OpenZFS 8115 - parallel zfs mount

Porting Notes:
* Use thread pools (tpool) API instead of introducing taskq interfaces
  to libzfs.
* Use pthread_mutext for locks as mutex_t isn't available.
* Ignore alternative libshare initialization since OpenZFS-7955 is
  not present on zfsonlinux.

Authored by: Sebastien Roy <seb@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Reviewed by: Prashanth Sreenivasa <pks@delphix.com>
Authored by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Matt Ahrens <mahrens@delphix.com>
Ported-by: Don Brady <don.brady@delphix.com>

OpenZFS-issue: https://www.illumos.org/issues/8115
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/a3f0e2b569
Closes #8092
This commit is contained in:
Sebastien Roy
2018-11-05 08:40:05 -07:00
committed by Brian Behlendorf
parent af2e8411da
commit a10d50f999
10 changed files with 718 additions and 141 deletions
+2 -3
View File
@@ -573,12 +573,11 @@ typedef struct get_all_cb {
zfs_handle_t **cb_handles;
size_t cb_alloc;
size_t cb_used;
boolean_t cb_verbose;
int (*cb_getone)(zfs_handle_t *, void *);
} get_all_cb_t;
void zfs_foreach_mountpoint(libzfs_handle_t *, zfs_handle_t **, size_t,
zfs_iter_f, void *, boolean_t);
void libzfs_add_handle(get_all_cb_t *, zfs_handle_t *);
int libzfs_dataset_cmp(const void *, const void *);
/*
* Functions to create and destroy datasets.
+8 -1
View File
@@ -21,7 +21,7 @@
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2011, 2015 by Delphix. All rights reserved.
* Copyright (c) 2011, 2017 by Delphix. All rights reserved.
* Copyright (c) 2018 Datto Inc.
*/
@@ -60,6 +60,13 @@ struct libzfs_handle {
void *libzfs_sharehdl; /* libshare handle */
uint_t libzfs_shareflags;
boolean_t libzfs_mnttab_enable;
/*
* We need a lock to handle the case where parallel mount
* threads are populating the mnttab cache simultaneously. The
* lock only protects the integrity of the avl tree, and does
* not protect the contents of the mnttab entries themselves.
*/
pthread_mutex_t libzfs_mnttab_cache_lock;
avl_tree_t libzfs_mnttab_cache;
int libzfs_pool_iter;
char libzfs_chassis_id[256];