X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Freadahead.c;h=bec83c15a78f61b58a1dfbb74a336b9848b5d876;hb=cc2559bccc72767cb446f79b071d96c30c26439b;hp=3d262bb738a90ca38747397cb81be365a1aab0d3;hpb=cf914a7d656e62b9dd3e0dffe4f62b953ae6048d;p=safe%2Fjmp%2Flinux-2.6 diff --git a/mm/readahead.c b/mm/readahead.c index 3d262bb..bec83c1 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -3,7 +3,7 @@ * * Copyright (C) 2002, Linus Torvalds * - * 09Apr2002 akpm@zip.com.au + * 09Apr2002 Andrew Morton * Initial version. */ @@ -15,22 +15,15 @@ #include #include #include +#include void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) { } EXPORT_SYMBOL(default_unplug_io_fn); -/* - * Convienent macros for min/max read-ahead pages. - * Note that MAX_RA_PAGES is rounded down, while MIN_RA_PAGES is rounded up. - * The latter is necessary for systems with large page size(i.e. 64k). - */ -#define MAX_RA_PAGES (VM_MAX_READAHEAD*1024 / PAGE_CACHE_SIZE) -#define MIN_RA_PAGES DIV_ROUND_UP(VM_MIN_READAHEAD*1024, PAGE_CACHE_SIZE) - struct backing_dev_info default_backing_dev_info = { - .ra_pages = MAX_RA_PAGES, + .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, .state = 0, .capabilities = BDI_CAP_MAP_COPY, .unplug_io_fn = default_unplug_io_fn, @@ -45,7 +38,7 @@ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = mapping->backing_dev_info->ra_pages; - ra->prev_index = -1; + ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); @@ -65,28 +58,25 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, int (*filler)(void *, struct page *), void *data) { struct page *page; - struct pagevec lru_pvec; int ret = 0; - pagevec_init(&lru_pvec, 0); - while (!list_empty(pages)) { page = list_to_page(pages); list_del(&page->lru); - if (add_to_page_cache(page, mapping, page->index, GFP_KERNEL)) { + if (add_to_page_cache_lru(page, mapping, + page->index, GFP_KERNEL)) { page_cache_release(page); continue; } + page_cache_release(page); + ret = filler(data, page); - if (!pagevec_add(&lru_pvec, page)) - __pagevec_lru_add(&lru_pvec); - if (ret) { + if (unlikely(ret)) { put_pages_list(pages); break; } task_io_account_read(PAGE_CACHE_SIZE); } - pagevec_lru_add(&lru_pvec); return ret; } @@ -96,7 +86,6 @@ static int read_pages(struct address_space *mapping, struct file *filp, struct list_head *pages, unsigned nr_pages) { unsigned page_idx; - struct pagevec lru_pvec; int ret; if (mapping->a_ops->readpages) { @@ -106,19 +95,15 @@ static int read_pages(struct address_space *mapping, struct file *filp, goto out; } - pagevec_init(&lru_pvec, 0); for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = list_to_page(pages); list_del(&page->lru); - if (!add_to_page_cache(page, mapping, + if (!add_to_page_cache_lru(page, mapping, page->index, GFP_KERNEL)) { mapping->a_ops->readpage(filp, page); - if (!pagevec_add(&lru_pvec, page)) - __pagevec_lru_add(&lru_pvec); - } else - page_cache_release(page); + } + page_cache_release(page); } - pagevec_lru_add(&lru_pvec); ret = 0; out: return ret; @@ -156,20 +141,19 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, /* * Preallocate as many pages as we will need. */ - read_lock_irq(&mapping->tree_lock); for (page_idx = 0; page_idx < nr_to_read; page_idx++) { pgoff_t page_offset = offset + page_idx; if (page_offset > end_index) break; + rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); + rcu_read_unlock(); if (page) continue; - read_unlock_irq(&mapping->tree_lock); page = page_cache_alloc_cold(mapping); - read_lock_irq(&mapping->tree_lock); if (!page) break; page->index = page_offset; @@ -178,7 +162,6 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, SetPageReadahead(page); ret++; } - read_unlock_irq(&mapping->tree_lock); /* * Now start the IO. We ignore I/O errors - if the page is not @@ -246,28 +229,35 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp, */ unsigned long max_sane_readahead(unsigned long nr) { - return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE) + return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE) + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2); } +static int __init readahead_init(void) +{ + int err; + + err = bdi_init(&default_backing_dev_info); + if (!err) + bdi_register(&default_backing_dev_info, NULL, "default"); + + return err; +} +subsys_initcall(readahead_init); + /* * Submit IO for the read-ahead request in file_ra_state. */ -unsigned long ra_submit(struct file_ra_state *ra, +static unsigned long ra_submit(struct file_ra_state *ra, struct address_space *mapping, struct file *filp) { - unsigned long ra_size; - unsigned long la_size; int actual; - ra_size = ra_readahead_size(ra); - la_size = ra_lookahead_size(ra); actual = __do_page_cache_readahead(mapping, filp, - ra->ra_index, ra_size, la_size); + ra->start, ra->size, ra->async_size); return actual; } -EXPORT_SYMBOL_GPL(ra_submit); /* * Set the initial window size, round to next power of 2 and square @@ -296,7 +286,7 @@ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { - unsigned long cur = ra->readahead_index - ra->ra_index; + unsigned long cur = ra->size; unsigned long newsize; if (cur < max / 16) @@ -313,32 +303,25 @@ static unsigned long get_next_ra_size(struct file_ra_state *ra, * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * - * |-------- last readahead window -------->| - * |-- application walking here -->| - * ======#============|==================#=====================| - * ^la_index ^ra_index ^lookahead_index ^readahead_index - * - * [ra_index, readahead_index) represents the last readahead window. - * - * [la_index, lookahead_index] is where the application would be walking(in - * the common case of cache-cold sequential reads): the last window was - * established when the application was at la_index, and the next window will - * be bring in when the application reaches lookahead_index. + * |<----- async_size ---------| + * |------------------- size -------------------->| + * |==================#===========================| + * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; - * Instead, submit an asynchronous readahead I/O as early as the application - * reads on the page at lookahead_index. Normally lookahead_index will be - * equal to ra_index, for maximum pipelining. + * Instead, submit an asynchronous readahead I/O as soon as there are + * only async_size pages left in the readahead window. Normally async_size + * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead - * page at lookahead_index with PG_readahead, and use it as readahead + * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * - * prev_index tracks the last visited page in the _previous_ read request. + * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as @@ -362,27 +345,25 @@ ondemand_readahead(struct address_space *mapping, bool hit_readahead_marker, pgoff_t offset, unsigned long req_size) { - unsigned long max; /* max readahead pages */ - pgoff_t ra_index; /* readahead index */ - unsigned long ra_size; /* readahead size */ - unsigned long la_size; /* lookahead size */ - int sequential; - - max = ra->ra_pages; - sequential = (offset - ra->prev_index <= 1UL) || (req_size > max); + int max = ra->ra_pages; /* max readahead pages */ + pgoff_t prev_offset; + int sequential; /* - * Lookahead/readahead hit, assume sequential access. + * It's the expected callback offset, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if (offset && (offset == ra->lookahead_index || - offset == ra->readahead_index)) { - ra_index = ra->readahead_index; - ra_size = get_next_ra_size(ra, max); - la_size = ra_size; - goto fill_ra; + if (offset && (offset == (ra->start + ra->size - ra->async_size) || + offset == (ra->start + ra->size))) { + ra->start += ra->size; + ra->size = get_next_ra_size(ra, max); + ra->async_size = ra->size; + goto readit; } + prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT; + sequential = offset - prev_offset <= 1UL || req_size > max; + /* * Standalone, small read. * Read as is, and do not pollute the readahead state. @@ -393,30 +374,40 @@ ondemand_readahead(struct address_space *mapping, } /* + * Hit a marked page without valid readahead state. + * E.g. interleaved reads. + * Query the pagecache for async_size, which normally equals to + * readahead size. Ramp it up and use it as the new readahead size. + */ + if (hit_readahead_marker) { + pgoff_t start; + + rcu_read_lock(); + start = radix_tree_next_hole(&mapping->page_tree, offset,max+1); + rcu_read_unlock(); + + if (!start || start - offset > max) + return 0; + + ra->start = start; + ra->size = start - offset; /* old async_size */ + ra->size = get_next_ra_size(ra, max); + ra->async_size = ra->size; + goto readit; + } + + /* * It may be one of * - first read on start of file * - sequential cache miss * - oversize random read * Start readahead for it. */ - ra_index = offset; - ra_size = get_init_ra_size(req_size, max); - la_size = ra_size > req_size ? ra_size - req_size : ra_size; - - /* - * Hit on a lookahead page without valid readahead state. - * E.g. interleaved reads. - * Not knowing its readahead pos/size, bet on the minimal possible one. - */ - if (hit_readahead_marker) { - ra_index++; - ra_size = min(4 * ra_size, max); - } - -fill_ra: - ra_set_index(ra, offset, ra_index); - ra_set_size(ra, ra_size, la_size); + ra->start = offset; + ra->size = get_init_ra_size(req_size, max); + ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; +readit: return ra_submit(ra, mapping, filp); } @@ -458,9 +449,10 @@ EXPORT_SYMBOL_GPL(page_cache_sync_readahead); * pagecache pages * * page_cache_async_ondemand() should be called when a page is used which - * has the PG_readahead flag: this is a marker to suggest that the application + * has the PG_readahead flag; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in - * more pages. */ + * more pages. + */ void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *filp,