Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Storages: Add Block pop-up latency metrics #9260

Merged
merged 3 commits into from
Jul 29, 2024
Merged

Storages: Add Block pop-up latency metrics #9260

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d29b538
Storages: Add Block pop-up latency metrics
JinheLin Jul 26, 2024
1941e8b
Update dbms/src/Storages/DeltaMerge/ReadThread/WorkQueue.h
JinheLin Jul 29, 2024
2f14a21
Merge branch 'master' into wq_me
ti-chi-bot[bot] Jul 29, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion dbms/src/Common/TiFlashMetrics.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -863,7 +863,11 @@ static_assert(RAFT_REGION_BIG_WRITE_THRES * 4 < RAFT_REGION_BIG_WRITE_MAX, "Inva
F(type_fg_read, {"type", "fg_read"}), \
F(type_bg_read, {"type", "bg_read"}), \
F(type_fg_write, {"type", "fg_write"}), \
F(type_bg_write, {"type", "bg_write"}))
F(type_bg_write, {"type", "bg_write"})) \
M(tiflash_read_thread_internal_us, \
"Durations of read thread internal components", \
Histogram, \
F(type_block_queue_pop_latency, {{"type", "block_queue_pop_latency"}}, ExpBuckets{1, 2, 20}))


/// Buckets with boundaries [start * base^0, start * base^1, ..., start * base^(size-1)]
Expand Down
21 changes: 17 additions & 4 deletions dbms/src/Storages/DeltaMerge/ReadThread/WorkQueue.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,8 @@ class WorkQueue
std::condition_variable writer_cv;
std::condition_variable finish_cv;
PipeConditionVariable pipe_cv;
std::queue<T> queue;
// <value, push_timestamp_ns>
std::queue<std::pair<T, UInt64>> queue;
bool done;
std::size_t max_size;

Expand All @@ -49,6 +50,12 @@ class WorkQueue
return queue.size() >= max_size;
}

static void reportPopLatency(UInt64 push_timestamp_ns)
{
auto latency_ns = clock_gettime_ns_adjusted(push_timestamp_ns) - push_timestamp_ns;
GET_METRIC(tiflash_read_thread_internal_us, type_block_queue_pop_latency).Observe(latency_ns / 1000.0);
}

public:
/**
* Constructs an empty work queue with an optional max size.
Expand Down Expand Up @@ -99,7 +106,7 @@ class WorkQueue
{
return false;
}
queue.push(std::forward<U>(item));
queue.push(std::make_pair(std::forward<U>(item), clock_gettime_ns()));
peak_queue_size = std::max(queue.size(), peak_queue_size);
if (size != nullptr)
{
Expand All @@ -121,6 +128,7 @@ class WorkQueue
*/
bool pop(T & item)
{
UInt64 push_timestamp_ns = 0;
{
std::unique_lock<std::mutex> lock(mu);
++pop_times;
Expand All @@ -134,10 +142,12 @@ class WorkQueue
assert(done);
return false;
}
item = std::move(queue.front());
item = std::move(queue.front().first);
push_timestamp_ns = queue.front().second;
queue.pop();
}
writer_cv.notify_one();
reportPopLatency(push_timestamp_ns);
return true;
}

Expand All @@ -152,6 +162,7 @@ class WorkQueue
*/
bool tryPop(T & item)
{
UInt64 push_timestamp_ns = 0;
{
std::lock_guard lock(mu);
++pop_times;
Expand All @@ -167,10 +178,12 @@ class WorkQueue
return false;
}
}
item = std::move(queue.front());
item = std::move(queue.front().first);
push_timestamp_ns = queue.front().second;
queue.pop();
}
writer_cv.notify_one();
reportPopLatency(push_timestamp_ns);
return true;
}

Expand Down
128 changes: 128 additions & 0 deletions metrics/grafana/tiflash_summary.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8559,6 +8559,134 @@
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_TEST-CLUSTER}",
"fieldConfig": {
"defaults": {},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 165
},
"hiddenSeries": false,
"id": 292,
"legend": {
"alignAsTable": false,
"avg": true,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null as zero",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "7.5.17",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"exemplar": true,
"expr": "histogram_quantile(0.999, sum(rate(tiflash_read_thread_internal_us_bucket{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$instance\"}[1m])) by (le, type))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "999-{{type}}",
"refId": "A"
},
{
"exemplar": true,
"expr": "histogram_quantile(0.99, sum(rate(tiflash_read_thread_internal_us_bucket{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$instance\"}[1m])) by (le, type))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "99-{{type}}",
"refId": "B"
},
{
"exemplar": true,
"expr": "histogram_quantile(0.95, sum(rate(tiflash_read_thread_internal_us_bucket{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$instance\"}[1m])) by (le, type))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "95-{{type}}",
"refId": "C"
},
{
"exemplar": true,
"expr": "histogram_quantile(0.80, sum(rate(tiflash_read_thread_internal_us_bucket{k8s_cluster=\"$k8s_cluster\", tidb_cluster=\"$tidb_cluster\", instance=~\"$instance\"}[1m])) by (le, type))",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "80-{{type}}",
"refId": "D"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Read Thread Internal Duration",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"$$hashKey": "object:222",
"format": "µs",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"$$hashKey": "object:223",
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
Expand Down