This patch fixes a long-standing performance bug in classic RCU that
results in massive internal-to-RCU lock contention on systems with
more than a few hundred CPUs. Although this patch creates a separate
flavor of RCU for ease of review and patch maintenance, it is intended
to replace classic RCU.
This patch still handles stress better than does mainline, so I am still
calling it ready for inclusion. This patch is against the -tip tree.
Nevertheless, experience on an actual 1000+ CPU machine would still be
most welcome.
Most of the changes noted below were found while creating an rcutiny
(which should permit ejecting the current rcuclassic) and while doing
detailed line-by-line documentation.
Updates from v9 (http://lkml.org/lkml/2008/12/2/334):
o Fixes from remainder of line-by-line code walkthrough,
including comment spelling, initialization, undesirable
narrowing due to type conversion, removing redundant memory
barriers, removing redundant local-variable initialization,
and removing redundant local variables.
I do not believe that any of these fixes address the CPU-hotplug
issues that Andi Kleen was seeing, but please do give it a whirl
in case the machine is smarter than I am.
A writeup from the walkthrough may be found at the following
URL, in case you are suffering from terminal insomnia or
masochism:
http://www.kernel.org/pub/linux/kernel/people/paulmck/tmp/rcutree-walkthrough.2008.12.16a.pdf
o Made rcutree tracing use seq_file, as suggested some time
ago by Lai Jiangshan.
o Added a .csv variant of the rcudata debugfs trace file, to allow
people having thousands of CPUs to drop the data into
a spreadsheet. Tested with oocalc and gnumeric. Updated
documentation to suit.
Updates from v8 (http://lkml.org/lkml/2008/11/15/139):
o Fix a theoretical race between grace-period initialization and
force_quiescent_state() that could occur if more than three
jiffies were required to carry out the grace-period
initialization. Which it might, if you had enough CPUs.
o Apply Ingo's printk-standardization patch.
o Substitute local variables for repeated accesses to global
variables.
o Fix comment misspellings and redundant (but harmless) increments
of ->n_rcu_pending (this latter after having explicitly added it).
o Apply checkpatch fixes.
Updates from v7 (http://lkml.org/lkml/2008/10/10/291):
o Fixed a number of problems noted by Gautham Shenoy, including
the cpu-stall-detection bug that he was having difficulty
convincing me was real. ;-)
o Changed cpu-stall detection to wait for ten seconds rather than
three in order to reduce false positive, as suggested by Ingo
Molnar.
o Produced a design document (http://lwn.net/Articles/305782/).
The act of writing this document uncovered a number of both
theoretical and "here and now" bugs as noted below.
o Fix dynticks_nesting accounting confusion, simplify WARN_ON()
condition, fix kerneldoc comments, and add memory barriers
in dynticks interface functions.
o Add more data to tracing.
o Remove unused "rcu_barrier" field from rcu_data structure.
o Count calls to rcu_pending() from scheduling-clock interrupt
to use as a surrogate timebase should jiffies stop counting.
o Fix a theoretical race between force_quiescent_state() and
grace-period initialization. Yes, initialization does have to
go on for some jiffies for this race to occur, but given enough
CPUs...
Updates from v6 (http://lkml.org/lkml/2008/9/23/448):
o Fix a number of checkpatch.pl complaints.
o Apply review comments from Ingo Molnar and Lai Jiangshan
on the stall-detection code.
o Fix several bugs in !CONFIG_SMP builds.
o Fix a misspelled config-parameter name so that RCU now announces
at boot time if stall detection is configured.
o Run tests on numerous combinations of configurations parameters,
which after the fixes above, now build and run correctly.
Updates from v5 (http://lkml.org/lkml/2008/9/15/92, bad subject line):
o Fix a compiler error in the !CONFIG_FANOUT_EXACT case (blew a
changeset some time ago, and finally got around to retesting
this option).
o Fix some tracing bugs in rcupreempt that caused incorrect
totals to be printed.
o I now test with a more brutal random-selection online/offline
script (attached). Probably more brutal than it needs to be
on the people reading it as well, but so it goes.
o A number of optimizations and usability improvements:
o Make rcu_pending() ignore the grace-period timeout when
there is no grace period in progress.
o Make force_quiescent_state() avoid going for a global
lock in the case where there is no grace period in
progress.
o Rearrange struct fields to improve struct layout.
o Make call_rcu() initiate a grace period if RCU was
idle, rather than waiting for the next scheduling
clock interrupt.
o Invoke rcu_irq_enter() and rcu_irq_exit() only when
idle, as suggested by Andi Kleen. I still don't
completely trust this change, and might back it out.
o Make CONFIG_RCU_TRACE be the single config variable
manipulated for all forms of RCU, instead of the prior
confusion.
o Document tracing files and formats for both rcupreempt
and rcutree.
Updates from v4 for those missing v5 given its bad subject line:
o Separated dynticks interface so that NMIs and irqs call separate
functions, greatly simplifying it. In particular, this code
no longer requires a proof of correctness. ;-)
o Separated dynticks state out into its own per-CPU structure,
avoiding the duplicated accounting.
o The case where a dynticks-idle CPU runs an irq handler that
invokes call_rcu() is now correctly handled, forcing that CPU
out of dynticks-idle mode.
o Review comments have been applied (thank you all!!!).
For but one example, fixed the dynticks-ordering issue that
Manfred pointed out, saving me much debugging. ;-)
o Adjusted rcuclassic and rcupreempt to handle dynticks changes.
Attached is an updated patch to Classic RCU that applies a hierarchy,
greatly reducing the contention on the top-level lock for large machines.
This passes 10-hour concurrent rcutorture and online-offline testing on
128-CPU ppc64 without dynticks enabled, and exposes some timekeeping
bugs in presence of dynticks (exciting working on a system where
"sleep 1" hangs until interrupted...), which were fixed in the
2.6.27 kernel. It is getting more reliable than mainline by some
measures, so the next version will be against -tip for inclusion.
See also Manfred Spraul's recent patches (or his earlier work from
2004 at http://marc.info/?l=linux-kernel&m=108546384711797&w=2).
We will converge onto a common patch in the fullness of time, but are
currently exploring different regions of the design space. That said,
I have already gratefully stolen quite a few of Manfred's ideas.
This patch provides CONFIG_RCU_FANOUT, which controls the bushiness
of the RCU hierarchy. Defaults to 32 on 32-bit machines and 64 on
64-bit machines. If CONFIG_NR_CPUS is less than CONFIG_RCU_FANOUT,
there is no hierarchy. By default, the RCU initialization code will
adjust CONFIG_RCU_FANOUT to balance the hierarchy, so strongly NUMA
architectures may choose to set CONFIG_RCU_FANOUT_EXACT to disable
this balancing, allowing the hierarchy to be exactly aligned to the
underlying hardware. Up to two levels of hierarchy are permitted
(in addition to the root node), allowing up to 16,384 CPUs on 32-bit
systems and up to 262,144 CPUs on 64-bit systems. I just know that I
am going to regret saying this, but this seems more than sufficient
for the foreseeable future. (Some architectures might wish to set
CONFIG_RCU_FANOUT=4, which would limit such architectures to 64 CPUs.
If this becomes a real problem, additional levels can be added, but I
doubt that it will make a significant difference on real hardware.)
In the common case, a given CPU will manipulate its private rcu_data
structure and the rcu_node structure that it shares with its immediate
neighbors. This can reduce both lock and memory contention by multiple
orders of magnitude, which should eliminate the need for the strange
manipulations that are reported to be required when running Linux on
very large systems.
Some shortcomings:
o More bugs will probably surface as a result of an ongoing
line-by-line code inspection.
Patches will be provided as required.
o There are probably hangs, rcutorture failures, &c. Seems
quite stable on a 128-CPU machine, but that is kind of small
compared to 4096 CPUs. However, seems to do better than
mainline.
Patches will be provided as required.
o The memory footprint of this version is several KB larger
than rcuclassic.
A separate UP-only rcutiny patch will be provided, which will
reduce the memory footprint significantly, even compared
to the old rcuclassic. One such patch passes light testing,
and has a memory footprint smaller even than rcuclassic.
Initial reaction from various embedded guys was "it is not
worth it", so am putting it aside.
Credits:
o Manfred Spraul for ideas, review comments, and bugs spotted,
as well as some good friendly competition. ;-)
o Josh Triplett, Ingo Molnar, Peter Zijlstra, Mathieu Desnoyers,
Lai Jiangshan, Andi Kleen, Andy Whitcroft, and Andrew Morton
for reviews and comments.
o Thomas Gleixner for much-needed help with some timer issues
(see patches below).
o Jon M. Tollefson, Tim Pepper, Andrew Theurer, Jose R. Santos,
Andy Whitcroft, Darrick Wong, Nishanth Aravamudan, Anton
Blanchard, Dave Kleikamp, and Nathan Lynch for keeping machines
alive despite my heavy abuse^Wtesting.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
cpuset: fix regression when failed to generate sched domains
sched, signals: fix the racy usage of ->signal in account_group_xxx/run_posix_cpu_timers
sched: fix kernel warning on /proc/sched_debug access
sched: correct sched-rt-group.txt pathname in init/Kconfig
In 2007, a0acd82080 changed the default
slab allocator to SLUB, but the SLAB help text still says SLAB is the
default. This change fixes that.
Signed-off-by: Simon Arlott <simon@fire.lp0.eu>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
init/Kconfig directs the user to Documentation/sched-rt-group.txt, but
the file is actually in Documentation/scheduler/sched-rt-group.txt.
This patch corrects the pathname mentioned in init/Kconfig.
Signed-off-by: Adrian Knoth <adi@drcomp.erfurt.thur.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Removed duplicated #include <linux/delay.h> in init/do_mounts_md.c.
The same compile error ("error: implicit declaration of function
'msleep'") got fixed twice:
- f8b77d3939 ("init/do_mounts_md.c:
msleep compile fix")
- 73b4a24f5f ("init/do_mounts_md.c must
#include <linux/delay.h>")
by people adding the <linux/delay.h> include in two slightly different
places. Andrew's quilt scripts happily ignore the fuzz, and will
re-apply the patch even though they had conflicts.
Signed-off-by: Huang Weiyi <weiyi.huang@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
page_cgroup is now allocated at boot and memmap doesn't includes pointer
for page_cgroup. Fix the menu help text.
Reviewed-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: KAMEZAWA hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit a802dd0eb5 by moving
the call to init_workqueues() back where it belongs - after SMP has been
initialized.
It also moves stop_machine_init() - which needs workqueues - to a later
phase using a core_initcall() instead of early_initcall(). That should
satisfy all ordering requirements, and was apparently the reason why
init_workqueues() was moved to be too early.
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:
stop_machine: fix error code handling on multiple cpus
stop_machine: use workqueues instead of kernel threads
workqueue: introduce create_rt_workqueue
Call init_workqueues before pre smp initcalls.
Make panic= and panic_on_oops into core_params
Make initcall_debug a core_param
core_param() for genuinely core kernel parameters
param: Fix duplicate module prefixes
module: check kernel param length at compile time, not runtime
Remove stop_machine during module load v2
module: simplify load_module.
page_cgroup_init() is called from mem_cgroup_init(). But at this
point, we cannot call alloc_bootmem().
(and this caused panic at boot.)
This patch moves page_cgroup_init() to init/main.c.
Time table is following:
==
parse_args(). # we can trust mem_cgroup_subsys.disabled bit after this.
....
cgroup_init_early() # "early" init of cgroup.
....
setup_arch() # memmap is allocated.
...
page_cgroup_init();
mem_init(); # we cannot call alloc_bootmem after this.
....
cgroup_init() # mem_cgroup is initialized.
==
Before page_cgroup_init(), mem_map must be initialized. So,
I added page_cgroup_init() to init/main.c directly.
(*) maybe this is not very clean but
- cgroup_init_early() is too early
- in cgroup_init(), we have to use vmalloc instead of alloc_bootmem().
use of vmalloc area in x86-32 is important and we should avoid very large
vmalloc() in x86-32. So, we want to use alloc_bootmem() and added page_cgroup_init()
directly to init/main.c
[akpm@linux-foundation.org: remove unneeded/bad mem_cgroup_subsys declaration]
[akpm@linux-foundation.org: fix build]
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit 3d13731024 ("PCI: allow quirks to be
compiled out") introduced CONFIG_PCI_QUIRKS, which now shows up in each
and every .config. Fix this by making it depend on PCI.
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This allows to create workqueues from within the context of
a pre smp initcall (aka early_initcall).
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This is the one I really wanted: now it effects module loading, it
makes sense to be able to flip it after boot.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
* 'linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: (41 commits)
PCI: fix pci_ioremap_bar() on s390
PCI: fix AER capability check
PCI: use pci_find_ext_capability everywhere
PCI: remove #ifdef DEBUG around dev_dbg call
PCI hotplug: fix get_##name return value problem
PCI: document the pcie_aspm kernel parameter
PCI: introduce an pci_ioremap(pdev, barnr) function
powerpc/PCI: Add legacy PCI access via sysfs
PCI: Add ability to mmap legacy_io on some platforms
PCI: probing debug message uniformization
PCI: support PCIe ARI capability
PCI: centralize the capabilities code in probe.c
PCI: centralize the capabilities code in pci-sysfs.c
PCI: fix 64-vbit prefetchable memory resource BARs
PCI: replace cfg space size (256/4096) by macros.
PCI: use resource_size() everywhere.
PCI: use same arg names in PCI_VDEVICE comment
PCI hotplug: rpaphp: make debug var unique
PCI: use %pF instead of print_fn_descriptor_symbol() in quirks.c
PCI: fix hotplug get_##name return value problem
...
This patch adds the CONFIG_PCI_QUIRKS option which allows to remove all
the PCI quirks, which are not necessarily used on embedded systems when
PCI is working properly. As this is a size-reduction option, it depends
on CONFIG_EMBEDDED. It allows to save almost 12 kilobytes of kernel
code:
text data bss dec hex filename
1287806 123596 212992 1624394 18c94a vmlinux.old
1275854 123596 212992 1612442 189a9a vmlinux
-11952 0 0 -11952 -2EB0 +/-
This patch has originally been written by Zwane Mwaikambo
<zwane@arm.linux.org.uk> and is part of the Linux Tiny project.
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
This patch implements a new freezer subsystem in the control groups
framework. It provides a way to stop and resume execution of all tasks in
a cgroup by writing in the cgroup filesystem.
The freezer subsystem in the container filesystem defines a file named
freezer.state. Writing "FROZEN" to the state file will freeze all tasks
in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in
the cgroup. Reading will return the current state.
* Examples of usage :
# mkdir /containers/freezer
# mount -t cgroup -ofreezer freezer /containers
# mkdir /containers/0
# echo $some_pid > /containers/0/tasks
to get status of the freezer subsystem :
# cat /containers/0/freezer.state
RUNNING
to freeze all tasks in the container :
# echo FROZEN > /containers/0/freezer.state
# cat /containers/0/freezer.state
FREEZING
# cat /containers/0/freezer.state
FROZEN
to unfreeze all tasks in the container :
# echo RUNNING > /containers/0/freezer.state
# cat /containers/0/freezer.state
RUNNING
This is the basic mechanism which should do the right thing for user space
task in a simple scenario.
It's important to note that freezing can be incomplete. In that case we
return EBUSY. This means that some tasks in the cgroup are busy doing
something that prevents us from completely freezing the cgroup at this
time. After EBUSY, the cgroup will remain partially frozen -- reflected
by freezer.state reporting "FREEZING" when read. The state will remain
"FREEZING" until one of these things happens:
1) Userspace cancels the freezing operation by writing "RUNNING" to
the freezer.state file
2) Userspace retries the freezing operation by writing "FROZEN" to
the freezer.state file (writing "FREEZING" is not legal
and returns EIO)
3) The tasks that blocked the cgroup from entering the "FROZEN"
state disappear from the cgroup's set of tasks.
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: export thaw_process]
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Matt Helsley <matthltc@us.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Matt Helsley <matthltc@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and
provide a fast, scalable percpu frontend for small vmaps (requires a
slightly different API, though).
The biggest problem with vmap is actually vunmap. Presently this requires
a global kernel TLB flush, which on most architectures is a broadcast IPI
to all CPUs to flush the cache. This is all done under a global lock. As
the number of CPUs increases, so will the number of vunmaps a scaled
workload will want to perform, and so will the cost of a global TLB flush.
This gives terrible quadratic scalability characteristics.
Another problem is that the entire vmap subsystem works under a single
lock. It is a rwlock, but it is actually taken for write in all the fast
paths, and the read locking would likely never be run concurrently anyway,
so it's just pointless.
This is a rewrite of vmap subsystem to solve those problems. The existing
vmalloc API is implemented on top of the rewritten subsystem.
The TLB flushing problem is solved by using lazy TLB unmapping. vmap
addresses do not have to be flushed immediately when they are vunmapped,
because the kernel will not reuse them again (would be a use-after-free)
until they are reallocated. So the addresses aren't allocated again until
a subsequent TLB flush. A single TLB flush then can flush multiple
vunmaps from each CPU.
XEN and PAT and such do not like deferred TLB flushing because they can't
always handle multiple aliasing virtual addresses to a physical address.
They now call vm_unmap_aliases() in order to flush any deferred mappings.
That call is very expensive (well, actually not a lot more expensive than
a single vunmap under the old scheme), however it should be OK if not
called too often.
The virtual memory extent information is stored in an rbtree rather than a
linked list to improve the algorithmic scalability.
There is a per-CPU allocator for small vmaps, which amortizes or avoids
global locking.
To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces
must be used in place of vmap and vunmap. Vmalloc does not use these
interfaces at the moment, so it will not be quite so scalable (although it
will use lazy TLB flushing).
As a quick test of performance, I ran a test that loops in the kernel,
linearly mapping then touching then unmapping 4 pages. Different numbers
of tests were run in parallel on an 4 core, 2 socket opteron. Results are
in nanoseconds per map+touch+unmap.
threads vanilla vmap rewrite
1 14700 2900
2 33600 3000
4 49500 2800
8 70631 2900
So with a 8 cores, the rewritten version is already 25x faster.
In a slightly more realistic test (although with an older and less
scalable version of the patch), I ripped the not-very-good vunmap batching
code out of XFS, and implemented the large buffer mapping with vm_map_ram
and vm_unmap_ram... along with a couple of other tricks, I was able to
speed up a large directory workload by 20x on a 64 CPU system. I believe
vmap/vunmap is actually sped up a lot more than 20x on such a system, but
I'm running into other locks now. vmap is pretty well blown off the
profiles.
Before:
1352059 total 0.1401
798784 _write_lock 8320.6667 <- vmlist_lock
529313 default_idle 1181.5022
15242 smp_call_function 15.8771 <- vmap tlb flushing
2472 __get_vm_area_node 1.9312 <- vmap
1762 remove_vm_area 4.5885 <- vunmap
316 map_vm_area 0.2297 <- vmap
312 kfree 0.1950
300 _spin_lock 3.1250
252 sn_send_IPI_phys 0.4375 <- tlb flushing
238 vmap 0.8264 <- vmap
216 find_lock_page 0.5192
196 find_next_bit 0.3603
136 sn2_send_IPI 0.2024
130 pio_phys_write_mmr 2.0312
118 unmap_kernel_range 0.1229
After:
78406 total 0.0081
40053 default_idle 89.4040
33576 ia64_spinlock_contention 349.7500
1650 _spin_lock 17.1875
319 __reg_op 0.5538
281 _atomic_dec_and_lock 1.0977
153 mutex_unlock 1.5938
123 iget_locked 0.1671
117 xfs_dir_lookup 0.1662
117 dput 0.1406
114 xfs_iget_core 0.0268
92 xfs_da_hashname 0.1917
75 d_alloc 0.0670
68 vmap_page_range 0.0462 <- vmap
58 kmem_cache_alloc 0.0604
57 memset 0.0540
52 rb_next 0.1625
50 __copy_user 0.0208
49 bitmap_find_free_region 0.2188 <- vmap
46 ia64_sn_udelay 0.1106
45 find_inode_fast 0.1406
42 memcmp 0.2188
42 finish_task_switch 0.1094
42 __d_lookup 0.0410
40 radix_tree_lookup_slot 0.1250
37 _spin_unlock_irqrestore 0.3854
36 xfs_bmapi 0.0050
36 kmem_cache_free 0.0256
35 xfs_vn_getattr 0.0322
34 radix_tree_lookup 0.1062
33 __link_path_walk 0.0035
31 xfs_da_do_buf 0.0091
30 _xfs_buf_find 0.0204
28 find_get_page 0.0875
27 xfs_iread 0.0241
27 __strncpy_from_user 0.2812
26 _xfs_buf_initialize 0.0406
24 _xfs_buf_lookup_pages 0.0179
24 vunmap_page_range 0.0250 <- vunmap
23 find_lock_page 0.0799
22 vm_map_ram 0.0087 <- vmap
20 kfree 0.0125
19 put_page 0.0330
18 __kmalloc 0.0176
17 xfs_da_node_lookup_int 0.0086
17 _read_lock 0.0885
17 page_waitqueue 0.0664
vmap has gone from being the top 5 on the profiles and flushing the crap
out of all TLBs, to using less than 1% of kernel time.
[akpm@linux-foundation.org: cleanups, section fix]
[akpm@linux-foundation.org: fix build on alpha]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Krzysztof Helt <krzysztof.h1@poczta.fm>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch fixes the following compile error caused by commit
589f800bb1 ("fastboot: make the raid
autodetect code wait for all devices to init"):
CC init/do_mounts_md.o
init/do_mounts_md.c: In function 'autodetect_raid':
init/do_mounts_md.c:285: error: implicit declaration of function 'msleep'
make[2]: *** [init/do_mounts_md.o] Error 1
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patchs adds the CONFIG_AIO option which allows to remove support
for asynchronous I/O operations, that are not necessarly used by
applications, particularly on embedded devices. As this is a
size-reduction option, it depends on CONFIG_EMBEDDED. It allows to
save ~7 kilobytes of kernel code/data:
text data bss dec hex filename
1115067 119180 217088 1451335 162547 vmlinux
1108025 119048 217088 1444161 160941 vmlinux.new
-7042 -132 0 -7174 -1C06 +/-
This patch has been originally written by Matt Mackall
<mpm@selenic.com>, and is part of the Linux Tiny project.
[randy.dunlap@oracle.com: build fix]
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
Cc: Benjamin LaHaise <bcrl@kvack.org>
Cc: Zach Brown <zach.brown@oracle.com>
Signed-off-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When unpacking the cpio into the initramfs, mtimes are not preserved by
default. This patch adds an INITRAMFS_PRESERVE_MTIME option that allows
mtimes stored in the cpio image to be used when constructing the
initramfs.
For embedded applications that run exclusively out of the initramfs, this
is invaluable:
When building embedded application initramfs images, its nice to know when
the files were actually created during the build process - that makes it
easier to see what files were modified when so we can compare the files
that are being used on the image with the files used during the build
process. This might help (for example) to determine if the target system
has all the updated files you expect to see w/o having to check MD5s etc.
In our environment, the whole system runs off the initramfs partition, and
seeing the modified times of the shared libraries (for example) helps us
find bugs that may have been introduced by the build system incorrectly
propogating outdated shared libraries into the image.
Similarly, many of the initializion/configuration files in /etc might be
dynamically built by the build system, and knowing when they were modified
helps us sanity check whether the target system has the "latest" files
etc.
Finally, we might use last modified times to determine whether a hot fix
should be applied or not to the running ramfs.
Signed-off-by: Nye Liu <nyet@nyet.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
identify_ramdisk_image() returns 0 (not -1) if a gzipped ramdisk is found:
if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) {
printk(KERN_NOTICE
"RAMDISK: Compressed image found at block %d\n",
start_block);
nblocks = 0;
^^^^^^^^^^^
goto done;
}
...
done:
sys_lseek(fd, start_block * BLOCK_SIZE, 0);
kfree(buf);
return nblocks;
^^^^^^^^^^^^^^
Hence correct the typo in the comment, which has existed since the
addition of compressed ramdisk support in 1.3.48.
Signed-off-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arjan/linux-2.6-fastboot:
raid, fastboot: hide RAID autodetect option if MD is compiled as a module
raid: make RAID autodetect default a KConfig option
warning: fix init do_mounts_md c
fastboot: make the RAID autostart code print a message just before waiting
fastboot: make the raid autodetect code wait for all devices to init
fastboot: Fix bootgraph.pl initcall name regexp
fastboot: fix issues and improve output of bootgraph.pl
Add a script to visualize the kernel boot process / time
Change the time resolution for initcall_debug to microseconds, from
milliseconds. This is handy to determine which initcalls you want to work
on for faster booting.
One one of my test machines, over 90% of the initcalls are less than a
millisecond and (without this patch) these are all reported as 0 msecs.
Working on the 900 us ones is more important than the 4 us ones.
With 'quiet' on the kernel command line, this adds no significant overhead
to kernel boot time.
Signed-off-by: Tim Bird <tim.bird@am.sony.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
At this time, only built-in initcalls interest us.
We can't really produce a relevant graph if we include
the modules initcall too.
I had good results after this patch (see svg in attachment).
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
After some initcall traces, some initcall names may be inconsistent.
That's because these functions will disappear from the .init section
and also their name from the symbols table.
So we have to copy the name of the function in a buffer large enough
during the trace appending. It is not costly for the ring_buffer because
the number of initcall entries is commonly not really large.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Change the boot tracer printing to make it parsable for
the scripts/bootgraph.pl script.
We have now to output two lines for each initcall, according to the
printk in do_one_initcall() in init/main.c
We need now the call's time and the return's time.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Launch the boot tracing inside the initcall_debug area. Old printk
have not been removed to keep the old way of initcall tracing for
backward compatibility.
[ mingo@elte.hu: resolved conflicts ]
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When optimizing the kernel boot time, it's very valuable to visualize
what is going on at which time. In addition, with the fastboot asynchronous
initcall level, it's very valuable to see which initcall gets run where
and when.
This patch adds a script to turn a dmesg into a SVG graph (that can be
shown with tools such as InkScape, Gimp or Firefox) and a small change
to the initcall code to print the PID of the thread calling the initcall
(so that the script can work out the parallelism).
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
This is the infrastructure to the converting the mcount call sites
recorded by the __mcount_loc section into nops on boot. It also allows
for using these sites to enable tracing as normal. When the __mcount_loc
section is used, the "ftraced" kernel thread is disabled.
This uses the current infrastructure to record the mcount call sites
as well as convert them to nops. The mcount function is kept as a stub
on boot up and not converted to the ftrace_record_ip function. We use the
ftrace_record_ip to only record from the table.
This patch does not handle modules. That comes with a later patch.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
do not expose users to CONFIG_TRACEPOINTS - tracers can select it
just fine.
update ftrace to select CONFIG_TRACEPOINTS.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Implementation of kernel tracepoints. Inspired from the Linux Kernel
Markers. Allows complete typing verification by declaring both tracing
statement inline functions and probe registration/unregistration static
inline functions within the same macro "DEFINE_TRACE". No format string
is required. See the tracepoint Documentation and Samples patches for
usage examples.
Taken from the documentation patch :
"A tracepoint placed in code provides a hook to call a function (probe)
that you can provide at runtime. A tracepoint can be "on" (a probe is
connected to it) or "off" (no probe is attached). When a tracepoint is
"off" it has no effect, except for adding a tiny time penalty (checking
a condition for a branch) and space penalty (adding a few bytes for the
function call at the end of the instrumented function and adds a data
structure in a separate section). When a tracepoint is "on", the
function you provide is called each time the tracepoint is executed, in
the execution context of the caller. When the function provided ends its
execution, it returns to the caller (continuing from the tracepoint
site).
You can put tracepoints at important locations in the code. They are
lightweight hooks that can pass an arbitrary number of parameters, which
prototypes are described in a tracepoint declaration placed in a header
file."
Addition and removal of tracepoints is synchronized by RCU using the
scheduler (and preempt_disable) as guarantees to find a quiescent state
(this is really RCU "classic"). The update side uses rcu_barrier_sched()
with call_rcu_sched() and the read/execute side uses
"preempt_disable()/preempt_enable()".
We make sure the previous array containing probes, which has been
scheduled for deletion by the rcu callback, is indeed freed before we
proceed to the next update. It therefore limits the rate of modification
of a single tracepoint to one update per RCU period. The objective here
is to permit fast batch add/removal of probes on _different_
tracepoints.
Changelog :
- Use #name ":" #proto as string to identify the tracepoint in the
tracepoint table. This will make sure not type mismatch happens due to
connexion of a probe with the wrong type to a tracepoint declared with
the same name in a different header.
- Add tracepoint_entry_free_old.
- Change __TO_TRACE to get rid of the 'i' iterator.
Masami Hiramatsu <mhiramat@redhat.com> :
Tested on x86-64.
Performance impact of a tracepoint : same as markers, except that it
adds about 70 bytes of instructions in an unlikely branch of each
instrumented function (the for loop, the stack setup and the function
call). It currently adds a memory read, a test and a conditional branch
at the instrumentation site (in the hot path). Immediate values will
eventually change this into a load immediate, test and branch, which
removes the memory read which will make the i-cache impact smaller
(changing the memory read for a load immediate removes 3-4 bytes per
site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it
also saves the d-cache hit).
About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added.
Quoting Hideo Aoki about Markers :
I evaluated overhead of kernel marker using linux-2.6-sched-fixes git
tree, which includes several markers for LTTng, using an ia64 server.
While the immediate trace mark feature isn't implemented on ia64, there
is no major performance regression. So, I think that we don't have any
issues to propose merging marker point patches into Linus's tree from
the viewpoint of performance impact.
I prepared two kernels to evaluate. The first one was compiled without
CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS.
I downloaded the original hackbench from the following URL:
http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c
I ran hackbench 5 times in each condition and calculated the average and
difference between the kernels.
The parameter of hackbench: every 50 from 50 to 800
The number of CPUs of the server: 2, 4, and 8
Below is the results. As you can see, major performance regression
wasn't found in any case. Even if number of processes increases,
differences between marker-enabled kernel and marker- disabled kernel
doesn't increase. Moreover, if number of CPUs increases, the differences
doesn't increase either.
Curiously, marker-enabled kernel is better than marker-disabled kernel
in more than half cases, although I guess it comes from the difference
of memory access pattern.
* 2 CPUs
Number of | without | with | diff | diff |
processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] |
--------------------------------------------------------------
50 | 4.811 | 4.872 | +0.061 | +1.27 |
100 | 9.854 | 10.309 | +0.454 | +4.61 |
150 | 15.602 | 15.040 | -0.562 | -3.6 |
200 | 20.489 | 20.380 | -0.109 | -0.53 |
250 | 25.798 | 25.652 | -0.146 | -0.56 |
300 | 31.260 | 30.797 | -0.463 | -1.48 |
350 | 36.121 | 35.770 | -0.351 | -0.97 |
400 | 42.288 | 42.102 | -0.186 | -0.44 |
450 | 47.778 | 47.253 | -0.526 | -1.1 |
500 | 51.953 | 52.278 | +0.325 | +0.63 |
550 | 58.401 | 57.700 | -0.701 | -1.2 |
600 | 63.334 | 63.222 | -0.112 | -0.18 |
650 | 68.816 | 68.511 | -0.306 | -0.44 |
700 | 74.667 | 74.088 | -0.579 | -0.78 |
750 | 78.612 | 79.582 | +0.970 | +1.23 |
800 | 85.431 | 85.263 | -0.168 | -0.2 |
--------------------------------------------------------------
* 4 CPUs
Number of | without | with | diff | diff |
processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] |
--------------------------------------------------------------
50 | 2.586 | 2.584 | -0.003 | -0.1 |
100 | 5.254 | 5.283 | +0.030 | +0.56 |
150 | 8.012 | 8.074 | +0.061 | +0.76 |
200 | 11.172 | 11.000 | -0.172 | -1.54 |
250 | 13.917 | 14.036 | +0.119 | +0.86 |
300 | 16.905 | 16.543 | -0.362 | -2.14 |
350 | 19.901 | 20.036 | +0.135 | +0.68 |
400 | 22.908 | 23.094 | +0.186 | +0.81 |
450 | 26.273 | 26.101 | -0.172 | -0.66 |
500 | 29.554 | 29.092 | -0.461 | -1.56 |
550 | 32.377 | 32.274 | -0.103 | -0.32 |
600 | 35.855 | 35.322 | -0.533 | -1.49 |
650 | 39.192 | 38.388 | -0.804 | -2.05 |
700 | 41.744 | 41.719 | -0.025 | -0.06 |
750 | 45.016 | 44.496 | -0.520 | -1.16 |
800 | 48.212 | 47.603 | -0.609 | -1.26 |
--------------------------------------------------------------
* 8 CPUs
Number of | without | with | diff | diff |
processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] |
--------------------------------------------------------------
50 | 2.094 | 2.072 | -0.022 | -1.07 |
100 | 4.162 | 4.273 | +0.111 | +2.66 |
150 | 6.485 | 6.540 | +0.055 | +0.84 |
200 | 8.556 | 8.478 | -0.078 | -0.91 |
250 | 10.458 | 10.258 | -0.200 | -1.91 |
300 | 12.425 | 12.750 | +0.325 | +2.62 |
350 | 14.807 | 14.839 | +0.032 | +0.22 |
400 | 16.801 | 16.959 | +0.158 | +0.94 |
450 | 19.478 | 19.009 | -0.470 | -2.41 |
500 | 21.296 | 21.504 | +0.208 | +0.98 |
550 | 23.842 | 23.979 | +0.137 | +0.57 |
600 | 26.309 | 26.111 | -0.198 | -0.75 |
650 | 28.705 | 28.446 | -0.259 | -0.9 |
700 | 31.233 | 31.394 | +0.161 | +0.52 |
750 | 34.064 | 33.720 | -0.344 | -1.01 |
800 | 36.320 | 36.114 | -0.206 | -0.57 |
--------------------------------------------------------------
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'proc' of git://git.kernel.org/pub/scm/linux/kernel/git/adobriyan/proc:
proc: remove kernel.maps_protect
proc: remove now unneeded ADDBUF macro
[PATCH] proc: show personality via /proc/pid/personality
[PATCH] signal, procfs: some lock_task_sighand() users do not need rcu_read_lock()
proc: move PROC_PAGE_MONITOR to fs/proc/Kconfig
proc: make grab_header() static
proc: remove unused get_dma_list()
proc: remove dummy vmcore_open()
proc: proc_sys_root tweak
proc: fix return value of proc_reg_open() in "too late" case
Fixed up trivial conflict in removed file arch/sparc/include/asm/dma_32.h
RAID autodetect has the side effect of requiring synchronisation
of all device drivers, which can make the boot several seconds longer
(I've measured 7 on one of my laptops).... even for systems that don't
have RAID setup for the root filesystem (the only FS where this matters).
This patch makes the default for autodetect a config option; either way
the user can always override via the kernel command line.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: NeilBrown <neilb@suse.de>
fix warning:
init/do_mounts_md.c: In function ‘md_run_setup’:
init/do_mounts_md.c:282: warning: ISO C90 forbids mixed declarations and code
also, use the opportunity to put the RAID autodetection code
into a separate function - this also solves a checkpatch style warning.
No code changed:
md5:
aa36a35faef371b05f1974ad583bdbbd do_mounts_md.o.before.asm
aa36a35faef371b05f1974ad583bdbbd do_mounts_md.o.after.asm
Signed-off-by: Ingo Molnar <mingo@elte.hu>
As requested/suggested by Neil Brown: make the raid code print that it's
about to wait for probing to be done as well as give a suggestion on how
to disable the probing if the user doesn't use raid.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com
The raid autodetect code really needs to have all devices probed before
it can detect raid arrays; not doing so would give rather messy situations
where arrays would get detected as degraded while they shouldn't be etc.
This is in preparation of removing the "wait for everything to init"
code that makes everyone pay, not just raid users.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
When optimizing the kernel boot time, it's very valuable to visualize
what is going on at which time. In addition, with some of the initializing
going asynchronous soon, it's valuable to track/print which worker thread
is executing the initialization.
This patch adds a script to turn a dmesg into a SVG graph (that can be
shown with tools such as InkScape, Gimp or Firefox) and a small change
to the initcall code to print the PID of the thread calling the initcall
(so that the script can work out the parallelism).
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
DEBUG_BLOCK_EXT_DEVT shuffles SCSI and IDE device numbers and root
device number set using rdev become meaningless. Root devices should
be explicitly specified using textual names. Warn about it if root
can't be found and DEBUG_BLOCK_EXT_DEVT is enabled. Also, add warning
to the help text.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
.. small detail, but the silly e1000e initcall warning debugging caused
me to look at this code. Rather than gouge my eyes out with a spoon, I
just fixed it.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I noticed that sysctl_check.o was the largest object file in
a allnoconfig build in kernel/*.
36243 0 0 36243 8d93 kernel/sysctl_check.o
This is because it was default y and && EMBEDDED. But I don't
really see a need for a non kernel developer to have their
sysctls checked all the time.
So move the Kconfig into the kernel debugging section and
also drop the default y and the EMBEDDED check.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The kernel has this really nice facility where if you put "initcall_debug"
on the kernel commandline, it'll print which function it's going to
execute just before calling an initcall, and then after the call completes
it will
1) print if it had an error code
2) checks for a few simple bugs (like leaving irqs off)
and
3) print how long the init call took in milliseconds.
While trying to optimize the boot speed of my laptop, I have been loving
number 3 to figure out what to optimize... ... and then I wished that
the same thing was done for module loading.
This patch makes the module loader use this exact same functionality; it's
a logical extension in my view (since modules are just sort of late
binding initcalls anyway) and so far I've found it quite useful in finding
where things are too slow in my boot.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Given that the init/Kconfig file uses a "menuconfig" directive for
modules already, might as well wrap all the submenu entries in an "if"
to toss all those dependencies.
Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild-fixes:
kbuild: scripts/ver_linux: don't set PATH
Kconfig/init: change help text to match default value
kbuild: genksyms: Include extern information in dumps
kbuild: genksyms parser: fix the __attribute__ rule
kbuild: scripts/genksyms/lex.l: add %option noinput
kconfig: scripts/kconfig/zconf.l: add %option noinput
kbuild: fix O=... build of um
