Re: [PATCH -mmotm 4/4] memcg: dirty pages instrumentation

From: Balbir Singh
Date: Fri Mar 05 2010 - 01:39:17 EST

* Andrea Righi <arighi@xxxxxxxxxxx> [2010-03-04 11:40:15]:

> Apply the cgroup dirty pages accounting and limiting infrastructure
> to the opportune kernel functions.
>
> Signed-off-by: Andrea Righi <arighi@xxxxxxxxxxx>
> ---
> fs/fuse/file.c | 5 +++
> fs/nfs/write.c | 4 ++
> fs/nilfs2/segment.c | 11 +++++-
> mm/filemap.c | 1 +
> mm/page-writeback.c | 91 ++++++++++++++++++++++++++++++++++-----------------
> mm/rmap.c | 4 +-
> mm/truncate.c | 2 +
> 7 files changed, 84 insertions(+), 34 deletions(-)
>
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index a9f5e13..dbbdd53 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -11,6 +11,7 @@
> #include <linux/pagemap.h>
> #include <linux/slab.h>
> #include <linux/kernel.h>
> +#include <linux/memcontrol.h>
> #include <linux/sched.h>
> #include <linux/module.h>
>
> @@ -1129,6 +1130,8 @@ static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req)
>
> list_del(&req->writepages_entry);
> dec_bdi_stat(bdi, BDI_WRITEBACK);
> + mem_cgroup_update_stat(req->pages[0],
> + MEM_CGROUP_STAT_WRITEBACK_TEMP, -1);
> dec_zone_page_state(req->pages[0], NR_WRITEBACK_TEMP);
> bdi_writeout_inc(bdi);
> wake_up(&fi->page_waitq);
> @@ -1240,6 +1243,8 @@ static int fuse_writepage_locked(struct page *page)
> req->inode = inode;
>
> inc_bdi_stat(mapping->backing_dev_info, BDI_WRITEBACK);
> + mem_cgroup_update_stat(tmp_page,
> + MEM_CGROUP_STAT_WRITEBACK_TEMP, 1);
> inc_zone_page_state(tmp_page, NR_WRITEBACK_TEMP);
> end_page_writeback(page);
>
> diff --git a/fs/nfs/write.c b/fs/nfs/write.c
> index b753242..7316f7a 100644
> --- a/fs/nfs/write.c
> +++ b/fs/nfs/write.c
> @@ -439,6 +439,7 @@ nfs_mark_request_commit(struct nfs_page *req)
> req->wb_index,
> NFS_PAGE_TAG_COMMIT);
> spin_unlock(&inode->i_lock);
> + mem_cgroup_update_stat(req->wb_page, MEM_CGROUP_STAT_UNSTABLE_NFS, 1);
> inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_UNSTABLE);
> __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
> @@ -450,6 +451,7 @@ nfs_clear_request_commit(struct nfs_page *req)
> struct page *page = req->wb_page;
>
> if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_UNSTABLE_NFS, -1);
> dec_zone_page_state(page, NR_UNSTABLE_NFS);
> dec_bdi_stat(page->mapping->backing_dev_info, BDI_UNSTABLE);
> return 1;
> @@ -1273,6 +1275,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
> req = nfs_list_entry(head->next);
> nfs_list_remove_request(req);
> nfs_mark_request_commit(req);
> + mem_cgroup_update_stat(req->wb_page,
> + MEM_CGROUP_STAT_UNSTABLE_NFS, -1);
> dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
> dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
> BDI_UNSTABLE);
> diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
> index ada2f1b..27a01b1 100644
> --- a/fs/nilfs2/segment.c
> +++ b/fs/nilfs2/segment.c
> @@ -24,6 +24,7 @@
> #include <linux/pagemap.h>
> #include <linux/buffer_head.h>
> #include <linux/writeback.h>
> +#include <linux/memcontrol.h>
> #include <linux/bio.h>
> #include <linux/completion.h>
> #include <linux/blkdev.h>
> @@ -1660,8 +1661,11 @@ nilfs_copy_replace_page_buffers(struct page *page, struct list_head *out)
> } while (bh = bh->b_this_page, bh2 = bh2->b_this_page, bh != head);
> kunmap_atomic(kaddr, KM_USER0);
>
> - if (!TestSetPageWriteback(clone_page))
> + if (!TestSetPageWriteback(clone_page)) {
> + mem_cgroup_update_stat(clone_page,
> + MEM_CGROUP_STAT_WRITEBACK, 1);

I wonder if we should start implementing inc and dec to avoid passing
the +1 and -1 parameters. It should make the code easier to read.

> inc_zone_page_state(clone_page, NR_WRITEBACK);
> + }
> unlock_page(clone_page);
>
> return 0;
> @@ -1783,8 +1787,11 @@ static void __nilfs_end_page_io(struct page *page, int err)
> }
>
> if (buffer_nilfs_allocated(page_buffers(page))) {
> - if (TestClearPageWriteback(page))
> + if (TestClearPageWriteback(page)) {
> + mem_cgroup_update_stat(page,
> + MEM_CGROUP_STAT_WRITEBACK, -1);
> dec_zone_page_state(page, NR_WRITEBACK);
> + }
> } else
> end_page_writeback(page);
> }
> diff --git a/mm/filemap.c b/mm/filemap.c
> index fe09e51..f85acae 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -135,6 +135,7 @@ void __remove_from_page_cache(struct page *page)
> * having removed the page entirely.
> */
> if (PageDirty(page) && mapping_cap_account_dirty(mapping)) {
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_FILE_DIRTY, -1);
> dec_zone_page_state(page, NR_FILE_DIRTY);
> dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTY);
> }
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 5a0f8f3..c5d14ea 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -137,13 +137,16 @@ static struct prop_descriptor vm_dirties;
> */
> static int calc_period_shift(void)
> {
> + struct dirty_param dirty_param;

vm_dirty_param?

> unsigned long dirty_total;
>
> - if (vm_dirty_bytes)
> - dirty_total = vm_dirty_bytes / PAGE_SIZE;
> + get_dirty_param(&dirty_param);

get_vm_dirty_param() is a nicer name.

> +
> + if (dirty_param.dirty_bytes)
> + dirty_total = dirty_param.dirty_bytes / PAGE_SIZE;
> else
> - dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
> - 100;
> + dirty_total = (dirty_param.dirty_ratio *
> + determine_dirtyable_memory()) / 100;
> return 2 + ilog2(dirty_total - 1);
> }
>
> @@ -408,41 +411,46 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
> */
> unsigned long determine_dirtyable_memory(void)
> {
> - unsigned long x;
> -
> - x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
> + unsigned long memory;
> + s64 memcg_memory;
>
> + memory = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
> if (!vm_highmem_is_dirtyable)
> - x -= highmem_dirtyable_memory(x);
> -
> - return x + 1; /* Ensure that we never return 0 */
> + memory -= highmem_dirtyable_memory(memory);
> + if (mem_cgroup_has_dirty_limit())
> + return memory + 1;

Vivek already pointed out this issue I suppose. Should be *not*

> + memcg_memory = mem_cgroup_page_stat(MEMCG_NR_DIRTYABLE_PAGES);

Can memcg_memory be 0?

> + return min((unsigned long)memcg_memory, memory + 1);
> }
>
> void
> get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
> unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
> {
> - unsigned long background;
> - unsigned long dirty;
> + unsigned long dirty, background;
> unsigned long available_memory = determine_dirtyable_memory();
> struct task_struct *tsk;
> + struct dirty_param dirty_param;
> +
> + get_dirty_param(&dirty_param);
>
> - if (vm_dirty_bytes)
> - dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
> + if (dirty_param.dirty_bytes)
> + dirty = DIV_ROUND_UP(dirty_param.dirty_bytes, PAGE_SIZE);
> else {
> int dirty_ratio;
>
> - dirty_ratio = vm_dirty_ratio;
> + dirty_ratio = dirty_param.dirty_ratio;
> if (dirty_ratio < 5)
> dirty_ratio = 5;
> dirty = (dirty_ratio * available_memory) / 100;
> }
>
> - if (dirty_background_bytes)
> - background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
> + if (dirty_param.dirty_background_bytes)
> + background = DIV_ROUND_UP(dirty_param.dirty_background_bytes,
> + PAGE_SIZE);
> else
> - background = (dirty_background_ratio * available_memory) / 100;
> -
> + background = (dirty_param.dirty_background_ratio *
> + available_memory) / 100;
> if (background >= dirty)
> background = dirty / 2;
> tsk = current;
> @@ -508,9 +516,15 @@ static void balance_dirty_pages(struct address_space *mapping,
> get_dirty_limits(&background_thresh, &dirty_thresh,
> &bdi_thresh, bdi);
>
> - nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
> + if (mem_cgroup_has_dirty_limit()) {
> + nr_reclaimable =
> + mem_cgroup_page_stat(MEMCG_NR_RECLAIM_PAGES);
> + nr_writeback = mem_cgroup_page_stat(MEMCG_NR_WRITEBACK);
> + } else {
> + nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
> global_page_state(NR_UNSTABLE_NFS);
> - nr_writeback = global_page_state(NR_WRITEBACK);
> + nr_writeback = global_page_state(NR_WRITEBACK);
> + }
>
> bdi_nr_reclaimable = bdi_stat(bdi, BDI_DIRTY);
> if (bdi_cap_account_unstable(bdi)) {
> @@ -611,10 +625,13 @@ static void balance_dirty_pages(struct address_space *mapping,
> * In normal mode, we start background writeout at the lower
> * background_thresh, to keep the amount of dirty memory low.
> */
> + if (mem_cgroup_has_dirty_limit())
> + nr_reclaimable = mem_cgroup_page_stat(MEMCG_NR_RECLAIM_PAGES);
> + else
> + nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
> + global_page_state(NR_UNSTABLE_NFS);
> if ((laptop_mode && pages_written) ||
> - (!laptop_mode && ((global_page_state(NR_FILE_DIRTY)
> - + global_page_state(NR_UNSTABLE_NFS))
> - > background_thresh)))
> + (!laptop_mode && (nr_reclaimable > background_thresh)))
> bdi_start_writeback(bdi, NULL, 0);
> }
>
> @@ -678,6 +695,8 @@ void throttle_vm_writeout(gfp_t gfp_mask)
> unsigned long dirty_thresh;
>
> for ( ; ; ) {
> + unsigned long dirty;
> +
> get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
>
> /*
> @@ -686,10 +705,15 @@ void throttle_vm_writeout(gfp_t gfp_mask)
> */
> dirty_thresh += dirty_thresh / 10; /* wheeee... */
>
> - if (global_page_state(NR_UNSTABLE_NFS) +
> - global_page_state(NR_WRITEBACK) <= dirty_thresh)
> - break;
> - congestion_wait(BLK_RW_ASYNC, HZ/10);
> + if (mem_cgroup_has_dirty_limit())
> + dirty = mem_cgroup_page_stat(
> + MEMCG_NR_DIRTY_WRITEBACK_PAGES);
> + else
> + dirty = global_page_state(NR_UNSTABLE_NFS) +
> + global_page_state(NR_WRITEBACK);
> + if (dirty <= dirty_thresh)
> + break;
> + congestion_wait(BLK_RW_ASYNC, HZ/10);
>
> /*
> * The caller might hold locks which can prevent IO completion
> @@ -1096,6 +1120,7 @@ int __set_page_dirty_no_writeback(struct page *page)
> void account_page_dirtied(struct page *page, struct address_space *mapping)
> {
> if (mapping_cap_account_dirty(mapping)) {
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_FILE_DIRTY, 1);
> __inc_zone_page_state(page, NR_FILE_DIRTY);
> __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTY);
> task_dirty_inc(current);
> @@ -1297,6 +1322,8 @@ int clear_page_dirty_for_io(struct page *page)
> * for more comments.
> */
> if (TestClearPageDirty(page)) {
> + mem_cgroup_update_stat(page,
> + MEM_CGROUP_STAT_FILE_DIRTY, -1);
> dec_zone_page_state(page, NR_FILE_DIRTY);
> dec_bdi_stat(mapping->backing_dev_info,
> BDI_DIRTY);
> @@ -1332,8 +1359,10 @@ int test_clear_page_writeback(struct page *page)
> } else {
> ret = TestClearPageWriteback(page);
> }
> - if (ret)
> + if (ret) {
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_WRITEBACK, -1);
> dec_zone_page_state(page, NR_WRITEBACK);
> + }
> return ret;
> }
>
> @@ -1363,8 +1392,10 @@ int test_set_page_writeback(struct page *page)
> } else {
> ret = TestSetPageWriteback(page);
> }
> - if (!ret)
> + if (!ret) {
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_WRITEBACK, 1);
> inc_zone_page_state(page, NR_WRITEBACK);
> + }
> return ret;
>
> }
> diff --git a/mm/rmap.c b/mm/rmap.c
> index fcd593c..d47c257 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -829,7 +829,7 @@ void page_add_file_rmap(struct page *page)
> {
> if (atomic_inc_and_test(&page->_mapcount)) {
> __inc_zone_page_state(page, NR_FILE_MAPPED);
> - mem_cgroup_update_file_mapped(page, 1);
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, 1);
> }
> }
>
> @@ -861,7 +861,7 @@ void page_remove_rmap(struct page *page)
> __dec_zone_page_state(page, NR_ANON_PAGES);
> } else {
> __dec_zone_page_state(page, NR_FILE_MAPPED);
> - mem_cgroup_update_file_mapped(page, -1);
> + mem_cgroup_update_stat(page, MEM_CGROUP_STAT_FILE_MAPPED, -1);
> }
> /*
> * It would be tidy to reset the PageAnon mapping here,
> diff --git a/mm/truncate.c b/mm/truncate.c
> index 2466e0c..5f437e7 100644
> --- a/mm/truncate.c
> +++ b/mm/truncate.c
> @@ -73,6 +73,8 @@ void cancel_dirty_page(struct page *page, unsigned int account_size)
> if (TestClearPageDirty(page)) {
> struct address_space *mapping = page->mapping;
> if (mapping && mapping_cap_account_dirty(mapping)) {
> + mem_cgroup_update_stat(page,
> + MEM_CGROUP_STAT_FILE_DIRTY, -1);
> dec_zone_page_state(page, NR_FILE_DIRTY);
> dec_bdi_stat(mapping->backing_dev_info,
> BDI_DIRTY);
> --
> 1.6.3.3
>

--
Three Cheers,
Balbir
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/