From: Vladimir Davydov <vdavydov.dev@gmail.com>
To: kostja@tarantool.org
Cc: tarantool-patches@freelists.org
Subject: [PATCH 4/7] vinyl: fix force compaction logic
Date: Sun, 2 Sep 2018 23:18:57 +0300 [thread overview]
Message-ID: <55436ba89b22a9f490c0642810986672a062cc73.1535917763.git.vdavydov.dev@gmail.com> (raw)
In-Reply-To: <cover.1535917763.git.vdavydov.dev@gmail.com>
In-Reply-To: <cover.1535917763.git.vdavydov.dev@gmail.com>
This patch address a few problems index.compact() is suffering from,
namely:
- When a range is split or coalesced, it should inherit the value of
needs_compaction flag from the source ranges. Currently, the flag is
cleared so that the resulting range may be not compacted.
- If a range has no slices, we shouldn't set needs_compaction flag for
it, because obviously it can't be compacted, but we do.
- The needs_compaction flag should be cleared as soon as we schedule a
range for compaction, not when all slices have been compacted into
one, as we presently expect, because the latter may never happen
under a write-intensive load.
---
src/box/vy_lsm.c | 9 +++++++--
src/box/vy_range.c | 16 ++--------------
src/box/vy_range.h | 8 ++------
src/box/vy_scheduler.c | 2 ++
4 files changed, 13 insertions(+), 22 deletions(-)
diff --git a/src/box/vy_lsm.c b/src/box/vy_lsm.c
index 15592fbf..a0d211f8 100644
--- a/src/box/vy_lsm.c
+++ b/src/box/vy_lsm.c
@@ -1040,6 +1040,7 @@ vy_lsm_split_range(struct vy_lsm *lsm, struct vy_range *range)
if (new_slice != NULL)
vy_range_add_slice(part, new_slice);
}
+ part->needs_compaction = range->needs_compaction;
part->compact_priority = range->compact_priority;
}
@@ -1147,6 +1148,8 @@ vy_lsm_coalesce_range(struct vy_lsm *lsm, struct vy_range *range)
rlist_splice(&result->slices, &it->slices);
result->slice_count += it->slice_count;
vy_disk_stmt_counter_add(&result->count, &it->count);
+ if (it->needs_compaction)
+ result->needs_compaction = true;
vy_range_delete(it);
it = next;
}
@@ -1181,8 +1184,10 @@ vy_lsm_force_compaction(struct vy_lsm *lsm)
struct vy_range_tree_iterator it;
vy_range_tree_ifirst(lsm->tree, &it);
- while ((range = vy_range_tree_inext(&it)) != NULL)
- vy_range_force_compaction(range);
+ while ((range = vy_range_tree_inext(&it)) != NULL) {
+ range->needs_compaction = true;
+ vy_range_update_compact_priority(range, &lsm->opts);
+ }
vy_range_heap_update_all(&lsm->range_heap);
}
diff --git a/src/box/vy_range.c b/src/box/vy_range.c
index 6a55a018..ddcd2ed3 100644
--- a/src/box/vy_range.c
+++ b/src/box/vy_range.c
@@ -262,18 +262,6 @@ vy_range_remove_slice(struct vy_range *range, struct vy_slice *slice)
vy_disk_stmt_counter_sub(&range->count, &slice->count);
}
-void
-vy_range_force_compaction(struct vy_range *range)
-{
- if (range->slice_count == 1) {
- /* Already compacted. */
- assert(!range->needs_compaction);
- return;
- }
- range->needs_compaction = true;
- range->compact_priority = range->slice_count;
-}
-
/**
* To reduce write amplification caused by compaction, we follow
* the LSM tree design. Runs in each range are divided into groups
@@ -304,9 +292,9 @@ vy_range_update_compact_priority(struct vy_range *range,
assert(opts->run_count_per_level > 0);
assert(opts->run_size_ratio > 1);
- if (range->slice_count == 1) {
+ if (range->slice_count <= 1) {
/* Nothing to compact. */
- range->compact_priority = 1;
+ range->compact_priority = 0;
range->needs_compaction = false;
return;
}
diff --git a/src/box/vy_range.h b/src/box/vy_range.h
index d7031e70..2ca19a1c 100644
--- a/src/box/vy_range.h
+++ b/src/box/vy_range.h
@@ -110,8 +110,8 @@ struct vy_range {
* If this flag is set, the range must be scheduled for
* major compaction, i.e. its compact_priority must be
* raised to max (slice_count). The flag is set by
- * vy_range_force_compaction() and cleared automatically
- * when all slices of the range have been compacted.
+ * vy_lsm_force_compaction() and cleared when the range
+ * is scheduled for compaction.
*/
bool needs_compaction;
/** Number of times the range was compacted. */
@@ -229,10 +229,6 @@ vy_range_add_slice_before(struct vy_range *range, struct vy_slice *slice,
void
vy_range_remove_slice(struct vy_range *range, struct vy_slice *slice);
-/** Mark a range for major compaction. */
-void
-vy_range_force_compaction(struct vy_range *range);
-
/**
* Update compaction priority of a range.
*
diff --git a/src/box/vy_scheduler.c b/src/box/vy_scheduler.c
index 4959300e..a1ae3f54 100644
--- a/src/box/vy_scheduler.c
+++ b/src/box/vy_scheduler.c
@@ -1604,6 +1604,8 @@ vy_task_compact_new(struct vy_scheduler *scheduler, struct vy_lsm *lsm,
assert(n == 0);
assert(new_run->dump_lsn >= 0);
+ range->needs_compaction = false;
+
task->range = range;
task->new_run = new_run;
task->wi = wi;
--
2.11.0
next prev parent reply other threads:[~2018-09-02 20:18 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-02 20:18 [PATCH 0/7] vinyl: improve stats for throttling Vladimir Davydov
2018-09-02 20:18 ` [PATCH 1/7] vinyl: fix accounting of secondary index cache statements Vladimir Davydov
2018-09-02 22:26 ` [tarantool-patches] " Konstantin Osipov
2018-09-02 20:18 ` [PATCH 2/7] vinyl: add global memory stats Vladimir Davydov
2018-09-02 22:27 ` [tarantool-patches] " Konstantin Osipov
2018-09-02 22:27 ` Konstantin Osipov
2018-09-03 8:10 ` Vladimir Davydov
2018-09-02 20:18 ` [PATCH 3/7] vinyl: add global disk stats Vladimir Davydov
2018-09-02 22:30 ` [tarantool-patches] " Konstantin Osipov
2018-09-02 20:18 ` Vladimir Davydov [this message]
2018-09-02 20:18 ` [PATCH 5/7] vinyl: update compact priority usual way on range split/coalesce Vladimir Davydov
2018-09-02 20:18 ` [PATCH 6/7] vinyl: keep track of compaction queue length and debt Vladimir Davydov
2018-09-02 20:19 ` [PATCH 7/7] vinyl: keep track of disk idle time Vladimir Davydov
2018-09-04 11:54 ` Vladimir Davydov
2018-09-04 17:23 ` Vladimir Davydov
2018-09-04 17:23 ` [PATCH 1/8] vinyl: add helper to check whether dump is in progress Vladimir Davydov
2018-09-06 7:33 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 2/8] vinyl: don't use mempool for allocating background tasks Vladimir Davydov
2018-09-06 7:33 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 3/8] vinyl: factor out worker pool from scheduler struct Vladimir Davydov
2018-09-06 7:34 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 4/8] vinyl: move worker allocation closer to task creation Vladimir Davydov
2018-09-06 7:35 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 5/8] vinyl: use separate thread pools for dump and compaction tasks Vladimir Davydov
2018-09-06 7:37 ` Konstantin Osipov
2018-09-06 9:48 ` Vladimir Davydov
2018-09-06 10:32 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 6/8] vinyl: zap vy_worker_pool::idle_worker_count Vladimir Davydov
2018-09-06 7:38 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 7/8] vinyl: don't start scheduler fiber until local recovery is complete Vladimir Davydov
2018-09-06 7:39 ` Konstantin Osipov
2018-09-04 17:23 ` [PATCH 8/8] vinyl: keep track of thread pool idle ratio Vladimir Davydov
2018-09-06 7:49 ` Konstantin Osipov
2018-09-06 8:18 ` Vladimir Davydov
2018-09-06 10:26 ` Konstantin Osipov
2018-09-06 10:52 ` Vladimir Davydov
2018-09-06 10:57 ` Konstantin Osipov
2018-09-06 11:59 ` Vladimir Davydov
2018-09-09 11:41 ` [PATCH 0/7] vinyl: improve stats for throttling Vladimir Davydov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=55436ba89b22a9f490c0642810986672a062cc73.1535917763.git.vdavydov.dev@gmail.com \
--to=vdavydov.dev@gmail.com \
--cc=kostja@tarantool.org \
--cc=tarantool-patches@freelists.org \
--subject='Re: [PATCH 4/7] vinyl: fix force compaction logic' \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox