library: properly handle memory used by tmpfs

tmpfs has become much more widely used since distributions use it for
/tmp (Fedora 18+). In /proc/meminfo, memory used by tmpfs is accounted
into "Cached" (aka "NR_FILE_PAGES",
 http://lxr.free-electrons.com/source/mm/shmem.c#L301 ).

The tools just pass it on, so what top, free and vmstat report as
"cached" is the sum of page cache and tmpfs.

free has the extremely useful "-/+ buffers/cache" output. However, now
that tmpfs is accounted into "cached", those numbers are way off once
you have big files in /tmp.

Fortunately, kernel 2.6.32 introduces "Shmem", which makes tmpfs memory
usage accessible from userspace (
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=4b02108ac1b3354a22b0d83c684797692efdc395 ).

This patch substracts Shmem from Cached to get the actual page cache
memory. This makes both issues mentioned above disappear. For older
kernels, Shmem is not available (hence zero) and this patch is no-op.

Additionally:
* Update the man pages of free and vmstat to explain what is happening
* Finally drop "MemShared" from the /proc/meminfo parser, it has been
  dead for 10+ years and is only causing confusion ( removed in kernel
  2.5.54, see
  https://git.kernel.org/cgit/linux/kernel/git/tglx/history.git/commit/?id=fe04e9451e5a159247cf9f03c615a4273ac0c571 )

diff --git a/free.1 b/free.1
index 1e8e7ef73fe1d067a388a49943ef668f0e82f41a..21cce28a495bf333d39afb281538806b409b1f0c 100644 (file)
--- a/free.1
+++ b/free.1
@@ -11,11 +11,30 @@ free \- Display amount of free and used memory in the system
 .SH DESCRIPTION
 .B free
 displays the total amount of free and used physical and swap memory in the
-system, as well as the buffers used by the kernel.
-The shared memory column represents either the MemShared value (2.4 series
-kernels) or the Shmem value (2.6 series kernels and later) taken from the
-/proc/meminfo file. The value is zero if none of the entries is exported
-by the kernel.
+system, as well as the buffers and caches used by the kernel. The
+information is gathered by parsing /proc/meminfo. The displayed
+columns are:
+.TP
+\fBtotal\fR
+Total installed memory (MemTotal and SwapTotal in /proc/meminfo)
+.TP
+\fBused\fR
+Used memory (calculated as total - free)
+.TP
+\fBfree\fR
+Unused memory (MemFree and SwapFree in /proc/meminfo)
+.TP
+\fBshared\fR
+Memory used (mostly) by tmpfs (Shmem in /proc/meminfo, available on
+kernels 2.6.32, displayed as zero if not available)
+.TP
+\fBbuffers\fR
+Memory used by kernel buffers (Buffers in /proc/meminfo)
+.TP
+\fBcached\fR
+Memory used by the page cache  (calculated as Cached - Shmem in
+/proc/meminfo - the Cached value is actually the sum of page cache and
+tmpfs memory)
 .SH OPTIONS
 .TP
 \fB\-b\fR, \fB\-\-bytes\fR

diff --git a/proc/sysinfo.c b/proc/sysinfo.c
index 1680cc4a7182f59d72dabf8de2d714efed888268..e07ca8669051abcce072d322d6a246563ba7e8a1 100644 (file)
--- a/proc/sysinfo.c
+++ b/proc/sysinfo.c
@@ -531,7 +531,6 @@ static int compare_mem_table_structs(const void *a, const void *b){
  *
  * MemTotal:        61768 kB    old
  * MemFree:          1436 kB    old
- * MemShared:           0 kB    old (now always zero; not calculated)
  * Buffers:          1312 kB    old
  * Cached:          20932 kB    old
  * Active:          12464 kB    new
@@ -560,7 +559,7 @@ static int compare_mem_table_structs(const void *a, const void *b){
  * Hugepagesize:     4096 kB    2.5.??+
  */
 
-/* obsolete since 2.6.x, but reused for shmem in 2.6.32+ */
+/* Shmem in 2.6.32+ */
 unsigned long kb_main_shared;
 /* old but still kicking -- the important stuff */
 unsigned long kb_main_buffers;
@@ -631,14 +630,13 @@ void meminfo(void){
   {"LowTotal",     &kb_low_total},
   {"Mapped",       &kb_mapped},       // kB version of vmstat nr_mapped
   {"MemFree",      &kb_main_free},    // important
-  {"MemShared",    &kb_main_shared},  // obsolete since kernel 2.6! (sharing the variable with Shmem replacement)
   {"MemTotal",     &kb_main_total},   // important
   {"NFS_Unstable", &kb_nfs_unstable},
   {"PageTables",   &kb_pagetables},   // kB version of vmstat nr_page_table_pages
   {"ReverseMaps",  &nr_reversemaps},  // same as vmstat nr_page_table_pages
   {"SReclaimable", &kb_swap_reclaimable}, // "swap reclaimable" (dentry and inode structures)
   {"SUnreclaim",   &kb_swap_unreclaimable},
-  {"Shmem",        &kb_main_shared},  // kernel 2.6 and later (sharing the output variable with obsolete MemShared)
+  {"Shmem",        &kb_main_shared},  // kernel 2.6.32 and later
   {"Slab",         &kb_slab},         // kB version of vmstat nr_slab
   {"SwapCached",   &kb_swap_cached},
   {"SwapFree",     &kb_swap_free},    // important
@@ -684,6 +682,8 @@ nextline:
   }
   kb_swap_used = kb_swap_total - kb_swap_free;
   kb_main_used = kb_main_total - kb_main_free;
+  /* "Cached" includes "Shmem" - we want only the page cache here */
+  kb_main_cached -= kb_main_shared;
 }
 
 /*****************************************************************/

diff --git a/proc/sysinfo.h b/proc/sysinfo.h
index 1eb34727055e58e0d804354c818d3b8309c7134d..22916319d8712ceba49dfc43ebebd400eac05157 100644 (file)
--- a/proc/sysinfo.h
+++ b/proc/sysinfo.h
@@ -20,8 +20,7 @@ extern int        uptime (double *uptime_secs, double *idle_secs);
 extern unsigned long getbtime(void);
 extern void       loadavg(double *av1, double *av5, double *av15);
 
-
-/* obsolete */
+/* Shmem in 2.6.32+ */
 extern unsigned long kb_main_shared;
 /* old but still kicking -- the important stuff */
 extern unsigned long kb_main_buffers;

diff --git a/vmstat.8 b/vmstat.8
index 420d9f394b373828cf0d805ae11d848f745d8717..2782a427dd32f2917b1bb677497bc086bfd9d11f 100644 (file)
--- a/vmstat.8
+++ b/vmstat.8
@@ -102,7 +102,8 @@ b: The number of processes in uninterruptible sleep.
 swpd: the amount of virtual memory used.
 free: the amount of idle memory.
 buff: the amount of memory used as buffers.
-cache: the amount of memory used as cache.
+cache: the amount of memory used as cache (excluding tmpfs memory for
+kernels 2.6.32+)
 inact: the amount of inactive memory.  (\-a option)
 active: the amount of active memory.  (\-a option)
 .fi