From 3910184d9ecf187f5f229798bab688d754fa1e30 Mon Sep 17 00:00:00 2001 From: Alex Zhuravlev Date: Mon, 8 Jan 2018 10:57:47 -0800 Subject: [PATCH] Use zap_count instead of cached z_size for unlink As a performance optimization Lustre does not strictly update the SA_ZPL_SIZE when adding/removing from non-directory entries. This results in entries which cannot be removed through the ZPL layer even though the ZAP is empty and safe to remove. Resolve this issue by checking the zap_count() directly instead on relying on the cached SA_ZPL_SIZE. Micro-benchmarks show no significant performance impact due to the additional overhead of using zap_count(). Reviewed-by: Olaf Faaland Reviewed-by: Giuseppe Di Natale Signed-off-by: Alex Zhuravlev Signed-off-by: Brian Behlendorf Closes #7019 --- module/zfs/zfs_dir.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/module/zfs/zfs_dir.c b/module/zfs/zfs_dir.c index c6ee30291f..9a8bbccd92 100644 --- a/module/zfs/zfs_dir.c +++ b/module/zfs/zfs_dir.c @@ -977,11 +977,25 @@ zfs_link_destroy(zfs_dirlock_t *dl, znode_t *zp, dmu_tx_t *tx, int flag, * Indicate whether the directory is empty. Works with or without z_lock * held, but can only be consider a hint in the latter case. Returns true * if only "." and ".." remain and there's no work in progress. + * + * The internal ZAP size, rather than zp->z_size, needs to be checked since + * some consumers (Lustre) do not strictly maintain an accurate SA_ZPL_SIZE. */ boolean_t zfs_dirempty(znode_t *dzp) { - return (dzp->z_size == 2 && dzp->z_dirlocks == 0); + zfsvfs_t *zfsvfs = ZTOZSB(dzp); + uint64_t count; + int error; + + if (dzp->z_dirlocks != NULL) + return (B_FALSE); + + error = zap_count(zfsvfs->z_os, dzp->z_id, &count); + if (error != 0 || count != 0) + return (B_FALSE); + + return (B_TRUE); } int