Log gets updated in a circular fashion, and that makes life-time of log-data different from other types of meta/user-data. By passing a write life-time hint with log, GC efficiency of multi-stream SSD gets improved, leading to endurance/performance benefits. It is described in greater detail (along with results) in this "FAST 2018" paper - https://www.usenix.org/conference/fast18/presentation/rho This patch introduces new mount option "logwritehint" to pass write hint with XFS log. Among other Linux file-systems, F2FS supports passing down such write hints. While for Ext4 journal, I am preparing similar proposal. Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx> --- fs/xfs/xfs_buf.c | 2 ++ fs/xfs/xfs_buf.h | 1 + fs/xfs/xfs_log.c | 3 +++ fs/xfs/xfs_log_recover.c | 1 + fs/xfs/xfs_mount.h | 2 ++ fs/xfs/xfs_super.c | 15 +++++++++++++-- 6 files changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index b21ea2b..00d17f6 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1370,6 +1370,8 @@ xfs_buf_ioapply_map( bio->bi_end_io = xfs_buf_bio_end_io; bio->bi_private = bp; bio_set_op_attrs(bio, op, op_flags); + /* set write hint in bio */ + bio->bi_write_hint = bp->b_write_hint; for (; size && nr_pages; nr_pages--, page_index++) { int rbytes, nbytes = PAGE_SIZE - offset; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index b9f5511..ba9c78c 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -196,6 +196,7 @@ typedef struct xfs_buf { int b_retries; unsigned long b_first_retry_time; /* in jiffies */ int b_last_error; + enum rw_hint b_write_hint; /* write hint for I/O */ const struct xfs_buf_ops *b_ops; } xfs_buf_t; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index c3b610b..45e220d 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1881,6 +1881,8 @@ xlog_sync( XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn))); XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count)); + /* set write hint in buffer */ + bp->b_write_hint = log->l_mp->m_logwritehint; /* Do we need to split this write into 2 parts? */ if (XFS_BUF_ADDR(bp) + BTOBB(count) > log->l_logBBsize) { @@ -1971,6 +1973,7 @@ xlog_sync( bp->b_log_item = iclog; bp->b_flags &= ~XBF_FLUSH; bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA); + bp->b_write_hint = log->l_mp->m_logwritehint; ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 1fc9e90..8bf89fa 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -282,6 +282,7 @@ xlog_bwrite( xfs_buf_lock(bp); bp->b_io_length = nbblks; bp->b_error = 0; + bp->b_write_hint = log->l_mp->m_logwritehint; error = xfs_bwrite(bp); if (error) diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 7964513..7f6b2b8 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -171,6 +171,8 @@ typedef struct xfs_mount { struct workqueue_struct *m_log_workqueue; struct workqueue_struct *m_eofblocks_workqueue; struct workqueue_struct *m_sync_workqueue; + /* To store write hint (for log writes) passed during mount */ + int m_logwritehint; /* * Generation of the filesysyem layout. This is incremented by each diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d3e6cd0..6449d213 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -71,7 +71,7 @@ enum { Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota, Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce, - Opt_discard, Opt_nodiscard, Opt_dax, Opt_err, + Opt_discard, Opt_nodiscard, Opt_dax, Opt_logwritehint, Opt_err, }; static const match_table_t tokens = { @@ -119,6 +119,7 @@ static const match_table_t tokens = { {Opt_discard, "discard"}, /* Discard unused blocks */ {Opt_nodiscard, "nodiscard"}, /* Do not discard unused blocks */ {Opt_dax, "dax"}, /* Enable direct access to bdev pages */ + {Opt_logwritehint, "logwritehint=%u"},/* Write-hint for log */ {Opt_err, NULL}, }; @@ -225,6 +226,10 @@ xfs_parseargs( if (match_int(args, &mp->m_logbufs)) return -EINVAL; break; + case Opt_logwritehint: + if (match_int(args, &mp->m_logwritehint)) + return -EINVAL; + break; case Opt_logbsize: if (suffix_kstrtoint(args, 10, &mp->m_logbsize)) return -EINVAL; @@ -405,7 +410,6 @@ xfs_parseargs( mp->m_dalign = dsunit; mp->m_swidth = dswidth; } - if (mp->m_logbufs != -1 && mp->m_logbufs != 0 && (mp->m_logbufs < XLOG_MIN_ICLOGS || @@ -438,6 +442,13 @@ xfs_parseargs( mp->m_readio_log = iosizelog; mp->m_writeio_log = iosizelog; } + if (mp->m_logwritehint < WRITE_LIFE_NOT_SET || + mp->m_logwritehint > WRITE_LIFE_EXTREME) { + xfs_warn(mp, "invalid logwritehint value: %d [not %d-%d]", + mp->m_logwritehint, WRITE_LIFE_NOT_SET, WRITE_LIFE_EXTREME); + return -EINVAL; + + } return 0; } -- 2.7.4
