From: MingXin Liu <mingxinliu@xxxxxxxxxxxxxxx>
Signed-off-by: MingXin Liu <mingxinliu@xxxxxxxxxxxxxxx>
Reviewed-by: Li Wang <liwang@xxxxxxxxxxxxxxx>
---
src/osd/osd_types.cc | 32 ++++++++++++++++++++++++++++++--
src/osd/osd_types.h | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 79 insertions(+), 2 deletions(-)
diff --git a/src/osd/osd_types.cc b/src/osd/osd_types.cc
index a73b46f..ba81889 100644
--- a/src/osd/osd_types.cc
+++ b/src/osd/osd_types.cc
@@ -871,7 +871,6 @@ void pool_snap_info_t::generate_test_instances(list<pool_snap_info_t*>& o)
o.back()->name = "foo";
}
-
// -- pg_pool_t --
void pg_pool_t::dump(Formatter *f) const
@@ -910,6 +909,7 @@ void pg_pool_t::dump(Formatter *f) const
f->dump_int("read_tier", read_tier);
f->dump_int("write_tier", write_tier);
f->dump_string("cache_mode", get_cache_mode_name());
+ f->dump_string("cache_measure", get_cache_measure_name());
f->dump_unsigned("target_max_bytes", target_max_bytes);
f->dump_unsigned("target_max_objects", target_max_objects);
f->dump_unsigned("cache_target_dirty_ratio_micro",
@@ -925,6 +925,11 @@ void pg_pool_t::dump(Formatter *f) const
f->dump_unsigned("hit_set_period", hit_set_period);
f->dump_unsigned("hit_set_count", hit_set_count);
f->dump_unsigned("min_read_recency_for_promote", min_read_recency_for_promote);
+ f->dump_unsigned("hit_set_grade_decay_rate",hit_set_grade_decay_rate);
+ f->open_array_section("grade_table");
+ for (vector<uint32_t>::const_iterator p = grade_table.begin(); p != grade_table.end(); ++p)
+ f->dump_unsigned("grade", *p);
+ f->close_section();
f->dump_unsigned("stripe_width", get_stripe_width());
f->dump_unsigned("expected_num_objects", expected_num_objects);
}
@@ -1226,7 +1231,7 @@ void pg_pool_t::encode(bufferlist& bl, uint64_t features) const
return;
}
- ENCODE_START(17, 5, bl);
+ ENCODE_START(18, 5, bl);
::encode(type, bl);
::encode(size, bl);
::encode(crush_ruleset, bl);
@@ -1268,6 +1273,9 @@ void pg_pool_t::encode(bufferlist& bl, uint64_t features) const
::encode(last_force_op_resend, bl);
::encode(min_read_recency_for_promote, bl);
::encode(expected_num_objects, bl);
+ __u8 m = cache_measure;
+ ::encode(m, bl);
+ ::encode(hit_set_grade_decay_rate, bl);
ENCODE_FINISH(bl);
}
@@ -1385,6 +1393,16 @@ void pg_pool_t::decode(bufferlist::iterator& bl)
} else {
expected_num_objects = 0;
}
+ if (struct_v >= 18) {
+ __u8 v;
+ ::decode(v, bl);
+ cache_measure = (cache_measure_t)v;
+ ::decode(hit_set_grade_decay_rate, bl);
+ set_grade(hit_set_grade_decay_rate, hit_set_count);
+ } else {
+ cache_measure = CACHEMEASURE_ATIME;
+ hit_set_grade_decay_rate = 0;
+ }
DECODE_FINISH(bl);
calc_pg_masks();
}
@@ -1425,12 +1443,16 @@ void pg_pool_t::generate_test_instances(list<pg_pool_t*>& o)
a.tiers.insert(1);
a.tier_of = 2;
a.cache_mode = CACHEMODE_WRITEBACK;
+ a.cache_measure = CACHEMEASURE_ATIME;
a.read_tier = 1;
a.write_tier = 1;
a.hit_set_params = HitSet::Params(new BloomHitSet::Params);
a.hit_set_period = 3600;
a.hit_set_count = 8;
a.min_read_recency_for_promote = 1;
+ a.hit_set_grade_decay_rate = 50;
+ a.grade_table.push_back(1000000);
+ a.grade_table.push_back(500000);
a.set_stripe_width(12345);
a.target_max_bytes = 1238132132;
a.target_max_objects = 1232132;
@@ -1475,6 +1497,8 @@ ostream& operator<<(ostream& out, const pg_pool_t& p)
out << " write_tier " << p.write_tier;
if (p.cache_mode)
out << " cache_mode " << p.get_cache_mode_name();
+ if (p.cache_mode)
+ out << " cache_measure " << p.get_cache_measure_name();
if (p.target_max_bytes)
out << " target_bytes " << p.target_max_bytes;
if (p.target_max_objects)
@@ -1483,6 +1507,10 @@ ostream& operator<<(ostream& out, const pg_pool_t& p)
out << " hit_set " << p.hit_set_params
<< " " << p.hit_set_period << "s"
<< " x" << p.hit_set_count;
+ if (p.cache_measure == pg_pool_t::CACHEMEASURE_TEMP) {
+ out << " decay_rate " << p.hit_set_grade_decay_rate
+ << " grade_table" << p.grade_table;
+ }
}
if (p.min_read_recency_for_promote)
out << " min_read_recency_for_promote " << p.min_read_recency_for_promote;
diff --git a/src/osd/osd_types.h b/src/osd/osd_types.h
index 18f5402..7bea017 100644
--- a/src/osd/osd_types.h
+++ b/src/osd/osd_types.h
@@ -888,6 +888,12 @@ struct pg_pool_t {
CACHEMODE_READFORWARD = 4, ///< forward reads, write to cache flush later
CACHEMODE_READPROXY = 5 ///< proxy reads, write to cache flush later
} cache_mode_t;
+
+ typedef enum {
+ CACHEMEASURE_ATIME = 0, ///< judge hot by atime
+ CACHEMEASURE_TEMP = 1 ///< judge hot by temperature
+ } cache_measure_t;
+
static const char *get_cache_mode_name(cache_mode_t m) {
switch (m) {
case CACHEMODE_NONE: return "none";
@@ -932,6 +938,24 @@ struct pg_pool_t {
}
}
+ static const char *get_cache_measure_name(cache_measure_t m) {
+ switch (m) {
+ case CACHEMEASURE_ATIME: return "atime";
+ case CACHEMEASURE_TEMP: return "temperature";
+ default: return "unknown";
+ }
+ }
+ static cache_measure_t get_cache_measure_from_str(const string& s) {
+ if (s == "atime")
+ return CACHEMEASURE_ATIME;
+ if (s == "temperature")
+ return CACHEMEASURE_TEMP;
+ return (cache_measure_t)-1;
+ }
+ const char *get_cache_measure_name() const {
+ return get_cache_measure_name(cache_measure);
+ }
+
uint64_t flags; ///< FLAG_*
__u8 type; ///< TYPE_*
__u8 size, min_size; ///< number of osds in each pg
@@ -976,6 +1000,7 @@ public:
int64_t read_tier; ///< pool/tier for objecter to direct reads to
int64_t write_tier; ///< pool/tier for objecter to direct writes to
cache_mode_t cache_mode; ///< cache pool mode
+ cache_measure_t cache_measure; ///< cache measure demension,atime or temperature
bool is_tier() const { return tier_of >= 0; }
bool has_tiers() const { return !tiers.empty(); }
@@ -993,6 +1018,7 @@ public:
if (cache_mode != CACHEMODE_NONE)
flags |= FLAG_INCOMPLETE_CLONES;
cache_mode = CACHEMODE_NONE;
+ cache_measure = CACHEMEASURE_ATIME;
target_max_bytes = 0;
target_max_objects = 0;
@@ -1001,6 +1027,8 @@ public:
hit_set_params = HitSet::Params();
hit_set_period = 0;
hit_set_count = 0;
+ hit_set_grade_decay_rate = 0;
+ grade_table.resize(0);
}
uint64_t target_max_bytes; ///< tiering: target max pool size
@@ -1016,6 +1044,25 @@ public:
uint32_t hit_set_period; ///< periodicity of HitSet segments (seconds)
uint32_t hit_set_count; ///< number of periods to retain
uint32_t min_read_recency_for_promote; ///< minimum number of HitSet to check before promote
+ uint32_t hit_set_grade_decay_rate; ///< current hit_set has highest priority on objects
+ ///temperature count,the follow hit_set's priority decay
+ ///by this params than pre hit_set
+ vector<uint32_t> grade_table;
+ void set_grade(uint32_t decay, unsigned size)
+ {
+ unsigned v = 1000000;
+ grade_table.resize(size);
+ for (unsigned i = 0; i < size; i++) {
+ grade_table[i] = v;
+ v = v * (1 - (decay / 100.0));
+ }
+ }
+ uint32_t get_grade(unsigned i)
+ {
+ if (grade_table.size() <= i)
+ return 0;
+ return grade_table[i];
+ }
uint32_t stripe_width; ///< erasure coded stripe size in bytes
@@ -1035,6 +1082,7 @@ public:
pg_num_mask(0), pgp_num_mask(0),
tier_of(-1), read_tier(-1), write_tier(-1),
cache_mode(CACHEMODE_NONE),
+ cache_measure(CACHEMEASURE_ATIME),
target_max_bytes(0), target_max_objects(0),
cache_target_dirty_ratio_micro(0),
cache_target_full_ratio_micro(0),
@@ -1044,6 +1092,7 @@ public:
hit_set_period(0),
hit_set_count(0),
min_read_recency_for_promote(0),
+ hit_set_grade_decay_rate(0),
stripe_width(0),
expected_num_objects(0)
{ }
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
