26 Jan, 2008
2 commits
-
Right now, the linux kernel (with scheduler statistics enabled) keeps track
of the maximum time a process is waiting to be scheduled. While the maximum
is a very useful metric, tracking average and total is equally useful
(at least for latencytop) to figure out the accumulated effect of scheduler
delays. The accumulated effect is important to judge the performance impact
of scheduler tuning/behavior.Signed-off-by: Arjan van de Ven
Signed-off-by: Ingo Molnar -
We monitor clock overflows, let's also monitor clock underflows.
Signed-off-by: Guillaume Chazarain
Signed-off-by: Ingo Molnar
31 Dec, 2007
1 commit
-
Meelis Roos reported these warnings on sparc64:
CC kernel/sched.o
In file included from kernel/sched.c:879:
kernel/sched_debug.c: In function 'nsec_high':
kernel/sched_debug.c:38: warning: comparison of distinct pointer types lacks a castthe debug check in do_div() is over-eager here, because the long long
is always positive in these places. Mark this by casting them to
unsigned long long.no change in code output:
text data bss dec hex filename
51471 6582 376 58429 e43d sched.o.before
51471 6582 376 58429 e43d sched.o.aftermd5:
7f7729c111f185bf3ccea4d542abc049 sched.o.before.asm
7f7729c111f185bf3ccea4d542abc049 sched.o.after.asmSigned-off-by: Ingo Molnar
28 Nov, 2007
1 commit
-
clean up overlong line in kernel/sched_debug.c.
Signed-off-by: Ingo Molnar
27 Nov, 2007
1 commit
-
bump version of kernel/sched_debug.c and remove CFS version
information from it.Signed-off-by: Ingo Molnar
10 Nov, 2007
1 commit
-
we lost the sched_min_granularity tunable to a clever optimization
that uses the sched_latency/min_granularity ratio - but the ratio
is quite unintuitive to users and can also crash the kernel if the
ratio is set to 0. So reintroduce the min_granularity tunable,
while keeping the ratio maintained internally.no functionality changed.
[ mingo@elte.hu: some fixlets. ]
Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar
25 Oct, 2007
1 commit
-
Lockdep noticed that this lock can also be taken from hardirq context, and can
thus not unconditionally disable/enable irqs.WARNING: at kernel/lockdep.c:2033 trace_hardirqs_on()
[show_trace_log_lvl+26/48] show_trace_log_lvl+0x1a/0x30
[show_trace+18/32] show_trace+0x12/0x20
[dump_stack+22/32] dump_stack+0x16/0x20
[trace_hardirqs_on+405/416] trace_hardirqs_on+0x195/0x1a0
[_read_unlock_irq+34/48] _read_unlock_irq+0x22/0x30
[sched_debug_show+2615/4224] sched_debug_show+0xa37/0x1080
[show_state_filter+326/368] show_state_filter+0x146/0x170
[sysrq_handle_showstate+10/16] sysrq_handle_showstate+0xa/0x10
[__handle_sysrq+123/288] __handle_sysrq+0x7b/0x120
[handle_sysrq+40/64] handle_sysrq+0x28/0x40
[kbd_event+1045/1680] kbd_event+0x415/0x690
[input_pass_event+206/208] input_pass_event+0xce/0xd0
[input_handle_event+170/928] input_handle_event+0xaa/0x3a0
[input_event+95/112] input_event+0x5f/0x70
[atkbd_interrupt+434/1456] atkbd_interrupt+0x1b2/0x5b0
[serio_interrupt+59/128] serio_interrupt+0x3b/0x80
[i8042_interrupt+263/576] i8042_interrupt+0x107/0x240
[handle_IRQ_event+40/96] handle_IRQ_event+0x28/0x60
[handle_edge_irq+175/320] handle_edge_irq+0xaf/0x140
[do_IRQ+64/128] do_IRQ+0x40/0x80
[common_interrupt+46/52] common_interrupt+0x2e/0x34Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar
19 Oct, 2007
1 commit
-
schedstat is useful in investigating CPU scheduler behavior. Ideally,
I think it is beneficial to have it on all the time. However, the
cost of turning it on in production system is quite high, largely due
to number of events it collects and also due to its large memory
footprint.Most of the fields probably don't need to be full 64-bit on 64-bit
arch. Rolling over 4 billion events will most like take a long time
and user space tool can be made to accommodate that. I'm proposing
kernel to cut back most of variable width on 64-bit system. (note,
the following patch doesn't affect 32-bit system).Signed-off-by: Ken Chen
Signed-off-by: Ingo Molnar
15 Oct, 2007
27 commits
-
In general, struct file_operations are const in the kernel, to not have
false cacheline sharing and to catch bugs at compiletime with accidental
writes to them. The new scheduler code introduces a new non-const one;
fix this up.Signed-off-by: Arjan van de Ven
Signed-off-by: Ingo Molnar -
add new migration statistics when SCHED_DEBUG and SCHEDSTATS
is enabled. Available in /proc//sched.Signed-off-by: Ingo Molnar
-
increase width of debug line - in preparation of more debugging info.
Signed-off-by: Ingo Molnar
-
Add tunables in sysfs to modify a user's cpu share.
A directory is created in sysfs for each new user in the system.
/sys/kernel/uids//cpu_share
Reading this file returns the cpu shares granted for the user.
Writing into this file modifies the cpu share for the user. Only an
administrator is allowed to modify a user's cpu share.Ex:
# cd /sys/kernel/uids/
# cat 512/cpu_share
1024
# echo 2048 > 512/cpu_share
# cat 512/cpu_share
2048
#Signed-off-by: Srivatsa Vaddagiri
Signed-off-by: Dhaval Giani
Signed-off-by: Ingo Molnar -
cleanup: rename task_grp to task_group. No need to save two characters
and 'grp' is annoying to read.Signed-off-by: Ingo Molnar
-
Fix coding style issues reported by Randy Dunlap and others
Signed-off-by: Dhaval Giani
Signed-off-by: Srivatsa Vaddagiri
Signed-off-by: Ingo Molnar
Reviewed-by: Thomas Gleixner -
speed up and simplify vslice calculations.
[ From: Mike Galbraith : build fix ]
Signed-off-by: Peter Zijlstra
Signed-off-by: Ingo Molnar -
rename all 'cnt' fields and variables to the less yucky 'count' name.
yuckage noticed by Andrew Morton.
no change in code, other than the /proc/sched_debug bkl_count string got
a bit larger:text data bss dec hex filename
38236 3506 24 41766 a326 sched.o.before
38240 3506 24 41770 a32a sched.o.afterSigned-off-by: Ingo Molnar
Reviewed-by: Thomas Gleixner -
debug feature: check how well we schedule within a reasonable
vruntime 'spread' range. (note that CPU overload can increase
the spread, so this is not a hard condition, but normal loads
should be within the spread.)Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra -
more width for parameter printouts in /proc/sched_debug.
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
print the current value of all tunables in /proc/sched_debug output.
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
build fix for the SCHED_DEBUG && !SCHEDSTATS case.
Signed-off-by: S.Ceglar Onur
Signed-off-by: Ingo Molnar
Reviewed-by: Thomas Gleixner -
add per task and per rq BKL usage statistics.
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
Enable user-id based fair group scheduling. This is useful for anyone
who wants to test the group scheduler w/o having to enable
CONFIG_CGROUPS.A separate scheduling group (i.e struct task_grp) is automatically created for
every new user added to the system. Upon uid change for a task, it is made to
move to the corresponding scheduling group.A /proc tunable (/proc/root_user_share) is also provided to tune root
user's quota of cpu bandwidth.Signed-off-by: Srivatsa Vaddagiri
Signed-off-by: Dhaval Giani
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
- print nr_running and load information for cfs_rq in /proc/sched_debug
Signed-off-by: Srivatsa Vaddagiri
Signed-off-by: Dhaval Giani
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
fix formatting of /proc/sched_debug
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
enhance debug output by changing 12345678 nsecs to 12.345678 output,
this is more human-readable.Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
print the correct amount of dashes in /proc/sched_debug.
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
Get rid of 'sched_entity::fair_key'.
As a side effect, 'current' is not kept withing the tree for
SCHED_NORMAL/BATCH tasks anymore. This simplifies some parts of code
(e.g. entity_tick() and yield_task_fair()) and also somewhat optimizes
them (e.g. a single update_curr() now vs. dequeue/enqueue() before in
entity_tick()).Signed-off-by: Dmitry Adamushko
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
remove wait_runtime based fields and features, now that the CFS
math has been changed over to the vruntime metric.Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner -
remove the wait_runtime-limit fields and the code depending on it, now
that the math has been changed over to rely on the vruntime metric.Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner -
'struct load_stat' is redundant now so let's get rid of it.
Signed-off-by: Dmitry Adamushko
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner -
add more vruntime statistics.
Signed-off-by: Ingo Molnar
Signed-off-by: Mike Galbraith
Signed-off-by: Peter Zijlstra
Reviewed-by: Thomas Gleixner -
debug se->vruntime fields.
Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith -
CPU load calculations are statistical anyway, and there's little benefit
from having it calculated on every scheduling event. So remove this code,
it gets rid of a divide from the scheduler wakeup and context-switch
fastpath.Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner -
track the maximum amount of time a task has executed while
the CPU load was at least 2x. (i.e. at least two nice-0
tasks were runnable)Signed-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner -
small kernel/sched_debug.c cleanup - break up
multi-variable assignment.no code changed:
text data bss dec hex filename
38869 3550 24 42443 a5cb sched.o.before
38869 3550 24 42443 a5cb sched.o.afterSigned-off-by: Ingo Molnar
Signed-off-by: Peter Zijlstra
Signed-off-by: Mike Galbraith
Reviewed-by: Thomas Gleixner
05 Sep, 2007
1 commit
-
when cleaning sched-stats also clear prev_sum_exec_runtime.
Signed-off-by: Ingo Molnar
23 Aug, 2007
1 commit
-
construct a more or less wall-clock time out of sched_clock(), by
using ACPI-idle's existing knowledge about how much time we spent
idling. This allows the rq clock to work around TSC-stops-in-C2,
TSC-gets-corrupted-in-C3 type of problems.( Besides the scheduler's statistics this also benefits blktrace and
printk-timestamps as well. )Furthermore, the precise before-C2/C3-sleep and after-C2/C3-wakeup
callbacks allow the scheduler to get out the most of the period where
the CPU has a reliable TSC. This results in slightly more precise
task statistics.the ACPI bits were acked by Len.
Signed-off-by: Ingo Molnar
Acked-by: Len Brown
11 Aug, 2007
1 commit
-
Arjan van de Ven pointed out that we should not print kernel addresses
in world-readable /proc files - fix that.Signed-off-by: Ingo Molnar
Signed-off-by: Arjan van de Ven
09 Aug, 2007
2 commits
-
remove the 'u64 now' parameter from sched_debug.c:print_task()/_rq().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar
-
remove the 'u64 now' parameter from print_cfs_rq().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar