@@ -3557,19 +3557,38 @@ int extent_readpages(struct extent_io_tree *tree,
struct bio *bio = NULL;
unsigned page_idx;
unsigned long bio_flags = 0;
+ struct page *pagepool[16];
+ struct page *page;
+ int i = 0;
+ int nr = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page = list_entry(pages->prev, struct page, lru);
+ page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
- if (!add_to_page_cache_lru(page, mapping,
+ if (add_to_page_cache_lru(page, mapping,
page->index, GFP_NOFS)) {
- __extent_read_full_page(tree, page, get_extent,
- &bio, 0, &bio_flags);
+ page_cache_release(page);
+ continue;
}
- page_cache_release(page);
+
+ pagepool[nr++] = page;
+ if (nr < ARRAY_SIZE(pagepool))
+ continue;
+ for (i = 0; i < nr; i++) {
+ __extent_read_full_page(tree, pagepool[i], get_extent,
+ &bio, 0, &bio_flags);
+ page_cache_release(pagepool[i]);
+ }
+ nr = 0;
}
+ for (i = 0; i < nr; i++) {
+ __extent_read_full_page(tree, pagepool[i], get_extent,
+ &bio, 0, &bio_flags);
+ page_cache_release(pagepool[i]);
+ }
+
BUG_ON(!list_empty(pages));
if (bio)
return submit_one_bio(READ, bio, 0, bio_flags);
While testing with my buffer read fio jobs[1], I find that btrfs does not perform well enough. Here is a scenario in fio jobs: We have 4 threads, "t1 t2 t3 t4", starting to buffer read a same file, and all of them will race on add_to_page_cache_lru(), and if one thread successfully puts its page into the page cache, it takes the responsibility to read the page's data. And what's more, reading a page needs a period of time to finish, in which other threads can slide in and process rest pages: t1 t2 t3 t4 add Page1 read Page1 add Page2 | read Page2 add Page3 | | read Page3 add Page4 | | | read Page4 -----|------------|-----------|-----------|-------- v v v v bio bio bio bio Now we have four bios, each of which holds only one page since we need to maintain consecutive pages in bio. Thus, we can end up with far more bios than we need. Here we're going to a) delay the real read-page section and b) try to put more pages into page cache. With that said, we can make each bio hold more pages and reduce the number of bios we need. Here is some numbers taken from fio results: w/o patch w patch ------------- -------- --------------- READ: 745MB/s +25% 934MB/s [1]: [global] group_reporting thread numjobs=4 bs=32k rw=read ioengine=sync directory=/mnt/btrfs/ [READ] filename=foobar size=2000M invalidate=1 Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com> --- v4->v5: avoid another ref inc on page. v3->v4: adopt a simple page array instead of pagevec to avoid side effect that may be brought by pagevec_release(). v2->v3: adopt kernel native pagevec instead of kmalloc. v1->v2: if we fail to make a allocation, just fall back to the old way to read page. fs/btrfs/extent_io.c | 29 ++++++++++++++++++++++++----- 1 files changed, 24 insertions(+), 5 deletions(-)