Skip to content

L
linux
Switch branch/tag
  1. 28 Oct, 2004 4 commits
    • Hugh Dickins's avatar
      [PATCH] statm: shared = rss - anon_rss · 8586febd
      Hugh Dickins authored 
      The third "shared" field of /proc/$pid/statm in 2.4 was a count of pages in
the mm whose page_count is more than 1 (oddly, including pages shared just
with swapcache).  That's too costly to calculate each time, so 2.6 changed
it to the total file-backed extent.  But Andrea knows apps and users
surprised when (rss - shared) goes negative: we need to provide an rss-like
statistic, close to the 2.4 interpretation.

Something that's quick and easy to maintain accurately is mm->anon_rss, the
count of anonymous pages in the mm.  Then shared = rss - anon_rss gives a
pretty good and meaningful approximation to 2.4's intention: wli confirms
that this will be useful to Oracle too.

Where to show it?  I think it's best to treat this as a bugfix and show it
in the third field of /proc/$pid/statm, after resident, as before - there's
no evidence that the total file-backed extent was found useful.

Albert would like other fields to revert to page counts, but that's a lot
harder: if mprotect can change the category of a page, then it can't be
accounted as simply as this.  Only go that route if real need shown.
Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
Acked-by: default avatarWilliam Irwin <wli@holomorphy.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      8586febd
    • Hugh Dickins's avatar
      [PATCH] statm: __vm_stat_accounting · da63671a
      Hugh Dickins authored 
      The procfs shared_vm accounting in do_mmap_pgoff didn't balance with munmap
in the case of shared anonymous: because file comes in NULL, whereas
vm_file gets set at the end by shmem_zero_setup.

Update file; and update vm_flags (a driver is likely to add VM_IO or
VM_RESERVED, modifying reserved_vm); and update pgoff (doesn't affect
procfs accounting, but could affect vma_merge - though at present all
drivers which modify vm_pgoff set a VM_SPECIAL which prevents merging). 
And do that __vm_stat_account before advancing to make_pages_present.
Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
Acked-by: default avatarWilliam Irwin <wli@holomorphy.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      da63671a
    • Hugh Dickins's avatar
      [PATCH] shmem NUMA policy spinlock · 64450ca0
      Hugh Dickins authored 
      The NUMA policy for shared memory or tmpfs page allocation was protected by
a semaphore.  It helps to improve scalability if we change that to a
spinlock (and there's only one place that needs to drop and reacquire). 
Oh, and don't even bother to get the spinlock while the tree is empty.
Acked-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      64450ca0
    • David Howells's avatar
      [PATCH] move key_init to security_initcall · 81fc7a04
      David Howells authored 
      During system boot many probes, etc.  will generate upcalls to userspace
via call_usermodehelper().  This has the effect of calling execve() before
the key subsystem has been initialized, and thus Oopsing on a NULL key_jar
during key_alloc().  Move key_init to security_initcall so that it's called
along with other security initialization routines which have similar
requirements.
Signed-off-by: default avatarChris Wright <chrisw@osdl.org>
Signed-off-by: default avatarDavid Howells <dhowells@redhat.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      81fc7a04
  3. 27 Oct, 2004 28 commits
  5. 28 Oct, 2004 1 commit
  7. 27 Oct, 2004 7 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7