All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tristan Ye <tristan.ye@oracle.com>
To: ocfs2-devel@oss.oracle.com
Subject: [Ocfs2-devel] [PATCH 1/3] ocfs2: Add ocfs2_trim_fs for SSD trim support.
Date: Tue, 08 Mar 2011 12:55:59 +0800	[thread overview]
Message-ID: <4D75B6DF.3030508@oracle.com> (raw)
In-Reply-To: <1299492356-7329-1-git-send-email-tm@tao.ma>

Hi Tao,

    Most of codes looks pretty neat to me, few comments inlined below:

Tao Ma wrote:
> From: Tao Ma <boyu.mt@taobao.com>
>
> Add ocfs2_trim_fs to support trimming freed clusters in the
> volume. A range will be given and all the freed clusters greater
> than minlen will be discarded to the block layer.
>
> Signed-off-by: Tao Ma <boyu.mt@taobao.com>
> ---
>  fs/ocfs2/alloc.c |  154 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  fs/ocfs2/alloc.h |    1 +
>  2 files changed, 155 insertions(+), 0 deletions(-)
>
> diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
> index b27a0d8..6e1b3b5 100644
> --- a/fs/ocfs2/alloc.c
> +++ b/fs/ocfs2/alloc.c
> @@ -29,6 +29,7 @@
>  #include <linux/highmem.h>
>  #include <linux/swap.h>
>  #include <linux/quotaops.h>
> +#include <linux/blkdev.h>
>  
>  #include <cluster/masklog.h>
>  
> @@ -7184,3 +7185,156 @@ out_commit:
>  out:
>  	return ret;
>  }
> +
> +static int ocfs2_trim_extent(struct super_block *sb,
> +			     struct ocfs2_group_desc *gd,
> +			     int start, int count)
> +{
> +	u64 discard;
> +
> +	count = ocfs2_clusters_to_blocks(sb, count);
> +	discard = le64_to_cpu(gd->bg_blkno) +
> +			ocfs2_clusters_to_blocks(sb, start);
> +
> +	return sb_issue_discard(sb, discard, count, GFP_NOFS, 0);
> +}
> +
> +static int ocfs2_trim_group(struct super_block *sb,
> +			    struct ocfs2_group_desc *gd,
> +			    int start, int max, int minbits)
> +{
> +	int ret = 0, count = 0, next;
> +	void *bitmap = gd->bg_bitmap;
> +
> +	while (start < max) {
> +		start = ocfs2_find_next_zero_bit(bitmap, max, start);
> +		if (start >= max)
> +			break;

    /* What if the 'start' stands within a hole */

    if (ocfs2_test_bit(...)) {
       start = ocfs2_find_next_zero_bit(...);
       if ((start == -1) || (start >= max))
          break;
    }

> +		next = ocfs2_find_next_bit(bitmap, max, start);
   
    next = ocfs2_find_next_bit(...);
    if (next == -1)
       break;

    if (next > max)
       next = max;
   
> +
> +		if ((next - start) >= minbits) {
> +			ret = ocfs2_trim_extent(sb, gd,
> +						start, next - start);
> +			if (ret < 0) {
> +				mlog_errno(ret);
> +				break;
> +			}
> +			count += next - start;
> +		}
> +		start = next + 1;
> +
> +		if (fatal_signal_pending(current)) {
> +			count = -ERESTARTSYS;
> +			break;
> +		}
> +
> +		if ((le16_to_cpu(gd->bg_free_bits_count) - count) < minbits)
> +			break;
> +	}
> +
> +	if (ret < 0)
> +		count = ret;
> +
> +	return count;
> +}
> +
> +int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
> +{
> +	struct ocfs2_super *osb = OCFS2_SB(sb);
> +	u64 start, len, minlen, trimmed, first_group, last_group, group;
    why not using u32 start, len, minlen, trimmed;
> +	int ret, cnt, first_bit, last_bit;
> +	struct buffer_head *main_bm_bh = NULL;
> +	struct inode *main_bm_inode = NULL;
> +	struct buffer_head *gd_bh = NULL;
> +	struct ocfs2_dinode *main_bm;
> +	struct ocfs2_group_desc *gd = NULL;
> +
> +	if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
> +		return -EROFS;
> +
> +	start = range->start >> osb->s_clustersize_bits;
> +	len = range->len >> osb->s_clustersize_bits;
> +	minlen = range->minlen >> osb->s_clustersize_bits;

    I guess you may want to count two corner clusters which cover the 
'start' and 'end' bytes,
so the appropriate way might be:

    start = range->start >> osb->s_clustersize_bits;
    len = ocfs2_clusters_for_bytes(osb->sb, range->start  + range->len);
    len -= start;
   
> +	trimmed = 0;
> +
> +	if (!len || !minlen || minlen >= osb->bitmap_cpg)
    'minlen == 0' looks acceptable, which means we allowing discarding 
for all size of extents.
and what's more, 'len == 0' may not be harmful enough to issue a 
'EINVAL', returning a legal '0'
to userspace immediately is fine.


> +		return -EINVAL;
> +
> +	main_bm_inode = ocfs2_get_system_file_inode(osb,
> +						    GLOBAL_BITMAP_SYSTEM_INODE,
> +						    OCFS2_INVALID_SLOT);
> +	if (!main_bm_inode) {
> +		ret = -EIO;
> +		mlog_errno(ret);
> +		goto out;
> +	}
> +
> +	mutex_lock(&main_bm_inode->i_mutex);
> +
> +	ret = ocfs2_inode_lock(main_bm_inode, &main_bm_bh, 0);
> +	if (ret < 0) {
> +		mlog_errno(ret);
> +		goto out_mutex;
> +	}
> +	main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data;
> +
> +	if (start >= le32_to_cpu(main_bm->i_clusters)) {
> +		ret = -EINVAL;
> +		mlog_errno(ret);
> +		goto out_unlock;
> +	}
> +
> +	if (start + len > le32_to_cpu(main_bm->i_clusters))
> +		len = le32_to_cpu(main_bm->i_clusters) - start;
> +
> +	/* Determine first and last group to examine based on start and len */
> +	first_group = ocfs2_which_cluster_group(main_bm_inode, start);
> +	if (first_group == osb->first_cluster_group_blkno)
> +		first_bit = start;
> +	else
> +		first_bit = start - ocfs2_blocks_to_clusters(sb, first_group);
> +	last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1);
> +	last_bit = osb->bitmap_cpg;
> +
> +	for (group = first_group; group <= last_group;) {
> +		if (first_bit + len >= osb->bitmap_cpg)
> +			last_bit = osb->bitmap_cpg - first_bit;

    is 'first_bit' and 'last_bit' both represent a local offset within a 
cluster group?
just wondering why last_bit wasn't equal to 'osb->bitmap_cpg' in above 
case(I meant the case
of 'first_bit + len >= osb->bitmap_cpg'

> +		else
> +			last_bit = start + len;

    why above case is not 'last_bit = first_bit + len';

> +
> +		ret = ocfs2_read_group_descriptor(main_bm_inode,
> +						  main_bm, group,
> +						  &gd_bh);
> +		if (ret < 0) {
> +			mlog_errno(ret);
> +			break;
> +		}
> +
> +		gd = (struct ocfs2_group_desc *)gd_bh->b_data;
> +		cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen);
> +		brelse(gd_bh);
> +		gd_bh = NULL;
> +		if (cnt < 0) {
> +			ret = cnt;
> +			mlog_errno(ret);
> +			break;
> +		}
> +
> +		trimmed += cnt;
> +		len -= osb->bitmap_cpg - first_bit;
> +		first_bit = 0;
> +		if (group == osb->first_cluster_group_blkno)
> +			group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
> +		else
> +			group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
> +	}
> +	range->len = trimmed * sb->s_blocksize;
> +out_unlock:
> +	ocfs2_inode_unlock(main_bm_inode, 0);
> +	brelse(main_bm_bh);
> +out_mutex:
> +	mutex_unlock(&main_bm_inode->i_mutex);
> +	iput(main_bm_inode);
> +out:
> +	return ret;
> +}
> diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
> index 3bd08a0..ca381c5 100644
> --- a/fs/ocfs2/alloc.h
> +++ b/fs/ocfs2/alloc.h
> @@ -239,6 +239,7 @@ int ocfs2_find_leaf(struct ocfs2_caching_info *ci,
>  		    struct buffer_head **leaf_bh);
>  int ocfs2_search_extent_list(struct ocfs2_extent_list *el, u32 v_cluster);
>  
> +int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range);
>  /*
>   * Helper function to look at the # of clusters in an extent record.
>   */

  reply	other threads:[~2011-03-08  4:55 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-07 10:02 [Ocfs2-devel] [PATCH 0/3] ocfs2: Add batched discard support Tao Ma
2011-03-07 10:05 ` [Ocfs2-devel] [PATCH 1/3] ocfs2: Add ocfs2_trim_fs for SSD trim support Tao Ma
2011-03-08  4:55   ` Tristan Ye [this message]
2011-03-08  5:53     ` Tao Ma
2011-03-08  6:23       ` Tristan Ye
2011-03-08  6:42         ` Tao Ma
2011-03-08  6:53           ` Tristan Ye
2011-03-08  7:47             ` Tao Ma
2011-03-08  7:53     ` Tao Ma
2011-03-08  7:59       ` Tristan Ye
2011-03-07 10:05 ` [Ocfs2-devel] [PATCH 2/3] ocfs2: Add FITRIM ioctl Tao Ma
2011-03-07 10:05 ` [Ocfs2-devel] [PATCH 3/3] ocfs2: Add trace event for trim Tao Ma
2011-03-08 15:26 ` [Ocfs2-devel] [PATCH 1/3 v2] ocfs2: Add ocfs2_trim_fs for SSD trim support Tao Ma
  -- strict thread matches above, loose matches on Subject: below --
2011-05-06  9:23 [Ocfs2-devel] [PATCH 0/3] ocfs2: Add batched discard support Tao Ma
2011-05-06  9:27 ` [Ocfs2-devel] [PATCH 1/3] ocfs2: Add ocfs2_trim_fs for SSD trim support Tao Ma
2011-05-09 23:02   ` Sunil Mushran
2011-05-10  3:14     ` Tao Ma

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4D75B6DF.3030508@oracle.com \
    --to=tristan.ye@oracle.com \
    --cc=ocfs2-devel@oss.oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.