The current implementation of worker threads in Btrfs has races in
worker stopping code, which cause all kinds of panics and lockups when
running btrfs/011 xfstest in a loop. The problem is that
btrfs_stop_workers is unsynchronized with respect to check_idle_worker,
check_busy_worker and __btrfs_start_workers.
E.g., check_idle_worker race flow:
btrfs_stop_workers(): check_idle_worker(aworker):
- grabs the lock
- splices the idle list into the
working list
- removes the first worker from the
working list
- releases the lock to wait for
its kthread's completion
- grabs the lock
- if aworker is on the working list,
moves aworker from the working list
to the idle list
- releases the lock
- grabs the lock
- puts the worker
- removes the second worker from the
working list
......
btrfs_stop_workers returns, aworker is on the idle list
FS is umounted, memory is freed
......
aworker is waken up, fireworks ensue
With this applied, I wasn't able to trigger the problem in 48 hours,
whereas previously I could reliably reproduce at least one of these
races within an hour.
Reported-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Each ordered operation has a free callback, and this was called with the
worker spinlock held. Josef made the free callback also call iput,
which we can't do with the spinlock.
This drops the spinlock for the free operation and grabs it again before
moving through the rest of the list. We'll circle back around to this
and find a cleaner way that doesn't bounce the lock around so much.
Signed-off-by: Chris Mason <chris.mason@fusionio.com>
cc: stable@kernel.org
* pm-sleep: (51 commits)
PM: Drop generic_subsys_pm_ops
PM / Sleep: Remove forward-only callbacks from AMBA bus type
PM / Sleep: Remove forward-only callbacks from platform bus type
PM: Run the driver callback directly if the subsystem one is not there
PM / Sleep: Make pm_op() and pm_noirq_op() return callback pointers
PM / Sleep: Merge internal functions in generic_ops.c
PM / Sleep: Simplify generic system suspend callbacks
PM / Hibernate: Remove deprecated hibernation snapshot ioctls
PM / Sleep: Fix freezer failures due to racy usermodehelper_is_disabled()
PM / Sleep: Recommend [un]lock_system_sleep() over using pm_mutex directly
PM / Sleep: Replace mutex_[un]lock(&pm_mutex) with [un]lock_system_sleep()
PM / Sleep: Make [un]lock_system_sleep() generic
PM / Sleep: Use the freezer_count() functions in [un]lock_system_sleep() APIs
PM / Freezer: Remove the "userspace only" constraint from freezer[_do_not]_count()
PM / Hibernate: Replace unintuitive 'if' condition in kernel/power/user.c with 'else'
Freezer / sunrpc / NFS: don't allow TASK_KILLABLE sleeps to block the freezer
PM / Sleep: Unify diagnostic messages from device suspend/resume
ACPI / PM: Do not save/restore NVS on Asus K54C/K54HR
PM / Hibernate: Remove deprecated hibernation test modes
PM / Hibernate: Thaw processes in SNAPSHOT_CREATE_IMAGE ioctl test path
...
Conflicts:
kernel/kmod.c
Dan Carpenter noticed that we were doing a double unlock on the worker
lock, and sometimes picking a worker thread without the lock held.
This fixes both errors.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
* master: (848 commits)
SELinux: Fix RCU deref check warning in sel_netport_insert()
binary_sysctl(): fix memory leak
mm/vmalloc.c: remove static declaration of va from __get_vm_area_node
ipmi_watchdog: restore settings when BMC reset
oom: fix integer overflow of points in oom_badness
memcg: keep root group unchanged if creation fails
nilfs2: potential integer overflow in nilfs_ioctl_clean_segments()
nilfs2: unbreak compat ioctl
cpusets: stall when updating mems_allowed for mempolicy or disjoint nodemask
evm: prevent racing during tfm allocation
evm: key must be set once during initialization
mmc: vub300: fix type of firmware_rom_wait_states module parameter
Revert "mmc: enable runtime PM by default"
mmc: sdhci: remove "state" argument from sdhci_suspend_host
x86, dumpstack: Fix code bytes breakage due to missing KERN_CONT
IB/qib: Correct sense on freectxts increment and decrement
RDMA/cma: Verify private data length
cgroups: fix a css_set not found bug in cgroup_attach_proc
oprofile: Fix uninitialized memory access when writing to writing to oprofilefs
Revert "xen/pv-on-hvm kexec: add xs_reset_watches to shutdown watches from old kernel"
...
Conflicts:
kernel/cgroup_freezer.c
Al pointed out we have some random problems with the way we account for
num_workers_starting in the async thread stuff. First of all we need to make
sure to decrement num_workers_starting if we fail to start the worker, so make
__btrfs_start_workers do this. Also fix __btrfs_start_workers so that it
doesn't call btrfs_stop_workers(), there is no point in stopping everybody if we
failed to create a worker. Also check_pending_worker_creates needs to call
__btrfs_start_work in it's work function since it already increments
num_workers_starting.
People only start one worker at a time, so get rid of the num_workers argument
everywhere, and make btrfs_queue_worker a void since it will always succeed.
Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
If we have a constant stream of end_io completions or crc work,
we can hit softlockup messages from the async helper threads. This
adds a cond_resched() into the loop to avoid them.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
There is no reason to export two functions for entering the
refrigerator. Calling refrigerator() instead of try_to_freeze()
doesn't save anything noticeable or removes any race condition.
* Rename refrigerator() to __refrigerator() and make it return bool
indicating whether it scheduled out for freezing.
* Update try_to_freeze() to return bool and relay the return value of
__refrigerator() if freezing().
* Convert all refrigerator() users to try_to_freeze().
* Update documentation accordingly.
* While at it, add might_sleep() to try_to_freeze().
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Samuel Ortiz <samuel@sortiz.org>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jan Kara <jack@suse.cz>
Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
Cc: Christoph Hellwig <hch@infradead.org>
Yan Zheng noticed two places we were doing a lot of work
without task->state set to TASK_RUNNING. This sets the state
properly after we get ready to sleep but decide not to.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
The btrfs async worker threads are used for a wide variety of things,
including processing bio end_io functions. This means that when
the endio threads aren't running, the rest of the FS isn't
able to do the final processing required to clear PageWriteback.
The endio threads also try to exit as they become idle and
start more as the work piles up. The problem is that starting more
threads means kthreadd may need to allocate ram, and that allocation
may wait until the global number of writeback pages on the system is
below a certain limit.
The result of that throttling is that end IO threads wait on
kthreadd, who is waiting on IO to end, which will never happen.
This commit fixes the deadlock by handing off thread startup to a
dedicated thread. It also fixes a bug where the on-demand thread
creation was creating far too many threads because it didn't take into
account threads being started by other procs.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
It was possible for an async worker thread to be selected to
receive a new work item, but exit before the work item was
actually placed into that thread's work list.
This commit fixes the race by incrementing the num_pending
counter earlier, and making sure to check the number of pending
work items before a thread exits.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The exit-on-idle code for async worker threads was incorrectly
calling spin_lock_irq with interrupts already off.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
After a new worker thread starts, it is placed into the
list of idle threads. But, this may race with a
check for idle done by the worker thread itself, resulting
in a double list_add operation.
This fix adds a check to make sure the idle thread addition
is done properly.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This changes the btrfs worker threads to batch work items
into a local list. It allows us to pull work items in
large chunks and significantly reduces the number of times we
need to take the worker thread spinlock.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btrfs worker thread spinlock was being used both for the
queueing of IO and for the processing of ordered events.
The ordered events never happen from end_io handlers, and so they
don't need to use the _irq version of spinlocks. This adds a
dedicated lock to the ordered lists so they don't have to run
with irqs off.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The Btrfs worker threads don't currently die off after they have
been idle for a while, leading to a lot of threads sitting around
doing nothing for each mount.
Also, they are unable to start atomically (from end_io hanlders).
This commit reworks the worker threads so they can be started
from end_io handlers (just setting a flag that asks for a thread
to be added at a later date) and so they can exit if they
have been idle for a long time.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If spin_lock_irqsave is called twice in a row with the same second
argument, the interrupt state at the point of the second call overwrites
the value saved by the first call. Indeed, the second call does not need
to save the interrupt state, so it is changed to a simple spin_lock.
Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
worker memory is already freed on one fail path in btrfs_start_workers,
but is still dereferenced. Switch the dereference and kfree.
Signed-off-by: Jiri Slaby <jirislaby@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch fixes a bug which may result race condition
between btrfs_start_workers() and worker_loop().
btrfs_start_workers() executed in a parent thread writes
on workers->worker and worker_loop() in a child thread
reads workers->worker. However, there is no synchronization
enforcing the order of two operations.
This patch makes btrfs_start_workers() fill workers->worker
before it starts a child thread with worker_loop()
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs is using WRITE_SYNC_PLUG to send down synchronous IOs with a
higher priority. But, the checksumming helper threads prevent it
from being fully effective.
There are two problems. First, a big queue of pending checksumming
will delay the synchronous IO behind other lower priority writes. Second,
the checksumming uses an ordered async work queue. The ordering makes sure
that IOs are sent to the block layer in the same order they are sent
to the checksumming threads. Usually this gives us less seeky IO.
But, when we start mixing IO priorities, the lower priority IO can delay
the higher priority IO.
This patch solves both problems by adding a high priority list to the async
helper threads, and a new btrfs_set_work_high_prio(), which is used
to make put a new async work item onto the higher priority list.
The ordering is still done on high priority IO, but all of the high
priority bios are ordered separately from the low priority bios. This
ordering is purely an IO optimization, it is not involved in data
or metadata integrity.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Need to check kthread_should_stop after schedule_timeout() before calling
schedule(). This causes threads to sleep with potentially no one to wake them
up causing mount(2) to hang in btrfs_stop_workers waiting for threads to stop.
Signed-off-by: Amit Gud <gud@ksu.edu>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Tracing shows the delay between when an async thread goes to sleep
and when more work is added is often very short. This commit adds
a little bit of delay and extra checking to the code right before
we schedule out.
It allows more work to be added to the worker
without requiring notifications from other procs.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The async bio submission thread was missing some bios that were
added after it had decided there was no work left to do.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
In worker_loop(), the func should check whether it has been requested to stop
before it decides to schedule out.
Otherwise if the stop request(also the last wake_up()) sent by
btrfs_stop_workers() happens when worker_loop() running after the "while"
judgement and before schedule(), woker_loop() will schedule away and never be
woken up, which will also cause btrfs_stop_workers() wait forever.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs uses kernel threads to create async work queues for cpu intensive
operations such as checksumming and decompression. These work well,
but they make it difficult to keep IO order intact.
A single writepages call from pdflush or fsync will turn into a number
of bios, and each bio is checksummed in parallel. Once the checksum is
computed, the bio is sent down to the disk, and since we don't control
the order in which the parallel operations happen, they might go down to
the disk in almost any order.
The code deals with this somewhat by having deep work queues for a single
kernel thread, making it very likely that a single thread will process all
the bios for a single inode.
This patch introduces an explicitly ordered work queue. As work structs
are placed into the queue they are put onto the tail of a list. They have
three callbacks:
->func (cpu intensive processing here)
->ordered_func (order sensitive processing here)
->ordered_free (free the work struct, all processing is done)
The work struct has three callbacks. The func callback does the cpu intensive
work, and when it completes the work struct is marked as done.
Every time a work struct completes, the list is checked to see if the head
is marked as done. If so the ordered_func callback is used to do the
order sensitive processing and the ordered_free callback is used to do
any cleanup. Then we loop back and check the head of the list again.
This patch also changes the checksumming code to use the ordered workqueues.
One a 4 drive array, it increases streaming writes from 280MB/s to 350MB/s.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When reading in block groups, a global mask of the available raid policies
should be adjusted based on the types of block groups found on disk. This
global mask is then used to decide which raid policy to use for new
block groups.
The recent allocator changes dropped the call that updated the global
mask, making all the block groups allocated at run time single striped
onto a single drive.
This also fixes the async worker threads to set any thread that uses
the requeue mechanism as busy. This allows us to avoid blocking
on get_request_wait for the async bio submission threads.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This improves the comments at the top of many functions. It didn't
dive into the guts of functions because I was trying to
avoid merging problems with the new allocator and back reference work.
extent-tree.c and volumes.c were both skipped, and there is definitely
more work todo in cleaning and commenting the code.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs had compatibility code for kernels back to 2.6.18. These have
been removed, and will be maintained in a separate backport
git tree from now on.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Before this change, btrfs would use a bdi congestion function to make
sure there weren't too many pending async checksum work items.
This change makes the process creating async work items wait instead,
leading to fewer congestion returns from the bdi. This improves
pdflush background_writeout scanning.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Large streaming reads make for large bios, which means each entry on the
list async work queues represents a large amount of data. IO
congestion throttling on the device was kicking in before the async
worker threads decided a single thread was busy and needed some help.
The end result was that a streaming read would result in a single CPU
running at 100% instead of balancing the work off to other CPUs.
This patch also changes the pre-IO checksum lookup done by reads to
work on a per-bio basis instead of a per-page. This results in many
extra btree lookups on large streaming reads. Doing the checksum lookup
right before bio submit allows us to reuse searches while processing
adjacent offsets.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When kthread_run() returns failure, this worker hasn't been
added to the list, so btrfs_stop_workers() won't free it.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This changes the worker thread pool to maintain a list of idle threads,
avoiding a complex search for a good thread to wake up.
Threads have two states:
idle - we try to reuse the last thread used in hopes of improving the batching
ratios
busy - each time a new work item is added to a busy task, the task is
rotated to the end of the line.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Btrfs has been using workqueues to spread the checksumming load across
other CPUs in the system. But, workqueues only schedule work on the
same CPU that queued the work, giving them a limited benefit for systems with
higher CPU counts.
This code adds a generic facility to schedule work with pools of kthreads,
and changes the bio submission code to queue bios up. The queueing is
important to make sure large numbers of procs on the system don't
turn streaming workloads into random workloads by sending IO down
concurrently.
The end result of all of this is much higher performance (and CPU usage) when
doing checksumming on large machines. Two worker pools are created,
one for writes and one for endio processing. The two could deadlock if
we tried to service both from a single pool.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
