OpenZFS 8604 - Simplify snapshots unmounting code

Authored by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Andy Stormont <astormont@racktopsystems.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Ported-by: Don Brady <don.brady@delphix.com>

Every time we want to unmount a snapshot (happens during snapshot
deletion or renaming) we unnecessarily iterate through all the
mountpoints in the VFS layer (see zfs_get_vfs).

The current patch completely gets rid of that code and changes
the approach while keeping the behavior of that code path the
same. Specifically, it puts a hold on the dataset/snapshot and
gets its vfs resource reference directly, instead of linearly
searching for it. If that reference exists we attempt to amount
it.

With the above change, it became obvious that the nvlist
manipulations that we do (add_boolean and add_nvlist) take a
significant amount of time ensuring uniqueness of every new
element even though they don't have too. Thus, we updated the
patch so those nvlists are not trying to enforce the uniqueness
of their elements.

A more complete analysis of the problem solved by this patch
can be found below:
https://sdimitro.github.io/post/snap-unmount-perf/

OpenZFS-issue: https://www.illumos.org/issues/8604
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/126118fb
This commit is contained in:
Serapheim Dimitropoulos
2018-02-08 09:32:45 -07:00
committed by Brian Behlendorf
parent fc5d4b6737
commit 8d103d8856
3 changed files with 28 additions and 30 deletions
+12 -6
View File
@@ -496,23 +496,29 @@ dsl_destroy_snapshots_nvl(nvlist_t *snaps, boolean_t defer,
if (nvlist_next_nvpair(snaps, NULL) == NULL)
return (0);
nvlist_t *arg = fnvlist_alloc();
nvlist_t *snaps_normalized = fnvlist_alloc();
/*
* lzc_destroy_snaps() is documented to take an nvlist whose
* values "don't matter". We need to convert that nvlist to one
* that we know can be converted to LUA.
* values "don't matter". We need to convert that nvlist to
* one that we know can be converted to LUA. We also don't
* care about any duplicate entries because the nvlist will
* be converted to a LUA table which should take care of this.
*/
nvlist_t *snaps_normalized;
VERIFY0(nvlist_alloc(&snaps_normalized, 0, KM_SLEEP));
for (nvpair_t *pair = nvlist_next_nvpair(snaps, NULL);
pair != NULL; pair = nvlist_next_nvpair(snaps, pair)) {
fnvlist_add_boolean_value(snaps_normalized,
nvpair_name(pair), B_TRUE);
}
nvlist_t *arg;
VERIFY0(nvlist_alloc(&arg, 0, KM_SLEEP));
fnvlist_add_nvlist(arg, "snaps", snaps_normalized);
fnvlist_free(snaps_normalized);
fnvlist_add_boolean_value(arg, "defer", defer);
nvlist_t *wrapper = fnvlist_alloc();
nvlist_t *wrapper;
VERIFY0(nvlist_alloc(&wrapper, 0, KM_SLEEP));
fnvlist_add_nvlist(wrapper, ZCP_ARG_ARGLIST, arg);
fnvlist_free(arg);
@@ -546,7 +552,7 @@ dsl_destroy_snapshots_nvl(nvlist_t *snaps, boolean_t defer,
program,
0,
zfs_lua_max_memlimit,
fnvlist_lookup_nvpair(wrapper, ZCP_ARG_ARGLIST), result);
nvlist_next_nvpair(wrapper, NULL), result);
if (error != 0) {
char *errorstr = NULL;
(void) nvlist_lookup_string(result, ZCP_RET_ERROR, &errorstr);