diff options
author | Bob Van Landuyt <bob@vanlanduyt.co> | 2017-11-27 08:28:59 +0100 |
---|---|---|
committer | Bob Van Landuyt <bob@vanlanduyt.co> | 2017-12-11 13:18:39 +0100 |
commit | d4d06bded14bf66b341b67a7771f5f2d1d9f400c (patch) | |
tree | fb523508698bb585676f19a317e66e9bf394cb57 | |
parent | 1eff1bd385a28ccde7d0dc3a991c499ada1a63bd (diff) | |
download | gitlab-ce-d4d06bded14bf66b341b67a7771f5f2d1d9f400c.tar.gz |
Keep track of storage check timings
-rw-r--r-- | doc/administration/monitoring/prometheus/gitlab_metrics.md | 3 | ||||
-rw-r--r-- | lib/gitlab/git/storage/checker.rb | 24 |
2 files changed, 25 insertions, 2 deletions
diff --git a/doc/administration/monitoring/prometheus/gitlab_metrics.md b/doc/administration/monitoring/prometheus/gitlab_metrics.md index 11d5e077a36..f495990d9a4 100644 --- a/doc/administration/monitoring/prometheus/gitlab_metrics.md +++ b/doc/administration/monitoring/prometheus/gitlab_metrics.md @@ -45,8 +45,9 @@ In this experimental phase, only a few metrics are available: | redis_ping_success | Gauge | 9.4 | Whether or not the last redis ping succeeded | | redis_ping_latency_seconds | Gauge | 9.4 | Round trip time of the redis ping | | user_session_logins_total | Counter | 9.4 | Counter of how many users have logged in | -| filesystem_circuitbreaker_latency_seconds | Histogram | 9.5 | Latency of the stat check the circuitbreaker uses to probe a shard | +| filesystem_circuitbreaker_latency_seconds | Gauge | 9.5 | Time spent validating if a storage is accessible | | filesystem_circuitbreaker | Gauge | 9.5 | Wether or not the circuit for a certain shard is broken or not | +| circuitbreaker_storage_check_duration_seconds | Histogram | 10.3 | Time a single storage probe took | ## Metrics shared directory diff --git a/lib/gitlab/git/storage/checker.rb b/lib/gitlab/git/storage/checker.rb index de63cb4b40c..d3c37f82101 100644 --- a/lib/gitlab/git/storage/checker.rb +++ b/lib/gitlab/git/storage/checker.rb @@ -5,6 +5,8 @@ module Gitlab include CircuitBreakerSettings attr_reader :storage_path, :storage, :hostname, :logger + METRICS_MUTEX = Mutex.new + STORAGE_TIMING_BUCKETS = [0.1, 0.15, 0.25, 0.33, 0.5, 1, 1.5, 2.5, 5, 10, 15].freeze def self.check_all(logger = Rails.logger) threads = Gitlab.config.repositories.storages.keys.map do |storage_name| @@ -19,6 +21,17 @@ module Gitlab end end + def self.check_histogram + @check_histogram ||= + METRICS_MUTEX.synchronize do + @check_histogram || Gitlab::Metrics.histogram(:circuitbreaker_storage_check_duration_seconds, + 'Storage check time in seconds', + {}, + STORAGE_TIMING_BUCKETS + ) + end + end + def initialize(storage, logger = Rails.logger) @storage = storage config = Gitlab.config.repositories.storages[@storage] @@ -45,7 +58,7 @@ module Gitlab end def check - if Gitlab::Git::Storage::ForkedStorageCheck.storage_available?(storage_path, storage_timeout, access_retries) + if perform_access_check track_storage_accessible true else @@ -57,6 +70,15 @@ module Gitlab private + def perform_access_check + start_time = Gitlab::Metrics::System.monotonic_time + + Gitlab::Git::Storage::ForkedStorageCheck.storage_available?(storage_path, storage_timeout, access_retries) + ensure + execution_time = Gitlab::Metrics::System.monotonic_time - start_time + self.class.check_histogram.observe({ storage: storage }, execution_time) + end + def track_storage_inaccessible first_failure = current_failure_info.first_failure || Time.now last_failure = Time.now |