ext4: make mballoc try target group first even with mb_optimize_scan

commit 4fca50d440cc5d4dc570ad5484cc0b70b381bc2a upstream.

One of the side-effects of mb_optimize_scan was that the optimized
functions to select next group to try were called even before we tried
the goal group. As a result we no longer allocate files close to
corresponding inodes as well as we don't try to expand currently
allocated extent in the same group. This results in reaim regression
with workfile.disk workload of upto 8% with many clients on my test
machine:

                     baseline               mb_optimize_scan
Hmean     disk-1       2114.16 (   0.00%)     2099.37 (  -0.70%)
Hmean     disk-41     87794.43 (   0.00%)    83787.47 *  -4.56%*
Hmean     disk-81    148170.73 (   0.00%)   135527.05 *  -8.53%*
Hmean     disk-121   177506.11 (   0.00%)   166284.93 *  -6.32%*
Hmean     disk-161   220951.51 (   0.00%)   207563.39 *  -6.06%*
Hmean     disk-201   208722.74 (   0.00%)   203235.59 (  -2.63%)
Hmean     disk-241   222051.60 (   0.00%)   217705.51 (  -1.96%)
Hmean     disk-281   252244.17 (   0.00%)   241132.72 *  -4.41%*
Hmean     disk-321   255844.84 (   0.00%)   245412.84 *  -4.08%*

Also this is causing huge regression (time increased by a factor of 5 or
so) when untarring archive with lots of small files on some eMMC storage
cards.

Fix the problem by making sure we try goal group first.

Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning")
CC: stable@kernel.org
Reported-and-tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://lore.kernel.org/all/20220727105123.ckwrhbilzrxqpt24@quack3/
Link: https://lore.kernel.org/all/0d81a7c2-46b7-6010-62a4-3e6cfc1628d6@i2se.com/
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220908092136.11770-1-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 697af6603652426b6115a6505b9863c09c900d2f..7d5e66fded0e55d9531026b4746a4765a3fe5c2a 100644 (file)
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1049,8 +1049,10 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
 {
        *new_cr = ac->ac_criteria;
 
-       if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining)
+       if (!should_optimize_scan(ac) || ac->ac_groups_linear_remaining) {
+               *group = next_linear_group(ac, *group, ngroups);
                return;
+       }
 
        if (*new_cr == 0) {
                ext4_mb_choose_next_group_cr0(ac, new_cr, group, ngroups);
@@ -2630,7 +2632,7 @@ static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
        ext4_group_t prefetch_grp = 0, ngroups, group, i;
-       int cr = -1;
+       int cr = -1, new_cr;
        int err = 0, first_err = 0;
        unsigned int nr = 0, prefetch_ios = 0;
        struct ext4_sb_info *sbi;
@@ -2705,13 +2707,11 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
                ac->ac_groups_linear_remaining = sbi->s_mb_max_linear_groups;
                prefetch_grp = group;
 
-               for (i = 0; i < ngroups; group = next_linear_group(ac, group, ngroups),
-                            i++) {
-                       int ret = 0, new_cr;
+               for (i = 0, new_cr = cr; i < ngroups; i++,
+                    ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups)) {
+                       int ret = 0;
 
                        cond_resched();
-
-                       ext4_mb_choose_next_group(ac, &new_cr, &group, ngroups);
                        if (new_cr != cr) {
                                cr = new_cr;
                                goto repeat;