Re: [PATCH 19/19] writeback: simplify writeback iteration

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Jan 31, 2024 at 08:14:37AM +0100, Christoph Hellwig wrote:
> On Tue, Jan 30, 2024 at 10:50:16PM +0100, Jan Kara wrote:
> > Well, batch release needs to be only here because if writeback_get_folio()
> > returns NULL, the batch has been already released by it.
> 
> Indeed.
> 
> > So what would be
> > duplicated is only the error assignment. But I'm fine with the version in
> > the following email and actually somewhat prefer it compared the yet
> > another variant you've sent.
> 
> So how about another variant, this is closer to your original suggestion.
> But I've switched around the ordered of the folio or not branches
> from my original patch, and completely reworked and (IMHO) improved the
> comments.  it replaces patch 19 instead of being incremental to be
> readable:
> 

Not a thorough review but at first glance I like it. I think the direct
function call makes things easier to follow. Just one quick thought...

...
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 0763c4353a676a..eefcb00cb7b227 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
...
> @@ -2458,60 +2433,107 @@ static struct folio *writeback_get_folio(struct address_space *mapping,
>  	return folio;
>  }
>  
...
> +struct folio *writeback_iter(struct address_space *mapping,
> +		struct writeback_control *wbc, struct folio *folio, int *error)
>  {
> -	if (wbc->range_cyclic)
> -		wbc->index = mapping->writeback_index; /* prev offset */
> -	else
> -		wbc->index = wbc->range_start >> PAGE_SHIFT;
> -
> -	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
> -		tag_pages_for_writeback(mapping, wbc->index, wbc_end(wbc));
> -
> -	wbc->err = 0;
> -	folio_batch_init(&wbc->fbatch);
> -	return writeback_get_folio(mapping, wbc);
> -}
> +	if (!folio) {
> +		folio_batch_init(&wbc->fbatch);
> +		wbc->err = 0;

The implied field initialization via !folio feels a little wonky to me
just because it's not clear from the client code that both fields must
be initialized. Even though the interface is simpler, I wonder if it's
still worth having a dumb/macro type init function that at least does
the batch and error field initialization.

Or on second thought maybe having writeback_iter() reset *error as well
on folio == NULL might be a little cleaner without changing the
interface....

Brian

>  
> -struct folio *writeback_iter_next(struct address_space *mapping,
> -		struct writeback_control *wbc, struct folio *folio, int error)
> -{
> -	unsigned long nr = folio_nr_pages(folio);
> +		/*
> +		 * For range cyclic writeback we remember where we stopped so
> +		 * that we can continue where we stopped.
> +		 *
> +		 * For non-cyclic writeback we always start at the beginning of
> +		 * the passed in range.
> +		 */
> +		if (wbc->range_cyclic)
> +			wbc->index = mapping->writeback_index;
> +		else
> +			wbc->index = wbc->range_start >> PAGE_SHIFT;
>  
> -	wbc->nr_to_write -= nr;
> +		/*
> +		 * To avoid livelocks when other processes dirty new pages, we
> +		 * first tag pages which should be written back and only then
> +		 * start writing them.
> +		 *
> +		 * For data-integrity sync we have to be careful so that we do
> +		 * not miss some pages (e.g., because some other process has
> +		 * cleared the TOWRITE tag we set).  The rule we follow is that
> +		 * TOWRITE tag can be cleared only by the process clearing the
> +		 * DIRTY tag (and submitting the page for I/O).
> +		 */
> +		if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
> +			tag_pages_for_writeback(mapping, wbc->index,
> +					wbc_end(wbc));
> +	} else {
> +		wbc->nr_to_write -= folio_nr_pages(folio);
>  
> -	/*
> -	 * Handle the legacy AOP_WRITEPAGE_ACTIVATE magic return value.
> -	 * Eventually all instances should just unlock the folio themselves and
> -	 * return 0;
> -	 */
> -	if (error == AOP_WRITEPAGE_ACTIVATE) {
> -		folio_unlock(folio);
> -		error = 0;
> +		/*
> +		 * For integrity writeback  we have to keep going until we have
> +		 * written all the folios we tagged for writeback prior to
> +		 * entering the writeback loop, even if we run past
> +		 * wbc->nr_to_write or encounter errors, and just stash away
> +		 * the first error we encounter in wbc->err so that it can
> +		 * be retrieved on return.
> +		 *
> +		 * This is because the file system may still have state to clear
> +		 * for each folio.  We'll eventually return the first error
> +		 * encountered.
> +		 */
> +		if (wbc->sync_mode == WB_SYNC_ALL) {
> +			if (*error && !wbc->err)
> +				wbc->err = *error;
> +		} else {
> +			if (*error || wbc->nr_to_write <= 0)
> +				goto done;
> +		}
>  	}
>  
> -	if (error && !wbc->err)
> -		wbc->err = error;
> +	folio = writeback_get_folio(mapping, wbc);
> +	if (!folio) {
> +		/*
> +		 * For range cyclic writeback not finding another folios means
> +		 * that we are at the end of the file.  In that case go back
> +		 * to the start of the file for the next call.
> +		 */
> +		if (wbc->range_cyclic)
> +			mapping->writeback_index = 0;
>  
> -	/*
> -	 * For integrity sync  we have to keep going until we have written all
> -	 * the folios we tagged for writeback prior to entering the writeback
> -	 * loop, even if we run past wbc->nr_to_write or encounter errors.
> -	 * This is because the file system may still have state to clear for
> -	 * each folio.   We'll eventually return the first error encountered.
> -	 *
> -	 * For background writeback just push done_index past this folio so that
> -	 * we can just restart where we left off and media errors won't choke
> -	 * writeout for the entire file.
> -	 */
> -	if (wbc->sync_mode == WB_SYNC_NONE &&
> -	    (wbc->err || wbc->nr_to_write <= 0)) {
> -		writeback_finish(mapping, wbc, folio->index + nr);
> -		return NULL;
> +		/*
> +		 * Return the first error we encountered (if there was any) to
> +		 * the caller now that we are done.
> +		 */
> +		*error = wbc->err;
>  	}
> +	return folio;
>  
> -	return writeback_get_folio(mapping, wbc);
> +done:
> +	if (wbc->range_cyclic)
> +		mapping->writeback_index = folio->index + folio_nr_pages(folio);
> +	folio_batch_release(&wbc->fbatch);
> +	return NULL;
>  }
>  
>  /**
> @@ -2549,13 +2571,18 @@ int write_cache_pages(struct address_space *mapping,
>  		      struct writeback_control *wbc, writepage_t writepage,
>  		      void *data)
>  {
> -	struct folio *folio;
> -	int error;
> +	struct folio *folio = NULL;
> +	int error = 0;
>  
> -	for_each_writeback_folio(mapping, wbc, folio, error)
> +	while ((folio = writeback_iter(mapping, wbc, folio, &error))) {
>  		error = writepage(folio, wbc, data);
> +		if (error == AOP_WRITEPAGE_ACTIVATE) {
> +			folio_unlock(folio);
> +			error = 0;
> +		}
> +	}
>  
> -	return wbc->err;
> +	return error;
>  }
>  EXPORT_SYMBOL(write_cache_pages);
>  
> @@ -2563,13 +2590,17 @@ static int writeback_use_writepage(struct address_space *mapping,
>  		struct writeback_control *wbc)
>  {
>  	struct blk_plug plug;
> -	struct folio *folio;
> -	int err;
> +	struct folio *folio = NULL;
> +	int err = 0;
>  
>  	blk_start_plug(&plug);
> -	for_each_writeback_folio(mapping, wbc, folio, err) {
> +	while ((folio = writeback_iter(mapping, wbc, folio, &err))) {
>  		err = mapping->a_ops->writepage(&folio->page, wbc);
>  		mapping_set_error(mapping, err);
> +		if (err == AOP_WRITEPAGE_ACTIVATE) {
> +			folio_unlock(folio);
> +			err = 0;
> +		}
>  	}
>  	blk_finish_plug(&plug);
>  
> 





[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [NTFS 3]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [NTFS 3]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux