@@ -8,7 +8,10 @@ import argparse
import sys
from drgn.helpers.linux import list_for_each_entry, list_empty
-from drgn import container_of
+from drgn.helpers.linux import for_each_page
+from drgn.helpers.linux.cpumask import for_each_online_cpu
+from drgn.helpers.linux.percpu import per_cpu_ptr
+from drgn import container_of, FaultError
DESC = """
@@ -47,7 +50,7 @@ def is_root_cache(s):
def cache_name(s):
if is_root_cache(s):
- return s.name
+ return s.name.string_().decode('utf-8')
else:
return s.memcg_params.root_cache.name.string_().decode('utf-8')
@@ -99,12 +102,16 @@ def slub_get_slabinfo(s, cfg):
# SLAB-specific functions can be added here...
-def cache_show(s, cfg):
+def cache_show(s, cfg, objs):
if cfg['allocator'] == 'SLUB':
sinfo = slub_get_slabinfo(s, cfg)
else:
err('SLAB isn\'t supported yet')
+ if cfg['shared_slab_pages']:
+ sinfo['active_objs'] = objs
+ sinfo['num_objs'] = objs
+
print('%-17s %6lu %6lu %6u %4u %4d'
' : tunables %4u %4u %4u'
' : slabdata %6lu %6lu %6lu' % (
@@ -127,9 +134,60 @@ def detect_kernel_config():
else:
err('Can\'t determine the slab allocator')
+ if prog.type('struct memcg_cache_params').members[1][1] == 'memcg_cache':
+ cfg['shared_slab_pages'] = True
+ else:
+ cfg['shared_slab_pages'] = False
+
return cfg
+def for_each_slab_page(prog):
+ PGSlab = 1 << prog.constant('PG_slab')
+ PGHead = 1 << prog.constant('PG_head')
+
+ for page in for_each_page(prog):
+ try:
+ if page.flags.value_() & PGSlab:
+ yield page
+ except FaultError:
+ pass
+
+
+# it doesn't find all objects, because by default full slabs are not
+# placed to the full list. however, it can be used in certain cases.
+def for_each_slab_page_fast(prog):
+ for s in list_for_each_entry('struct kmem_cache',
+ prog['slab_caches'].address_of_(),
+ 'list'):
+ if is_root_cache(s):
+ continue
+
+ if s.cpu_partial:
+ for cpu in for_each_online_cpu(prog):
+ cpu_slab = per_cpu_ptr(s.cpu_slab, cpu)
+ if cpu_slab.page:
+ yield cpu_slab.page
+
+ page = cpu_slab.partial
+ while page:
+ yield page
+ page = page.next
+
+ for node in range(prog['nr_online_nodes'].value_()):
+ n = s.node[node]
+
+ for page in list_for_each_entry('struct page',
+ n.partial.address_of_(),
+ 'slab_list'):
+ yield page
+
+ for page in list_for_each_entry('struct page',
+ n.full.address_of_(),
+ 'slab_list'):
+ yield page
+
+
def main():
parser = argparse.ArgumentParser(description=DESC,
formatter_class=argparse.RawTextHelpFormatter)
@@ -150,10 +208,43 @@ def main():
' : tunables <limit> <batchcount> <sharedfactor>'
' : slabdata <active_slabs> <num_slabs> <sharedavail>')
- for s in list_for_each_entry('struct kmem_cache',
- memcg.kmem_caches.address_of_(),
- 'memcg_params.kmem_caches_node'):
- cache_show(s, cfg)
+ if cfg['shared_slab_pages']:
+ memcg_ptrs = set()
+ stats = {}
+ caches = {}
+
+ # find memcg pointers belonging to the specified cgroup
+ for ptr in list_for_each_entry('struct mem_cgroup_ptr',
+ memcg.kmem_memcg_ptr_list.address_of_(),
+ 'list'):
+ memcg_ptrs.add(ptr.value_())
+
+ # look over all slab pages, belonging to non-root memcgs
+ # and look for objects belonging to the given memory cgroup
+ for page in for_each_slab_page(prog):
+ cache = page.slab_cache
+ if not cache or is_root_cache(cache):
+ continue
+ addr = cache.value_()
+ caches[addr] = cache
+ memcg_vec = page.mem_cgroup_vec
+
+ if addr not in stats:
+ stats[addr] = 0
+
+ for i in range(oo_objects(cache)):
+ if memcg_vec[i].value_() in memcg_ptrs:
+ stats[addr] += 1
+
+ for addr in caches:
+ if stats[addr] > 0:
+ cache_show(caches[addr], cfg, stats[addr])
+
+ else:
+ for s in list_for_each_entry('struct kmem_cache',
+ memcg.kmem_caches.address_of_(),
+ 'memcg_params.kmem_caches_node'):
+ cache_show(s, cfg, None)
main()
Make slabinfo.py compatible with the new slab controller. Because there are no more per-memcg kmem_caches, and also there is no list of all slab pages in the system, it has to walk over all pages and filter out slab pages belonging to non-root kmem_caches. Then it counts objects belonging to the given cgroup. It might sound as a very slow operation, however it's not so slow. It takes about 30s seconds to walk over 8Gb of slabs out of 64Gb, and filter out all objects belonging to the cgroup of interest. Also, it provides an accurate number of active objects, which isn't true for the old slab controller. The script is backward compatible and works for both kernel versions. Signed-off-by: Roman Gushchin <guro@fb.com> --- tools/cgroup/slabinfo.py | 105 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 98 insertions(+), 7 deletions(-)