The correct behavior for all registered shrinkers is to return the
number of objects in their cache. In theory this allows the Linux
VM to balance memory reclaim across all registered caches.
In commit b9b3715 this behavior was disabled in favor of returning
-1 which notifies the VM that no additional objects are available
for reclaim. This was done as a workaround to resolve thrashing
in shrink_slabs() which could occur when memory was low and numerous
core where in reclaim. Unfortunately, this has been observed to
increase the likelihood of OOM events when SPL slab consumers are
responsible for consuming the majority of memory.
Therefore, this patch makes this behavior tunable. Setting the
spl_kmem_cache_reclaim module option to 0x1 will result in the
shrinker only being called once. This is the default behavior.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Closes#358
For small objects the Linux slab allocator has several advantages
over its counterpart in the SPL. These include:
1) It is more memory-efficient and packs objects more tightly.
2) It is continually tuned to maximize performance.
Therefore it makes sense to layer the SPLs slab allocator on top
of the Linux slab allocator. This allows us to leverage the
advantages above while preserving the Illumos semantics we depend
on. However, there are some things we need to be careful of:
1) The Linux slab allocator was never designed to work well with
large objects. Because the SPL slab must still handle this use
case a cut off limit was added to transition from Linux slab
backed objects to kmem or vmem backed slabs.
spl_kmem_cache_slab_limit - Objects less than or equal to this
size in bytes will be backed by the Linux slab. By default
this value is zero which disables the Linux slab functionality.
Reasonable values for this cut off limit are in the range of
4096-16386 bytes.
spl_kmem_cache_kmem_limit - Objects less than or equal to this
size in bytes will be backed by a kmem slab. Objects over this
size will be vmem backed instead. This value defaults to
1/8 a page, or 512 bytes on an x86_64 architecture.
2) Be aware that using the Linux slab may inadvertently introduce
new deadlocks. Care has been taken previously to ensure that
all allocations which occur in the write path use GFP_NOIO.
However, there may be internal allocations performed in the
Linux slab which do not honor these flags. If this is the case
a deadlock may occur.
The path forward is definitely to start relying on the Linux slab.
But for that to happen we need to start building confidence that
there aren't any unexpected surprises lurking for us. And ideally
need to move completely away from using the SPLs slab for large
memory allocations. This patch is a first step.
NOTES:
1) The KMC_NOMAGAZINE flag was leveraged to support the Linux slab
backed caches but it is not supported for kmem/vmem backed caches.
2) Regardless of the spl_kmem_cache_*_limit settings a cache may
be explicitly set to a given type by passed the KMC_KMEM,
KMC_VMEM, or KMC_SLAB flags during cache creation.
3) The constructors, destructors, and reclaim callbacks are all
functional and will be called regardless of the cache type.
4) KMC_SLAB caches will not appear in /proc/spl/kmem/slab due to
the issues involved in presenting correct object accounting.
Instead they will appear in /proc/slabinfo under the same names.
5) Several kmem SPLAT tests needed to be fixed because they relied
incorrectly on internal kmem slab accounting. With the updated
test cases all the SPLAT tests pass as expected.
6) An autoconf test was added to ensure that the __GFP_COMP flag
was correctly added to the default flags used when allocating
a slab. This is required to ensure all pages in higher order
slabs are properly refcounted, see ae16ed9.
7) When using the SLUB allocator there is no need to attempt to
set the __GFP_COMP flag. This has been the default behavior
for the SLUB since Linux 2.6.25.
8) When using the SLUB it may be desirable to set the slub_nomerge
kernel parameter to prevent caches from being merged.
Original-patch-by: DHE <git@dehacked.net>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: DHE <git@dehacked.net>
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Closes#356
Detect the updated vfs_rename() interface and call it with an
extra flags argument.
References:
torvalds/linux@520c8b1
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #355
The problem is described in commit aeeb4e0c0a.
However, instead of disabling the binding to CPU altogether we just keep the
last CPU index across calls to taskq_create() and thus achieve even
distribution of the taskq threads across all available CPUs.
The implementation based on assumption that task queues initialization
performed in serial manner.
Signed-off-by: Andrey Vesnovaty <andrey.vesnovaty@gmail.com>
Signed-off-by: Andrey Vesnovaty <andreyv@infinidat.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#336
When using __get_free_pages to get high order memory, only the first page's
_count will set to 1, other's will be 0. When an internal page get passed into
rbd, it will eventully go into tcp_sendpage. There, it will be called with
get_page and put_page, and get freed erroneously when _count jump back to 0.
The solution to this problem is to use compound page. All pages in a
high order compound page share a single _count. So get_page and put_page in
tcp_sendpage will not cause _count jump to 0.
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#251
This behavior is more consistent with the way memory reclaim
is expected to work under Linux.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#349
By default maximal number of objects in slab can't exceed (16*2 - 1) and slab
size can't exceed 32M.
Today's high end servers having couple hundreds of RAM available for ARC may
run into a trouble with virtual memory because of the restriction mentioned
above.
Problem:
Reasons for very high number of virtual memory allocations:
* Real slab size very small relative to the size of the entire RAM
* Slabs allocated on virtual memory and fill entire ARC
The result is very high number of allocated virtual memory ranges (hundreds of
ranges). When virtual memory subsystem manages high number of ranges its
performance become so poor that it freezes from time to time.
Solution:
Number of objects per slab should be increased taking into account maximal
slab size which can also be increased if needed.
Signed-off-by: Andrey Vesnovaty <andrey.vesnovaty@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#337
When comparing times gotten from ddi_get_lbolt, we have to take account of
wrap around of jiffies. Therefore, we cannot use 't1 < t2'. Instead we should
use 't1 - t2 < 0'.
This patch add ddi_time_after and friends to address this issue. They have
strict type restriction, clock_t for vanilla and int64_t for 64 version, to
prevent type conversion from screwing things.
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#335
There is plenty of compatibility code for a hw_hostid
that isn't used by anything. At the same time, there are apparently
issues with the current hostid logic. coredumb in #zfsonlinux on
freenode reported that Fedora 17 changes its hostid on every boot, which
required force importing his pool. A suggestion by wca was to adopt
FreeBSD's behavior, where it treats hostid as zero if /etc/hostid does
not exist
Adopting FreeBSD's behavior permits us to eliminate plenty of code,
including a userland helper that invokes the system's hostid as a
fallback.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#224
The kernel's kthread_create() function is defined as "..." and there is
no va_list variant at the moment. The task name is pre-formatted into
a local buffer and passed to kthread_create() with fixed arguments.
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#347
The function was defined as a static inline with variable arguments
which causes gcc to generate errors on some distros.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tim Chase <tim@chase2k.com>
Closes#346
Provide spl_kthread_create() as a wrapper to the kernel's kthread_create()
to provide pre-3.13 semantics. Re-try if the call is interrupted or if it
would have returned -ENOMEM. Otherwise return NULL.
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#339
Due to certain assumptions made in the the cred:groupmember test it
could result in false positives when run on specific distributions.
This was solely a bug in the test case and not in the groupmember()
function which the test case was validating.
To prevent future false positives the test case has been rewritten
to be both more rigerous and to make fewer assumptions about the
system.
Minor style cleanup was done to cr_groups_search() and groupmember()
functions.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
By setting __GFP_NORETRY the kernel memory reclaim logic was allowed to
abort early and dump a falled allocation stack to the console. Since
this was done in a tight loop to fill memory it could result in a large
number of stacks being dumped to the console. This in turn slowed down
the test sufficiently so it exceeded the time limit and failed.
To resolve this issue the __GFP_NORETRY flag is being removed. This is
how it should have been called originally to ensure we're simulating
the behavior of most callers which will use the GFP_KERNEL flag.
In addition, the reclaim granularity of 1000 objects was far to coarse
for this to be a realistic test. For kmem:slab_reclaim there might
only be a few thousand objects total in the cache. Therefore, the
SPLAT_KMEM_OBJ_RECLAIM constant for these tests was lowered. This
will cause the reclaim callback to run more frequently which makes
for a better test case.
The frequency of the cache reaping in kmem:slab_reap was increased
to accommodate the reduced number of objects released during the
reclaim.
These changes only impact the test cases and were done to remove
false positives caused by the test case itself.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When this code was written it appears to have been assumed that
every taskq would have a large number of threads. In this case
it would make sense to attempt to evenly bind the threads over
all available CPUs. However, it failed to consider that creating
taskqs with a small number of threads will cause the CPUs with
lower ids become over-subscribed.
For this reason the kthread_bind() call is being removed and
we're leaving the kernel to schedule these threads as it sees fit.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#325
Use the standard Linux MODULE_VERSION macro to expose the installed
spl and splat module versions. This will also automatically add a
checksum of the .c files and headers in "srcversion". See:
/sys/module/spl/version
/sys/module/spl/srcversion
/sys/module/splat/version
/sys/module/splat/srcversion
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closeszfsonlinux/zfs#1923
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This check was originally added for SLES10, a093c6a, to check for
a 'struct vfsmount *' argument which they added. However, since
SLES10 is based on a 2.6.16 kernel which is no longer supported
this functionality was dropped. The checks were refactored to
support Linux 3.13 without concern for historical versions.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#312
GCC 4.8.1 complained about an unused flags variable when building
against Linux 2.6.26.8:
/var/tmp/portage/sys-kernel/spl-9999/work/spl-9999/module/spl/../../module/spl/spl-condvar.c:
In function ‘__cv_init’:
/var/tmp/portage/sys-kernel/spl-9999/work/spl-9999/module/spl/../../module/spl/spl-condvar.c:39:6:
error: variable ‘flags’ set but not used
[-Werror=unused-but-set-variable]
int flags = KM_SLEEP;
^
cc1: all warnings being treated as errors
Additionally, the superfluous code uses a preempt_count variable that is
no longer available on Linux 3.13. Deleting the unnecessary code fixes a
Linux 3.13 compatibility issue.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#312
Needed for Illumos #3582. This interface is supposed to support
a variable-resolution timeout with nanosecond granularity. This
implementation rounds up to microsecond resolution, as nanosecond-
precision timing is rarely needed for real-world performance
tuning and may incur unnecessary busy-waiting. usleep_range() is
used if available, otherwise udelay() or msleep() are used
depending on the length of the delay interval.
Add flags from sys/callo.h as these are used to control the behavior of
cv_timedwait_hires(). Specifically,
CALLOUT_FLAG_ABSOLUTE
Normally, the expiration passed to the timeout API functions is
an expiration interval. If this flag is specified, then it is
interpreted as the expiration time itself.
CALLOUT_FLAG_ROUNDUP
Roundup the expiration time to the next resolution boundary. If this
flag is not specified, the expiration time is rounded down.
References:
https://www.illumos.org/issues/3582illumos/illumos-gate@0689f76
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#304
These kstat interfaces are required to port
"Illumos #3537 want pool io kstats" to ZFS on Linux.
kstat_waitq_enter()
kstat_waitq_exit()
kstat_runq_enter()
kstat_runq_exit()
Additionally, zero out the ks_data buffer in __kstat_create() so
that the kstat_io_t counters are initialized to zero.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
While porting Illumos #3537 I found that ks_lock member of kstat_t
structure is different between Illumos and SPL. It is a pointer to
the kmutex_t in Illumos, but the mutex lock itself in SPL.
Apparently Illumos kstat API allows consumer to override the lock
if required. With SPL implementation it is not possible anymore.
Things were alright until the first attempt to actually override
the lock. Porting of Illumos #3537 introduced such code for the
first time.
In order to provide the Solaris/Illumos like functionality we:
1. convert ks_lock to "kmutex_t *ks_lock"
2. create a new field "kmutex_t ks_private_lock"
3. On kstat_create() ks_lock = &ks_private_lock
Thus if consumer doesn't care we still have our internal lock in use.
If, however, consumer does care she has a chance to set ks_lock to
anything else before calling kstat_install().
The rest of the code will use ks_lock regardless of its origin.
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #286
This reverts commit dba79fcbf2 in
favor of using the generic KSTAT_TYPE_RAW callbacks. The advantage
of this approach is that arbitrary types can be added without the
need to add them to the SPL.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #296
The current implementation for displaying kstats of type KSTAT_TYPE_RAW
is rather crude. This patch attempts to enhance this handling by
allowing a kstat user to register formatting callbacks which can
optionally be used.
The callbacks allow the user to implement functions for interpreting
their data and transposing it into a character buffer. This buffer,
containing a string representation of the raw data, is then be displayed
through the current /proc textual interface.
Additionally the kstats are made writable because it's now possible
to provide a useful handler via the existing ks_update() interface.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #296
It was observed that spl_kmem_cache_alloc() uses local_irq_save()
and saves the interrupt state in a local variable. This would
normally be fine except that spl_kmem_cache_alloc() calls
spl_cache_refill() which re-enables interrupts. It is then
possible that while interrupts are enabled the process is
rescheduled to a different cpu before being disable again.
This could result in us restoring the saved interrupt state
from one cpu to another.
What the consequences of this are aren't perfectly clear, but
this is clearly a bug and it has the potential to cause issues.
The code has been updated to just use local_irq_enable() and
local_irq_disable() to avoid this.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
current_kernel_time() is used by the SPLAT, but it is not meant for
performance measurement. We modify the SPLAT to use getnstimeofday(),
which is equivalent to the gethrestime() function on Solaris.
Additionally, we update gethrestime() to invoke getnstimeofday().
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#279
When CONFIG_UIDGID_STRICT_TYPE_CHECKS is enabled uid_t/git_t are
replaced by kuid_t/kgid_t, which are structures instead of integral
types. This causes any code that uses an integral type to fail to build.
The User Namespace functionality introduced in Linux 3.8 requires
CONFIG_UIDGID_STRICT_TYPE_CHECKS, so we could not build against any
kernel that supported it.
We resolve this by converting between the new kuid_t/kgid_t structures
and the original uid_t/gid_t types.
Original-patch-by: DHE
Rewrite-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#260
The PaX team started constifying `struct ctl_table` as of their Linux
3.8.0 patchset. This lead to zfsonlinux/spl#225 and Gentoo bug #463012.
While investigating our options, I learned that there is a preprocessor
directive called CONSTIFY_PLUGIN that we can use to detect the presence
of the PaX changes and adjust the code accordingly.
The PaX Team had suggested adopting ctl_table_no_const, but supporting
older kernels required declaring that whenever the CONSTIFY_PLUGIN was
set. Future compiler changes could potentially cause that to break in
the presence of -Werror, so instead we define our own spl_ctl_table
typdef and use that. This should be compatible with all PaX kernels.
This introduces a Linux kernel version number check to prevent a build
failure on versions of the PaX GCC plugin that existed for kernels
before Linux 3.8.0. Affected versions of the PaX plugin will trigger a
compiler error when they see no_const cast on a non-constified
structure. Ordinarily, we would need an autotools check to catch that.
However, it is safe to do a kernel version check instead of an autotools
check in this specific instance because the affected versions of the PaX
GCC plugin only exist for Linux kernels before 3.8.0 and the
constification of `struct ctl_table` by the PaX developers only occurs
in Linux 3.8.0 and later.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#225
The current code contains a race condition that triggers when bit 2 in
spl.spl_kmem_cache_expire is set, spl_kmem_cache_reap_now() is invoked
and another thread is concurrently accessing its magazine.
spl_kmem_cache_reap_now() currently invokes spl_cache_flush() on each
magazine in the same thread when bit 2 in spl.spl_kmem_cache_expire is
set. This is unsafe because there is one magazine per CPU and the
magazines are lockless, so it is impossible to guarentee that another
CPU is not using its magazine when this function is called.
The solution is to only touch the local CPU's magazine and leave other
CPU's magazines to other CPUs.
Reported-by: DHE
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#274
num_physpages was removed by
torvalds/linux@cfa11e08ed, so lets replace
it with totalram_pages.
This is a bug fix as much as it is a compatibility fix because
num_physpages did not reflect the number of pages actually available to
the kernel:
http://lkml.indiana.edu/hypermail/linux/kernel/0908.2/01001.html
Also, there are known issues with memory calculations when ZFS is in a
Xen dom0. There is a chance that using totalram_pages could resolve
them. This conjecture is untested at the time of writing.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#273
Because spl_slab_size() was always returning -ENOSPC for caches of
type KMC_OFFSLAB the cache could never be created. Additionally
the slab size is rounded up to a page which is what kv_alloc()
expects. The kv_alloc() code will minimally allocate a page,
in the KMC_OFFSLAB case this could be reduced.
The basic regression tests kmem:slab_small, kmem:slab_large,
and kmem:slab_align regression were updated to test KMC_OFFSLAB.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ying Zhu <casualfisher@gmail.com>
Closes#266
It has been observed that it's possible to get in a state where
shrink_slabs() will spin repeated invoking the generic kmem cache
shrinker. It fails to detect it's not making forward progress
reclaiming from the cache and doesn't give up. To ensure this
never occurs we unconditionally return -1 after reclaiming what
we can.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Richard Yao <ryao@gentoo.org>
Closeszfsonlinux/zfs#1276Closeszfsonlinux/zfs#1598Closeszfsonlinux/zfs#1432
This allows us to get nanosecond resolution. It also means
we use the same time source as utimensat(now) etc.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#255
Commit 5c7a036 correctly relocated the creation of a taskq
and the registraction of the kmem_cache_shrinker after the
initialization of the kmem tracking code. However, the
cleanup of these structures was not done before the leak
checks in spl_kmem_fini(). This resulted in an incorrect
'kmem leaked' warning even though there was no actual leak.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closeszfsonlinux/zfs#1569
This code has gotten something stale and no longer builds cleanly
against modern kernels. The two issues addressed here are as
follows:
* The hlist_*_rcu interfaces in the kernel have been relatively
unstable. Since this isn't performance critical code just use
the long standing hlist_* variants.
* In older kernels the hash_ptr() function takes a 'void *' but
in newer kernels it expects a 'const void *'. To silence the
compiler warnings about this explicitly cast it to a 'void *'.
The memset function is a similar case but it always expects
a 'void *'.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#256
Linux kernel commit torvalds/linux#59d8053f moved the definition of
struct proc_dir_entry from include/linux/proc_fs.h to the private
header fs/proc/internal.h. The SPL relied on that to map Solaris'
kstat to entries in /proc/spl/kstat.
Since the proc_dir_entry structure is now private the only safe
thing to do is wrap the opaque proc handle with our own structure.
This actually ends up simplify the code and is good because it
moves us away from depending on implementation details of /proc.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #257
Linux kernel commit torvalds/linux@0d01ff2 changes some
includes we were depending on through linux/proc_fs.h.
Signed-off-by: Yuxuan Shui <yshuiv7@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #257
Linux kernel commit torvalds/linux@d9dda78b renamed PDE() to
PDE_DATA(). To handle this detect the prefered interface
and define a PDE_DATA() wrapper for consistency.
Signed-off-by: Yuxuan Shui <yshuiv7@gmail.com>
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #257
Re-order initialization in spl_kmem_init to allow for kmem tracing
to work. The spl_kmem_init function calls taskq_create prior to
initializing the tracking (calling spl_kmem_init_tracking). Since
taskq_create uses kmem_alloc, NULL dereferences occur because the
global kmem_list hasn't had its next & prev pointers initialized yet.
This commit moves the calls to spl_kmem_init_tracking earlier in the
spl_kmem_init function in order that the subsequent kmem_alloc calls
(by taskq_create) work properly.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#243
The existing taskq_wait_id() function can incorrectly block
indefinitely. Reimplement it more simply using wait_event()
in a similar fashion to taskq_wait_all().
This flaw was uncovered in the context of moving vn_rdwr() to
a taskq. Previously taskq_wait_id() had no consumers outside
the SPLAT task framework which is why the issue went unnoticed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Calling cond_resched() after each object is freed and then after each
slab is freed can cause slabs of objects to live for excessive periods
of time following reclaimation. This interferes with the kernel's own
memory management when called from kswapd and can cause direct reclaim
to occur in response to memory pressure that should have been resolved.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
torvalds/linux@b67bfe0d42 changed
hlist_for_each_entry{,_rcu} to take 3 arguments instead of 4. We handle
this by switching to hlist_for_each{,_rcu}, which works across all
supported kernels.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This was a suggestion that Brian Behlendorf made when reviewing an early
pull request for Linux 3.9 support. This commit was made intentionally
easy to revert should we ever have a reason to reintroduce support for
older kernels.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
torvalds/linux@dcf787f391 enforces
const-correctness in passing struct path *.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The function prototype of vfs_getattr previoulsy took struct vfsmount *
and struct dentry * as arguments. These would always be defined together
in a struct path *.
torvalds/linux@3dadecce20 modified
vfs_getattr to take struct path * is taken as an argument instead.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
torvalds/linux@182be68478 removed the
preprocessor definition for f_vfsmnt. The ability to access the
mountpoint via ->f_path.mnt has been stable for a long time, so we
switch to that.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Update links to refer to the official ZFS on Linux website instead of
@behlendorf's personal fork on github.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Provide a mechanism to control the directory name the modules
are installed in. The kernel privdes INSTALL_MOD_DIR for
this but it was hardcoded to be 'addon/spl'.
Add a KMODDIR variable which can be passed to 'make install'
to override the default directory name. While we're here
change the default from 'addon/spl' to 'extra' which is the
kernel.org default.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Long ago infrastructure was added to the SPL to keep an internal
debug log of the last few seconds of activity. This was helpful
during the early development, but these days it is no longer
needed. I haven't had to resort to this debug buffer to resolve
an issue for several years now.
Today better more generic tools like systemtap and ftrace have
evolved to the point where they can be used for this purpose.
Along with the stack trace dumped to the system console, and in
rare cases a crash dump we almost always have the debug we need.
Therefore, I'm disabling the code which automatically dumps
this log to disk during an assertion except for the case where
spl_debug_panic_on_bug is set (disabled by default).
This should be viewed as a first step towards either.
a) Retiring this infrastructure and complexity entirely, or
b) Integrating this logging more properly with ftrace.
As part of this change I'm also removing from the packages the
undocumented spl utility which is used to decode the binary logs.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The tsd_exit() and tsd_destroy() functions remove entries from
hash bins without taking the hash bin lock. They do take the
table lock, but tsd_get() and tsd_set() only take the hash bin
lock to allow for maximum concurency.
The result is that while tsd_get() and tsd_set() are traversing
the hash bin list it can be modified by another thread in which
happens to hash to the same value. To avoid this add the needed
locking to tsd_exit() and tsd_destroy().
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#174
Cache aging was implemented because it was part of the default Solaris
kmem_cache behavior. The idea is that per-cpu objects which haven't been
accessed in several seconds should be returned to the cache. On the other
hand Linux slabs never move objects back to the slabs unless there is
memory pressure on the system.
This behavior is now configurable through the 'spl_kmem_cache_expire'
module option. The value is a bit mask with the following meaning.
0x1 - Solaris style cache aging eviction is enabled.
0x2 - Linux style low memory eviction is enabled.
Both methods may be safely enabled simultaneously, but by default
both are disabled. It has never been clear if the kmem cache aging
(which has been around from day one) actually does any good. It has
however been the source of numerous bugs so I wouldn't mind retiring
it entirely.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes zfsonlinux/zfs#1227
Closes#210
This functionality is no longer required by ZFS, see commit
zfsonlinux/zfs@7b3e34ba5a.
Since there are no other consumers, and because it adds
additional autoconf complexity which must be maintained
the spl_invalidate_inodes() function has been removed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#795
Commit a10287e00d slightly reworked
the slab ageing code such that it is no longer dependent on the
Linux delayed work queue interfaces.
This was good for portability and performance, but it requires us
to use the on_each_cpu() function to execute the spl_magazine_age()
function. That means that the function is now executing in interrupt
context whereas before it was scheduled in normal process context.
And that means we need to be slightly more careful about the locking
in the interrupt handler.
With the reworked code it's possible that we'll be holding the
skc->skc_lock and be interrupted to handle the spl_magazine_age()
IRQ. This will result in a deadlock and soft lockup errors unless
we're careful to detect the contention and avoid taking the lock in
the interupt handler. So that's what this patch does.
Alternately, (and slightly more conventionally) we could have used
spin_lock_irqsave() to prevent this race entirely but I'd perfer to
avoid disabling interrupts as much as possible due to performance
concerns. There is absolutely no penalty for us not aging objects
out of the magazine due to contention.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Closeszfsonlinux/zfs#1193
As of Linux 3.4 the UMH_WAIT_* constants were renumbered. In
particular, the meaning of "1" changed from UMH_WAIT_PROC (wait for
process to complete), to UMH_WAIT_EXEC (wait for the exec, but not the
process). A number of call sites used the number 1 instead of the
constant name, so the behavior was not as expected on kernels with
this change.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
In the upstream kernel the FALLOC_FL_PUNCH_HOLE #define was
introduced after the fallocate() function was moved from the
inode_operations to the file_operations structure. Therefore,
the SPL code assumed that if FALLOC_FL_PUNCH_HOLE was defined
it was safe to use f_ops->fallocate().
Unfortunately, the RHEL6.4 kernel has only backported the
FALLOC_FL_PUNCH_HOLE #define and not the fallocate() change.
To address this compatibility issue the spl_filp_fallocate()
helper function was added to properly detect which interface
is available.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Under Linux when a task is waiting on I/O it should call the
io_schedule() function for proper accounting. The Solaris
cv_wait() function provides no way to specify what the cv
is waiting on therefore cv_wait_io() is introduced.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#206
Due to I/O buffering the helper may return successfully before
the proc handler has a chance to execute. To catch this case
wait up to 1 second to verify spl_kallsyms_lookup_name_fn was
updated to a non SYMBOL_POISON value.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closeszfsonlinux/zfs#699Closeszfsonlinux/zfs#859
Shift the asynchronous allocations over to use the taskq interfaces.
This allows us to abandon the kernels delayed work queue interface
and all the compatibility code it requires.
This code never actually used the delay functionality it was just
done this way to leverage the existing compatibility code. All that
is required is a thread context to perform the allocation in. The
only thing clever in this change is that we take advantage of the
preallocated task queue entries to avoid a memory allocation.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Shift the cache and magazine ageing functionality over to the new
delayed taskq interfaces. This allows us to abandon the kernels
delayed work queue interface and all the compatibility code it
requires.
However, the delayed taskq interface does not allow us to schedule
a task for a specfic cpu so the ageing code was slightly reworked.
The magazine ageing delay has been directly linked to the cache
ageing function. The spl_cache_age() function invokes on_each_cpu()
in order to run spl_magazine_age() on each cpu. It then blocks
waiting for them to complete and promptly reclaims any free slabs.
When restructing the code wasn't the primary goal I think the
new code is far more understable and maintainable. It also should
help minimize magazine thrashing because free slabs are immediately
released after the magazine is aged.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When this code was originally written I went overboard and allowed
for the possibility of creating a cache in an atomic context. In
practice there are no callers which ever do this. This makes sense
since a cache is by design a long lived data structure.
To prevent abuse of this function going forward I'm removing the
code which is supported to handle an atomic context. All allocators
have been updated to use KM_SLEEP and the might_sleep() debug macro
has been added to immediately detect atomic callers.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The slightly increased size of the taskq_ent_t when debugging is
enabled has pushed the taskq:front splat test over frame size
limit. To resolve this dynamically allocate the taskq_ent_t
structures so they are part of the heap instead of the stack.
In function 'splat_taskq_test6_impl'
error: the frame size of 1648 bytes is larger than 1024 bytes
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The slightly increased size of the taskq_ent_t when debugging is
enabled has pushed the taskq:order splat test over frame size
limit. To resolve this dynamically allocate the taskq_ent_t
structures so they are part of the heap instead of the stack.
In function 'splat_taskq_test5_impl'
error: the frame size of 1680 bytes is larger than 1024 bytes
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Add a test case for taskq_cancel_id() to verify it is working
properly. Just like taskq:delay we start by dispatching 100
tasks. However this time 1/3 of the tasks use taskq_dispatch()
and will be run immediately, and 2/3 use taskq_dispatch_delay().
The idea is to create a busy taskq with both active, pending,
and delayed tasks.
After all the items have been successfully dispatched the test
begins randomly canceling known task ids. It will do this for
5 seconds randomly canceling a task id and then sleeping for a
few milliseconds. The task being canceled may have already run,
still be on the pending list, or may be currently being executed
by a worker thread. The idea is to ensure we catch any subtle
race conditions.
Once all the non-canceled tasks have completed we cross check
the number of tasks which ran with the number of tasks which
were successfully canceled. Additionally, we verify that the
taskq_cancel_id() function never blocks longer than needed.
This time is bounded by the longest run time of the task which
was dispatched.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Add a test case for taskq_dispatch_delay() to verify it is working
properly. The test dispatchs 100 tasks to a taskq with random
expiration times spread over 5 seconds. As each task expires and
gets executed by a worker thread it verifies that it was run at
the correct time. Once all the delayed tasks have been executed
we double check that all the dispatched tasks were successful.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Add the ability to dispatch a delayed task to a taskq. The desired
behavior is for the task to be queued but not executed by a worker
thread until the expiration time is reached. To achieve this two
new functions were added.
* taskq_dispatch_delay() -
This function behaves exactly like taskq_dispatch() however it
takes a third 'expire_time' argument. The caller should pass the
desired time the task should be executed as an absolute value in
jiffies. The task is guarenteed not to run before this time, it
may run slightly latter if all the worker threads are busy.
* taskq_cancel_id() -
Given a task id attempt to cancel the task before it gets executed.
This is primarily useful for canceling delay tasks but can be used for
canceling any previously dispatched task. There are three possible
return values.
0 - The task was found and canceled before it was executed.
ENOENT - The task was not found, either it was already run or an
invalid task id was supplied by the caller.
EBUSY - The task is currently executing any may not be canceled.
This function will block until the task has been completed.
* taskq_wait_all() -
The taskq_wait_id() function was renamed taskq_wait_all() to more
clearly reflect its actual behavior. It is only curreny used by
the splat taskq regression tests.
* taskq_wait_id() -
Historically, the only difference between this function and
taskq_wait() was that you passed the task id. In both functions you
would block until ALL lower task ids which executed. This was
semantically correct but could be very slow particularly if there
were delay tasks submitted.
To better accomidate the delay tasks this function was reimplemnted.
It will now only block until the passed task id has been completed.
This is actually a fairly low risk change for a few reasons.
* Only new ZFS callers will make use of the new interfaces and
very little common code was changed to support the new functions.
* The existing taskq_wait() implementation was not changed just
slightly refactored.
* The newly optimized taskq_wait_id() implementation was never
used by ZFS we can't accidentally introduce a new bug there.
NOTE: This functionality does not exist in the Illumos taskqs.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When the taskq implementation was originally written I wrapped all
the API functions in #define's. This was done as a preventative
measure to ensure that a taskq symbol never conflicted with an
existing kernel symbol.
However, in practice the taskq symbols never conflicted. The only
major conflicts occured with the kmem cache API. Since this added
layer of obfuscation never bought us anything for the taskq's I'm
removing it.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Update the taskq implementation to conform with the style used
throughout the rest of the code. There are no functional
changes in this commit.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Ensure the test thread blocks until the shrinker has completed its
work. This is done by putting the test thread to sleep and waking
it each time the shrinker callback runs. Once the shrinker size
drops to zero or we time out the test is allowed to proceed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#96Closes#125Closes#182
The taskq:front test has a race condition where task 4 and 8
race to complete, due to an incorrectly calculated set of delay
"factors" (T). If task 4 wins and actually finishes first, the
verification of the order of completion will fail.
The delays calculated to order task completion do not take into
account the terminal line in the table, and so are all off by
a factor of 1. This causes all the tasks in all queues to finish
sooner than expected and the accumulated error is the root cause
of tasks 4 and 8 racing to complete first. Before the change the
"actual" table looks like I commented in #130.
I changed:
* the table in the comment to correctly reflect the test and the
factor timings needed.
* the individual task delay factors of T so that ONLY 1 task will
every 2T. (on average)
* 1T was reduced from 100ms to 50ms. This halves the duration of
the test and makes any remaining raciness more likely to cause
failures, but it did not cause the test to fail.
* simplified the delay factor logic by using a table look-up
instead of a switch.
* Added a "task started" message so that with -v it is possible
to see the order tasks are started.
* Moved the "task completed" message inside the spinlock so that
with -v the message truly reflects the absolute order of
completion as guaranteed by the spinlock.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#130
When the Linux 3.6 KERN_PATH_LOCKED compatibility code was added
by commit bcb1589 an entirely new vn_remove() implementation was
added. That function did not properly handle an error from
spl_kern_path_locked() which would result in an panic. This
patch addresses the issue by returning the error to the caller.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#187
The preferred kernel interface for creating threads has been
kthread_create() for a long time now. However, several of the
SPLAT tests still use the legacy kernel_thread() function which
has finally been dropped (mostly).
Update the condvar and rwlock SPLAT tests to use the modern
interface. Frankly this is something we should have done a
long time ago.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#194
Allowing the spl_cache_grow_work() function to reclaim inodes
allows for two unlikely deadlocks. Therefore, we clear __GFP_FS
for these allocations. The two deadlocks are:
* While holding the ZFS_OBJ_HOLD_ENTER(zsb, obj1) lock a function
calls kmem_cache_alloc() which happens to need to allocate a
new slab. To allocate the new slab we enter FS level reclaim
and attempt to evict several inodes. To evict these inodes we
need to take the ZFS_OBJ_HOLD_ENTER(zsb, obj2) lock and it
just happens that obj1 and obj2 use the same hashed lock.
* Similar to the first case however instead of getting blocked
on the hash lock we block in txg_wait_open() which is waiting
for the next txg which isn't coming because the txg_sync
thread is blocked in kmem_cache_alloc().
Note this isn't a 100% fix because vmalloc() won't strictly
honor __GFP_FS. However, it practice this is sufficient because
several very unlikely things must all occur concurrently.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#1101
If we are reaping from the cache and a concurrent allocation
occurs then the caller must block until the reaping is complete.
This is signaled by the clearing of the KMC_BIT_REAPING bit.
Otherwise the caller will be in a tight loop which takes and
releases the skc->skc_cache lock. When there are multiple
concurrent callers the system will thrash on the lock and
appear to lock up.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Because only virtual slabs may have emergency objects and these
objects are guaranteed to have physical addresses. It can be
easily determined if the passed object is a virtual slab object
or an emergency object. This allows us to completely optimize
the emergency object free case out of the common free path.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
In the initial implementation emergency objects were tracked on a
per-cache list. The assumption was that under normal operation we
would never allocate more than a handful of these objects. So the
cost of walking the list during free was expected to be negligible.
However real world usage has shown that emergency objects tend to
be allocated in batches. A deadlock will be detected and several
thousand emergency objects will be allocated before the original
blocked slab allocation can complete.
Therefore the original list has been replaced by a red black tree
which is sorted by the memory address of each allocated object.
This bounds the worst case insertion and removal time to O(log n)
which minimize contention on the assoicated spin lock.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The entire goal of performing the slab allocations asynchronously
is to be able to detect when a vmalloc() deadlocks. In this case,
and only this case, do we want to start allocating emergency objects.
The trick here is to minimize false positives because the overhead
of tracking emergency objects is far higher than normal slab objects.
With that goal in mind the code was reworked to be less sensitive
to slow allocations by increasing the wait time. Once a cache is
is marked deadlocked all subsequent allocations which can not be
satisfied with existing cache objects will immediately allocate new
emergency objects. This behavior persists until the asynchronous
allocation completes and clears the deadlocked flag.
The result of these tweaks is that far fewer emergency objects
get created which is important because this minimizes the cost of
releasing them latter in kmem_cache_free().
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Disable this test because it may result in an OOM event on the
system which can result in the test infrastructure being killed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The Fedora 3.6 debug kernel identified the following issue where
we create a thread under a spin lock. This isn't safe because
sleeping could result in a deadlock. Therefore the lock is changed
to a mutex so it's safe to sleep.
BUG: sleeping function called from invalid context at mm/slub.c:930
in_atomic(): 1, irqs_disabled(): 0, pid: 10583, name: splat
1 lock held by splat/10583:
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The Fedora 3.6 debug kernel identified the following issue where
we call copy_to_user() under a spin lock(). This used to be safe
in older kernels but no longer appears to be true so the spin
lock was changed to a mutex. None of this code is performance
critical so allowing the process to sleep is harmless.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Restructure the the SPLAT headers such that each test only
includes the minimal set of headers it requires.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reference count every entry and exit from the condition variable
functions: cv_wait(), cv_wait_timeout(), cv_signal(), cv_broadcast().
This allows us to safely block in cv_destroy() until all consumers
have been scheduled and are no longer accessing the condition
variable memory.
In addition poison the magic value at the start of cv_destroy() to
ensure there are never any new callers after cv_destroy() is called.
The consumer is responsible for ensuring this never occurs.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Add a new kstat type for tracking useful statistics about a TXG.
The new KSTAT_TYPE_TXG type can be used to tracks the following
statistics per-txg.
txg - Unique txg number
state - State (O)pen/(Q)uiescing/(S)yncing/(C)ommitted
birth; - Creation time
nread - Bytes read
nwritten; - Bytes written
reads - IOPs read
writes - IOPs write
open_time; - Length in nanoseconds the txg was open
quiesce_time - Length in nanoseconds the txg was quiescing
sync_time; - Length in nanoseconds the txg was syncing
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Move the kstat ks_update() callback under the ks_lock. This
enables dynamically sized kstats without modification to the
kstat API.
* Create a kstat with the KSTAT_FLAG_VIRTUAL flag.
* Register a ->ks_update() callback which does:
o Frees any existing ks_data buffer.
o Set ks_data_size to the kstat array size.
o Set ks_data to an allocated buffer of size ks_data_size
o Populate the array of buffers with the required data.
The buffer allocated in the ks_update() callback is guaranteed
to remain allocated and valid while the proc sequence handler
iterates over the buffer. The lock will not be dropped until
kstat_seq_stop() function is run making it safe for concurrent
access. To allow the ks_update() callback to perform memory
allocations the lock was changed to a mutex.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Commit torvalds/linux@b8318b0 moved the __clear_close_on_exec()
function out of include/linux/fdtable.h and in to fs/file.c
making it unavailable to the SPL.
Now as it turns out we only used this function to tear down
some test infrastructure for the vn_getf()/vn_releasef() SPLAT
regression tests. Rather than implement even more autoconf
compatibilty code to handle this we just remove the test case.
This also allows us to drop three existing autoconf tests.
This does mean the SPLAT tests will no longer verify these
functions but historically they have never been a problem.
And if we feel we absolutely need this test coverage I'm
sure a more portable version of the test case could be added.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#183
The kern_path_parent() function was removed from Linux 3.6 because
it was observed that all the callers just want the parent dentry.
The simpler kern_path_locked() function replaces kern_path_parent()
and does the lookup while holding the ->i_mutex lock.
This is good news for the vn implementation because it removes the
need for us to handle the locking. However, it makes it harder to
implement a single readable vn_remove()/vn_rename() function which
is usually what we prefer.
Therefore, we implement a new version of vn_remove()/vn_rename()
for Linux 3.6 and newer kernels. This allows us to leave the
existing working implementation untouched, and to add a simpler
version for newer kernels.
Long term I would very much like to see all of the vn code removed
since what this code enabled is generally frowned upon in the kernel.
But that can't happen util we either abondon the zpool.cache file
or implement alternate infrastructure to update is correctly in
user space.
Signed-off-by: Yuxuan Shui <yshuiv7@gmail.com>
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#154
In this particular instance the allocation occurred in the context
of sys_msync()->...->zpl_putpage() where we must be careful not to
initiate additional I/O.
Signed-off-by: Massimo Maggi <massimo@mmmm.it>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This adds an interface to "punch holes" (deallocate space) in VFS
files. The interface is identical to the Solaris VOP_SPACE interface.
This interface is necessary for TRIM support on file vdevs.
This is implemented using Linux fallocate(FALLOC_FL_PUNCH_HOLE), which
was introduced in 2.6.38. For a brief time before 2.6.38 this was done
using the truncate_range inode operation, which was quickly deprecated.
This patch only supports FALLOC_FL_PUNCH_HOLE.
This adds support for the truncate_range() inode operation to
VOP_SPACE() for file hole punching. This API is deprecated and removed
in 3.5, so it's only useful for old kernels.
On tmpfs, the truncate_range() inode operation translates to
shmem_truncate_range(). Unfortunately, this function expects the end
offset to be inclusive and aligned to the end of a page. If it is not,
the kernel will stop with a BUG_ON().
This patch fixes the issue by adapting to the constraints set forth by
shmem_truncate_range().
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#168
Under certain circumstances the following functions may be called
in a context where KM_SLEEP is unsafe and can result in a deadlocked
system. To avoid this problem the unconditional KM_SLEEPs are
converted to KM_PUSHPAGEs. This will prevent them from attempting
to initiate any I/O during direct reclaim.
This change was originally part of cd5ca4b but was reverted by
330fe01. It always should have had its own commit for exactly
this reason.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When the taskq code was originally written it seemed like a good
idea to simply map TQ_SLEEP to KM_SLEEP. Unfortunately, this
assumed that the TQ_* flags would never confict with any of the
Linux GFP_* flags. When adding the TQ_PUSHPAGE support in commit
cd5ca4b this invariant was accidentally broken.
Therefore to support TQ_PUSHPAGE, which is needed for Linux, and
prevent any further confusion I have removed this direct mapping.
The TQ_SLEEP, TQ_NOSLEEP, and TQ_PUSHPAGE are no longer defined
in terms of their KM_* counterparts. Instead a simple mapping
function is introduce to convert TQ_* -> KM_* where needed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #171
This reverts commit cd5ca4b2f8
due to conflicts in the higher TQ_ bits which caused incorrect
behavior.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
There still appears to be a race in the condition variables where
->cv_mutex is set after we are woken from the cv_destroy wait queue.
This might be possible when cv_destroy() is called immediately after
cv_broadcast(). We had some troubles with this previously but
there may still be a small race, see commit d599e4f.
The following patch closes one small race and improves the ASSERTs
such that they log the offending value.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
zfsonlinux/zfs#943
The workspace required by zlib to perform compression is roughly
512MB (order-7). These allocations are so large that we should
never attempt to directly kmalloc an emergency object for them.
It is far preferable to asynchronously vmalloc an additional slab
in case it's needed. Then simply block waiting for an existing
object to be released or for the new slab to be allocated.
This can be accomplished by disabling emergency slab objects by
passing the KMC_NOEMERGENCY flag at slab creation time.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
zfsonlinux/zfs#917
Provide a flag to disable the use of emergency objects for a
specific kmem cache. There may be instances where under no
circumstances should you kmalloc() an emergency object. For
example, when you cache contains very large objects (>128k).
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When various kernel debuging options are enabled this allocation
may be larger than usual as shown by the following warning. It
is in no way harmful so we suppress the warning.
SPL: large kmem_alloc(40960, 0x80d0) at
tsd_hash_table_init:358 (76495/76495)
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#93
After the emergency slab objects were merged I started observing
timeout failures in the kmem:slab_overcommit test. These were
due to the ineffecient way the slab_overcommit reclaim function
was implemented. And due to the additional cost of potentially
allocating ten of thousands of emergency objects and tracking
them on a single list.
This patch addresses the first concern by enhansing the test
case to trace all of the allocations objects as a linked list.
This allows for a cleaner version of the reclaim function to
simply release SPLAT_KMEM_OBJ_RECLAIM objects.
Since this touches some common code all the tests which share
these data structions were also updated. After making these
changes slab_overcommit is reliably passing. However, there
is certainly additional cleanup which could be done here.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Under certain circumstances the following functions may be called
in a context where KM_SLEEP is unsafe and can result in a deadlocked
system. To avoid this problem the unconditional KM_SLEEPs are
converted to KM_PUSHPAGEs. This will prevent them from attempting
to initiate any I/O during direct reclaim.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This reverts commit 2092cf68d8. The
use of the PF_MEMALLOC flag was always a hack to work around memory
reclaim deadlocks. Those issues are believed to be resolved so this
workaround can be safely reverted.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This reverts commit b8b6e4c453. The
use of the PF_MEMALLOC flag was always a hack to work around memory
reclaim deadlocks. Those issues are believed to be resolved so this
workaround can be safely reverted.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This reverts commit 36811b4430.
Which is no longer required because there is now SPL code in
place to safely handle the deadlocks the kernel patch was designed
to address. Therefore we can unconditionally use vmalloc() and
drop all the PF_MEMALLOC code.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This reverts commit 372c257233. The
use of the PF_MEMALLOC flag was always a hack to work around memory
reclaim deadlocks. Those issues are believed to be resolved so this
workaround can be safely reverted.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This patch is designed to resolve a deadlock which can occur with
__vmalloc() based slabs. The issue is that the Linux kernel does
not honor the flags passed to __vmalloc(). This makes it unsafe
to use in a writeback context. Unfortunately, this is a use case
ZFS depends on for correct operation.
Fixing this issue in the upstream kernel was pursued and patches
are available which resolve the issue.
https://bugs.gentoo.org/show_bug.cgi?id=416685
However, these changes were rejected because upstream felt that
using __vmalloc() in the context of writeback should never be done.
Their solution was for us to rewrite parts of ZFS to accomidate
the Linux VM.
While that is probably the right long term solution, and it is
something we want to pursue, it is not a trivial task and will
likely destabilize the existing code. This work has been planned
for the 0.7.0 release but in the meanwhile we want to improve the
SPL slab implementation to accomidate this expected ZFS usage.
This is accomplished by performing the __vmalloc() asynchronously
in the context of a work queue. This doesn't prevent the posibility
of the worker thread from deadlocking. However, the caller can now
safely block on a wait queue for the slab allocation to complete.
Normally this will occur in a reasonable amount of time and the
caller will be woken up when the new slab is available,. The objects
will then get cached in the per-cpu magazines and everything will
proceed as usual.
However, if the __vmalloc() deadlocks for the reasons described
above, or is just very slow, then the callers on the wait queues
will timeout out. When this rare situation occurs they will attempt
to kmalloc() a single minimally sized object using the GFP_NOIO flags.
This allocation will not deadlock because kmalloc() will honor the
passed flags and the caller will be able to make forward progress.
As long as forward progress can be maintained then even if the
worker thread is deadlocked the critical thread will make progress.
This will eventually allow the deadlocked worker thread to complete
and normal operation will resume.
These emergency allocations will likely be slow since they require
contiguous pages. However, their use should be rare so the impact
is expected to be minimal. If that turns out not to be the case in
practice further optimizations are possible.
One additional concern is if these emergency objects are long lived.
Right now they are simply tracked on a list which must be walked when
an object is freed. Is they accumulate on a system and the list
grows freeing objects will become more expensive. This could be
handled relatively easily by using a hash instead of a list, but that
optimization (if needed) is left for a follow up patch.
Additionally, these emeregency objects could be repacked in to existing
slabs as objects are freed if the kmem_cache_set_move() functionality
was implemented. See issue https://github.com/zfsonlinux/spl/issues/26
for full details. This work would also help reduce ZFS's memory
fragmentation problems.
The /proc/spl/kmem/slab file has had two new columns added at the
end. The 'emerg' column reports the current number of these emergency
objects in use for the cache, and the following 'max' column shows
the historical worst case. These value should give us a good idea
of how often these objects are needed. Based on these values under
real use cases we can tune the default behavior.
Lastly, as a side benefit using a single work queue for the slab
allocations should reduce cpu contention on the global virtual address
space lock. This should manifest itself as reduced cpu usage for
the system.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The spl_magazine_age function had the implied assumption that it will
remain on its current cpu through its execution. In order to support
preempt enabled kernels, this assumption had to be removed.
The spl_kmem_magazine structure now holds the cpu id of the cpu it is
local to. This allows spl_magazine_age to use this field when scheduling
work to be done by the magazine's local cpu.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #98
When building SPL support into the kernel, ./copy-builtin will copy
non-toplevel .gitignore files. These files list /Makefile, which causes
git-archive to omit ./module/{spl,splat}/Makefile. The absence of these
files result in build failures when SPL is selected. ZFS is unaffected
because it puts Makefile in the toplevel .gitignore, which is not
copied. We fix SPL by emulating that behavior.
Reported-by: Fabio Erculiani <lxnay@gentoo.org>
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#152
To properly support CONFIG_PREEMPT enabled kernels, we must refrain from
using a CPU index when preemption is enabled. As a result, this change
moves the trace_set_debug_header call (which calls smp_processor_id)
within trace_get_tcd and trace_put_tcd (which disable and enable
preemption respectively).
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#160
A preprocessor definition renders this harmless. However, it is a good
idea to change this to be consistent.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Currently, the SPL tries to determine the hostid at module load. The
hostid is usually determined by running the userland program "hostid"
during module initialization.
Unfortunately, when the module initializes, it may be way too soon to be
able to run any userland programs. This is especially true when the
module is compiled directly inside the kernel (built-in); in that case,
the SPL would try to run hostid when the kernel is still initializing,
which of course is doomed to fail.
This patch fixes the issue by deferring hostid generation until
something actually needs the hostid (that is, when zone_get_hostid() is
called), thus switching to a "on-initialization" model to a "on-demand"
(lazy loading) model. ZFS only needs the hostid when some pool
operations are requested, and this always happens way after the kernel
has finished initialization, thus solving the problem.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#851
This commit introduces a "copy-builtin" script designed to prepare a
kernel source tree for building SPL as a builtin module. The script
makes a full copy of all needed files, thus making the kernel source
tree fully independent of the spl source package.
To achieve that, some compilation flags (-include, -I) have been moved
to module/Makefile. This Makefile is only used when compiling external
modules; when compiling builtin modules, a Kbuild file generated by the
configure-builtin script is used instead. This makes sure Makefiles
inside the kernel source tree does not contain references to the spl
source package.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#851
Commit 3160d4f56b changed the set of
conditions under which spl_mutex_spin_max would be implemented as a
function by changing an #if in sys/mutex.h. The corresponding
implementation file spl-mutex.c, however, has not been updated to
reflect the change. This results in undefined reference errors on
spl_mutex_spin_max under the following condition:
((!CONFIG_SMP || CONFIG_DEBUG_MUTEXES) && HAVE_MUTEX_OWNER && HAVE_TASK_CURR)
This patch fixes the issue by using the same #if in sys/mutex.h and
spl-mutex.c.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#851
In zfs, each module Makefile contains a MODULE variable which contains
the name of the module, and the following declarations reference this
variable.
In spl, there is a MODULES variable which is never used. Rename it to
MODULE and use it like in zfs. This improves consistency between the two
build systems.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue zfsonlinux/zfs#851
Explicitly cast the sizeof in hostid_read() to prevent the
following compiler warning on 32-bit systems.
module/spl/spl-generic.c:490:10: error: format '%lu' expects
argument of type 'long unsigned int', but argument 4 has type
'unsigned int' [-Werror=format]
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
zfsonlinux/spl@2092cf68d8 used
PF_MEMALLOC to workaround a bug in the Linux kernel where
allocations did not honor the gfp flags passed to vmalloc().
Unfortunately, PF_MEMALLOC has the side effect of permitting
allocations to allocate pages outside of ZONE_NORMAL. This
has been observed to result in the depletion of ZONE_DMA32.
A kernel patch is available in the Gentoo bug tracker for
this issue.
https://bugs.gentoo.org/show_bug.cgi?id=416685
This negates any benefit PF_MEMALLOC provides, so we introduce
an autotools check to disable the use of PF_MEMALLOC on
systems with patched kernels.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#126
This prevents warnings in ZFS that were caused by changes necessary to
support PaX patched kernels. When debugging is enabled, these warnings
become build failures.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#131
Usage of get_current() is not supported across all architectures.
The correct interface to use is the '#define current' which will
map to the appropriate function, usually current_thread_info().
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#119
torvalds/linux@1dce27c5aa introduced
__clear_close_on_exec() as a replacement for FD_CLR. Further commits
appear to have removed FD_CLR from the Linux source tree. This
causes the following failure:
error: implicit declaration of function '__FD_CLR'
[-Werror=implicit-function-declaration]
To correct this we update the code to use the current
__clear_close_on_exec() interface for readability. Then we introduce
an autotools check to determine if __clear_close_on_exec() is available.
If it isn't then we define some compatibility logic which used the older
FD_CLR() interface.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#124
Gcc version 4.7.0 reports the delta.tv_sec in the slab reclaim test
as potentially unitialized. In practice this will never occur but
to keep gcc happy we initialize the variable to zero.
Signed-off-by: Brian Behlendorf <behlendo@fedora-17-amd64.(none)>
In the module unload path the vm_file_cache was being destroyed
under a spin lock. Because this operation might sleep it was
possible, although very very unlikely, that this could result
in a deadlock.
This issue was indentified by using a Linux debug kernel and
has been fixed by moving the kmem_cache_destroy() out from under
the spin lock. There is no need to lock this operation here.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closeszfsonlinux/zfs#771
Correctly implementating 64-bit division for ARM requires more than
just providing the __aeabi_uldivmod() and __aeabi_ldivmod() symbols.
They are need to be implemented is such a way that the quotient and
remainder and left in specific registers after the division operation
completes. This change updates the wrapper functions to accomplish
this according to the official ARM Run-time ABI.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closeszfsonlinux/zfs#706
Originally I believed that these interfaces would be needed.
However, in practice it turned out that it was more straight
forward and maintainable to use the native Linux interfaces.
As such, this is all dead code and can be safely removed.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#109
This test is designed to verify that direct reclaim is functioning as
expected. We allocate a large number of objects thus creating a large
number of slabs. We then apply memory pressure and expect that the
direct reclaim path can easily recover those slabs. The registered
reclaim function will free the objects and the slab shrinker will call
it repeatedly until at least a single slab can be freed.
Note it may not be possible to reclaim every last slab via direct reclaim
without a failure because the shrinker_rwsem may be contended. For this
reason, quickly reclaiming 3/4 of the slabs is considered a success.
This should all be possible within 10 seconds. For reference, on a
system with 2G of memory this test takes roughly 0.2 seconds to run.
It may take longer on larger memory systems but should still easily
complete in the alloted 10 seconds.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#107
To minimize the chance of triggering an OOM during direct reclaim.
The kmem caches have been improved to make a best effort to reclaim
at least one slab when a reclaim function is registered. This helps
avoid the case where objects are released but they are spread over
multiple slabs so no memory gets reclaimed.
Care has been taken to avoid deadlocking if the reclaim function
is unable to make forward progress. Additionally, the reclaim
function may be skipped entirely if there are already free slabs
which can be safely reaped.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#107
The Linux direct reclaim path uses this out of band value to
determine if forward progress is being made. Normally this is
incremented by kmem_freepages() which is part of the various
Linux slab implementations. However, since we are using none
of that infrastructure we're responsible for incrementing this
count.
If no forward progress is detected and a subsequent allocation
fails the OOM killer will be invoked. If there was forward
progress additional reclaim will be attempted via the page
cache and registerd shrinker until the allocation succeeds.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#107
When memory pressure triggers direct memory reclaim, a slabs age
and delay should not prevent it from being freed. This patch ensures
these values are ignored, allowing an empty slab to be freed in this
code path no matter the value of its age and delay.
This prevents needless scanning of the partial slabs and has been
observed to significantly reduce the total cpu usage. In addition,
it should allow for snappier reclaim under memory pressure.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#102
Previously, the SPL tried to maintain Solaris semantics by freeing
all available (empty) slabs from its slab caches when the shrinker
was called. This is not desirable when running on Linux. To make
the SPL shrinker more Linux friendly, the actual number of freed
slabs from each of the slab caches is now derived from nr_to_scan
and skc_slab_objs.
Additionally, an accounting bug was fixed in spl_slab_reclaim()
which could cause us to reclaim one more slab than requested.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#101
Leverage the existing generic 64-bit division operations which
were originally implemented for x86 to support ARM. All that is
required is to make the symbols available to the linker with the
expected names.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
As of the removal of the taskq work list made in commit:
commit 2c02b71b14
Author: Prakash Surya <surya1@llnl.gov>
Date: Mon Dec 5 17:32:48 2011 -0800
Replace tq_work_list and tq_threads in taskq_t
To lay the ground work for introducing the taskq_dispatch_prealloc()
interface, the tq_work_list and tq_threads fields had to be replaced
with new alternatives in the taskq_t structure.
the comment above taskq_wait_check has been incorrect. This change is an
attempt at bringing that description more in line with the current
implementation. Essentially, references to the old task work list had to
be updated to reference the new taskq thread active list.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #65
Long ago I added support to the spl for condition variable names
because I thought they might be needed. It turns out they aren't.
In fact the official Solaris cv_init(9F) man page discourages
their use in the kernel.
cv_init(9F)
Parameters
name - Descriptive string. This is obsolete and should be
NULL. (Non-NULL strings are legal, but they're a
waste of kernel memory.)
Therefore, I'm removing them from the spl to reclaim this memory
and adding an ASSERT() to ensure no new consumers are added which
make use of the name.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Include the ZFS_META_RELEASE in the module load/unload messages
to more clearly indicate exactly what version of the SPL has
been loaded.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Add the bare minimum functionality to support dynamic kstats. A
complete kstat implementation should be done as part of issue #84.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #84
Until now the notion of an internal debug logging infrastructure
was conflated with enabling ASSERT()s. This patch clarifies things
by cleanly breaking the two subsystem apart. The result of this
is the following behavior.
--enable-debug - Enable/disable code wrapped in ASSERT()s.
--disable-debug ASSERT()s are used to check invariants and
are never required for correct operation.
They are disabled by default because they
may impact performance.
--enable-debug-log - Enable/disable the debug log infrastructure.
--disable-debug-log This infrastructure allows the spl code and
its consumer to log messages to an in-kernel
log. The granularity of the logging can be
controlled by a debug mask. By default the
mask disables most debug messages resulting
in a negligible performance impact. Because
of this the debug log is enabled by default.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Testing has shown that tq->tq_lock can be highly contended when a
large number of small work items are dispatched. The lock hold time
is reduced by the following changes:
1) Use exclusive threads in the work_waitq
When a single work item is dispatched we only need to wake a single
thread to service it. The current implementation uses non-exclusive
threads so all threads are woken when the dispatcher calls wake_up().
If a large number of threads are in the queue this overhead can become
non-negligible.
2) Conditionally add/remove threads from work waitq
Taskq threads need only add themselves to the work wait queue if
there are no pending work items.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #32
This reverts commit ec2b41049f.
A race condition was introduced by which a wake_up() call can be lost
after the taskq thread determines there is no pending work items,
leading to deadlock:
1. taksq thread enables interrupts
2. dispatcher thread runs, queues work item, call wake_up()
3. taskq thread runs, adds self to waitq, sleeps
This could easily happen if an interrupt for an IO completion was
outstanding at the point where the taskq thread reenables interrupts,
just before the call to add_wait_queue_exclusive(). The handler would
run immediately within the race window.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #32
Testing has shown that tq->tq_lock can be highly contended when a
large number of small work items are dispatched. The lock hold time
is reduced by the following changes:
1) Use exclusive threads in the work_waitq
When a single work item is dispatched we only need to wake a single
thread to service it. The current implementation uses non-exclusive
threads so all threads are woken when the dispatcher calls wake_up().
If a large number of threads are in the queue this overhead can become
non-negligible.
2) Conditionally add/remove threads from work waitq outside of tq_lock
Taskq threads need only add themselves to the work wait queue if there
are no pending work items. Furthermore, the add and remove function
calls can be made outside of the taskq lock since the wait queues are
protected from concurrent access by their own spinlocks.
3) Call wake_up() outside of tq->tq_lock
Again, the wait queues are protected by their own spinlock, so the
dispatcher functions can drop tq->tq_lock before calling wake_up().
A new splat test taskq:contention was added in a prior commit to measure
the impact of these changes. The following table summarizes the
results using data from the kernel lock profiler.
tq_lock time %diff Wall clock (s) %diff
original: 39117614.10 0 41.72 0
exclusive threads: 31871483.61 18.5 34.2 18.0
unlocked add/rm waitq: 13794303.90 64.7 16.17 61.2
unlocked wake_up(): 1589172.08 95.9 16.61 60.2
Each row reflects the average result over 5 test runs.
/proc/lock_stats was zeroed out before and collected after each run.
Column 1 is the cumulative hold time in microseconds for tq->tq_lock.
The tests are cumulative; each row reflects the code changes of the
previous rows. %diff is calculated with respect to "original" as
100*(orig-new)/orig.
Although calling wake_up() outside of the taskq lock dramatically
reduced the taskq lock hold time, the test actually took slightly more
wall clock time. This is because the point of contention shifts from
the taskq lock to the wait queue lock. But the change still seems
worthwhile since it removes our taskq implementation as a bottleneck,
assuming the small increase in wall clock time to be statistical
noise.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#32
Add a test designed to generate contention on the taskq spinlock by
using a large number of threads (100) to perform a large number (131072)
of trivial work items from a single queue. This simulates conditions
that may occur with the zio free taskq when a 1TB file is removed from a
ZFS filesystem, for example. This test should always pass. Its purpose
is to provide a benchmark to easily measure the effectiveness of taskq
optimizations using statistics from the kernel lock profiler.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #32
Apply the same fix to SPL that was applied to ZFS earlier at:
zfsonlinux/zfs@d433c20651
Additionally quote @LINUX_SYMBOLS@ because it is a null substitution
in this configuration, which results in a `[ -f ]` expression that
incorrectly evaluates to true.
# ./configure --with-config=user
# make distclean
Making distclean in module
make[1]: Entering directory `/spl/module'
make -C SUBDIRS=`pwd` clean
make: Entering an unknown directory
make: *** SUBDIRS=/spl/module: No such file or directory. Stop.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The Proxmox VE kernel contains a patch which renames the function
invalidate_inodes() to invalidate_inodes_check(). In the process
it adds a 'check' argument and a '#define invalidate_inodes(x)'
compatibility wrapper for legacy callers. Therefore, if either
of these functions are exported invalidate_inodes() can be
safely used.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#58
A preallocated taskq_ent_t's tqent_flags must be checked prior to
servicing the taskq_ent_t. Once a preallocated taskq entry is serviced,
the ownership of the entry is handed back to the caller of
taskq_dispatch, thus the entry's contents can potentially be mangled.
In particular, this is a problem in the case where a preallocated taskq
entry is serviced, and the caller clears it's tqent_flags field. Thus,
when the function returns and task_done is called, it looks as though
the entry is **not** a preallocated task (when in fact it **is** a
preallocated task).
In this situation, task_done will place the preallocated taskq_ent_t
structure onto the taskq_t's free list. This is a **huge** mistake. If
the taskq_ent_t is then freed by the caller of taskq_dispatch, the
taskq_t's free list will hold a pointer to garbage data. Even worse, if
nothing has over written the freed memory before the pointer is
dereferenced, it may still look as though it points to a valid list_head
belonging to a taskq_ent_t structure.
Thus, the task entry's flags are now copied prior to servicing the task.
This copy is then checked to see if it is a preallocated task, and
determine if the entry needs to be passed down to the task_done
function.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#71
The taskq_t's active thread list is sorted based on its
tqt_ent->tqent_id field. The list is kept sorted solely by inserting
new taskq_thread_t's in their correct sorted location; no other
means is used. This means that once inserted, if a taskq_thread_t's
tqt_ent->tqent_id field changes, the list runs the risk of no
longer being sorted.
Prior to the introduction of the taskq_dispatch_prealloc() interface,
this was not a problem as a taskq_ent_t actively being serviced under
the old interface should always have a static tqent_id field. Thus,
once the taskq_thread_t is added to the taskq_t's active thread list,
the taskq_thread_t's tqt_ent->tqent_id field would remain constant.
Now, this is no longer the case. Currently, if using the
taskq_dispatch_prealloc() interface, any given taskq_ent_t actively
being serviced _may_ have its tqent_id value incremented. This happens
when the preallocated taskq_ent_t structure is recursively dispatched.
Thus, a taskq_thread_t could potentially have its tqt_ent->tqent_id
field silently modified from under its feet. If this were to happen
to a taskq_thread_t on a taskq_t's active thread list, this would
compromise the integrity of the order of the list (as the list
_may_ no longer be sorted).
To get around this, the taskq_thread_t's taskq_ent_t pointer was
replaced with its own static copy of the tqent_id. So, as a taskq_ent_t
is pulled off of the taskq_t's pending list, a static copy of its
tqent_id is made and this copy is used to sort the active thread
list. Using a static copy is key in ensuring the integrity of the
order of the active thread list. Even if the underlying taskq_ent_t
is recursively dispatched (as has its tqent_id modified), this
static copy stored inside the taskq_thread_t will remain constant.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #71
The splat-taskq test functions were slightly modified to exercise
the new taskq interface in addition to the old interface. If the
old interface passes each of its tests, the new interface is
exercised. Both sub tests (old interface and new interface) must
pass for each test as a whole to pass.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#65
This patch implements the taskq_dispatch_prealloc() interface which
was introduced by the following illumos-gate commit. It allows for
a preallocated taskq_ent_t to be used when dispatching items to a
taskq. This eliminates a memory allocation which helps minimize
lock contention in the taskq when dispatching functions.
commit 5aeb94743e3be0c51e86f73096334611ae3a058e
Author: Garrett D'Amore <garrett@nexenta.com>
Date: Wed Jul 27 07:13:44 2011 -0700
734 taskq_dispatch_prealloc() desired
943 zio_interrupt ends up calling taskq_dispatch with TQ_SLEEP
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #65
Added another splat taskq test to ensure tasks can be recursively
submitted to a single task queue without issue. When the
taskq_dispatch_prealloc() interface is introduced, this use case
can potentially cause a deadlock if a taskq_ent_t is dispatched
while its tqent_list field is not empty. This _should_ never be
a problem with the existing taskq_dispatch() interface.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #65
To lay the ground work for introducing the taskq_dispatch_prealloc()
interface, the tq_work_list and tq_threads fields had to be replaced
with new alternatives in the taskq_t structure.
The tq_threads field was replaced with tq_thread_list. Rather than
storing the pointers to the taskq's kernel threads in an array, they are
now stored as a list. In addition to laying the ground work for the
taskq_dispatch_prealloc() interface, this change could also enable taskq
threads to be dynamically created and destroyed as threads can now be
added and removed to this list relatively easily.
The tq_work_list field was replaced with tq_active_list. Instead of
keeping a list of taskq_ent_t's which are currently being serviced, a
list of taskq_threads currently servicing a taskq_ent_t is kept. This
frees up the taskq_ent_t's tqent_list field when it is being serviced
(i.e. now when a taskq_ent_t is being serviced, it's tqent_list field
will be empty).
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #65
The spl_task structure was renamed to taskq_ent, and all of
its fields were renamed to have a prefix of 'tqent' rather
than 't'. This was to align with the naming convention which
the ZFS code assumes. Previously these fields were private
so the name never mattered.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #65
This change adds the neglected SPLAT_TEST_FINI call for the
SPLAT_TASKQ_TEST6_ID, just as is done for the other 5 SPLAT_TASKQ_*
tests.
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#64
The splat_taskq_test4_common function was incorrectly referencing
the splat_taskq-test13_func symbol, when it meant to be using the
splat_taskq_test4_func symbol.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#61
This is a bit of cleanup I'd been meaning to get to for a while
to reduce the chance of a type conflict. Well that conflict
finally occurred with the kstat_init() function which conflicts
with a function in the 2.6.32-6-pve kernel.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#56
As of Linux 3.1 the shrink_dcache_memory and shrink_icache_memory
functions have been removed. This same task is now accomplished
more cleanly with per super block shrinkers. This unfortunately
leaves us no easy way to support the dnlc_reduce_cache() function.
This support has always been entirely optional. So when no
reasonable interface is available allow the dnlc_reduce_cache()
function to effectively become a no-op.
The downside of this change is that it will prevent the zfs arc
meta data limts from being enforced. However, the current zfs
implementation in this regard is already flawed and needs to
be reworked. If the arc needs to enfore a meta data limit it
will need to be extended to coordinate directly with the zpl.
This will allow us to drop all this compatibility code and get
more fine grained control over the cache management.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #52
Prior to Linux 3.1 the kern_path_parent symbol was exported for
use by kernel modules. As of Linux 3.1 it is now longer easily
available. To handle this case the spl will now dynamically
look up address of the missing symbol at module load time.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #52
Be careful not to unconditionally clear the PF_MEMALLOC bit in
the task structure. It may have already been set when entering
kv_alloc() in which case it must remain set on exit. In
particular the kswapd thread will have PF_MEMALLOC set in
order to prevent it from entering direct reclaim. By clearing
it we allow the following NULL deref to potentially occur.
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [<ffffffff8109c7ab>] balance_pgdat+0x25b/0x4ff
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes ZFS issue #287
This would cause problems when using 'zfs send' with a file as the
target (rather than a pipe or a socket as is usually the case) as
for each write the destination offset in the file would be 0.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes ZFS issue #391
The typo did not have any effect (apart from a negligible performance
impact) because skc->skc_flags * KMC_OFFSLAB is always non-null when
at least one bit in skc->skc_flags is set.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
In a non-debug build the ASSERT() would be optimized away
which could cause pending work items to not be cancelled.
We must also use cancel_delayed_work_sync() rather than just
cancel_delayed_work() to actually wait until work items have
completed. Otherwise they might accidentally access free'd
memory.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes ZFS bugs #279, #62, #363, #418
File descriptors are a per-process resource. The same descriptor
in different processes can refer to different files. find_file()
incorrectly assumed that file descriptors are globally unique.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes ZFS issue #386
No longer print the following warning to the console when the
/etc/hostid file is missing. This is the expected default behavior.
Keeping the hostid in sync with the initramfs is now accomplished
by creating the /etc/hostid in the initramfs not on the system.
SPL: The /etc/hostid file is not found.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When running 'make install' without DESTDIR set the module install
rules would mistakenly destroy the 'modules.*' files for ALL of
your installed kernels. This could lead to a non-functional system
for the alternate kernels because 'depmod -a' will only be run for
the kernel which was compiled against. This issue would not impact
anyone using the 'make <deb|rpm|pkg>' build targets to build and
install packages.
The fix for this issue is to only remove extraneous build products
when DESTDIR is set. This almost exclusively indicates we are
building packages and installed the build products in to a temporary
staging location. Additionally, limit the removal the unneeded
build products to the target kernel version.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#328
Deprecate the /usr/bin/hostid call by reading the /etc/hostid file
directly. Add the spl_hostid_path parameter to override the default
/etc/hostid path.
Rename the set_hostid() function to hostid_exec() to better reflect
actual behavior and complement the new hostid_read() function.
Use HW_INVALID_HOSTID as the spl_hostid sentinel value because
zero seems to be a valid gethostid() result on Linux.
While the splat tests were originally designed to stress test
the Solaris primatives. I am extending them to include some kernel
compatibility tests. Certain linux APIs have changed frequently.
These tests ensure that added compatibility is working properly
and no unnoticed regression have slipped in.
Test 1 and 2 add basic regression tests for shrink_icache_memory
and shrink_dcache_memory. These are simply functional tests to
ensure we can call these functions safely. Checking for correct
behavior is more difficult since other running processes will
influence the behavior. However, these functions are provided
by the kernel so if we can successfully call them we assume they
are working correctly.
Test 3 checks that shrinker functions are being registered and
called correctly. As of Linux 3.0 the shrinker API has changed
four different times so I felt the need to add a trivial test
case to ensure each variant works as expected.
Update the the wrapper macros for the memory shrinker to handle
this 4th API change. The callback function now takes a
shrink_control structure. This is certainly a step in the
right direction but it's annoying to have to accomidate yet
another version of the API.
It has become necessary to be able to optionally disable
direct memory reclaim for certain taskqs. To support
this the TASKQ_NORECLAIM flags has been added which sets
the PF_MEMALLOC bit for all threads in the taskq.
Change the SPL kernel messages for module loading and module
unloading so that they are similar to the ZFS kernel messages.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
This reverts commit 1814251453.
Demote the gawk call back to awk and ensure that stderr is attached. GNU gawk
tolerates a missing stderr handle, but many utilities do not, which could be
why a regular awk call was unexplainably failing on some systems.
Use argv[0] instead of sh_path for consistency internally and with other Linux
drivers.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Provide a call_usermodehelper() alternative by letting the hostid be passed as
a module parameter like this:
$ modprobe spl spl_hostid=0x12345678
Internally change the spl_hostid variable to unsigned long because that is the
type that the coreutils /usr/bin/hostid returns.
Move the hostid command into GET_HOSTID_CMD for consistency with the similar
GET_KALLSYMS_ADDR_CMD invocation.
Use argv[0] instead of sh_path for consistency internally and with other Linux
drivers.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
The function zlib_deflate_workspacesize() now take 2 arguments.
This was done to avoid always having to allocate the maximum size
workspace (268K). The caller can now specific the windowBits and
memLevel compression parameters to get a smaller workspace.
For our purposes we introduce a spl_zlib_deflate_workspacesize()
wrapper which accepts both arguments. When the two argument
version of zlib_deflate_workspacesize() is available the arguments
are passed through. When it's not we assume the worst case and
a maximally sized workspace is used.
The path_lookup() function has been renamed to kern_path_parent()
and the flags argument has been removed. The only behavior now
offered is that of LOOKUP_PARENT. The spl already always passed
this flag so dropping the flag does not impact us.
This is a long over due compatibility change. Way, way, way back
in 2007 there was a push to remove all consumers of SPIN_LOCK_UNLOCKED.
Finally, in 2011 with 2.6.39 all the consumers have been updated
and SPIN_LOCK_UNLOCKED was removed. It's about time we use the
new API as well, this change does exactly that. DEFINE_SPINLOCK()
was available as far back as 2.6.12 so there doesn't need to be
any additional autoconf-foo for this change.
Flagged by the default -Wunused-but-set-variable gcc option when
running under Fedora 15. Since it's correct this variable is
entirely unused this commit removes it.
To resolve a potiential filesystem corruption issue a second
argument was added to invalidate_inodes(). This argument controls
whether dirty inodes are dropped or treated as busy when invalidating
a super block. When only the legacy API is available the second
argument will be dropped for compatibility.
Provide the dnlc_reduce_cache() function which attempts to prune
cached entries from the dcache and icache. After the entries are
pruned any slabs which they may have been using are reaped.
Note the API takes a reclaim percentage but we don't have easy
access to the total number of cache entries to calculate the
reclaim count. However, in practice this doesn't need to be
exactly correct. We simply need to reclaim some useful fraction
(but not all) of the cache. The caller can determine if more
needs to be done.
One of the most common things you want to know when looking at
the slab is how much memory is being used. This information was
available in /proc/spl/kmem/slab but only on a per-slab basis.
This commit adds the following /proc/sys/kernel/spl/kmem/slab*
entries to make total slab usage easily available at a glance.
slab_kmem_total - Total kmem slab size
slab_kmem_avail - Alloc'd kmem slab size
slab_kmem_max - Max observed kmem slab size
slab_vmem_total - Total vmem slab size
slab_vmem_avail - Alloc'd vmem slab size
slab_vmem_max - Max observed vmem slab size
NOTE: The slab_*_max values are expected to over report because
they show maximum values since boot, not current values.
The 'slab_fail', 'slab_create', and 'slab_destroy' columns in the slab
output have been removed because they are virtually always zero and
not very useful.
The much more useful 'size' and 'alloc' columns have been added which
show the total slab size and how much of the total size has been
allocated to objects.
Finally, the formatting has been updated to be much more human
readable while still being friendly for tool like awk to parse.
The Linux shrinker has gone through three API changes since 2.6.22.
Rather than force every caller to understand all three APIs this
change consolidates the compatibility code in to the mm-compat.h
header. The caller then can then use a single spl provided
shrinker API which does the right thing for your kernel.
SPL_SHRINKER_CALLBACK_PROTO(shrinker_callback, cb, nr_to_scan, gfp_mask);
SPL_SHRINKER_DECLARE(shrinker_struct, shrinker_callback, seeks);
spl_register_shrinker(&shrinker_struct);
spl_unregister_shrinker(&&shrinker_struct);
spl_exec_shrinker(&shrinker_struct, nr_to_scan, gfp_mask);
Solaris credentials don't have an fsuid/fsguid field but Linux
credentials do. To handle this case the Solaris API is being
modestly extended to include the crgetfsuid()/crgetfsgid()
helper functions.
Addititionally, because the crget*() helpers are implemented
identically regardless of HAVE_CRED_STRUCT they have been
moved outside the #ifdef to common code. This simplification
means we only have one version of the helper to keep to to date.
As part of vmalloc() a __pte_alloc_kernel() allocation may occur. This
internal allocation does not honor the gfp flags passed to vmalloc().
This means even when vmalloc(GFP_NOFS) is called it is possible that a
synchronous reclaim will occur. This reclaim can trigger file IO which
can result in a deadlock. This issue can be avoided by explicitly
setting PF_MEMALLOC on the process to subvert synchronous reclaim when
vmalloc() is called with !__GFP_FS.
An example stack of the deadlock can be found here (1), along with the
upstream kernel bug (2), and the original bug discussion on the
linux-mm mailing list (3). This code can be properly autoconf'ed
when the upstream bug is fixed.
1) http://github.com/behlendorf/zfs/issues/labels/Vmalloc#issue/133
2) http://bugzilla.kernel.org/show_bug.cgi?id=30702
3) http://marc.info/?l=linux-mm&m=128942194520631&w=4
The xvattr support in the spl has always simply consisted of
defining a couple structures and a few #defines. This was enough
to enable compilation of code which just passed xvattr types
around but not enough to effectively manipulate them.
This change removes even this minimal support leaving it up
to packages which leverage the spl to prove the full xvattr
support. By removing it from the spl we ensure not conflict
with the higher level packages.
This just leaves minimal vnode support for basical manipulation
of files. This code is does have the proper support functions
in the spl and a set of regression tests.
Additionally, this change removed the unused 'caller_context_t *'
type and replaces it with a 'void *'.
A zlib regression test has been added to verify the correct behavior
of z_compress_level() and z_uncompress. The test case simply takes
a 128k buffer, it compresses the buffer, it them uncompresses the
buffer, and finally it compares the buffers after the transform.
If the buffers match then everything is fine and no data was lost.
It performs this test for all 9 zlib compression levels.
While portions of the code needed to support z_compress_level() and
z_uncompress() where in place. In reality the current implementation
was non-functional, it just was compilable.
The critical missing component was to setup a workspace for the
compress/uncompress stream structures to use. A kmem_cache was
added for the workspace area because we require a large chunk
of memory. This avoids to need to continually alloc/free this
memory and vmap() the pages which is very slow. Several objects
will reside in the per-cpu kmem_cache making them quick to acquire
and release. A further optimization would be to adjust the
implementation to additional ensure the memory is local to the cpu.
Currently that may not be the case.
In the 2.6.37 kernel the function invalidate_inodes() is no longer
exported for use by modules. This memory management functionality
is needed to invalidate the inodes attached to a super block without
unmounting the filesystem.
Because this function still exists in the kernel and the prototype
is available is a common header all we strictly need is the symbol
address. The address is obtained using spl_kallsyms_lookup_name()
and assigned to the variable invalidate_inodes_fn. Then a #define
is used to replace all instances of invalidate_inodes() with a
call to the acquired address. All the complexity is hidden behind
HAVE_INVALIDATE_INODES and invalidate_inodes() can be used as usual.
Long term we should try to get this, or another, interface made
available to modules again.
Previously we would ASSERT in cv_destroy() if it was ever called
with active waiters. However, I've now seen several instances in
OpenSolaris code where they do the following:
cv_broadcast();
cv_destroy();
This leaves no time for active waiters to be woken up and scheduled
and we trip the ASSERT. This has not been observed to be an issue
on OpenSolaris because their cv_destroy() basically does nothing.
They still do run the risk of the memory being free'd after the
cv_destroy() and hitting a bad paging request. But in practice
this race is so small and unlikely it either doesn't happen, or
is so unlikely when it does happen the root cause has not yet been
identified.
Rather than risk the same issue in our code this change updates
cv_destroy() to block until all waiters have been woken and
scheduled. This may take some time because each waiter must
acquire the mutex.
This change may have an impact on performance for frequently
created and destroyed condition variables. That however is a price
worth paying it avoid crashing your system. If performance issues
are observed they can be addressed by the caller.
Previously these were defined to noops but rather than give
the misleading impression that these are actually implemented
I'm removing the type entirely for clarity.
Both of these caches were previously allowed to be either a
vmem or kmem cache based on the size of the object involved.
Since we know the object won't be to large and performce is
much better for a kmem cache for them to be kmem backed.
The cv_timedwait() function by definition must wait unconditionally
for cv_signal()/cv_broadcast() before waking. This causes processes
to go in the D state which increases the load average. The load
average is the summation of processes in D state and run queue.
To avoid this it can be desirable to sleep interruptibly. These
processes do not count against the load average but may be woken by
a signal. It is up to the caller to determine why the process
was woken it may be for one of three reasons.
1) cv_signal()/cv_broadcast()
2) the timeout expired
3) a signal was received
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Create spl_inode_lock/spl_inode_unlock compability macros to simply
access to the inode mutex/sem. This avoids the need to have to ugly
up the code with the required #define's at every call site. At the
moment the SPL only uses this in one place but higher layers can
benefit from the macro.
To validate the correct behavior of the TSD interfaces it's
important that we add a regression test. This test is designed
to minimally exercise the fundamental TSD behavior, it does not
attempt to validate all potential corner cases.
The test will first create 32 keys via tsd_create() and register
a common destructor. Next 16 wait threads will be created each
of which set/verify a random value for all 32 keys, then block
waiting to be released by the control thread. Meanwhile the
control thread verifies that none of the destructors have been
run prematurely.
The next phase of the test is to create 16 exit threads which
set/verify a random value for all 32 keys. They then immediately
exit. This is is designed to verify tsd_exit() which will be
called via thread_exit(). This must result in all registered
destructors being run and the memory for the tsd being free'd.
After this tsd_destroy() is verified by destroying all 32 keys.
Once again we must see the expected number of destructors run
and the tsd memory free'd. At this point the blocked threads
are released and they exit calling tsd_exit() which should do
very little since all the tsd has already been destroyed.
If this all goes off without a hitch the test passes. To ensure
no memory has been leaked, I have manually verified that after
spl module unload no memory is reported leaked.
Thread specific data has implemented using a hash table, this avoids
the need to add a member to the task structure and allows maximum
portability between kernels. This implementation has been optimized
to keep the tsd_set() and tsd_get() times as small as possible.
The majority of the entries in the hash table are for specific tsd
entries. These entries are hashed by the product of their key and
pid because by design the key and pid are guaranteed to be unique.
Their product also has the desirable properly that it will be uniformly
distributed over the hash bins providing neither the pid nor key is zero.
Under linux the zero pid is always the init process and thus won't be
used, and this implementation is careful to never to assign a zero key.
By default the hash table is sized to 512 bins which is expected to
be sufficient for light to moderate usage of thread specific data.
The hash table contains two additional type of entries. They first
type is entry is called a 'key' entry and it is added to the hash during
tsd_create(). It is used to store the address of the destructor function
and it is used as an anchor point. All tsd entries which use the same
key will be linked to this entry. This is used during tsd_destory() to
quickly call the destructor function for all tsd associated with the key.
The 'key' entry may be looked up with tsd_hash_search() by passing the
key you wish to lookup and DTOR_PID constant as the pid.
The second type of entry is called a 'pid' entry and it is added to the
hash the first time a process set a key. The 'pid' entry is also used
as an anchor and all tsd for the process will be linked to it. This
list is using during tsd_exit() to ensure all registered destructors
are run for the process. The 'pid' entry may be looked up with
tsd_hash_search() by passing the PID_KEY constant as the key, and
the process pid. Note that tsd_exit() is called by thread_exit()
so if your using the Solaris thread API you should not need to call
tsd_exit() directly.
For debugging purposes the condition varaibles keep track of the
mutex used during a wait. The idea is to validate that all callers
always use the same mutex. Unfortunately, we have seen cases where
the caller reuses the condition variable with a different mutex but
in a way which is known to be safe. My reading of the man pages
suggests you should not do this and always cv_destroy()/cv_init()
a new mutex. However, there is overhead in doing this and it does
appear to be allowed under Solaris.
To accomidate this behavior cv_wait_common() and __cv_timedwait()
have been modified to clear the associated mutex when the last
waiter is dropped. This ensures that while the condition variable
is in use the incorrect mutex case is detected. It also allows the
condition variable to be safely recycled without requiring the
overhead of a cv_destroy()/cv_init() as long as it isn't currently
in use.
Finally, spin lock cv->cv_lock was removed because it is not required.
When the condition variable is used properly the caller will always
be holding the mutex so the spin lock is redundant. The lock was
originally added because I expected to need to protect more than
just the cv->cv_mutex. It turns out that was not the case.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
As of linux-2.6.36 the last in-tree consumer of fops->ioctl() has
been removed and thus fops()->ioctl() has also been removed. The
replacement hook is fops->unlocked_ioctl() which has existed in
kernel since 2.6.12. Since the SPL only contains support back
to 2.6.18 vintage kernels, I'm not adding an autoconf check for
this and simply moving everything to use fops->unlocked_ioctl().
In the linux-2.6.36 kernel the fs_struct lock was changed from a
rwlock_t to a spinlock_t. If the kernel would export the set_fs_pwd()
symbol by default this would not have caused us any issues, but they
don't. So we're forced to add a new autoconf check which sets the
HAVE_FS_STRUCT_SPINLOCK define when a spinlock_t is used. We can
then correctly use either spin_lock or write_lock in our custom
set_fs_pwd() implementation.
Flagged by the default compile options on archlinux 2010.05, we should
be using the krw_t type not the krw_type_t type in the private data.
module/splat/splat-rwlock.c: In function ‘splat_rwlock_test4_func’:
module/splat/splat-rwlock.c:432:6: warning: case value ‘1’ not in
enumerated type ‘krw_type_t’
As of linux-2.6.35 the shrinker callback API now takes an additional
argument. The shrinker struct is passed to the callback so that users
can embed the shrinker structure in private data and use container_of()
to access it. This removes the need to always use global state for the
shrinker.
To handle this we add the SPL_AC_3ARGS_SHRINKER_CALLBACK autoconf
check to properly detect the API. Then we simply setup a callback
function with the correct number of arguments. For now we do not make
use of the new 3rd argument.
One of the neat tricks an autoconf style project is capable of
is allow configurion/building in a directory other than the
source directory. The major advantage to this is that you can
build the project various different ways while making changes
in a single source tree.
For example, this project is designed to work on various different
Linux distributions each of which work slightly differently. This
means that changes need to verified on each of those supported
distributions perferably before the change is committed to the
public git repo.
Using nfs and custom build directories makes this much easier.
I now have a single source tree in nfs mounted on several different
systems each running a supported distribution. When I make a
change to the source base I suspect may break things I can
concurrently build from the same source on all the systems each
in their own subdirectory.
wget -c http://github.com/downloads/behlendorf/spl/spl-x.y.z.tar.gz
tar -xzf spl-x.y.z.tar.gz
cd spl-x-y-z
------------------------- run concurrently ----------------------
<ubuntu system> <fedora system> <debian system> <rhel6 system>
mkdir ubuntu mkdir fedora mkdir debian mkdir rhel6
cd ubuntu cd fedora cd debian cd rhel6
../configure ../configure ../configure ../configure
make make make make
make check make check make check make check
This is something the project has almost supported for a long time
but finishing this support should save me lots of time.
At some point we are going to need to implement the kmem cache
move callbacks to allow for kmem cache defragmentation. This
commit simply lays a small part of the API ground work, it does
not actually implement any of this feature. This is safe for
now because the move callbacks are just an optimization. Even
if they are registered we don't ever really have to call them.
Unless __GFP_IO and __GFP_FS are removed from the file mapping gfp
mask we may enter memory reclaim during IO. In this case shrink_slab()
entered another file system which is notoriously hungry for stack.
This additional stack usage may cause a stack overflow. This patch
removes __GFP_IO and __GFP_FS from the mapping gfp mask of each file
during vn_open() to avoid any reclaim in the vn_rdwr() IO path. The
original mask is then restored at vn_close() time. Hats off to the
loop driver which does something similiar for the same reason.
[...]
shrink_slab+0xdc/0x153
try_to_free_pages+0x1da/0x2d7
__alloc_pages+0x1d7/0x2da
do_generic_mapping_read+0x2c9/0x36f
file_read_actor+0x0/0x145
__generic_file_aio_read+0x14f/0x19b
generic_file_aio_read+0x34/0x39
do_sync_read+0xc7/0x104
vfs_read+0xcb/0x171
:spl:vn_rdwr+0x2b8/0x402
:zfs:vdev_file_io_start+0xad/0xe1
[...]
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
When TQ_SLEEP is used, taskq_dispatch() should always succeed even if the
number of pending tasks is above tq->tq_maxalloc. This semantic is similar
to KM_SLEEP in kmem allocations, which also always succeed.
However, we cannot block forever otherwise there is a risk of deadlock.
Therefore, we still allow the number of pending tasks to go above
tq->tq_maxalloc with TQ_SLEEP, but we may sleep up to 1 second per task
dispatch, thereby throttling the task dispatch rate.
One of the existing splat tests was also augmented to test for this scenario.
The test would fail with the previous implementation but now it succeeds.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Using kmem_free() results in deducting X bytes from the memory
accounting when --enable-debug is set. Unfortunately, currently
the counterpart kmem_asprintf() and friends do not properly
account for memory allocated, so we must do the same on free.
If we don't then we end up with a negative number of lost bytes
reported when the module is unloaded.
A better long term fix would be to add the accounting in to the
allocation side but that's a project for another day.
Extend the Makefiles with an uninstall target to cleanly
remove a package which was installed with 'make install'.
Additionally, ensure a 'depmod -a' is run as part of the
install to update the module dependency information.
The Solaris semantics for kmem_alloc() and vmem_alloc() are that they
must never fail when called with KM_SLEEP. They may only fail if
called with KM_NOSLEEP otherwise they must block until memory is
available. This is quite different from how the Linux memory
allocators work, under Linux a memory allocation failure is always
possible and must be dealt with.
At one point in the past the kmem code did properly implement this
behavior, however as the code evolved this behavior was overlooked
in places. This patch goes through all three implementations of
the kmem/vmem allocation functions and ensures that they will all
block in the KM_SLEEP case when memory is not available. They
may still fail in the KM_NOSLEEP case in which case the caller
is responsible for handling the failure.
Special care is taken in vmalloc_nofail() to avoid thrashing the
system on the virtual address space spin lock. The down side of
course is if you do see a failure here, which is unlikely for
64-bit systems, your allocation will delay for an entire second.
Still this is preferable to locking up your system and it is the
best we can do given the constraints.
Additionally, the code was cleaned up to be much more readable
and comments were added to describe the various kmem-debug-*
configure options. The default configure options remain:
"--enable-debug-kmem --disable-debug-kmem-tracking"
