c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-25 19:57:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add TRIM support

Browse Source 
UNMAP/TRIM support is a frequently-requested feature to help
prevent performance from degrading on SSDs and on various other
SAN-like storage back-ends.  By issuing UNMAP/TRIM commands for
sectors which are no longer allocated the underlying device can
often more efficiently manage itself.

This TRIM implementation is modeled on the `zpool initialize`
feature which writes a pattern to all unallocated space in the
pool.  The new `zpool trim` command uses the same vdev_xlate()
code to calculate what sectors are unallocated, the same per-
vdev TRIM thread model and locking, and the same basic CLI for
a consistent user experience.  The core difference is that
instead of writing a pattern it will issue UNMAP/TRIM commands
for those extents.

The zio pipeline was updated to accommodate this by adding a new
ZIO_TYPE_TRIM type and associated spa taskq.  This new type makes
is straight forward to add the platform specific TRIM/UNMAP calls
to vdev_disk.c and vdev_file.c.  These new ZIO_TYPE_TRIM zios are
handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs.
This makes it possible to largely avoid changing the pipieline,
one exception is that TRIM zio's may exceed the 16M block size
limit since they contain no data.

In addition to the manual `zpool trim` command, a background
automatic TRIM was added and is controlled by the 'autotrim'
property.  It relies on the exact same infrastructure as the
manual TRIM.  However, instead of relying on the extents in a
metaslab's ms_allocatable range tree, a ms_trim tree is kept
per metaslab.  When 'autotrim=on', ranges added back to the
ms_allocatable tree are also added to the ms_free tree.  The
ms_free tree is then periodically consumed by an autotrim
thread which systematically walks a top level vdev's metaslabs.

Since the automatic TRIM will skip ranges it considers too small
there is value in occasionally running a full `zpool trim`.  This
may occur when the freed blocks are small and not enough time
was allowed to aggregate them.  An automatic TRIM and a manual
`zpool trim` may be run concurrently, in which case the automatic
TRIM will yield to the manual TRIM.

Reviewed-by: Jorgen Lundman <lundman@lundman.net>
Reviewed-by: Tim Chase <tim@chase2k.com>
Reviewed-by: Matt Ahrens <mahrens@delphix.com>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Contributions-by: Saso Kiselkov <saso.kiselkov@nexenta.com>
Contributions-by: Tim Chase <tim@chase2k.com>
Contributions-by: Chunwei Chen <tuxoko@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8419 
Closes #598
This commit is contained in:
Brian Behlendorf
2019-03-29 09:13:20 -07:00
committed by GitHub
parent f94b3cbf43
commit 1b939560be
91 changed files with 5593 additions and 439 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/libzfs_core/libzfs_core.c
+45 -1
View File
@@ -1412,7 +1412,8 @@ lzc_reopen(const char *pool_name, boolean_t scrub_restart)
* - ENODEV if the device was not found
* - EINVAL if the devices is not a leaf or is not concrete (e.g. missing)
* - EROFS if the device is not writeable
* - EBUSY start requested but the device is already being initialized
* - EBUSY start requested but the device is already being either
* initialized or trimmed
* - ESRCH cancel/suspend requested but device is not being initialized
*
* If the errlist is empty, then return value will be:
@@ -1425,6 +1426,7 @@ lzc_initialize(const char *poolname, pool_initialize_func_t cmd_type,
nvlist_t *vdevs, nvlist_t **errlist)
{
int error;
nvlist_t *args = fnvlist_alloc();
fnvlist_add_uint64(args, ZPOOL_INITIALIZE_COMMAND, (uint64_t)cmd_type);
fnvlist_add_nvlist(args, ZPOOL_INITIALIZE_VDEVS, vdevs);
@@ -1435,3 +1437,45 @@ lzc_initialize(const char *poolname, pool_initialize_func_t cmd_type,
return (error);
}
/*
* Changes TRIM state.
*
* vdevs should be a list of (<key>, guid) where guid is a uint64 vdev GUID.
* The key is ignored.
*
* If there are errors related to vdev arguments, per-vdev errors are returned
* in an nvlist with the key "vdevs". Each error is a (guid, errno) pair where
* guid is stringified with PRIu64, and errno is one of the following as
* an int64_t:
* - ENODEV if the device was not found
* - EINVAL if the devices is not a leaf or is not concrete (e.g. missing)
* - EROFS if the device is not writeable
* - EBUSY start requested but the device is already being either trimmed
* or initialized
* - ESRCH cancel/suspend requested but device is not being initialized
* - EOPNOTSUPP if the device does not support TRIM (or secure TRIM)
*
* If the errlist is empty, then return value will be:
* - EINVAL if one or more arguments was invalid
* - Other spa_open failures
* - 0 if the operation succeeded
*/
int
lzc_trim(const char *poolname, pool_trim_func_t cmd_type, uint64_t rate,
boolean_t secure, nvlist_t *vdevs, nvlist_t **errlist)
{
int error;
nvlist_t *args = fnvlist_alloc();
fnvlist_add_uint64(args, ZPOOL_TRIM_COMMAND, (uint64_t)cmd_type);
fnvlist_add_nvlist(args, ZPOOL_TRIM_VDEVS, vdevs);
fnvlist_add_uint64(args, ZPOOL_TRIM_RATE, rate);
fnvlist_add_boolean_value(args, ZPOOL_TRIM_SECURE, secure);
error = lzc_ioctl(ZFS_IOC_POOL_TRIM, poolname, args, errlist);
fnvlist_free(args);
return (error);
}