Next: Mathematical Function Probes, Up: Internal probes [Contents][Index]
These probes are designed to signal relatively unusual situations within the virtual memory subsystem of the GNU C Library.
This probe is triggered after the main arena is extended by calling
sbrk
. Argument $arg1 is the additional size requested to
sbrk
, and $arg2 is the pointer that marks the end of the
sbrk
area, returned in response to the request.
This probe is triggered after the size of the main arena is decreased by
calling sbrk
. Argument $arg1 is the size released by
sbrk
(the positive value, rather than the negative value passed
to sbrk
), and $arg2 is the pointer that marks the end of
the sbrk
area, returned in response to the request.
This probe is triggered after a new heap is mmap
ed. Argument
$arg1 is a pointer to the base of the memory area, where the
heap_info
data structure is held, and $arg2 is the size of
the heap.
This probe is triggered before (unlike the other sbrk and heap
probes) a heap is completely removed via munmap
. Argument
$arg1 is a pointer to the heap, and $arg2 is the size of the
heap.
This probe is triggered after a trailing portion of an mmap
ed
heap is extended. Argument $arg1 is a pointer to the heap, and
$arg2 is the new size of the heap.
This probe is triggered after a trailing portion of an mmap
ed
heap is released. Argument $arg1 is a pointer to the heap, and
$arg2 is the new size of the heap.
These probes are triggered when the corresponding functions fail to
obtain the requested amount of memory from the arena in use, before they
call arena_get_retry
to select an alternate arena in which to
retry the allocation. Argument $arg1 is the amount of memory
requested by the user; in the calloc
case, that is the total size
computed from both function arguments. In the realloc
case,
$arg2 is the pointer to the memory area being resized. In the
memalign
case, $arg2 is the alignment to be used for the
request, which may be stricter than the value passed to the
memalign
function. A memalign
probe is also used by functions
posix_memalign, valloc
and pvalloc
.
Note that the argument order does not match that of the corresponding two-argument functions, so that in all of these probes the user-requested allocation size is in $arg1.
This probe is triggered within arena_get_retry
(the function
called to select the alternate arena in which to retry an allocation
that failed on the first attempt), before the selection of an alternate
arena. This probe is redundant, but much easier to use when it’s not
important to determine which of the various memory allocation functions
is failing to allocate on the first try. Argument $arg1 is the
same as in the function-specific probes, except for extra room for
padding introduced by functions that have to ensure stricter alignment.
Argument $arg2 is the arena in which allocation failed.
This probe is triggered when malloc
allocates and initializes an
additional arena (not the main arena), but before the arena is assigned
to the running thread or inserted into the internal linked list of
arenas. The arena’s malloc_state
internal data structure is
located at $arg1, within a newly-allocated heap big enough to hold
at least $arg2 bytes.
This probe is triggered when malloc
has just selected an existing
arena to reuse, and (temporarily) reserved it for exclusive use.
Argument $arg1 is a pointer to the newly-selected arena, and
$arg2 is a pointer to the arena previously used by that thread.
This occurs within
reused_arena
, right after the mutex mentioned in probe
memory_arena_reuse_wait
is acquired; argument $arg1 will
point to the same arena. In this configuration, this will usually only
occur once per thread. The exception is when a thread first selected
the main arena, but a subsequent allocation from it fails: then, and
only then, may we switch to another arena to retry that allocation, and
for further allocations within that thread.
This probe is triggered when malloc
is about to wait for an arena
to become available for reuse. Argument $arg1 holds a pointer to
the mutex the thread is going to wait on, $arg2 is a pointer to a
newly-chosen arena to be reused, and $arg3 is a pointer to the
arena previously used by that thread.
This occurs within
reused_arena
, when a thread first tries to allocate memory or
needs a retry after a failure to allocate from the main arena, there
isn’t any free arena, the maximum number of arenas has been reached, and
an existing arena was chosen for reuse, but its mutex could not be
immediately acquired. The mutex in $arg1 is the mutex of the
selected arena.
This probe is triggered when malloc
has chosen an arena that is
in the free list for use by a thread, within the get_free_list
function. The argument $arg1 holds a pointer to the selected arena.
This probe is triggered when function mallopt
is called to change
malloc
internal configuration parameters, before any change to
the parameters is made. The arguments $arg1 and $arg2 are
the ones passed to the mallopt
function.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_MXFAST
, and the requested
value is in an acceptable range. Argument $arg1 is the requested
value, and $arg2 is the previous value of this malloc
parameter.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_TRIM_THRESHOLD
. Argument
$arg1 is the requested value, $arg2 is the previous value of
this malloc
parameter, and $arg3 is nonzero if dynamic
threshold adjustment was already disabled.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_TOP_PAD
. Argument
$arg1 is the requested value, $arg2 is the previous value of
this malloc
parameter, and $arg3 is nonzero if dynamic
threshold adjustment was already disabled.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_MMAP_THRESHOLD
, and the
requested value is in an acceptable range. Argument $arg1 is the
requested value, $arg2 is the previous value of this malloc
parameter, and $arg3 is nonzero if dynamic threshold adjustment
was already disabled.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_MMAP_MAX
. Argument
$arg1 is the requested value, $arg2 is the previous value of
this malloc
parameter, and $arg3 is nonzero if dynamic
threshold adjustment was already disabled.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_CHECK_ACTION
. Argument
$arg1 is the requested value, and $arg2 is the previous
value of this malloc
parameter.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_PERTURB
. Argument
$arg1 is the requested value, and $arg2 is the previous
value of this malloc
parameter.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_ARENA_TEST
, and the
requested value is in an acceptable range. Argument $arg1 is the
requested value, and $arg2 is the previous value of this
malloc
parameter.
This probe is triggered shortly after the memory_mallopt
probe,
when the parameter to be changed is M_ARENA_MAX
, and the
requested value is in an acceptable range. Argument $arg1 is the
requested value, and $arg2 is the previous value of this
malloc
parameter.
This probe is triggered when function free
decides to adjust the
dynamic brk/mmap thresholds. Argument $arg1 and $arg2 are
the adjusted mmap and trim thresholds, respectively.
This probe is triggered when the glibc.malloc.tcache_max
tunable is set. Argument $arg1 is the requested value, and
$arg2 is the previous value of this tunable.
This probe is triggered when the glibc.malloc.tcache_count
tunable is set. Argument $arg1 is the requested value, and
$arg2 is the previous value of this tunable.
This probe is triggered when the
glibc.malloc.tcache_unsorted_limit
tunable is set. Argument
$arg1 is the requested value, and $arg2 is the previous
value of this tunable.
Next: Mathematical Function Probes, Up: Internal probes [Contents][Index]