Added -z and -Z switches for filtering by size, added copyright notices

man/man8/memleak.8

@@ -2,7 +2,8 @@
 .SH NAME
 memleak \- Print a summary of outstanding allocations and their call stacks to detect memory leaks. Uses Linux eBPF/bcc.
 .SH SYNOPSIS
-.B memleak [-h] [-p PID] [-t] [-a] [-o OLDER] [-c COMMAND] [-s SAMPLE_RATE] [-d STACK_DEPTH] [-T TOP] [INTERVAL] [COUNT]
+.B memleak [-h] [-p PID] [-t] [-a] [-o OLDER] [-c COMMAND] [-s SAMPLE_RATE]
+[-d STACK_DEPTH] [-T TOP] [-z MIN_SIZE] [-Z MAX_SIZE] [INTERVAL] [COUNT]
 .SH DESCRIPTION
 memleak traces and matches memory allocation and deallocation requests, and
 collects call stacks for each allocation. memleak can then print a summary
@@ -52,6 +53,12 @@ The default value is 10.
 Print only the top TOP stacks (sorted by size).
 The default value is 10.
 .TP
+\-z MIN_SIZE
+Capture only allocations that are larger than or equal to MIN_SIZE bytes.
+.TP
+\-Z MAX_SIZE
+Capture only allocations that are smaller than or equal to MAX_SIZE bytes.
+.TP
 INTERVAL
 Print a summary of oustanding allocations and their call stacks every INTERVAL seconds.
 The default interval is 5 seconds.
@@ -76,12 +83,17 @@ stacks 10 times before quitting.
 Run ./allocs and print outstanding allocation stacks for that process: 
 #
 .B memleak -c "./allocs"
+.TP
+Capture only allocations between 16 and 32 bytes in size:
+#
+.B memleak -z 16 -Z 32
 .SH OVERHEAD
 memleak can have significant overhead if the target process or kernel performs
 allocations at a very high rate. Pathological cases may exhibit up to 100x
 degradation in running time. Most of the time, however, memleak shouldn't cause
-a significant slowdown. You can also use the \-s switch to reduce the overhead
-further by capturing only every N-th allocation.
+a significant slowdown. You can use the \-s switch to reduce the overhead
+further by capturing only every N-th allocation. The \-z and \-Z switches can
+also reduce overhead by capturing only allocations of specific sizes.
 
 To determine the rate at which your application is calling malloc/free, or the
 rate at which your kernel is calling kmalloc/kfree, place a probe with perf and

tools/memleak.c

@@ -1,3 +1,10 @@
+/*
+ * memleak.c Trace and display outstanding allocations to detect 
+ * memory leaks in user-mode processes and the kernel.
+ *
+ * Copyright (C) 2016 Sasha Goldshtein.
+ */
+
 #include <uapi/linux/ptrace.h>
 
 struct alloc_info_t {
@@ -33,9 +40,7 @@ static int grab_stack(struct pt_regs *ctx, struct alloc_info_t *info)
 
 int alloc_enter(struct pt_regs *ctx, size_t size)
 {
- // Ideally, this should use a random number source, such as 
- // BPF_FUNC_get_prandom_u32, but that's currently not supported
- // by the bcc front-end.
+ SIZE_FILTER
  if (SAMPLE_EVERY_N > 1) {
  u64 ts = bpf_ktime_get_ns();
  if (ts % SAMPLE_EVERY_N != 0)

tools/memleak.py

@@ -1,4 +1,14 @@
 #!/usr/bin/env python
+#
+# memleak.py Trace and display outstanding allocations to detect 
+# memory leaks in user-mode processes and the kernel.
+#
+# USAGE: memleak.py [-h] [-p PID] [-t] [-a] [-o OLDER] [-c COMMAND]
+# [-s SAMPLE_RATE] [-d STACK_DEPTH] [-T TOP] [-z MIN_SIZE]
+# [-Z MAX_SIZE]
+# [interval] [count]
+#
+# Copyright (C) 2016 Sasha Goldshtein.
 
 from bcc import BPF
 from time import sleep
@@ -195,6 +205,10 @@ def run_command_get_pid(command):
  help="maximum stack depth to capture")
 parser.add_argument("-T", "--top", type=int, default=10,
  help="display only this many top allocating stacks (by size)")
+parser.add_argument("-z", "--min-size", type=int,
+ help="capture only allocations larger than this size")
+parser.add_argument("-Z", "--max-size", type=int,
+ help="capture only allocations smaller than this size")
 
 args = parser.parse_args()
 
@@ -208,6 +222,12 @@ def run_command_get_pid(command):
 num_prints = args.count
 max_stack_size = args.stack_depth + 2
 top_stacks = args.top
+min_size = args.min_size
+max_size = args.max_size
+
+if min_size is not None and max_size is not None and min_size > max_size:
+ print("min_size (-z) can't be greater than max_size (-Z)")
+ exit(1)
 
 if command is not None:
  print("Executing '%s' and tracing the resulting process." % command)
@@ -219,6 +239,17 @@ def run_command_get_pid(command):
 bpf_source = bpf_source.replace("GRAB_ONE_FRAME", max_stack_size *
  "\tif (!(info->callstack[depth++] = get_frame(&bp))) return depth;\n")
 bpf_source = bpf_source.replace("MAX_STACK_SIZE", str(max_stack_size))
+
+size_filter = ""
+if min_size is not None and max_size is not None:
+ size_filter = "if (size < %d || size > %d) return 0;" % \
+ (min_size, max_size)
+elif min_size is not None:
+ size_filter = "if (size < %d) return 0;" % min_size
+elif max_size is not None:
+ size_filter = "if (size > %d) return 0;" % max_size
+bpf_source = bpf_source.replace("SIZE_FILTER", size_filter)
+
 bpf_program = BPF(text=bpf_source)
 
 if not kernel_trace:

tools/memleak_examples.txt

@@ -178,6 +178,10 @@ optional arguments:
  -d STACK_DEPTH, --stack_depth STACK_DEPTH
  maximum stack depth to capture
  -T TOP, --top TOP display only this many top allocating stacks (by size)
+ -z MIN_SIZE, --min-size MIN_SIZE
+ capture only allocations larger than this size
+ -Z MAX_SIZE, --max-size MAX_SIZE
+ capture only allocations smaller than this size
 
 EXAMPLES: