summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLuigi Semenzato <semenzato@chromium.org>2019-07-11 21:00:10 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-07-12 11:05:47 -0700
commitee2ad71b0756e995fa4f6d922463e9bccd71b198 (patch)
tree0ca5415368b95cbe6890d915a98fc83c9e1eee3e
parent1e426fe28261b03f297992e89da3320b42816f4e (diff)
mm: smaps: split PSS into components
Report separate components (anon, file, and shmem) for PSS in smaps_rollup. This helps understand and tune the memory manager behavior in consumer devices, particularly mobile devices. Many of them (e.g. chromebooks and Android-based devices) use zram for anon memory, and perform disk reads for discarded file pages. The difference in latency is large (e.g. reading a single page from SSD is 30 times slower than decompressing a zram page on one popular device), thus it is useful to know how much of the PSS is anon vs. file. All the information is already present in /proc/pid/smaps, but much more expensive to obtain because of the large size of that procfs entry. This patch also removes a small code duplication in smaps_account, which would have gotten worse otherwise. Also updated Documentation/filesystems/proc.txt (the smaps section was a bit stale, and I added a smaps_rollup section) and Documentation/ABI/testing/procfs-smaps_rollup. [semenzato@chromium.org: v5] Link: http://lkml.kernel.org/r/20190626234333.44608-1-semenzato@chromium.org Link: http://lkml.kernel.org/r/20190626180429.174569-1-semenzato@chromium.org Signed-off-by: Luigi Semenzato <semenzato@chromium.org> Acked-by: Yu Zhao <yuzhao@chromium.org> Cc: Sonny Rao <sonnyrao@chromium.org> Cc: Yu Zhao <yuzhao@chromium.org> Cc: Brian Geffon <bgeffon@chromium.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--Documentation/ABI/testing/procfs-smaps_rollup14
-rw-r--r--Documentation/filesystems/proc.txt41
-rw-r--r--fs/proc/task_mmu.c92
3 files changed, 105 insertions, 42 deletions
diff --git a/Documentation/ABI/testing/procfs-smaps_rollup b/Documentation/ABI/testing/procfs-smaps_rollup
index 0a54ed0d63c9..274df44d8b1b 100644
--- a/Documentation/ABI/testing/procfs-smaps_rollup
+++ b/Documentation/ABI/testing/procfs-smaps_rollup
@@ -3,18 +3,28 @@ Date: August 2017
Contact: Daniel Colascione <dancol@google.com>
Description:
This file provides pre-summed memory information for a
- process. The format is identical to /proc/pid/smaps,
+ process. The format is almost identical to /proc/pid/smaps,
except instead of an entry for each VMA in a process,
smaps_rollup has a single entry (tagged "[rollup]")
for which each field is the sum of the corresponding
fields from all the maps in /proc/pid/smaps.
- For more details, see the procfs man page.
+ Additionally, the fields Pss_Anon, Pss_File and Pss_Shmem
+ are not present in /proc/pid/smaps. These fields represent
+ the sum of the Pss field of each type (anon, file, shmem).
+ For more details, see Documentation/filesystems/proc.txt
+ and the procfs man page.
Typical output looks like this:
00100000-ff709000 ---p 00000000 00:00 0 [rollup]
+ Size: 1192 kB
+ KernelPageSize: 4 kB
+ MMUPageSize: 4 kB
Rss: 884 kB
Pss: 385 kB
+ Pss_Anon: 301 kB
+ Pss_File: 80 kB
+ Pss_Shmem: 4 kB
Shared_Clean: 696 kB
Shared_Dirty: 0 kB
Private_Clean: 120 kB
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a226061fa109..d750b6926899 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -154,9 +154,11 @@ Table 1-1: Process specific entries in /proc
symbol the task is blocked in - or "0" if not blocked.
pagemap Page table
stack Report full stack trace, enable via CONFIG_STACKTRACE
- smaps an extension based on maps, showing the memory consumption of
+ smaps An extension based on maps, showing the memory consumption of
each mapping and flags associated with it
- numa_maps an extension based on maps, showing the memory locality and
+ smaps_rollup Accumulated smaps stats for all mappings of the process. This
+ can be derived from smaps, but is faster and more convenient
+ numa_maps An extension based on maps, showing the memory locality and
binding policy as well as mem usage (in pages) of each mapping.
..............................................................................
@@ -366,7 +368,7 @@ Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
exit_code the thread's exit_code in the form reported by the waitpid system call
..............................................................................
-The /proc/PID/maps file containing the currently mapped memory regions and
+The /proc/PID/maps file contains the currently mapped memory regions and
their access permissions.
The format is:
@@ -417,11 +419,14 @@ is not associated with a file:
or if empty, the mapping is anonymous.
The /proc/PID/smaps is an extension based on maps, showing the memory
-consumption for each of the process's mappings. For each of mappings there
-is a series of lines such as the following:
+consumption for each of the process's mappings. For each mapping (aka Virtual
+Memory Area, or VMA) there is a series of lines such as the following:
08048000-080bc000 r-xp 00000000 03:02 13130 /bin/bash
+
Size: 1084 kB
+KernelPageSize: 4 kB
+MMUPageSize: 4 kB
Rss: 892 kB
Pss: 374 kB
Shared_Clean: 892 kB
@@ -443,11 +448,14 @@ Locked: 0 kB
THPeligible: 0
VmFlags: rd ex mr mw me dw
-the first of these lines shows the same information as is displayed for the
-mapping in /proc/PID/maps. The remaining lines show the size of the mapping
-(size), the amount of the mapping that is currently resident in RAM (RSS), the
-process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping.
+The first of these lines shows the same information as is displayed for the
+mapping in /proc/PID/maps. Following lines show the size of the mapping
+(size); the size of each page allocated when backing a VMA (KernelPageSize),
+which is usually the same as the size in the page table entries; the page size
+used by the MMU when backing a VMA (in most cases, the same as KernelPageSize);
+the amount of the mapping that is currently resident in RAM (RSS); the
+process' proportional share of this mapping (PSS); and the number of clean and
+dirty shared and private pages in the mapping.
The "proportional set size" (PSS) of a process is the count of pages it has
in memory, where each page is divided by the number of processes sharing it.
@@ -532,6 +540,19 @@ guarantees:
2) If there is something at a given vaddr during the entirety of the
life of the smaps/maps walk, there will be some output for it.
+The /proc/PID/smaps_rollup file includes the same fields as /proc/PID/smaps,
+but their values are the sums of the corresponding values for all mappings of
+the process. Additionally, it contains these fields:
+
+Pss_Anon
+Pss_File
+Pss_Shmem
+
+They represent the proportional shares of anonymous, file, and shmem pages, as
+described for smaps above. These fields are omitted in smaps since each
+mapping identifies the type (anon, file, or shmem) of all pages it contains.
+Thus all information in smaps_rollup can be derived from smaps, but at a
+significantly higher cost.
The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
bits on both physical and virtual pages associated with a process, and the
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 7f84d1477b5b..dedca3da428a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -421,17 +421,53 @@ struct mem_size_stats {
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
u64 pss;
+ u64 pss_anon;
+ u64 pss_file;
+ u64 pss_shmem;
u64 pss_locked;
u64 swap_pss;
bool check_shmem_swap;
};
+static void smaps_page_accumulate(struct mem_size_stats *mss,
+ struct page *page, unsigned long size, unsigned long pss,
+ bool dirty, bool locked, bool private)
+{
+ mss->pss += pss;
+
+ if (PageAnon(page))
+ mss->pss_anon += pss;
+ else if (PageSwapBacked(page))
+ mss->pss_shmem += pss;
+ else
+ mss->pss_file += pss;
+
+ if (locked)
+ mss->pss_locked += pss;
+
+ if (dirty || PageDirty(page)) {
+ if (private)
+ mss->private_dirty += size;
+ else
+ mss->shared_dirty += size;
+ } else {
+ if (private)
+ mss->private_clean += size;
+ else
+ mss->shared_clean += size;
+ }
+}
+
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty, bool locked)
{
int i, nr = compound ? 1 << compound_order(page) : 1;
unsigned long size = nr * PAGE_SIZE;
+ /*
+ * First accumulate quantities that depend only on |size| and the type
+ * of the compound page.
+ */
if (PageAnon(page)) {
mss->anonymous += size;
if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
@@ -444,42 +480,25 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
mss->referenced += size;
/*
+ * Then accumulate quantities that may depend on sharing, or that may
+ * differ page-by-page.
+ *
* page_count(page) == 1 guarantees the page is mapped exactly once.
* If any subpage of the compound page mapped with PTE it would elevate
* page_count().
*/
if (page_count(page) == 1) {
- if (dirty || PageDirty(page))
- mss->private_dirty += size;
- else
- mss->private_clean += size;
- mss->pss += (u64)size << PSS_SHIFT;
- if (locked)
- mss->pss_locked += (u64)size << PSS_SHIFT;
+ smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty,
+ locked, true);
return;
}
-
for (i = 0; i < nr; i++, page++) {
int mapcount = page_mapcount(page);
- unsigned long pss = (PAGE_SIZE << PSS_SHIFT);
-
- if (mapcount >= 2) {
- if (dirty || PageDirty(page))
- mss->shared_dirty += PAGE_SIZE;
- else
- mss->shared_clean += PAGE_SIZE;
- mss->pss += pss / mapcount;
- if (locked)
- mss->pss_locked += pss / mapcount;
- } else {
- if (dirty || PageDirty(page))
- mss->private_dirty += PAGE_SIZE;
- else
- mss->private_clean += PAGE_SIZE;
- mss->pss += pss;
- if (locked)
- mss->pss_locked += pss;
- }
+ unsigned long pss = PAGE_SIZE << PSS_SHIFT;
+ if (mapcount >= 2)
+ pss /= mapcount;
+ smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked,
+ mapcount < 2);
}
}
@@ -758,10 +777,23 @@ static void smap_gather_stats(struct vm_area_struct *vma,
seq_put_decimal_ull_width(m, str, (val) >> 10, 8)
/* Show the contents common for smaps and smaps_rollup */
-static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss)
+static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
+ bool rollup_mode)
{
SEQ_PUT_DEC("Rss: ", mss->resident);
SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT);
+ if (rollup_mode) {
+ /*
+ * These are meaningful only for smaps_rollup, otherwise two of
+ * them are zero, and the other one is the same as Pss.
+ */
+ SEQ_PUT_DEC(" kB\nPss_Anon: ",
+ mss->pss_anon >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_File: ",
+ mss->pss_file >> PSS_SHIFT);
+ SEQ_PUT_DEC(" kB\nPss_Shmem: ",
+ mss->pss_shmem >> PSS_SHIFT);
+ }
SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean);
SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty);
SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean);
@@ -798,7 +830,7 @@ static int show_smap(struct seq_file *m, void *v)
SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma));
seq_puts(m, " kB\n");
- __show_smap(m, &mss);
+ __show_smap(m, &mss, false);
seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma));
@@ -848,7 +880,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
seq_pad(m, ' ');
seq_puts(m, "[rollup]\n");
- __show_smap(m, &mss);
+ __show_smap(m, &mss, true);
release_task_mempolicy(priv);
up_read(&mm->mmap_sem);