[XFS] Increase the size of the buffer holding the local inode cluster

list, to increase our potential readahead window and in turn improve
bulkstat performance.

SGI-PV: 944409
SGI-Modid: xfs-linux-melb:xfs-kern:26607a

Signed-off-by: Nathan Scott <nathans@sgi.com>
Signed-off-by: Tim Shimmin <tes@sgi.com>

diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index e6dbe6ba6fbd2da4f28bf8e9be8a8bd82062a102..315c9bcd3be385c47c32c4ec9005a8c8b78b8330 100644 (file)
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -324,6 +324,8 @@ xfs_bulkstat(
        xfs_agino_t             gino;   /* current btree rec's start inode */
        int                     i;      /* loop index */
        int                     icount; /* count of inodes good in irbuf */
+       int                     irbsize; /* size of irec buffer in bytes */
+       unsigned int            kmflags; /* flags for allocating irec buffer */
        xfs_ino_t               ino;    /* inode number (filesystem) */
        xfs_inobt_rec_incore_t  *irbp;  /* current irec buffer pointer */
        xfs_inobt_rec_incore_t  *irbuf; /* start of irec buffer */
@@ -369,12 +371,20 @@ xfs_bulkstat(
        nimask = ~(nicluster - 1);
        nbcluster = nicluster >> mp->m_sb.sb_inopblog;
        /*
-        * Allocate a page-sized buffer for inode btree records.
-        * We could try allocating something smaller, but for normal
-        * calls we'll always (potentially) need the whole page.
+        * Allocate a local buffer for inode cluster btree records.
+        * This caps our maximum readahead window (so don't be stingy)
+        * but we must handle the case where we can't get a contiguous
+        * multi-page buffer, so we drop back toward pagesize; the end
+        * case we ensure succeeds, via appropriate allocation flags.
         */
-       irbuf = kmem_alloc(NBPC, KM_SLEEP);
-       nirbuf = NBPC / sizeof(*irbuf);
+       irbsize = NBPP * 4;
+       kmflags = KM_SLEEP | KM_MAYFAIL;
+       while (!(irbuf = kmem_alloc(irbsize, kmflags))) {
+               if ((irbsize >>= 1) <= NBPP)
+                       kmflags = KM_SLEEP;
+       }
+       nirbuf = irbsize / sizeof(*irbuf);
+
        /*
         * Loop over the allocation groups, starting from the last
         * inode returned; 0 means start of the allocation group.
@@ -672,7 +682,7 @@ xfs_bulkstat(
        /*
         * Done, we're either out of filesystem or space to put the data.
         */
-       kmem_free(irbuf, NBPC);
+       kmem_free(irbuf, irbsize);
        *ubcountp = ubelem;
        if (agno >= mp->m_sb.sb_agcount) {
                /*