lkml.org 
[lkml]   [2018]   [Dec]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[RFC][PATCH v2 17/21] proc: introduce /proc/PID/idle_pages
This will be similar to /sys/kernel/mm/page_idle/bitmap documented in
Documentation/admin-guide/mm/idle_page_tracking.rst, however indexed
by process virtual address.

When using the global PFN indexed idle bitmap, we find 2 kind of
overheads:

- to track a task's working set, Brendan Gregg end up writing wss-v1
for small tasks and wss-v2 for large tasks:

https://github.com/brendangregg/wss

That's because VAs may point to random PAs throughout the physical
address space. So we either query /proc/pid/pagemap first and access
the lots of random PFNs (with lots of syscalls) in the bitmap, or
write+read the whole system idle bitmap beforehand.

- page table walking by PFN has much more overheads than to walk a
page table in its natural order:
- rmap queries
- more locking
- random memory reads/writes

This interface provides a cheap path for the majority non-shared mapping
pages. To walk 1TB memory of 4k active pages, it costs 2s vs 15s system
time to scan the per-task/global idle bitmaps. Which means ~7x speedup.
The gap will be enlarged if consider

- the extra /proc/pid/pagemap walk
- natural page table walks can skip the whole 512 PTEs if PMD is idle

OTOH, the per-task idle bitmap is not suitable in some situations:

- not accurate for shared pages
- don't work with non-mapped file pages
- don't perform well for sparse page tables (pointed out by Huang Ying)

So it's more about complementing the existing global idle bitmap.

CC: Huang Ying <ying.huang@intel.com>
CC: Brendan Gregg <bgregg@netflix.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
fs/proc/base.c | 2 +
fs/proc/internal.h | 1
fs/proc/task_mmu.c | 54 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 57 insertions(+)

--- linux.orig/fs/proc/base.c 2018-12-23 20:08:14.228919325 +0800
+++ linux/fs/proc/base.c 2018-12-23 20:08:14.224919327 +0800
@@ -2969,6 +2969,7 @@ static const struct pid_entry tgid_base_
REG("smaps", S_IRUGO, proc_pid_smaps_operations),
REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
REG("pagemap", S_IRUSR, proc_pagemap_operations),
+ REG("idle_pages", S_IRUSR|S_IWUSR, proc_mm_idle_operations),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
@@ -3357,6 +3358,7 @@ static const struct pid_entry tid_base_s
REG("smaps", S_IRUGO, proc_pid_smaps_operations),
REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations),
REG("pagemap", S_IRUSR, proc_pagemap_operations),
+ REG("idle_pages", S_IRUSR|S_IWUSR, proc_mm_idle_operations),
#endif
#ifdef CONFIG_SECURITY
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
--- linux.orig/fs/proc/internal.h 2018-12-23 20:08:14.228919325 +0800
+++ linux/fs/proc/internal.h 2018-12-23 20:08:14.224919327 +0800
@@ -298,6 +298,7 @@ extern const struct file_operations proc
extern const struct file_operations proc_pid_smaps_rollup_operations;
extern const struct file_operations proc_clear_refs_operations;
extern const struct file_operations proc_pagemap_operations;
+extern const struct file_operations proc_mm_idle_operations;

extern unsigned long task_vsize(struct mm_struct *);
extern unsigned long task_statm(struct mm_struct *,
--- linux.orig/fs/proc/task_mmu.c 2018-12-23 20:08:14.228919325 +0800
+++ linux/fs/proc/task_mmu.c 2018-12-23 20:08:14.224919327 +0800
@@ -1559,6 +1559,60 @@ const struct file_operations proc_pagema
.open = pagemap_open,
.release = pagemap_release,
};
+
+/* will be filled when kvm_ept_idle module loads */
+struct file_operations proc_ept_idle_operations = {
+};
+EXPORT_SYMBOL_GPL(proc_ept_idle_operations);
+
+static ssize_t mm_idle_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ if (proc_ept_idle_operations.read)
+ return proc_ept_idle_operations.read(file, buf, count, ppos);
+
+ return 0;
+}
+
+
+static int mm_idle_open(struct inode *inode, struct file *file)
+{
+ struct mm_struct *mm = proc_mem_open(inode, PTRACE_MODE_READ);
+
+ if (IS_ERR(mm))
+ return PTR_ERR(mm);
+
+ file->private_data = mm;
+
+ if (proc_ept_idle_operations.open)
+ return proc_ept_idle_operations.open(inode, file);
+
+ return 0;
+}
+
+static int mm_idle_release(struct inode *inode, struct file *file)
+{
+ struct mm_struct *mm = file->private_data;
+
+ if (mm) {
+ if (!mm_kvm(mm))
+ flush_tlb_mm(mm);
+ mmdrop(mm);
+ }
+
+ if (proc_ept_idle_operations.release)
+ return proc_ept_idle_operations.release(inode, file);
+
+ return 0;
+}
+
+const struct file_operations proc_mm_idle_operations = {
+ .llseek = mem_lseek, /* borrow this */
+ .read = mm_idle_read,
+ .open = mm_idle_open,
+ .release = mm_idle_release,
+};
+
#endif /* CONFIG_PROC_PAGE_MONITOR */

#ifdef CONFIG_NUMA

\
 
 \ /
  Last update: 2018-12-26 14:37    [W:0.254 / U:0.576 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site