Update bcachefs sources to 1a739db0b256 bcachefs; guard against overflow in btree...

[bcachefs-tools-debian] / libbcachefs / journal_reclaim.c

diff --git a/libbcachefs/journal_reclaim.c b/libbcachefs/journal_reclaim.c
index 658aaa2c3c6d753cc92f9a494466ddcef6181d31..820d25e19e5fe3ee6a45e70f23eb74fc1d558e88 100644 (file)
--- a/libbcachefs/journal_reclaim.c
+++ b/libbcachefs/journal_reclaim.c
@@ -3,6 +3,7 @@
 #include "bcachefs.h"
 #include "btree_key_cache.h"
 #include "btree_update.h"
+#include "btree_write_buffer.h"
 #include "buckets.h"
 #include "errcode.h"
 #include "error.h"
@@ -50,20 +51,23 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j,
        return available;
 }
 
-static inline void journal_set_watermark(struct journal *j)
+void bch2_journal_set_watermark(struct journal *j)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
        bool low_on_space = j->space[journal_space_clean].total * 4 <=
                j->space[journal_space_total].total;
        bool low_on_pin = fifo_free(&j->pin) < j->pin.size / 4;
-       unsigned watermark = low_on_space || low_on_pin
+       bool low_on_wb = bch2_btree_write_buffer_must_wait(c);
+       unsigned watermark = low_on_space || low_on_pin || low_on_wb
                ? BCH_WATERMARK_reclaim
                : BCH_WATERMARK_stripe;
 
        if (track_event_change(&c->times[BCH_TIME_blocked_journal_low_on_space],
                               &j->low_on_space_start, low_on_space) ||
            track_event_change(&c->times[BCH_TIME_blocked_journal_low_on_pin],
-                              &j->low_on_pin_start, low_on_pin))
+                              &j->low_on_pin_start, low_on_pin) ||
+           track_event_change(&c->times[BCH_TIME_blocked_write_buffer_full],
+                              &j->write_buffer_full_start, low_on_wb))
                trace_and_count(c, journal_full, c);
 
        swap(watermark, j->watermark);
@@ -132,15 +136,13 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
                            enum journal_space_from from)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
-       struct bch_dev *ca;
-       unsigned i, pos, nr_devs = 0;
+       unsigned pos, nr_devs = 0;
        struct journal_space space, dev_space[BCH_SB_MEMBERS_MAX];
 
        BUG_ON(nr_devs_want > ARRAY_SIZE(dev_space));
 
        rcu_read_lock();
-       for_each_member_device_rcu(ca, c, i,
-                                  &c->rw_devs[BCH_DATA_journal]) {
+       for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
                if (!ca->journal.nr)
                        continue;
 
@@ -169,19 +171,17 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne
 void bch2_journal_space_available(struct journal *j)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
-       struct bch_dev *ca;
        unsigned clean, clean_ondisk, total;
        unsigned max_entry_size  = min(j->buf[0].buf_size >> 9,
                                       j->buf[1].buf_size >> 9);
-       unsigned i, nr_online = 0, nr_devs_want;
+       unsigned nr_online = 0, nr_devs_want;
        bool can_discard = false;
        int ret = 0;
 
        lockdep_assert_held(&j->lock);
 
        rcu_read_lock();
-       for_each_member_device_rcu(ca, c, i,
-                                  &c->rw_devs[BCH_DATA_journal]) {
+       for_each_member_device_rcu(c, ca, &c->rw_devs[BCH_DATA_journal]) {
                struct journal_device *ja = &ca->journal;
 
                if (!ja->nr)
@@ -212,7 +212,7 @@ void bch2_journal_space_available(struct journal *j)
 
        nr_devs_want = min_t(unsigned, nr_online, c->opts.metadata_replicas);
 
-       for (i = 0; i < journal_space_nr; i++)
+       for (unsigned i = 0; i < journal_space_nr; i++)
                j->space[i] = __journal_space_available(j, nr_devs_want, i);
 
        clean_ondisk    = j->space[journal_space_clean_ondisk].total;
@@ -230,7 +230,7 @@ void bch2_journal_space_available(struct journal *j)
        else
                clear_bit(JOURNAL_MAY_SKIP_FLUSH, &j->flags);
 
-       journal_set_watermark(j);
+       bch2_journal_set_watermark(j);
 out:
        j->cur_entry_sectors    = !ret ? j->space[journal_space_discarded].next_entry : 0;
        j->cur_entry_error      = ret;
@@ -259,12 +259,10 @@ static bool should_discard_bucket(struct journal *j, struct journal_device *ja)
 void bch2_journal_do_discards(struct journal *j)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
-       struct bch_dev *ca;
-       unsigned iter;
 
        mutex_lock(&j->discard_lock);
 
-       for_each_rw_member(ca, c, iter) {
+       for_each_rw_member(c, ca) {
                struct journal_device *ja = &ca->journal;
 
                while (should_discard_bucket(j, ja)) {
@@ -303,6 +301,7 @@ void bch2_journal_reclaim_fast(struct journal *j)
         * all btree nodes got written out
         */
        while (!fifo_empty(&j->pin) &&
+              j->pin.front <= j->seq_ondisk &&
               !atomic_read(&fifo_peek_front(&j->pin).count)) {
                j->pin.front++;
                popped = true;
@@ -578,13 +577,11 @@ static size_t journal_flush_pins(struct journal *j,
 static u64 journal_seq_to_flush(struct journal *j)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
-       struct bch_dev *ca;
        u64 seq_to_flush = 0;
-       unsigned iter;
 
        spin_lock(&j->lock);
 
-       for_each_rw_member(ca, c, iter) {
+       for_each_rw_member(c, ca) {
                struct journal_device *ja = &ca->journal;
                unsigned nr_buckets, bucket_to_flush;
 
@@ -635,6 +632,7 @@ static u64 journal_seq_to_flush(struct journal *j)
 static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
 {
        struct bch_fs *c = container_of(j, struct bch_fs, journal);
+       bool kthread = (current->flags & PF_KTHREAD) != 0;
        u64 seq_to_flush;
        size_t min_nr, min_key_cache, nr_flushed;
        unsigned flags;
@@ -650,7 +648,7 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked)
        flags = memalloc_noreclaim_save();
 
        do {
-               if (kthread_should_stop())
+               if (kthread && kthread_should_stop())
                        break;
 
                if (bch2_journal_error(j)) {
@@ -787,10 +785,9 @@ int bch2_journal_reclaim_start(struct journal *j)
        p = kthread_create(bch2_journal_reclaim_thread, j,
                           "bch-reclaim/%s", c->name);
        ret = PTR_ERR_OR_ZERO(p);
-       if (ret) {
-               bch_err_msg(c, ret, "creating journal reclaim thread");
+       bch_err_msg(c, ret, "creating journal reclaim thread");
+       if (ret)
                return ret;
-       }
 
        get_task_struct(p);
        j->reclaim_thread = p;
@@ -816,6 +813,9 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush,
                               (1U << JOURNAL_PIN_btree), 0, 0, 0))
                *did_work = true;
 
+       if (seq_to_flush > journal_cur_seq(j))
+               bch2_journal_entry_close(j);
+
        spin_lock(&j->lock);
        /*
         * If journal replay hasn't completed, the unreplayed journal entries