1 .. _overcommit_accounting:
7 The Linux kernel supports the following overcommit handling modes
10 Heuristic overcommit handling. Obvious overcommits of address
11 space are refused. Used for a typical system. It ensures a
12 seriously wild allocation fails while allowing overcommit to
13 reduce swap usage. root is allowed to allocate slightly more
14 memory in this mode. This is the default.
17 Always overcommit. Appropriate for some scientific
18 applications. Classic example is code using sparse arrays and
19 just relying on the virtual memory consisting almost entirely
23 Don't overcommit. The total address space commit for the
24 system is not permitted to exceed swap + a configurable amount
25 (default is 50%) of physical RAM. Depending on the amount you
26 use, in most situations this means a process will not be
27 killed while accessing pages but will receive errors on memory
28 allocation as appropriate.
30 Useful for applications that want to guarantee their memory
31 allocations will be available in the future without having to
32 initialize every page.
34 The overcommit policy is set via the sysctl ``vm.overcommit_memory``.
36 The overcommit amount can be set via ``vm.overcommit_ratio`` (percentage)
37 or ``vm.overcommit_kbytes`` (absolute value). These only have an effect
38 when ``vm.overcommit_memory`` is set to 2.
40 The current overcommit limit and amount committed are viewable in
41 ``/proc/meminfo`` as CommitLimit and Committed_AS respectively.
46 The C language stack growth does an implicit mremap. If you want absolute
47 guarantees and run close to the edge you MUST mmap your stack for the
48 largest size you think you will need. For typical stack usage this does
49 not matter much but it's a corner case if you really really care
51 In mode 2 the MAP_NORESERVE flag is ignored.
57 The overcommit is based on the following rules
60 | SHARED or READ-only - 0 cost (the file is the map not swap)
61 | PRIVATE WRITABLE - size of mapping per instance
63 For an anonymous or ``/dev/zero`` map
64 | SHARED - size of mapping
65 | PRIVATE READ-only - 0 cost (but of little use)
66 | PRIVATE WRITABLE - size of mapping per instance
69 | Pages made writable copies by mmap
70 | shmfs memory drawn from the same pool
75 * We account mmap memory mappings
76 * We account mprotect changes in commit
77 * We account mremap changes in size
80 * We report the commit status in /proc
81 * Account and check on fork
82 * Review stack handling/building on exec
84 * Implement actual limit enforcement
88 * Account ptrace pages (this is hard)