Use a generic trace_event_raw_init() function for all event's raw_init
callbacks (but kprobes) instead of defining the same version for each
of these.
This shrinks the kernel code:
text data bss dec hex filename
5355293 1961928 7103260 14420481 dc0a01 vmlinux.o.old
5346802 1961864 7103260 14411926 dbe896 vmlinux.o
raw_init can't be removed, because ftrace events and kprobe events
use different raw_init callbacks. Though it's possible to totally
remove raw_init, I choose to leave it as it is for now.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
LKML-Reference: <4B1DC48C.7080603@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Compiling powerpc64 results in:
include/trace/events/timer.h:279: warning:
format '%lu' expects type 'long unsigned int', but argument 4 has type 'cputime_t'
....
cputime_t on power is u64, which triggers the above warning.
Cast the cputime_t to unsigned long long and fix the print format
string. That works on both 32 and 64 bit architectures.
While at it change the print format for long variables from %lu to %ld.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
use only one prof_sysenter_enable() instead of
prof_sysenter_enable_##sname()
use only one prof_sysenter_disable() instead of
prof_sysenter_disable_##sname()
use only one prof_sysexit_enable() instead of
prof_sysexit_enable_##sname()
use only one prof_sysexit_disable() instead of
prof_sysexit_disable_##sname()
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14D2A1.8060304@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
use only one init_syscall_trace instead of
many init_enter_##sname()/init_exit_##sname()
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14D29B.6090708@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add syscall_nr field to struct syscall_metadata,
it helps us to get syscall number easier.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14D293.6090800@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
use ->enter_event->id instead of ->enter_id
use ->exit_event->id instead of ->exit_id
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14D288.7030001@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Set event_enter_##sname->data to its metadata,
it makes codes simpler.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jason Baron <jbaron@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B14D282.7050709@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use DECLARE_EVENT_CLASS to remove duplicate code:
text data bss dec hex filename
4312 524 12 4848 12f0 kernel/trace/power-traces.o.old
3455 524 8 3987 f93 kernel/trace/power-traces.o
Two events are converted:
power: power_start, power_frequency
No change in functionality.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arjan van de Ven <arjan@infradead.org>
LKML-Reference: <4B0E28C2.1090906@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use DECLARE_EVENT_CLASS to remove duplicate code:
text data bss dec hex filename
13171 800 72 14043 36db kernel/workqueue.o.old
12243 800 68 13111 3337 kernel/workqueue.o
Two events are converted:
workqueue: workqueue_insertion, workqueue_execution
No change in functionality.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B0E289F.5010104@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use DECLARE_EVENT_CLASS to remove duplicate code:
text data bss dec hex filename
12781 952 36 13769 35c9 kernel/softirq.o.old
11981 952 32 12965 32a5 kernel/softirq.o
Two events are converted:
softirq: softirq_entry, softirq_exit
No change in functionality.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B0E287F.4030708@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use DECLARE_EVENT_CLASS to remove duplicate code:
text data bss dec hex filename
29854 1980 128 31962 7cda kernel/module.o.old
28750 1980 128 30858 788a kernel/module.o
Two events are converted:
module_refcnt: module_get, module_put
No change in functionality.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B0E283B.3010508@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It is not quite obvious at first sight what TRACE_EVENT_TEMPLATE
does: does it define an event as well beyond defining a template?
To clarify this, rename it to DECLARE_EVENT_CLASS, which follows
the various 'DECLARE_*()' idioms we already have in the kernel:
DECLARE_EVENT_CLASS(class)
DEFINE_EVENT(class, event1)
DEFINE_EVENT(class, event2)
DEFINE_EVENT(class, event3)
To complete this logic we should also rename TRACE_EVENT() to:
DEFINE_SINGLE_EVENT(single_event)
... but in a more quiet moment of the kernel cycle.
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4B0E286A.2000405@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The current syscall tracer mixes raw syscalls and real syscalls.
echo 1 > events/syscalls/enable
And we get these from the output:
(XXXX insteads " grep-20914 [001] 588211.446347" .. etc)
XXXX: sys_read(fd: 3, buf: 80609a8, count: 7000)
XXXX: sys_enter: NR 3 (3, 80609a8, 7000, a, 1000, bfce8ef8)
XXXX: sys_read -> 0x138
XXXX: sys_exit: NR 3 = 312
XXXX: sys_read(fd: 3, buf: 8060ae0, count: 7000)
XXXX: sys_enter: NR 3 (3, 8060ae0, 7000, a, 1000, bfce8ef8)
XXXX: sys_read -> 0x138
XXXX: sys_exit: NR 3 = 312
There are 2 drawbacks here.
A) two almost identical records are saved in ringbuffer
when a syscall enters or exits. (4 records for every syscall)
This wastes precious space in the ring buffer.
B) the lines including "sys_enter/sys_exit" produces
hardly any useful information for the output (no labels).
The user can use this method to prevent these drawbacks:
echo 1 > events/syscalls/enable
echo 0 > events/syscalls/sys_enter/enable
echo 0 > events/syscalls/sys_exit/enable
But this is not user friendly. So we separate raw syscall
from syscall tracer.
After this fix applied:
syscall tracer's output (echo 1 > events/syscalls/enable):
XXXX: sys_read(fd: 3, buf: bfe87d88, count: 200)
XXXX: sys_read -> 0x200
XXXX: sys_fstat64(fd: 3, statbuf: bfe87c98)
XXXX: sys_fstat64 -> 0x0
XXXX: sys_close(fd: 3)
raw syscall tracer's output (echo 1 > events/raw_syscalls/enable):
XXXX: sys_enter: NR 175 (0, bf92bf18, bf92bf98, 8, b748cff4, bf92bef8)
XXXX: sys_exit: NR 175 = 0
XXXX: sys_enter: NR 175 (2, bf92bf98, 0, 8, b748cff4, bf92bef8)
XXXX: sys_exit: NR 175 = 0
XXXX: sys_enter: NR 3 (9, bf927f9c, 4000, b77e2518, b77dce60, bf92bff8)
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
LKML-Reference: <4AEFC37C.5080609@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Converting some of the scheduler trace events to use the
TRACE_EVENT_TEMPLATE, DEFINE_EVENT and DEFINE_EVENT_PRINT helped to
save some space:
$ size kernel/sched.o-*
text data bss dec hex filename
79299 6776 2520 88595 15a13 kernel/sched.o-notrace
101941 11896 2584 116421 1c6c5 kernel/sched.o-templ
104779 11896 2584 119259 1d1db kernel/sched.o-trace
sched.o-notrace is without any tracepoints compiled
sched.o-templ is with this patch
sched.o-trace is the tracepoints before this patch
The trace events converted to DEFINE_EVENT:
sched_wakeup, sched_wakeup_new, sched_process_free, sched_process_exit,
and sched_stat_wait.
The trace events converted to DEFINE_EVENT_PRINT:
sched_stat_sleep and sched_stat_iowait.
Note, since the TRACE_EVENT_TEMPLATE always uses a print, the
sched_stat_wait print format is defined in the template and this
template is used by sched_stat_sleep and sched_stat_iowait. But the
later two override the print format.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
After creating the TRACE_EVENT_TEMPLATE I started to look at other
trace points to see what duplication was made. I noticed that there
are several trace points where they are almost identical except for
the name and the output format. Since TRACE_EVENT_TEMPLATE was successful
in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT.
DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the
DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the
developer to overwrite the print format. If there are two or more
TRACE_EVENTS that are identical except for the name and print, then
they can be converted to use a TRACE_EVENT_TEMPLATE. Since the
TRACE_EVENT_TEMPLATE already does the print output, the first trace event
would have its print format held in the TRACE_EVENT_TEMPLATE and
be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT
and override the print format.
Converting the sched trace points to both DEFINE_EVENT and
DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were
converted to DEFINE_EVENT_PRINT.
I was able to get the following:
$ size kernel/sched.o-*
text data bss dec hex filename
79299 6776 2520 88595 15a13 kernel/sched.o-notrace
101941 11896 2584 116421 1c6c5 kernel/sched.o-templ
104779 11896 2584 119259 1d1db kernel/sched.o-trace
sched.o-notrace is the scheduler compiled with no trace points.
sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT
sched.o-trace is the current trace events.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
There are some places in the kernel that define several tracepoints and
they are all identical besides the name. The code to enable, disable and
record is created for every trace point even if most of the code is
identical.
This patch adds TRACE_EVENT_TEMPLATE that lets the developer create
a template TRACE_EVENT and create trace points with DEFINE_EVENT, which
is based off of a given template. Each trace point used by this
will share most of the code, and bring down the size of the kernel
when there are several duplicate events.
Usage is:
TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print);
Which would be the same as defining a normal TRACE_EVENT.
To create the trace events that the trace points will use:
DEFINE_EVENT(template, name, proto, args) is done. The template
is the name of the TRACE_EVENT_TEMPLATE to use. The name is the
name of the trace point. The parameters proto and args must be the same
as the proto and args of the template. If they are not the same,
then a compile error will result. I tried hard removing this duplication
but the C preprocessor is not powerful enough (or my CPP magic
experience points is not at a high enough level) to not need them.
A lot of trace events are coming in with new XFS development. Most of
the trace points are identical except for the name. The following shows
the advantage of having TRACE_EVENT_TEMPLATE:
$ size fs/xfs/xfs.o.*
text data bss dec hex filename
452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old
638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template
996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace
xfs.o.old is without any tracepoints.
xfs.o.template uses the new TRACE_EVENT_TEMPLATE.
xfs.o.trace uses the current TRACE_EVENT macros.
Requested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Make perf_swevent_get_recursion_context return a context number
and disable preemption.
This could be used to remove the IRQ disable from the trace bit
and index the per-cpu buffer with.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20091123103819.993226816@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add the facility for ext4_forget() to be called from
ext4_free_blocks(). This simplifies the code in a large number of
places, and centralizes most of the work of calling ext4_forget() into
a single place.
Also fix a bug in the extents migration code; it wasn't calling
ext4_forget() when releasing the indirect blocks during the
conversion. As a result, if the system cashed during or shortly after
the extents migration, and the released indirect blocks get reused as
data blocks, the journal replay would corrupt the data blocks. With
this new patch, fixing this bug was as simple as adding the
EXT4_FREE_BLOCKS_FORGET flags to the call to ext4_free_blocks().
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
When we commit a trace to perf, we first check if we are
recursing in the same buffer so that we don't mess-up the buffer
with a recursing trace. But later on, we do the same check from
perf to avoid commit recursion. The recursion check is desired
early before we touch the buffer but we want to do this check
only once.
Then export the recursion protection from perf and use it from
the trace events before submitting a trace.
v2: Put appropriate Reported-by tag
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
LKML-Reference: <1258864015-10579-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Commit 6161352 moved the power tracing to include/trace/events/,
but left the old header behind. No one is using the old header,
and its declarations are now incorrect, so it should be removed.
Signed-off-by: Josh Stone <jistone@redhat.com>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <1258578415-14752-1-git-send-email-jistone@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For some reason the export of the event print format to userspace
uses '#fmt' which breaks if the format string is anything but a plain
string, for example if it is built with macros then the macro names
are exported instead of their contents.
Use
"\"%s\"", fmt
instead of
"%s", #fmt
to export the string and not the way it is built.
For example, in net/mac80211/driver-trace.h for the trace event drv_start
there is:
TP_printk(
LOCAL_PR_FMT, LOCAL_PR_ARG
)
Which use to produce:
print fmt: LOCAL_PR_FMT, REC->wiphy_name
Now produces:
print fmt: "%s", REC->wiphy_name
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
LKML-Reference: <20091113224009.GB23942@elte.hu>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Lockdep events subsystem gathers various locking related events
such as a request, release, contention or acquisition of a lock.
The name of this event subsystem is a bit of a misnomer since
these events are not quite related to lockdep but more generally
to locking, ie: these events are not reporting lock dependencies
or possible deadlock scenario but pure locking events.
Hence this rename.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1258103194-843-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While tracing using events with perf, if one enables the
lockdep:lock_acquire event, it will infect every other perf
trace events.
Basically, you can enable whatever set of trace events through
perf but if this event is part of the set, the only result we
can get is a long list of lock_acquire events of rcu read lock,
and only that.
This is because of a recursion inside perf.
1) When a trace event is triggered, it will fill a per cpu
buffer and submit it to perf.
2) Perf will commit this event but will also protect some data
using rcu_read_lock
3) A recursion appears: rcu_read_lock triggers a lock_acquire
event that will fill the per cpu event and then submit the
buffer to perf.
4) Perf detects a recursion and ignores it
5) Perf continues its work on the previous event, but its buffer
has been overwritten by the lock_acquire event, it has then
been turned into a lock_acquire event of rcu read lock
Such scenario also happens with lock_release with
rcu_read_unlock().
We could turn the rcu_read_lock() into __rcu_read_lock() to drop
the lock debugging from perf fast path, but that would make us
lose the rcu debugging and that doesn't prevent from other
possible kind of recursion from perf in the future.
This patch adds a recursion protection based on a counter on the
perf trace per cpu buffers to solve the problem.
-v2: Fixed lost whitespace, added reviewed-by tag
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
LKML-Reference: <1257477185-7838-1-git-send-email-fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that we can filter based on fields via perf record, people
will start using filter expressions and will expect them to
be obvious.
The primary way to see which fields are available is by looking
at the trace output, such as:
gcc-18676 [000] 343.011728: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.012727: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.032692: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.033690: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.034687: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.035686: irq_handler_entry: irq=0 handler=timer
cc1-18677 [000] 343.036684: irq_handler_entry: irq=0 handler=timer
While 'irq==0' filters work, the 'handler==<x>' filter expression
does not work:
$ perf record -R -f -a -e irq:irq_handler_entry --filter handler=timer sleep 1
Error: failed to set filter with 22 (Invalid argument)
The problem is that while an 'irq' field exists and is recognized
as a filter field - 'handler' does not exist - its name is 'name'
in the output.
To solve this, we need to synchronize the printout and the field
names, wherever possible.
In cases where the printout prints a non-field, we enclose
that information in square brackets, such as:
perf-1380 [013] 724.903505: softirq_exit: vec=9 [action=RCU]
perf-1380 [013] 724.904482: softirq_exit: vec=1 [action=TIMER]
This way users can use filter expressions more intuitively: all
fields that show up as 'primary' (non-bracketed) information is
filterable.
This patch harmonizes the field names for all irq, bkl, power,
sched and timer events.
We might in fact think about dropping the print format bit of
generic tracepoints altogether, and just print the fields that
are being recorded.
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Most of the syscalls metadata processing is done from arch.
But these operations are mostly generic accross archs. Especially now
that we have a common variable name that expresses the number of
syscalls supported by an arch: NR_syscalls, the only remaining bits
that need to reside in arch is the syscall nr to addr translation.
v2: Compare syscalls symbols only after the "sys" prefix so that we
avoid spurious mismatches with archs that have syscalls wrappers,
in which case syscalls symbols have "SyS" prefixed aliases.
(Reported by: Heiko Carstens)
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
This approach is the first baby step towards solving many of the
structural problems the x86 MCE logging code is having today:
- It has a private ring-buffer implementation that has a number
of limitations and has been historically fragile and buggy.
- It is using a quirky /dev/mcelog ioctl driven ABI that is MCE
specific. /dev/mcelog is not part of any larger logging
framework and hence has remained on the fringes for many years.
- The MCE logging code is still very unclean partly due to its ABI
limitations. Fields are being reused for multiple purposes, and
the whole message structure is limited and x86 specific to begin
with.
All in one, the x86 tree would like to move away from this private
implementation of an event logging facility to a broader framework.
By using perf events we gain the following advantages:
- Multiple user-space agents can access MCE events. We can have an
mcelog daemon running but also a system-wide tracer capturing
important events in flight-recorder mode.
- Sampling support: the kernel and the user-space call-chain of MCE
events can be stored and analyzed as well. This way actual patterns
of bad behavior can be matched to precisely what kind of activity
happened in the kernel (and/or in the app) around that moment in
time.
- Coupling with other hardware and software events: the PMU can track a
number of other anomalies - monitoring software might chose to
monitor those plus the MCE events as well - in one coherent stream of
events.
- Discovery of MCE sources - tracepoints are enumerated and tools can
act upon the existence (or non-existence) of various channels of MCE
information.
- Filtering support: we just subscribe to and act upon the events we
are interested in. Then even on a per event source basis there's
in-kernel filter expressions available that can restrict the amount
of data that hits the event channel.
- Arbitrary deep per cpu buffering of events - we can buffer 32
entries or we can buffer as much as we want, as long as we have
the RAM.
- An NMI-safe ring-buffer implementation - mappable to user-space.
- Built-in support for timestamping of events, PID markers, CPU
markers, etc.
- A rich ABI accessible over system call interface. Per cpu, per task
and per workload monitoring of MCE events can be done this way. The
ABI itself has a nice, meaningful structure.
- Extensible ABI: new fields can be added without breaking tooling.
New tracepoints can be added as the hardware side evolves. There's
various parsers that can be used.
- Lots of scheduling/buffering/batching modes of operandi for MCE
events. poll() support. mmap() support. read() support. You name it.
- Rich tooling support: even without any MCE specific extensions added
the 'perf' tool today offers various views of MCE data: perf report,
perf stat, perf trace can all be used to view logged MCE events and
perhaps correlate them to certain user-space usage patterns. But it
can be used directly as well, for user-space agents and policy action
in mcelog, etc.
With this we hope to achieve significant code cleanup and feature
improvements in the MCE code, and we hope to be able to drop the
/dev/mcelog facility in the end.
This patch is just a plain dumb dump of mce_log() records to
the tracepoints / perf events framework - a first proof of
concept step.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
LKML-Reference: <4AD42A0D.7050104@jp.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The sign info used for filters in the kernel is also useful to
applications that process the trace stream. Add it to the format
files and make it available to userspace.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: rostedt@goodmis.org
Cc: lizf@cn.fujitsu.com
Cc: hch@infradead.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <1254809398-8078-2-git-send-email-tzanussi@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since 2.6.31 now has request-based device-mapper, it's useful to have
a tracepoint for request-remapping as well as bio-remapping.
This patch adds a tracepoint for request-remapping, trace_block_rq_remap().
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Since 2.6.31 now has request-based device-mapper, it's useful to have
a tracepoint for request-remapping as well as bio-remapping.
This patch adds a tracepoint for request-remapping, trace_block_rq_remap().
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The tracepoint ext4_da_write_pages has a struct mpage_da_data*
parameter, but that struct is only defined in fs/ext4/ext4.h. This
patch adds a forward declaration for that struct, so this tracepoint
header can still be used by tools like SystemTap.
This is a continuation of the fix in commit 3661d286.
http://sourceware.org/bugzilla/show_bug.cgi?id=10703
Signed-off-by: Josh Stone <jistone@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
The /proc/fs/jbd2/<dev>/history was maintained manually; by using
tracepoints, we can get all of the existing functionality of the /proc
file plus extra capabilities thanks to the ftrace infrastructure. We
save memory as a bonus.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
The /proc/fs/ext4/<dev>/mb_history was maintained manually, and had a
number of problems: it required a largish amount of memory to be
allocated for each ext4 filesystem, and the s_mb_history_lock
introduced a CPU contention problem.
By ripping out the mb_history code and replacing it with ftrace
tracepoints, and we get more functionality: timestamps, event
filtering, the ability to correlate mballoc history with other ext4
tracepoints, etc.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Work around problems in the writeback code to force out writebacks in
larger chunks than just 4mb, which is just too small. This also works
around limitations in the ext4 block allocator, which can't allocate
more than 2048 blocks at a time. So we need to defeat the round-robin
characteristics of the writeback code and try to write out as many
blocks in one inode before allowing the writeback code to move on to
another inode. We add a a new per-filesystem tunable,
max_writeback_mb_bump, which caps this to a default of 128mb per
inode.
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Add two events lock_kernel and unlock_kernel() to trace the bkl uses.
This opens the door for userspace tools to perform statistics about
the callsites that use it, dependencies with other locks (by pairing
the trace with lock events), use with recursivity and so on...
The {__reacquire,release}_kernel_lock() events are not traced because
these are called from schedule, thus the sched events are sufficient
to trace them.
Example of a trace:
hald-addon-stor-4152 [000] 165.875501: unlock_kernel: depth: 0, fs/block_dev.c:1358 __blkdev_put()
hald-addon-stor-4152 [000] 167.832974: lock_kernel: depth: 0, fs/block_dev.c:1167 __blkdev_get()
How to get the callsites that acquire it recursively:
cd /debug/tracing/events/bkl
echo "lock_depth > 0" > filter
firefox-4951 [001] 206.276967: unlock_kernel: depth: 1, fs/reiserfs/super.c:575 reiserfs_dirty_inode()
You can also filter by file and/or line.
v2: Use of FILTER_PTR_STRING attribute for files and lines fields to
make them traceable.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Using %pf instead of %pF supresses printing of the function offset
which will always be 0 in the case of worklet functions.
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Zhaolei <zhaolei@cn.fujitsu.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <20090922024033.GB31801@kryten>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Li Zefan