cachestat: implement cachestat syscall
ANBZ: #5940
commit cf264e1329 upstream.
There is currently no good way to query the page cache state of large file
sets and directory trees. There is mincore(), but it scales poorly: the
kernel writes out a lot of bitmap data that userspace has to aggregate,
when the user really doesn not care about per-page information in that
case. The user also needs to mmap and unmap each file as it goes along,
which can be quite slow as well.
Some use cases where this information could come in handy:
* Allowing database to decide whether to perform an index scan or
direct table queries based on the in-memory cache state of the
index.
* Visibility into the writeback algorithm, for performance issues
diagnostic.
* Workload-aware writeback pacing: estimating IO fulfilled by page
cache (and IO to be done) within a range of a file, allowing for
more frequent syncing when and where there is IO capacity, and
batching when there is not.
* Computing memory usage of large files/directory trees, analogous to
the du tool for disk usage.
More information about these use cases could be found in the following
thread:
https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/
This patch implements a new syscall that queries cache state of a file and
summarizes the number of cached pages, number of dirty pages, number of
pages marked for writeback, number of (recently) evicted pages, etc. in a
given range. Currently, the syscall is only wired in for x86
architecture.
NAME
cachestat - query the page cache statistics of a file.
SYNOPSIS
#include <sys/mman.h>
struct cachestat_range {
__u64 off;
__u64 len;
};
struct cachestat {
__u64 nr_cache;
__u64 nr_dirty;
__u64 nr_writeback;
__u64 nr_evicted;
__u64 nr_recently_evicted;
};
int cachestat(unsigned int fd, struct cachestat_range *cstat_range,
struct cachestat *cstat, unsigned int flags);
DESCRIPTION
cachestat() queries the number of cached pages, number of dirty
pages, number of pages marked for writeback, number of evicted
pages, number of recently evicted pages, in the bytes range given by
`off` and `len`.
An evicted page is a page that is previously in the page cache but
has been evicted since. A page is recently evicted if its last
eviction was recent enough that its reentry to the cache would
indicate that it is actively being used by the system, and that
there is memory pressure on the system.
These values are returned in a cachestat struct, whose address is
given by the `cstat` argument.
The `off` and `len` arguments must be non-negative integers. If
`len` > 0, the queried range is [`off`, `off` + `len`]. If `len` ==
0, we will query in the range from `off` to the end of the file.
The `flags` argument is unused for now, but is included for future
extensibility. User should pass 0 (i.e no flag specified).
Currently, hugetlbfs is not supported.
Because the status of a page can change after cachestat() checks it
but before it returns to the application, the returned values may
contain stale information.
RETURN VALUE
On success, cachestat returns 0. On error, -1 is returned, and errno
is set to indicate the error.
ERRORS
EFAULT cstat or cstat_args points to an invalid address.
EINVAL invalid flags.
EBADF invalid file descriptor.
EOPNOTSUPP file descriptor is of a hugetlbfs file
[nphamcs@gmail.com: replace rounddown logic with the existing helper]
Link: https://lkml.kernel.org/r/20230504022044.3675469-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20230503013608.2431726-3-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Brian Foster <bfoster@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Bo Liu <boliu@linux.alibaba.com>
Reviewed-by: Xu Yu <xuyu@linux.alibaba.com>
Link: https://gitee.com/anolis/cloud-kernel/pulls/2061
This commit is contained in:
Nhat Pham
Bo Liu
parent
b325e563df
commit
632e946040
|
|
@ -452,3 +452,7 @@
|
|||
445 i386 landlock_add_rule sys_ni_syscall
|
||||
446 i386 landlock_restrict_self sys_ni_syscall
|
||||
447 i386 memfd_secret sys_memfd_secret
|
||||
448 i386 process_mrelease sys_ni_syscall
|
||||
449 i386 futex_waitv sys_ni_syscall
|
||||
450 i386 set_mempolicy_home_node sys_ni_syscall
|
||||
451 i386 cachestat sys_cachestat
|
||||
|
|
|
|||
|
|
@ -369,6 +369,10 @@
|
|||
445 common landlock_add_rule sys_ni_syscall
|
||||
446 common landlock_restrict_self sys_ni_syscall
|
||||
447 common memfd_secret sys_memfd_secret
|
||||
448 common process_mrelease sys_ni_syscall
|
||||
449 common futex_waitv sys_ni_syscall
|
||||
450 common set_mempolicy_home_node sys_ni_syscall
|
||||
451 common cachestat sys_cachestat
|
||||
|
||||
#
|
||||
# Due to a historical design error, certain syscalls are numbered differently
|
||||
|
|
|
|||
|
|
@ -68,6 +68,8 @@ union bpf_attr;
|
|||
struct io_uring_params;
|
||||
struct clone_args;
|
||||
struct open_how;
|
||||
struct cachestat_range;
|
||||
struct cachestat;
|
||||
|
||||
#include <linux/types.h>
|
||||
#include <linux/aio_abi.h>
|
||||
|
|
@ -1033,6 +1035,9 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
|
|||
unsigned int flags);
|
||||
asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
|
||||
asmlinkage long sys_memfd_secret(unsigned int flags);
|
||||
asmlinkage long sys_cachestat(unsigned int fd,
|
||||
struct cachestat_range __user *cstat_range,
|
||||
struct cachestat __user *cstat, unsigned int flags);
|
||||
|
||||
/*
|
||||
* Architecture-specific system calls
|
||||
|
|
|
|||
|
|
@ -875,9 +875,17 @@ __SYSCALL(__NR_landlock_restrict_self, sys_ni_syscall)
|
|||
#define __NR_memfd_secret 447
|
||||
__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
|
||||
#endif
|
||||
#define __NR_process_mrelease 448
|
||||
__SYSCALL(__NR_process_mrelease, sys_ni_syscall)
|
||||
#define __NR_futex_waitv 449
|
||||
__SYSCALL(__NR_futex_waitv, sys_ni_syscall)
|
||||
#define __NR_set_mempolicy_home_node 450
|
||||
__SYSCALL(__NR_set_mempolicy_home_node, sys_ni_syscall)
|
||||
#define __NR_cachestat 451
|
||||
__SYSCALL(__NR_cachestat, sys_cachestat)
|
||||
|
||||
#undef __NR_syscalls
|
||||
#define __NR_syscalls 448
|
||||
#define __NR_syscalls 452
|
||||
|
||||
/*
|
||||
* 32 bit systems traditionally used different
|
||||
|
|
|
|||
|
|
@ -4,6 +4,7 @@
|
|||
|
||||
#include <asm/mman.h>
|
||||
#include <asm-generic/hugetlb_encode.h>
|
||||
#include <linux/types.h>
|
||||
|
||||
#define MREMAP_MAYMOVE 1
|
||||
#define MREMAP_FIXED 2
|
||||
|
|
@ -41,4 +42,17 @@
|
|||
#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
|
||||
#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
|
||||
|
||||
struct cachestat_range {
|
||||
__u64 off;
|
||||
__u64 len;
|
||||
};
|
||||
|
||||
struct cachestat {
|
||||
__u64 nr_cache;
|
||||
__u64 nr_dirty;
|
||||
__u64 nr_writeback;
|
||||
__u64 nr_evicted;
|
||||
__u64 nr_recently_evicted;
|
||||
};
|
||||
|
||||
#endif /* _UAPI_LINUX_MMAN_H */
|
||||
|
|
|
|||
10
init/Kconfig
10
init/Kconfig
|
|
@ -1855,6 +1855,16 @@ config RSEQ
|
|||
|
||||
If unsure, say Y.
|
||||
|
||||
config CACHESTAT_SYSCALL
|
||||
bool "Enable cachestat() system call" if EXPERT
|
||||
default y
|
||||
help
|
||||
Enable the cachestat system call, which queries the page cache
|
||||
statistics of a file (number of cached pages, dirty pages,
|
||||
pages marked for writeback, (recently) evicted pages).
|
||||
|
||||
If unsure say Y here.
|
||||
|
||||
config DEBUG_RSEQ
|
||||
default n
|
||||
bool "Enabled debugging of rseq() system call" if EXPERT
|
||||
|
|
|
|||
|
|
@ -291,7 +291,7 @@ COND_SYSCALL_COMPAT(set_mempolicy);
|
|||
COND_SYSCALL(migrate_pages);
|
||||
COND_SYSCALL_COMPAT(migrate_pages);
|
||||
COND_SYSCALL(move_pages);
|
||||
COND_SYSCALL_COMPAT(move_pages);
|
||||
COND_SYSCALL(cachestat);
|
||||
|
||||
COND_SYSCALL(perf_event_open);
|
||||
COND_SYSCALL(accept4);
|
||||
|
|
|
|||
170
mm/filemap.c
170
mm/filemap.c
|
|
@ -21,6 +21,8 @@
|
|||
#include <linux/gfp.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/swap.h>
|
||||
#include <linux/swapops.h>
|
||||
#include <linux/syscalls.h>
|
||||
#include <linux/mman.h>
|
||||
#include <linux/pagemap.h>
|
||||
#include <linux/file.h>
|
||||
|
|
@ -3671,3 +3673,171 @@ int try_to_release_page(struct page *page, gfp_t gfp_mask)
|
|||
}
|
||||
|
||||
EXPORT_SYMBOL(try_to_release_page);
|
||||
|
||||
#ifdef CONFIG_CACHESTAT_SYSCALL
|
||||
/**
|
||||
* filemap_cachestat() - compute the page cache statistics of a mapping
|
||||
* @mapping: The mapping to compute the statistics for.
|
||||
* @first_index: The starting page cache index.
|
||||
* @last_index: The final page index (inclusive).
|
||||
* @cs: the cachestat struct to write the result to.
|
||||
*
|
||||
* This will query the page cache statistics of a mapping in the
|
||||
* page range of [first_index, last_index] (inclusive). The statistics
|
||||
* queried include: number of dirty pages, number of pages marked for
|
||||
* writeback, and the number of (recently) evicted pages.
|
||||
*/
|
||||
static void filemap_cachestat(struct address_space *mapping,
|
||||
pgoff_t first_index, pgoff_t last_index, struct cachestat *cs)
|
||||
{
|
||||
XA_STATE(xas, &mapping->i_pages, first_index);
|
||||
struct page *page;
|
||||
|
||||
rcu_read_lock();
|
||||
xas_for_each(&xas, page, last_index) {
|
||||
unsigned long nr_pages;
|
||||
pgoff_t page_first_index, page_last_index;
|
||||
|
||||
if (xas_retry(&xas, page))
|
||||
continue;
|
||||
|
||||
if (xa_is_value(page)) {
|
||||
/* page is evicted */
|
||||
void *shadow = (void *)page;
|
||||
bool workingset; /* not used */
|
||||
int order = xa_get_order(xas.xa, xas.xa_index);
|
||||
|
||||
nr_pages = 1 << order;
|
||||
page_first_index = round_down(xas.xa_index, 1 << order);
|
||||
page_last_index = page_first_index + nr_pages - 1;
|
||||
|
||||
/* Pages might straddle the range boundaries, only count covered pages */
|
||||
if (page_first_index < first_index)
|
||||
nr_pages -= first_index - page_first_index;
|
||||
|
||||
if (page_last_index > last_index)
|
||||
nr_pages -= page_last_index - last_index;
|
||||
|
||||
cs->nr_evicted += nr_pages;
|
||||
|
||||
#ifdef CONFIG_SWAP /* implies CONFIG_MMU */
|
||||
if (shmem_mapping(mapping)) {
|
||||
/* shmem file - in swap cache */
|
||||
swp_entry_t swp = radix_to_swp_entry(page);
|
||||
|
||||
shadow = get_shadow_from_swap_cache(swp);
|
||||
}
|
||||
#endif
|
||||
if (workingset_test_recent(shadow, true, &workingset))
|
||||
cs->nr_recently_evicted += nr_pages;
|
||||
|
||||
goto resched;
|
||||
}
|
||||
|
||||
nr_pages = compound_nr(page);
|
||||
page_first_index = page_to_pgoff(page);
|
||||
page_last_index = page_first_index + nr_pages - 1;
|
||||
|
||||
/* Pages might straddle the range boundaries, only count covered pages */
|
||||
if (page_first_index < first_index)
|
||||
nr_pages -= first_index - page_first_index;
|
||||
|
||||
if (page_last_index > last_index)
|
||||
nr_pages -= page_last_index - last_index;
|
||||
|
||||
/* page is in cache */
|
||||
cs->nr_cache += nr_pages;
|
||||
|
||||
if (PageDirty(page))
|
||||
cs->nr_dirty += nr_pages;
|
||||
|
||||
if (PageWriteback(page))
|
||||
cs->nr_writeback += nr_pages;
|
||||
|
||||
resched:
|
||||
if (need_resched()) {
|
||||
xas_pause(&xas);
|
||||
cond_resched_rcu();
|
||||
}
|
||||
}
|
||||
rcu_read_unlock();
|
||||
}
|
||||
|
||||
/*
|
||||
* The cachestat(2) system call.
|
||||
*
|
||||
* cachestat() returns the page cache statistics of a file in the
|
||||
* bytes range specified by `off` and `len`: number of cached pages,
|
||||
* number of dirty pages, number of pages marked for writeback,
|
||||
* number of evicted pages, and number of recently evicted pages.
|
||||
*
|
||||
* An evicted page is a page that is previously in the page cache
|
||||
* but has been evicted since. A page is recently evicted if its last
|
||||
* eviction was recent enough that its reentry to the cache would
|
||||
* indicate that it is actively being used by the system, and that
|
||||
* there is memory pressure on the system.
|
||||
*
|
||||
* `off` and `len` must be non-negative integers. If `len` > 0,
|
||||
* the queried range is [`off`, `off` + `len`]. If `len` == 0,
|
||||
* we will query in the range from `off` to the end of the file.
|
||||
*
|
||||
* The `flags` argument is unused for now, but is included for future
|
||||
* extensibility. User should pass 0 (i.e no flag specified).
|
||||
*
|
||||
* Currently, hugetlbfs is not supported.
|
||||
*
|
||||
* Because the status of a page can change after cachestat() checks it
|
||||
* but before it returns to the application, the returned values may
|
||||
* contain stale information.
|
||||
*
|
||||
* return values:
|
||||
* zero - success
|
||||
* -EFAULT - cstat or cstat_range points to an illegal address
|
||||
* -EINVAL - invalid flags
|
||||
* -EBADF - invalid file descriptor
|
||||
* -EOPNOTSUPP - file descriptor is of a hugetlbfs file
|
||||
*/
|
||||
SYSCALL_DEFINE4(cachestat, unsigned int, fd,
|
||||
struct cachestat_range __user *, cstat_range,
|
||||
struct cachestat __user *, cstat, unsigned int, flags)
|
||||
{
|
||||
struct fd f = fdget(fd);
|
||||
struct address_space *mapping;
|
||||
struct cachestat_range csr;
|
||||
struct cachestat cs;
|
||||
pgoff_t first_index, last_index;
|
||||
|
||||
if (!f.file)
|
||||
return -EBADF;
|
||||
|
||||
if (copy_from_user(&csr, cstat_range,
|
||||
sizeof(struct cachestat_range))) {
|
||||
fdput(f);
|
||||
return -EFAULT;
|
||||
}
|
||||
|
||||
/* hugetlbfs is not supported */
|
||||
if (is_file_hugepages(f.file)) {
|
||||
fdput(f);
|
||||
return -EOPNOTSUPP;
|
||||
}
|
||||
|
||||
if (flags != 0) {
|
||||
fdput(f);
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
first_index = csr.off >> PAGE_SHIFT;
|
||||
last_index =
|
||||
csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT;
|
||||
memset(&cs, 0, sizeof(struct cachestat));
|
||||
mapping = f.file->f_mapping;
|
||||
filemap_cachestat(mapping, first_index, last_index, &cs);
|
||||
fdput(f);
|
||||
|
||||
if (copy_to_user(cstat, &cs, sizeof(struct cachestat)))
|
||||
return -EFAULT;
|
||||
|
||||
return 0;
|
||||
}
|
||||
#endif /* CONFIG_CACHESTAT_SYSCALL */
|
||||
|
|
|
|||
Loading…
Reference in New Issue