From: Brian Foster <bfoster@redhat.com>
To: "Darrick J. Wong" <darrick.wong@oracle.com>
Cc: linux-xfs@vger.kernel.org
Subject: Re: [PATCH 2/8] xfs: track unlinked inode counts in per-ag data
Date: Fri, 1 Feb 2019 13:59:24 -0500 [thread overview]
Message-ID: <20190201185924.GA31203@bfoster> (raw)
In-Reply-To: <154897668290.26065.2216454639188570690.stgit@magnolia>
On Thu, Jan 31, 2019 at 03:18:03PM -0800, Darrick J. Wong wrote:
> From: Darrick J. Wong <darrick.wong@oracle.com>
>
> Track the number of unlinked inodes in each AG so that we can use these
> decisions to throttle inactivations when the unlinked list gets long.
>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
> fs/xfs/xfs_inode.c | 40 +++++++++++++++++++++++++++++-----------
> fs/xfs/xfs_log_recover.c | 8 ++++++++
> fs/xfs/xfs_mount.c | 5 +++++
> fs/xfs/xfs_mount.h | 4 ++++
> 4 files changed, 46 insertions(+), 11 deletions(-)
>
>
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index d18354517320..98355f5f9253 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -1900,6 +1900,7 @@ xfs_iunlink(
> struct xfs_dinode *dip;
> struct xfs_buf *agibp;
> struct xfs_buf *ibp;
> + struct xfs_perag *pag;
> xfs_agnumber_t agno;
> xfs_agino_t agino;
> short bucket_index;
> @@ -1912,6 +1913,8 @@ xfs_iunlink(
> agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
> agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
> bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
> + pag = xfs_perag_get(mp, agno);
> + mutex_lock(&pag->pagi_unlinked_lock);
Any particular reason for using a mutex over a spinlock or atomic_t?
Brian
>
> /*
> * Get the agi buffer first. It ensures lock ordering
> @@ -1919,7 +1922,7 @@ xfs_iunlink(
> */
> error = xfs_read_agi(mp, tp, agno, &agibp);
> if (error)
> - return error;
> + goto out_unlock;
> agi = XFS_BUF_TO_AGI(agibp);
>
> /*
> @@ -1939,7 +1942,7 @@ xfs_iunlink(
> error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
> 0, 0);
> if (error)
> - return error;
> + goto out_unlock;
>
> ASSERT(dip->di_next_unlinked == cpu_to_be32(NULLAGINO));
> dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
> @@ -1964,7 +1967,12 @@ xfs_iunlink(
> (sizeof(xfs_agino_t) * bucket_index);
> xfs_trans_log_buf(tp, agibp, offset,
> (offset + sizeof(xfs_agino_t) - 1));
> - return 0;
> + pag->pagi_unlinked_count++;
> +
> +out_unlock:
> + mutex_unlock(&pag->pagi_unlinked_lock);
> + xfs_perag_put(pag);
> + return error;
> }
>
> /*
> @@ -1982,6 +1990,7 @@ xfs_iunlink_remove(
> struct xfs_buf *ibp;
> struct xfs_buf *last_ibp;
> struct xfs_dinode *last_dip = NULL;
> + struct xfs_perag *pag;
> xfs_ino_t next_ino;
> xfs_agnumber_t agno;
> xfs_agino_t agino;
> @@ -1997,6 +2006,8 @@ xfs_iunlink_remove(
> agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
> agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
> bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
> + pag = xfs_perag_get(mp, agno);
> + mutex_lock(&pag->pagi_unlinked_lock);
>
> /*
> * Get the agi buffer first. It ensures lock ordering
> @@ -2004,7 +2015,7 @@ xfs_iunlink_remove(
> */
> error = xfs_read_agi(mp, tp, agno, &agibp);
> if (error)
> - return error;
> + goto out_unlock;
> agi = XFS_BUF_TO_AGI(agibp);
>
> /*
> @@ -2015,7 +2026,8 @@ xfs_iunlink_remove(
> be32_to_cpu(agi->agi_unlinked[bucket_index]))) {
> XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
> agi, sizeof(*agi));
> - return -EFSCORRUPTED;
> + error = -EFSCORRUPTED;
> + goto out_unlock;
> }
>
> if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
> @@ -2031,7 +2043,7 @@ xfs_iunlink_remove(
> if (error) {
> xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
> __func__, error);
> - return error;
> + goto out_unlock;
> }
> next_agino = be32_to_cpu(dip->di_next_unlinked);
> ASSERT(next_agino != 0);
> @@ -2080,7 +2092,7 @@ xfs_iunlink_remove(
> xfs_warn(mp,
> "%s: xfs_imap returned error %d.",
> __func__, error);
> - return error;
> + goto out_unlock;
> }
>
> error = xfs_imap_to_bp(mp, tp, &imap, &last_dip,
> @@ -2089,7 +2101,7 @@ xfs_iunlink_remove(
> xfs_warn(mp,
> "%s: xfs_imap_to_bp returned error %d.",
> __func__, error);
> - return error;
> + goto out_unlock;
> }
>
> last_offset = imap.im_boffset;
> @@ -2098,7 +2110,8 @@ xfs_iunlink_remove(
> XFS_CORRUPTION_ERROR(__func__,
> XFS_ERRLEVEL_LOW, mp,
> last_dip, sizeof(*last_dip));
> - return -EFSCORRUPTED;
> + error = -EFSCORRUPTED;
> + goto out_unlock;
> }
> }
>
> @@ -2111,7 +2124,7 @@ xfs_iunlink_remove(
> if (error) {
> xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.",
> __func__, error);
> - return error;
> + goto out_unlock;
> }
> next_agino = be32_to_cpu(dip->di_next_unlinked);
> ASSERT(next_agino != 0);
> @@ -2146,7 +2159,12 @@ xfs_iunlink_remove(
> (offset + sizeof(xfs_agino_t) - 1));
> xfs_inobp_check(mp, last_ibp);
> }
> - return 0;
> + pag->pagi_unlinked_count--;
> +
> +out_unlock:
> + mutex_unlock(&pag->pagi_unlinked_lock);
> + xfs_perag_put(pag);
> + return error;
> }
>
> /*
> diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
> index ff9a27834c50..c920b8aeba01 100644
> --- a/fs/xfs/xfs_log_recover.c
> +++ b/fs/xfs/xfs_log_recover.c
> @@ -5054,6 +5054,7 @@ xlog_recover_process_one_iunlink(
> struct xfs_buf *ibp;
> struct xfs_dinode *dip;
> struct xfs_inode *ip;
> + struct xfs_perag *pag;
> xfs_ino_t ino;
> int error;
>
> @@ -5077,6 +5078,13 @@ xlog_recover_process_one_iunlink(
> agino = be32_to_cpu(dip->di_next_unlinked);
> xfs_buf_relse(ibp);
>
> + /* Make sure the in-core data knows about this unlinked inode. */
> + pag = xfs_perag_get(mp, agno);
> + mutex_lock(&pag->pagi_unlinked_lock);
> + pag->pagi_unlinked_count++;
> + mutex_unlock(&pag->pagi_unlinked_lock);
> + xfs_perag_put(pag);
> +
> /*
> * Prevent any DMAPI event from being sent when the reference on
> * the inode is dropped.
> diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> index 10be706ec72e..6bfc985669e0 100644
> --- a/fs/xfs/xfs_mount.c
> +++ b/fs/xfs/xfs_mount.c
> @@ -149,6 +149,9 @@ xfs_free_perag(
> spin_unlock(&mp->m_perag_lock);
> ASSERT(pag);
> ASSERT(atomic_read(&pag->pag_ref) == 0);
> + ASSERT(pag->pagi_unlinked_count == 0 ||
> + XFS_FORCED_SHUTDOWN(mp));
> + mutex_destroy(&pag->pagi_unlinked_lock);
> xfs_buf_hash_destroy(pag);
> mutex_destroy(&pag->pag_ici_reclaim_lock);
> call_rcu(&pag->rcu_head, __xfs_free_perag);
> @@ -227,6 +230,7 @@ xfs_initialize_perag(
> /* first new pag is fully initialized */
> if (first_initialised == NULLAGNUMBER)
> first_initialised = index;
> + mutex_init(&pag->pagi_unlinked_lock);
> }
>
> index = xfs_set_inode_alloc(mp, agcount);
> @@ -249,6 +253,7 @@ xfs_initialize_perag(
> if (!pag)
> break;
> xfs_buf_hash_destroy(pag);
> + mutex_destroy(&pag->pagi_unlinked_lock);
> mutex_destroy(&pag->pag_ici_reclaim_lock);
> kmem_free(pag);
> }
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index e344b1dfde63..0fcc6b6a4f67 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -388,6 +388,10 @@ typedef struct xfs_perag {
>
> /* reference count */
> uint8_t pagf_refcount_level;
> +
> + /* unlinked inodes */
> + struct mutex pagi_unlinked_lock;
> + uint32_t pagi_unlinked_count;
> } xfs_perag_t;
>
> static inline struct xfs_ag_resv *
>
next prev parent reply other threads:[~2019-02-01 18:59 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-31 23:17 [PATCH 0/8] xfs: incore unlinked list Darrick J. Wong
2019-01-31 23:17 ` [PATCH 1/8] xfs: clean up iunlink functions Darrick J. Wong
2019-02-01 8:01 ` Christoph Hellwig
2019-02-02 19:15 ` Darrick J. Wong
2019-01-31 23:18 ` [PATCH 2/8] xfs: track unlinked inode counts in per-ag data Darrick J. Wong
2019-02-01 18:59 ` Brian Foster [this message]
2019-02-01 19:33 ` Darrick J. Wong
2019-02-02 16:14 ` Christoph Hellwig
2019-02-02 19:28 ` Darrick J. Wong
2019-01-31 23:18 ` [PATCH 3/8] xfs: refactor AGI unlinked bucket updates Darrick J. Wong
2019-02-01 19:00 ` Brian Foster
2019-02-02 19:50 ` Darrick J. Wong
2019-02-02 16:21 ` Christoph Hellwig
2019-02-02 19:51 ` Darrick J. Wong
2019-01-31 23:18 ` [PATCH 4/8] xfs: strengthen AGI unlinked inode bucket pointer checks Darrick J. Wong
2019-02-01 19:00 ` Brian Foster
2019-02-02 16:22 ` Christoph Hellwig
2019-01-31 23:18 ` [PATCH 5/8] xfs: refactor inode unlinked pointer update functions Darrick J. Wong
2019-02-01 19:01 ` Brian Foster
2019-02-02 22:00 ` Darrick J. Wong
2019-02-02 16:27 ` Christoph Hellwig
2019-02-02 20:29 ` Darrick J. Wong
2019-01-31 23:18 ` [PATCH 6/8] xfs: hoist unlinked list search and mapping to a separate function Darrick J. Wong
2019-02-01 19:01 ` Brian Foster
2019-02-02 20:46 ` Darrick J. Wong
2019-02-04 13:18 ` Brian Foster
2019-02-04 16:31 ` Darrick J. Wong
2019-02-02 16:30 ` Christoph Hellwig
2019-02-02 20:42 ` Darrick J. Wong
2019-02-02 16:51 ` Christoph Hellwig
2019-01-31 23:18 ` [PATCH 7/8] xfs: add tracepoints for high level iunlink operations Darrick J. Wong
2019-02-01 19:01 ` Brian Foster
2019-02-01 19:14 ` Darrick J. Wong
2019-01-31 23:18 ` [PATCH 8/8] xfs: cache unlinked pointers in an rhashtable Darrick J. Wong
2019-02-01 8:03 ` Christoph Hellwig
2019-02-01 23:59 ` Dave Chinner
2019-02-02 4:31 ` Darrick J. Wong
2019-02-02 16:07 ` Christoph Hellwig
2019-02-01 19:29 ` Brian Foster
2019-02-01 19:40 ` Darrick J. Wong
2019-02-02 17:01 ` Christoph Hellwig
2019-02-01 7:57 ` [PATCH 0/8] xfs: incore unlinked list Christoph Hellwig
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=20190201185924.GA31203@bfoster \
--to=bfoster@redhat.com \
--cc=darrick.wong@oracle.com \
--cc=linux-xfs@vger.kernel.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).