Linux缓存机制之块缓存 2.。。。。。。
Linux缓存机制之块缓存 2.。。。。。。除了读操作之外，页面的写操作也可以划分为更小的单位。只有页中实际修改的内容需要回写，而不用回写整页的内容。遗憾的是，从缓冲区的角度来看，写操作的实现比上述的读操作复杂的多。
__block_wirte_full_page函数中回写脏页面设计的缓冲区相关操作。 view plaincopyprint?
/*
* NOTE! All mapped/uptodate combinations are valid:
*
*MappedUptodate Meaning
*
*NoNo "unknown" - must do get_block()
*NoYes "hole" - zero-filled
*Yes No "allocated" - allocated on disk, not read in
*Yes Yes "valid" - allocated and up-to-date in memory.
*
* "Dirty" is valid only with the last case (mapped+uptodate).
*/
/*
* While block_write_full_page is writing back the dirty buffers under
* the page lock, whoever dirtied the buffers may decide to clean them
* again at any time.We handle that by only looking at the buffer
* state inside lock_buffer().
*
* If block_write_full_page() is called for regular writeback
* (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a
* locked buffer. This only can happen if someone has written the buffer
* directly, with submit_bh().At the address_space level PageWriteback
* prevents this contention from occurring.
*
* If block_write_full_page() is called with wbc->sync_mode ==
* WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this
* causes the writes to be flagged as synchronous writes, but the
* block device queue will NOT be unplugged, since usually many pages
* will be pushed to the out before the higher-level caller actually
* waits for the writes to be completed.The various wait functions,
* such as wait_on_writeback_range() will ultimately call sync_page()
* which will ultimately call blk_run_backing_dev(), which will end up
* unplugging the device queue.
*/
static int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler)
{
int err;
sector_t block;
sector_t last_block;
struct buffer_head *bh, *head;
const unsigned blocksize = 1 << inode->i_blkbits;
int nr_underway = 0;
int write_op = (wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC_PLUG : WRITE);
BUG_ON(!PageLocked(page));
last_block = (i_size_read(inode) - 1) >> inode->i_blkbits;
/*页面是否有关联缓冲区，如果没有创建他*/
if (!page_has_buffers(page)) {
create_empty_buffers(page, blocksize,
(1 << BH_Dirty)|(1 << BH_Uptodate));
}
/*
* Be very careful.We have no exclusion from __set_page_dirty_buffers
* here, and the (potentially unmapped) buffers may become dirty at
* any time.If a buffer becomes dirty here after we've inspected it
* then we just miss that fact, and the page stays dirty.
*
* Buffers outside i_size may be dirtied by __set_page_dirty_buffers;
* handle that here by just cleaning them.
*/
block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
head = page_buffers(page);
bh = head;
/*
* Get all the dirty buffers mapped to disk addresses and
* handle any aliases from the underlying blockdev's mapping.
*/
/*对所有未映射的脏缓冲区，在缓冲区和块设备
之间建立映射*/
do {
if (block > last_block) {
/*
* mapped buffers outside i_size will occur, because
* this page can be outside i_size when there is a
* truncate in progress.
*/
/*
* The buffer was zeroed by block_write_full_page()
*/
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
} else if ((!buffer_mapped(bh) || buffer_delay(bh)) &&
buffer_dirty(bh)) {
WARN_ON(bh->b_size != blocksize);
/*查找块设备上与缓冲区项匹配的块*/
err = get_block(inode, block, bh, 1);
if (err)
goto recover;
clear_buffer_delay(bh);
if (buffer_new(bh)) {
/* blockdev mappings never come here */
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
}
}
bh = bh->b_this_page;
block++;
} while (bh != head);
/*第二遍遍历，将滤出所有的脏缓冲区*/
do {
if (!buffer_mapped(bh))
continue;
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the page.Note that this can
* potentially cause a busy-wait loop from writeback threads
* and kswapd activity, but those code paths have their own
* higher-level throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
redirty_page_for_writepage(wbc, page);
continue;
}
/*如果设置了脏页标志，则会在调用该函数时清除
因为缓冲区的内容将立即回写*/
if (test_clear_buffer_dirty(bh)) {
/*设置BH_Async_Write状态位，并将end_buffer_async_write
指定为BIO完成处理程序即b_end_io*/
mark_buffer_async_write_endio(bh, handler);
} else {
unlock_buffer(bh);
}
} while ((bh = bh->b_this_page) != head);
/*
* The page and its buffers are protected by PageWriteback(), so we can
* drop the bh refcounts early.
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
/*最后一次遍历*/
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
/*将前一次遍历中标记为BH_Async_Write的所有缓冲区
转交给块层执行实际的写操作，该函数向块层提交
了对应的请求*/
submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
err = 0;
done:
if (nr_underway == 0) {
/*
* The page was marked dirty, but the buffers were
* clean.Someone wrote them back by hand with
* ll_rw_block/submit_bh.A rare case.
*/
end_page_writeback(page);
/*
* The page and buffer_heads can be released at any time from
* here on.
*/
}
return err;
recover:
/*
* ENOSPC, or some other error.We may already have added some
* blocks to the file, so we need to write these out to avoid
* exposing stale data.
* The page is currently locked and not marked for writeback
*/
bh = head;
/* Recovery: lock and submit the mapped buffers */
do {
if (buffer_mapped(bh) && buffer_dirty(bh) &&
!buffer_delay(bh)) {
lock_buffer(bh);
mark_buffer_async_write_endio(bh, handler);
} else {
/*
* The buffer may have been set dirty during
* attachment to a dirty page.
*/
clear_buffer_dirty(bh);
}
} while ((bh = bh->b_this_page) != head);
SetPageError(page);
BUG_ON(PageWriteback(page));
mapping_set_error(page->mapping, err);
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
clear_buffer_dirty(bh);
submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
goto done;
} 谢谢分享
页:
[1]