kernel_optimize_test/block/blk-cgroup-rwstat.c
Xunlei Pang 71b996c9b8 blk-cgroup: Fix the recursive blkg rwstat
[ Upstream commit 4f44657d74873735e93a50eb25014721a66aac19 ]

The current blkio.throttle.io_service_bytes_recursive doesn't
work correctly.

As an example, for the following blkcg hierarchy:
 (Made 1GB READ in test1, 512MB READ in test2)
     test
    /    \
 test1   test2

$ head -n 1 test/test1/blkio.throttle.io_service_bytes_recursive
8:0 Read 1073684480
$ head -n 1 test/test2/blkio.throttle.io_service_bytes_recursive
8:0 Read 537448448
$ head -n 1 test/blkio.throttle.io_service_bytes_recursive
8:0 Read 537448448

Clearly, above data of "test" reflects "test2" not "test1"+"test2".

Do the correct summary in blkg_rwstat_recursive_sum().

Signed-off-by: Xunlei Pang <xlpang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2021-03-30 14:31:48 +02:00

131 lines
3.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0
*
* Legacy blkg rwstat helpers enabled by CONFIG_BLK_CGROUP_RWSTAT.
* Do not use in new code.
*/
#include "blk-cgroup-rwstat.h"
int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp)
{
int i, ret;
for (i = 0; i < BLKG_RWSTAT_NR; i++) {
ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp);
if (ret) {
while (--i >= 0)
percpu_counter_destroy(&rwstat->cpu_cnt[i]);
return ret;
}
atomic64_set(&rwstat->aux_cnt[i], 0);
}
return 0;
}
EXPORT_SYMBOL_GPL(blkg_rwstat_init);
void blkg_rwstat_exit(struct blkg_rwstat *rwstat)
{
int i;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
percpu_counter_destroy(&rwstat->cpu_cnt[i]);
}
EXPORT_SYMBOL_GPL(blkg_rwstat_exit);
/**
* __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
* @sf: seq_file to print to
* @pd: policy private data of interest
* @rwstat: rwstat to print
*
* Print @rwstat to @sf for the device assocaited with @pd.
*/
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
const struct blkg_rwstat_sample *rwstat)
{
static const char *rwstr[] = {
[BLKG_RWSTAT_READ] = "Read",
[BLKG_RWSTAT_WRITE] = "Write",
[BLKG_RWSTAT_SYNC] = "Sync",
[BLKG_RWSTAT_ASYNC] = "Async",
[BLKG_RWSTAT_DISCARD] = "Discard",
};
const char *dname = blkg_dev_name(pd->blkg);
u64 v;
int i;
if (!dname)
return 0;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
rwstat->cnt[i]);
v = rwstat->cnt[BLKG_RWSTAT_READ] +
rwstat->cnt[BLKG_RWSTAT_WRITE] +
rwstat->cnt[BLKG_RWSTAT_DISCARD];
seq_printf(sf, "%s Total %llu\n", dname, v);
return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);
/**
* blkg_prfill_rwstat - prfill callback for blkg_rwstat
* @sf: seq_file to print to
* @pd: policy private data of interest
* @off: offset to the blkg_rwstat in @pd
*
* prfill callback for printing a blkg_rwstat.
*/
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
int off)
{
struct blkg_rwstat_sample rwstat = { };
blkg_rwstat_read((void *)pd + off, &rwstat);
return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);
/**
* blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
* @blkg: blkg of interest
* @pol: blkcg_policy which contains the blkg_rwstat
* @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
* @sum: blkg_rwstat_sample structure containing the results
*
* Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
* online descendants and their aux counts. The caller must be holding the
* queue lock for online tests.
*
* If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
* is at @off bytes into @blkg's blkg_policy_data of the policy.
*/
void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol,
int off, struct blkg_rwstat_sample *sum)
{
struct blkcg_gq *pos_blkg;
struct cgroup_subsys_state *pos_css;
unsigned int i;
lockdep_assert_held(&blkg->q->queue_lock);
memset(sum, 0, sizeof(*sum));
rcu_read_lock();
blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
struct blkg_rwstat *rwstat;
if (!pos_blkg->online)
continue;
if (pol)
rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
else
rwstat = (void *)pos_blkg + off;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
sum->cnt[i] += blkg_rwstat_read_counter(rwstat, i);
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);