From 2ee1abad73a12df5521cd3f017f081f1f684a361 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 24 Nov 2009 18:03:15 +0000 Subject: [PATCH] xfs: improve metadata I/O merging in the elevator Change all async metadata buffers to use [READ|WRITE]_META I/O types so that the I/O doesn't get issued immediately. This allows merging of adjacent metadata requests but still prioritises them over bulk data. This shows a 10-15% improvement in sequential create speed of small files. Don't include the log buffers in this classification - leave them as sync types so they are issued immediately. Signed-off-by: Dave Chinner Signed-off-by: Christoph Hellwig Signed-off-by: Alex Elder --- fs/xfs/linux-2.6/xfs_buf.c | 6 +++++- fs/xfs/linux-2.6/xfs_buf.h | 1 + fs/xfs/xfs_log.c | 2 ++ include/linux/fs.h | 1 + 4 files changed, 9 insertions(+), 1 deletion(-) diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c index b4c7d4248aac..162359b664ca 100644 --- a/fs/xfs/linux-2.6/xfs_buf.c +++ b/fs/xfs/linux-2.6/xfs_buf.c @@ -1149,10 +1149,14 @@ _xfs_buf_ioapply( if (bp->b_flags & XBF_ORDERED) { ASSERT(!(bp->b_flags & XBF_READ)); rw = WRITE_BARRIER; - } else if (bp->b_flags & _XBF_RUN_QUEUES) { + } else if (bp->b_flags & XBF_LOG_BUFFER) { ASSERT(!(bp->b_flags & XBF_READ_AHEAD)); bp->b_flags &= ~_XBF_RUN_QUEUES; rw = (bp->b_flags & XBF_WRITE) ? WRITE_SYNC : READ_SYNC; + } else if (bp->b_flags & _XBF_RUN_QUEUES) { + ASSERT(!(bp->b_flags & XBF_READ_AHEAD)); + bp->b_flags &= ~_XBF_RUN_QUEUES; + rw = (bp->b_flags & XBF_WRITE) ? WRITE_META : READ_META; } else { rw = (bp->b_flags & XBF_WRITE) ? WRITE : (bp->b_flags & XBF_READ_AHEAD) ? READA : READ; diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h index a509f4addc2a..a34c7b54822d 100644 --- a/fs/xfs/linux-2.6/xfs_buf.h +++ b/fs/xfs/linux-2.6/xfs_buf.h @@ -55,6 +55,7 @@ typedef enum { XBF_FS_MANAGED = (1 << 8), /* filesystem controls freeing memory */ XBF_ORDERED = (1 << 11), /* use ordered writes */ XBF_READ_AHEAD = (1 << 12), /* asynchronous read-ahead */ + XBF_LOG_BUFFER = (1 << 13), /* this is a buffer used for the log */ /* flags used only as arguments to access routines */ XBF_LOCK = (1 << 14), /* lock requested */ diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 4cb1792040e3..600b5b06aaeb 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1441,6 +1441,7 @@ xlog_sync(xlog_t *log, XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); + bp->b_flags |= XBF_LOG_BUFFER; /* * Do an ordered write for the log block. * Its unnecessary to flush the first split block in the log wrap case. @@ -1478,6 +1479,7 @@ xlog_sync(xlog_t *log, XFS_BUF_ZEROFLAGS(bp); XFS_BUF_BUSY(bp); XFS_BUF_ASYNC(bp); + bp->b_flags |= XBF_LOG_BUFFER; if (log->l_mp->m_flags & XFS_MOUNT_BARRIER) XFS_BUF_ORDERED(bp); dptr = XFS_BUF_PTR(bp); diff --git a/include/linux/fs.h b/include/linux/fs.h index b23a7018eb90..cf7fc8a7fe6a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -152,6 +152,7 @@ struct inodes_stat_t { #define WRITE_SYNC_PLUG (WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define WRITE_SYNC (WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG)) #define WRITE_ODIRECT_PLUG (WRITE | (1 << BIO_RW_SYNCIO)) +#define WRITE_META (WRITE | (1 << BIO_RW_META)) #define SWRITE_SYNC_PLUG \ (SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE)) #define SWRITE_SYNC (SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))