Currently UBI has one small flaw - when we read EC or VID header, but find only
0xFF bytes, we return UBI_IO_FF and do not report whether we had bit-flips or
not. In case of the VID header, the scanning code adds this PEB to the free list,
even though there were bit-flips.
Imagine the following situation: we start writing VID header to a PEB and have a
power cut, so the PEB becomes unstable. When we scan and read the PEB, we get
a bit-flip. Currently, UBI would just ignore this and treat the PEB as free. This
patch changes UBI behavior and now UBI will schedule this PEB for erasure.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
The 'UBI_IO_PEB_EMPTY' and 'UBI_IO_PEB_FREE' are essentially the same
and mean that there are only 0xFF bytes instead of headers. Simplify
UBI a little by turning them into a single 'UBI_IO_FF' error code.
Also, stop maintaining commentaries in 'ubi_io_read_vid_hdr()' which are
almost identical to commentaries in 'ubi_io_read_ec_hdr()'.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Rename UBI_IO_BAD_HDR_READ into UBI_IO_BAD_HDR_EBADMSG which is presumably more
self-documenting and readable. Indeed, the '_READ' suffix does not tell much and
even confuses, while '_EBADMSG' tells about uncorrectable ECC error, because we
use -EBADMSG all over the place to represent ECC errors.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Cleanup the Kconfig for UBI by using menuconfig to enable/disable the entire
driver. Remove the dependency checks for MTD_UBI and MTD_UBI_DEBUG by
wrapping the options in if/endif blocks and remove any redundant checks.
Remove all default n since that is the Kconfig default. Change menu "Additional
UBI debugging messages" into a comment to remove one menu level.
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Remove a couple of pointless header file includes.
Fixes a compile bug caused by header file include dependencies with
"irq: Add tracepoint to softirq_raise" within linux-next.
Reported-by: Sachin Sant <sachinp@in.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[ cherry-picked from the s390 tree to fix "2bf2160: irq: Add tracepoint to softirq_raise" ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ugly #include dependencies. We need to have local_softirq_pending()
defined before it gets used in <linux/interrupt.h>. But <asm/hardirq.h>
provides the definition *after* this #include chain:
<linux/irq.h>
<asm/irq.h>
<asm/hw_irq.h>
<linux/interrupt.h>
Signed-off-by: Tony Luck <tony.luck@intel.com>
[ cherry-picked from the ia64 tree to fix "2bf2160: irq: Add tracepoint to softirq_raise" ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
futex_wait() is leaking key references due to futex_wait_setup()
acquiring an additional reference via the queue_lock() routine. The
nested key ref-counting has been masking bugs and complicating code
analysis. queue_lock() is only called with a previously ref-counted
key, so remove the additional ref-counting from the queue_(un)lock()
functions.
Also futex_wait_requeue_pi() drops one key reference too many in
unqueue_me_pi(). Remove the key reference handling from
unqueue_me_pi(). This was paired with a queue_lock() in
futex_lock_pi(), so the count remains unchanged.
Document remaining nested key ref-counting sites.
Signed-off-by: Darren Hart <dvhart@linux.intel.com>
Reported-and-tested-by: Matthieu Fertré<matthieu.fertre@kerlabs.com>
Reported-by: Louis Rilling<louis.rilling@kerlabs.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <4CBB17A8.70401@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
The dabusb device driver is sufficiently serialized using
its own mutex, no need for the big kernel lock here
in addition.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
The sunrpc cache_ioctl function does not need the big kernel lock
because it uses its own queue_lock already.
rpc_pipe_ioctl apparently should be using i_lock like the other
operations on the pipe file descriptor do.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
According to commit 5e3d20a68f
(init: Remove the BKL from startup code) these sparse notations
should be removed also.
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
According to Jens, this code does not need the BKL at all,
it is sufficiently serialized by bd_mutex.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jens Axboe <jaxboe@fusionio.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
The big kernel lock is going away, so make sure
that if it is disabled by Kconfig, we do not
try to validate it, which would result in
compile errors.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
The dvb core only uses the big kernel lock in the open
and ioctl functions, which means it can be replaced with
a dvb specific mutex. Fortunately, all the ioctl functions
go through dvb_usercopy, so we can move the serialization
in there.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
Cc: linux-media@vger.kernel.org
The bt8xx driver only uses the big kernel lock in its dst_ca_ioctl
function and never to serialize against other code, so we can
trivially replace it with a private mutex.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: linux-media@vger.kernel.org
Cc: Mauro Carvalho Chehab <mchehab@infradead.org>
This driver already has a global mutex, so let's just
use that in the open function instead of the BKL.
It may not even be needed there, but this patch should
have the smallest impact.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Mark Gross <mark.gross@intel.com>
RAW_SETBIND and RAW_GETBIND 32bit versions are fscked in interesting ways.
1) fs/compat_ioctl.c has COMPATIBLE_IOCTL(RAW_SETBIND) followed by
HANDLE_IOCTL(RAW_SETBIND, raw_ioctl). The latter is ignored.
2) on amd64 (and itanic) the damn thing is broken - we have int + u64 + u64
and layouts on i386 and amd64 are _not_ the same. raw_ioctl() would
work there, but it's never called due to (1). As it is, i386 /sbin/raw
definitely doesn't work on amd64 boxen.
3) switching to raw_ioctl() as is would *not* work on e.g. sparc64 and ppc64,
which would be rather sad, seeing that normal userland there is 32bit.
The thing is, slapping __packed on the struct in question does not DTRT -
it eliminates *all* padding. The real solution is to use compat_u64.
4) of course, all that stuff has no business being outside of raw.c in the
first place - there should be ->compat_ioctl() for /dev/rawctl instead of
messing with compat_ioctl.c.
[akpm@linux-foundation.org: coding-style fixes]
[arnd@arndb.de: port to 2.6.36]
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Three uml device drivers still use the big kernel lock,
but all of them can be safely converted to using
a per-driver mutex instead. Most likely this is not
even necessary, so after further review these can
and should be removed as well.
The exec system call no longer requires the BKL either,
so remove it from there, too.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: user-mode-linux-devel@lists.sourceforge.net
cciss: fix PCI IDs for new controllers
This patch fixes the botched up PCI IDs of new controllers. Please consider
this patch for inclusion.
Signed-off-by: Mike Miller <mike.miller@hp.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
On a system that support intr-rempping when booting with "intremap=off"
[ 177.895501] BUG: unable to handle kernel NULL pointer dereference at 00000000000000f8
[ 177.913316] IP: [<ffffffff8145fc18>] free_irte+0x47/0xc0
...
[ 178.173326] Call Trace:
[ 178.173574] [<ffffffff810515b4>] destroy_irq+0x3a/0x75
[ 178.192934] [<ffffffff81051834>] arch_teardown_msi_irq+0xe/0x10
[ 178.193418] [<ffffffff81458dc3>] arch_teardown_msi_irqs+0x56/0x7f
[ 178.213021] [<ffffffff81458e79>] free_msi_irqs+0x8d/0xeb
Call free_irte only when interrupt remapping is enabled.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <4CBCB274.7010108@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Commit c3f00c70 ("perf: Separate find_get_context() from event
initialization") changed the generic perf_event code to call
perf_event_alloc, which calls the arch-specific event_init code,
before looking up the context for the new event. Unfortunately,
power_pmu_event_init uses event->ctx->task to see whether the
new event is a per-task event or a system-wide event, and thus
crashes since event->ctx is NULL at the point where
power_pmu_event_init gets called.
(The reason it needs to know whether it is a per-task event is
because there are some hardware events on Power systems which
only count when the processor is not idle, and there are some
fixed-function counters which count such events. For example,
the "run cycles" event counts cycles when the processor is not
idle. If the user asks to count cycles, we can use "run cycles"
if this is a per-task event, since the processor is running when
the task is running, by definition. We can't use "run cycles"
if the user asks for "cycles" on a system-wide counter.)
Fortunately the information we need is in the
event->attach_state field, so we just use that instead.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20101019055535.GA10398@drongo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Alexey Kardashevskiy <aik@au1.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
/proc/diskstats would display a strange output as follows.
$ cat /proc/diskstats |grep sda
8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089
8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691
~~~~~~~~~~
8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390
8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92
8 4 sda4 4 0 8 0 0 0 0 0 0 0 0
8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137
Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is
merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE.
The detailed root cause is as follows.
Assuming that there are two partition, sda1 and sda2.
1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight
is 0 and sda2's one is 1.
| hd_struct->in_flight
---------------------------
sda1 | 0
sda2 | 1
---------------------------
2. A bio belongs to sda1 is issued and is merged into the request mentioned on
step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed
from sda2 region to sda1 region. However the two partition's
hd_struct->in_flight are not changed.
| hd_struct->in_flight
---------------------------
sda1 | 0
sda2 | 1
---------------------------
3. The request is finished and blk_account_io_done() is called. In this case,
sda2's hd_struct->in_flight, not a sda1's one, is decremented.
| hd_struct->in_flight
---------------------------
sda1 | -1
sda2 | 1
---------------------------
The patch fixes the problem by caching the partition lookup
inside the request structure, hence making sure that the increment
and decrement will always happen on the same partition struct. This
also speeds up IO with accounting enabled, since it cuts down on
the number of lookups we have to do.
When reloading partition tables, quiesce IO to ensure that no
request references to the partition struct exists. When it is safe
to free the partition table, the IO for that device is restarted
again.
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: stable@kernel.org
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This patch fixes build error about GPIO address due to
conflict of commit 4d914705 and 19a2c065.
- commit 4d914705: Fix on GPIO base addresses
- commit 19a2c065: Moves initial map for merging S5P64X0
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
When DYNAMIC_FTRACE is enabled and we use the C version of recordmcount,
all objects are run through the recordmcount program to create a
separate section that stores all the callers of mcount.
The build process has a special file: scripts/mod/empty.o. This is
built from empty.c which is literally an empty file (except for a
single comment). This file is used to find information about the target
elf format, like endianness and word size.
The problem comes up when we need to build recordmcount. The
build process requires that empty.o is built first. The build rules
for empty.o will try to execute recordmcount on the empty.o file.
We get an error that recordmcount does not exist.
To avoid this recursion, the build file will skip running recordmcount
if the file that it is building is script/mod/empty.o.
[ extra comment Suggested-by: Sam Ravnborg <sam@ravnborg.org> ]
Reported-by: Ingo Molnar <mingo@elte.hu>
Tested-by: Ingo Molnar <mingo@elte.hu>
Cc: Michal Marek <mmarek@suse.cz>
Cc: linux-kbuild@vger.kernel.org
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
* 'upstream' of git://git.linux-mips.org/pub/scm/upstream-linus:
MIPS: Enable ISA_DMA_API config to fix build failure
MIPS: 32-bit: Fix build failure in asm/fcntl.h
MIPS: Remove all generated vmlinuz* files on "make clean"
MIPS: do_sigaltstack() expects userland pointers
MIPS: Fix error values in case of bad_stack
MIPS: Sanitize restart logics
MIPS: secure_computing, syscall audit: syscall number should in r2, not r0.
MIPS: Don't block signals if we'd failed to setup a sigframe
This patch reverts the driver to enabling/disabling the NFC interrupt
mask rather than enabling/disabling the system interrupt. This cleans
up the driver so that it doesn't rely on interrupts being disabled
within the interrupt handler.
For i.MX21 we keep the current behaviour, that is calling
enable_irq/disable_irq_nosync to enable/disable interrupts. This patch
is based on earlier work by John Ogness.
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Acked-by: John Ogness <john.ogness@linutronix.de>
Tested-by: John Ogness <john.ogness@linutronix.de>
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus/i2c/2636-rc8' of git://git.fluff.org/bjdooks/linux:
i2c-imx: do not allow interruptions when waiting for I2C to complete
i2c-davinci: Fix TX setup for more SoCs
When CPU is idle and on first interrupt, irq_enter calls tick_check_idle()
to notify interruption from idle. But, there is a problem if this call
is done after __irq_enter, as all routines in __irq_enter may find
stale time due to yet to be done tick_check_idle.
Specifically, trace calls in __irq_enter when they use global clock and also
account_system_vtime change in this patch as it wants to use sched_clock_cpu()
to do proper irq timing.
But, tick_check_idle was moved after __irq_enter intentionally to
prevent problem of unneeded ksoftirqd wakeups by the commit ee5f80a:
irq: call __irq_enter() before calling the tick_idle_check
Impact: avoid spurious ksoftirqd wakeups
Moving tick_check_idle() before __irq_enter and wrapping it with
local_bh_enable/disable would solve both the problems.
Fixed-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-9-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The idea was suggested by Peter Zijlstra here:
http://marc.info/?l=linux-kernel&m=127476934517534&w=2
irq time is technically not available to the tasks running on the CPU.
This patch removes irq time from CPU power piggybacking on
sched_rt_avg_update().
Tested this by keeping CPU X busy with a network intensive task having 75%
oa a single CPU irq processing (hard+soft) on a 4-way system. And start seven
cycle soakers on the system. Without this change, there will be two tasks on
each CPU. With this change, there is a single task on irq busy CPU X and
remaining 7 tasks are spread around among other 3 CPUs.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-8-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Scheduler accounts both softirq and interrupt processing times to the
currently running task. This means, if the interrupt processing was
for some other task in the system, then the current task ends up being
penalized as it gets shorter runtime than otherwise.
Change sched task accounting to acoount only actual task time from
currently running task. Now update_curr(), modifies the delta_exec to
depend on rq->clock_task.
Note that this change only handles CONFIG_IRQ_TIME_ACCOUNTING case. We can
extend this to CONFIG_VIRT_CPU_ACCOUNTING with minimal effort. But, thats
for later.
This change will impact scheduling behavior in interrupt heavy conditions.
Tested on a 4-way system with eth0 handled by CPU 2 and a network heavy
task (nc) running on CPU 3 (and no RSS/RFS). With that I have CPU 2
spending 75%+ of its time in irq processing. CPU 3 spending around 35%
time running nc task.
Now, if I run another CPU intensive task on CPU 2, without this change
/proc/<pid>/schedstat shows 100% of time accounted to this task. With this
change, it rightly shows less than 25% accounted to this task as remaining
time is actually spent on irq processing.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-7-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds IRQ_TIME_ACCOUNTING option on x86 and runtime enables it
when TSC is enabled.
This change just enables fine grained irq time accounting, isn't used yet.
Following patches use it for different purposes.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-6-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
s390/powerpc/ia64 have support for CONFIG_VIRT_CPU_ACCOUNTING which does
the fine granularity accounting of user, system, hardirq, softirq times.
Adding that option on archs like x86 will be challenging however, given the
state of TSC reliability on various platforms and also the overhead it will
add in syscall entry exit.
Instead, add a lighter variant that only does finer accounting of
hardirq and softirq times, providing precise irq times (instead of timer tick
based samples). This accounting is added with a new config option
CONFIG_IRQ_TIME_ACCOUNTING so that there won't be any overhead for users not
interested in paying the perf penalty.
This accounting is based on sched_clock, with the code being generic.
So, other archs may find it useful as well.
This patch just adds the core logic and does not enable this logic yet.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-5-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
To account softirq time cleanly in scheduler, we need to identify whether
softirq is invoked in ksoftirqd context or softirq at hardirq tail context.
Add PF_KSOFTIRQD for that purpose.
As all PF flag bits are currently taken, create space by moving one of the
infrequently used bits (PF_THREAD_BOUND) down in task_struct to be along
with some other state fields.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-4-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Just a minor cleanup patch that makes things easier to the following patches.
No functionality change in this patch.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-3-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Zijlstra found a bug in the way softirq time is accounted in
VIRT_CPU_ACCOUNTING on this thread:
http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/01366.html
The problem is, softirq processing uses local_bh_disable internally. There
is no way, later in the flow, to differentiate between whether softirq is
being processed or is it just that bh has been disabled. So, a hardirq when bh
is disabled results in time being wrongly accounted as softirq.
Looking at the code a bit more, the problem exists in !VIRT_CPU_ACCOUNTING
as well. As account_system_time() in normal tick based accouting also uses
softirq_count, which will be set even when not in softirq with bh disabled.
Peter also suggested solution of using 2*SOFTIRQ_OFFSET as irq count
for local_bh_{disable,enable} and using just SOFTIRQ_OFFSET while softirq
processing. The patch below does that and adds API in_serving_softirq() which
returns whether we are currently processing softirq or not.
Also changes one of the usages of softirq_count in net/sched/cls_cgroup.c
to in_serving_softirq.
Looks like many usages of in_softirq really want in_serving_softirq. Those
changes can be made individually on a case by case basis.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-2-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When SD_PREFER_SIBLING is set on a sched domain, drop group_capacity to 1
only if the local group has extra capacity. The extra check prevents the case
where you always pull from the heaviest group when it is already under-utilized
(possible with a large weight task outweighs the tasks on the system).
For example, consider a 16-cpu quad-core quad-socket machine with MC and NUMA
scheduling domains. Let's say we spawn 15 nice0 tasks and one nice-15 task,
and each task is running on one core. In this case, we observe the following
events when balancing at the NUMA domain:
- find_busiest_group() will always pick the sched group containing the niced
task to be the busiest group.
- find_busiest_queue() will then always pick one of the cpus running the
nice0 task (never picks the cpu with the nice -15 task since
weighted_cpuload > imbalance).
- The load balancer fails to migrate the task since it is the running task
and increments sd->nr_balance_failed.
- It repeats the above steps a few more times until sd->nr_balance_failed > 5,
at which point it kicks off the active load balancer, wakes up the migration
thread and kicks the nice 0 task off the cpu.
The load balancer doesn't stop until we kick out all nice 0 tasks from
the sched group, leaving you with 3 idle cpus and one cpu running the
nice -15 task.
When balancing at the NUMA domain, we drop sgs.group_capacity to 1 if the child
domain (in this case MC) has SD_PREFER_SIBLING set. Subsequent load checks are
not relevant because the niced task has a very large weight.
In this patch, we add an extra condition to the "if(prefer_sibling)" check in
update_sd_lb_stats(). We drop the capacity of a group only if the local group
has extra capacity, ie. nr_running < group_capacity. This patch preserves the
original intent of the prefer_siblings check (to spread tasks across the system
in low utilization scenarios) and fixes the case above.
It helps in the following ways:
- In low utilization cases (where nr_tasks << nr_cpus), we still drop
group_capacity down to 1 if we prefer siblings.
- On very busy systems (where nr_tasks >> nr_cpus), sgs.nr_running will most
likely be > sgs.group_capacity.
- When balancing large weight tasks, if the local group does not have extra
capacity, we do not pick the group with the niced task as the busiest group.
This prevents failed balances, active migration and the under-utilization
described above.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-5-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch forces a load balance on a newly idle cpu when the local group has
extra capacity and the busiest group does not have any. It improves system
utilization when balancing tasks with a large weight differential.
Under certain situations, such as a niced down task (i.e. nice = -15) in the
presence of nr_cpus NICE0 tasks, the niced task lands on a sched group and
kicks away other tasks because of its large weight. This leads to sub-optimal
utilization of the machine. Even though the sched group has capacity, it does
not pull tasks because sds.this_load >> sds.max_load, and f_b_g() returns NULL.
With this patch, if the local group has extra capacity, we shortcut the checks
in f_b_g() and try to pull a task over. A sched group has extra capacity if the
group capacity is greater than the number of running tasks in that group.
Thanks to Mike Galbraith for discussions leading to this patch and for the
insight to reuse SD_NEWIDLE_BALANCE.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-4-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When cycling through sched groups to determine the busiest group, set
group_imb only if the busiest cpu has more than 1 runnable task. This patch
fixes the case where two cpus in a group have one runnable task each, but there
is a large weight differential between these two tasks. The load balancer is
unable to migrate any task from this group, and hence do not consider this
group to be imbalanced.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286996978-7007-3-git-send-email-ncrao@google.com>
[ small code readability edits ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds a check in task_hot to return if the task has SCHED_IDLE
policy. SCHED_IDLE tasks have very low weight, and when run with regular
workloads, are typically scheduled many milliseconds apart. There is no
need to consider these tasks hot for load balancing.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-2-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The use of the JUMP_LABEL() construct ends up creating endless silly
wrappers, create a higher level construct to reduce this clutter.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>