daisuke,
>
> Good catch! Plus your re-worked patch cleans things up nicely.
>
> And "runq -d" paid off quickly, didn't it? ;-)
>
> One minor problem, while testing your patch on a variety of kernels,
> several "runq" commands failed because the test kernels were
> not configured with CONFIG_FAIR_GROUP_SCHED:
>
> struct sched_entity {
> struct load_weight load; /* for load-balancing */
> struct rb_node run_node;
> struct list_head group_node;
> unsigned int on_rq;
>
> u64 exec_start;
> u64 sum_exec_runtime;
> u64 vruntime;
> u64 prev_sum_exec_runtime;
>
> u64 nr_migrations;
>
> #ifdef CONFIG_SCHEDSTATS
> struct sched_statistics statistics;
> #endif
>
> #ifdef CONFIG_FAIR_GROUP_SCHED
> struct sched_entity *parent;
> /* rq on which this entity is (to be) queued: */
> struct cfs_rq *cfs_rq;
> /* rq "owned" by this entity/group: */
> struct cfs_rq *my_q;
> #endif
> };
>
> so they failed like so:
>
> CPU 0 RUNQUEUE: ffffffff825f7520
> CURRENT: PID: 3790 TASK: ffff88000c8f2cf0 COMMAND: "bash"
> RT PRIO_ARRAY: ffffffff825f75e8
> [no tasks queued]
> CFS RB_ROOT: ffffffff825f75a0
> runq: invalid structure member offset: sched_entity_my_q
> FILE: task.c LINE: 7035 FUNCTION: dump_tasks_in_cfs_rq()
>
> where line 7035 is where the first possible recursion is done:
>
> 7021 static int
> 7022 dump_tasks_in_cfs_rq(ulong cfs_rq)
> 7023 {
> 7024 struct task_context *tc;
> 7025 struct rb_root *root;
> 7026 struct rb_node *node;
> 7027 ulong my_q, leftmost, curr, curr_my_q;
> 7028 int total;
> 7029
> 7030 total = 0;
> 7031
> 7032 readmem(cfs_rq + OFFSET(cfs_rq_curr), KVADDR, &curr, sizeof(ulong),
> 7033 "curr", FAULT_ON_ERROR);
> 7034 if (curr) {
> 7035 readmem(curr + OFFSET(sched_entity_my_q), KVADDR, &curr_my_q,
> 7036 sizeof(ulong), "curr->my_q", FAULT_ON_ERROR);
> 7037 if (curr_my_q)
> 7038 total += dump_tasks_in_cfs_rq(curr_my_q);
> 7039 }
> 7040
> 7041 readmem(cfs_rq + OFFSET(cfs_rq_rb_leftmost), KVADDR, &leftmost,
> 7042 sizeof(ulong), "rb_leftmost", FAULT_ON_ERROR);
> 7043 root = (struct rb_root *)(cfs_rq + OFFSET(cfs_rq_tasks_timeline));
> 7044
> 7045 for (node = rb_first(root); leftmost && node; node = rb_next(node)) {
> 7046 if (VALID_MEMBER(sched_entity_my_q)) {
> 7047 readmem((ulong)node - OFFSET(sched_entity_run_node)
> 7048 + OFFSET(sched_entity_my_q), KVADDR, &my_q,
> 7049 sizeof(ulong), "my_q", FAULT_ON_ERROR);
> 7050 if (my_q) {
> 7051 total += dump_tasks_in_cfs_rq(my_q);
> 7052 continue;
> 7053 }
> 7054 }
>
> I fixed it by imposing a VALID_MEMBER(sched_entity_my_q) check, similar
> to what is done at the second recursive call at line 7046 above:
>
> if (VALID_MEMBER(sched_entity_my_q)) {
> readmem(cfs_rq + OFFSET(cfs_rq_curr), KVADDR, &curr,
> sizeof(ulong), "curr", FAULT_ON_ERROR);
> if (curr) {
> readmem(curr + OFFSET(sched_entity_my_q), KVADDR,
> &curr_my_q, sizeof(ulong), "curr->my_q",
> FAULT_ON_ERROR);
> if (curr_my_q)
> total += dump_tasks_in_cfs_rq(curr_my_q);
> }
> }
>
> and that worked OK.
>
> I also added "sched_entity_my_q" to dump_offset_table() for "help -o".
>
> If you are OK with the changes above, the patch is queued for crash-6.0.3.
>
I missed the case where fair scheduler is disabled.
I'm of course OK. Thanks for the fix.
Thanks.
HATAYAMA, Daisuke
--
Crash-utility mailing list
Crash-utility@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/crash-utility
