Illumos #4045 write throttle & i/o scheduler performance work

[mirror_zfs.git] / module / zfs / zfs_vnops.c

diff --git a/module/zfs/zfs_vnops.c b/module/zfs/zfs_vnops.c
index 1552b61e0e3e3e7380438dfa7dd601b42ee10502..6f25a6fff1b80f1c9d2928ddaf17631aca552baf 100644 (file)
--- a/module/zfs/zfs_vnops.c
+++ b/module/zfs/zfs_vnops.c
@@ -125,7 +125,11 @@
  *     forever, because the previous txg can't quiesce until B's tx commits.
  *
  *     If dmu_tx_assign() returns ERESTART and zsb->z_assign is TXG_NOWAIT,
- *     then drop all locks, call dmu_tx_wait(), and try again.
+ *     then drop all locks, call dmu_tx_wait(), and try again.  On subsequent
+ *     calls to dmu_tx_assign(), pass TXG_WAITED rather than TXG_NOWAIT,
+ *     to indicate that this operation has already called dmu_tx_wait().
+ *     This will ensure that we don't retry forever, waiting a short bit
+ *     each time.
  *
  *  (5)        If the operation succeeded, generate the intent log entry for it
  *     before dropping locks.  This ensures that the ordering of events
@@ -147,12 +151,13 @@
  *     rw_enter(...);                  // grab any other locks you need
  *     tx = dmu_tx_create(...);        // get DMU tx
  *     dmu_tx_hold_*();                // hold each object you might modify
- *     error = dmu_tx_assign(tx, TXG_NOWAIT);  // try to assign
+ *     error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
  *     if (error) {
  *             rw_exit(...);           // drop locks
  *             zfs_dirent_unlock(dl);  // unlock directory entry
  *             iput(...);              // release held vnodes
  *             if (error == ERESTART) {
+ *                     waited = B_TRUE;
  *                     dmu_tx_wait(tx);
  *                     dmu_tx_abort(tx);
  *                     goto top;
@@ -1279,6 +1284,7 @@ zfs_create(struct inode *dip, char *name, vattr_t *vap, int excl,
        zfs_acl_ids_t   acl_ids;
        boolean_t       fuid_dirtied;
        boolean_t       have_acl = B_FALSE;
+       boolean_t       waited = B_FALSE;
 
        /*
         * If we have an ephemeral id, ACL, or XVATTR then
@@ -1391,10 +1397,11 @@ top:
                        dmu_tx_hold_write(tx, DMU_NEW_OBJECT,
                            0, acl_ids.z_aclp->z_acl_bytes);
                }
-               error = dmu_tx_assign(tx, TXG_NOWAIT);
+               error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
                if (error) {
                        zfs_dirent_unlock(dl);
                        if (error == ERESTART) {
+                               waited = B_TRUE;
                                dmu_tx_wait(tx);
                                dmu_tx_abort(tx);
                                goto top;
@@ -1524,6 +1531,7 @@ zfs_remove(struct inode *dip, char *name, cred_t *cr)
 #endif /* HAVE_PN_UTILS */
        int             error;
        int             zflg = ZEXISTS;
+       boolean_t       waited = B_FALSE;
 
        ZFS_ENTER(zsb);
        ZFS_VERIFY_ZP(dzp);
@@ -1599,13 +1607,14 @@ top:
        /* charge as an update -- would be nice not to charge at all */
        dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
 
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                zfs_dirent_unlock(dl);
                iput(ip);
                if (xzp)
                        iput(ZTOI(xzp));
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;
@@ -1710,6 +1719,7 @@ zfs_mkdir(struct inode *dip, char *dirname, vattr_t *vap, struct inode **ipp,
        gid_t           gid = crgetgid(cr);
        zfs_acl_ids_t   acl_ids;
        boolean_t       fuid_dirtied;
+       boolean_t       waited = B_FALSE;
 
        ASSERT(S_ISDIR(vap->va_mode));
 
@@ -1801,10 +1811,11 @@ top:
        dmu_tx_hold_sa_create(tx, acl_ids.z_aclp->z_acl_bytes +
            ZFS_SA_BASE_ATTR_SIZE);
 
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                zfs_dirent_unlock(dl);
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;
@@ -1882,6 +1893,7 @@ zfs_rmdir(struct inode *dip, char *name, struct inode *cwd, cred_t *cr,
        dmu_tx_t        *tx;
        int             error;
        int             zflg = ZEXISTS;
+       boolean_t       waited = B_FALSE;
 
        ZFS_ENTER(zsb);
        ZFS_VERIFY_ZP(dzp);
@@ -1935,13 +1947,14 @@ top:
        dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
        zfs_sa_upgrade_txholds(tx, zp);
        zfs_sa_upgrade_txholds(tx, dzp);
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                rw_exit(&zp->z_parent_lock);
                rw_exit(&zp->z_name_lock);
                zfs_dirent_unlock(dl);
                iput(ip);
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;
@@ -3169,6 +3182,7 @@ zfs_rename(struct inode *sdip, char *snm, struct inode *tdip, char *tnm,
        int             cmp, serr, terr;
        int             error = 0;
        int             zflg = 0;
+       boolean_t       waited = B_FALSE;
 
        ZFS_ENTER(zsb);
        ZFS_VERIFY_ZP(sdzp);
@@ -3383,7 +3397,7 @@ top:
 
        zfs_sa_upgrade_txholds(tx, szp);
        dmu_tx_hold_zap(tx, zsb->z_unlinkedobj, FALSE, NULL);
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                if (zl != NULL)
                        zfs_rename_unlock(&zl);
@@ -3397,6 +3411,7 @@ top:
                if (tzp)
                        iput(ZTOI(tzp));
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;
@@ -3504,6 +3519,7 @@ zfs_symlink(struct inode *dip, char *name, vattr_t *vap, char *link,
        zfs_acl_ids_t   acl_ids;
        boolean_t       fuid_dirtied;
        uint64_t        txtype = TX_SYMLINK;
+       boolean_t       waited = B_FALSE;
 
        ASSERT(S_ISLNK(vap->va_mode));
 
@@ -3568,10 +3584,11 @@ top:
        }
        if (fuid_dirtied)
                zfs_fuid_txhold(zsb, tx);
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                zfs_dirent_unlock(dl);
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;
@@ -3699,6 +3716,7 @@ zfs_link(struct inode *tdip, struct inode *sip, char *name, cred_t *cr)
        int             zf = ZNEW;
        uint64_t        parent;
        uid_t           owner;
+       boolean_t       waited = B_FALSE;
 
        ASSERT(S_ISDIR(tdip->i_mode));
 
@@ -3782,10 +3800,11 @@ top:
        dmu_tx_hold_zap(tx, dzp->z_id, TRUE, name);
        zfs_sa_upgrade_txholds(tx, szp);
        zfs_sa_upgrade_txholds(tx, dzp);
-       error = dmu_tx_assign(tx, TXG_NOWAIT);
+       error = dmu_tx_assign(tx, waited ? TXG_WAITED : TXG_NOWAIT);
        if (error) {
                zfs_dirent_unlock(dl);
                if (error == ERESTART) {
+                       waited = B_TRUE;
                        dmu_tx_wait(tx);
                        dmu_tx_abort(tx);
                        goto top;