[taler-grid5k] 79/189: add histograms

[gnunet]

This is an automated email from the git hooks/post-receive script.

marco-boss pushed a commit to branch master
in repository grid5k.

commit b6b72c873ea41ddf7e00bd0cf31cfdcfa6200c89
Author: Boss Marco <bossm8@bfh.ch>
AuthorDate: Sun Mar 13 09:05:46 2022 +0100

    add histograms
---
 configs/etc/monitor/postgres-exporter.yaml | 142 ++++++++++++++---------------
 configs/etc/monitor/promtail.yaml          |  32 +++++--
 2 files changed, 97 insertions(+), 77 deletions(-)

diff --git a/configs/etc/monitor/postgres-exporter.yaml 
b/configs/etc/monitor/postgres-exporter.yaml
index 67c3562..1f4eb37 100644
--- a/configs/etc/monitor/postgres-exporter.yaml
+++ b/configs/etc/monitor/postgres-exporter.yaml
@@ -158,77 +158,77 @@ pg_database:
         usage: "GAUGE"
         description: "Disk space used by the database"
 
-pg_stat_statements:
-  query: "SELECT t2.rolname, t3.datname, substring(query from 1 for 265) as 
query, calls, total_exec_time / 1000 as total_time_seconds, min_exec_time / 
1000 as min_time_seconds, max_exec_time / 1000 as max_time_seconds, 
mean_exec_time / 1000 as mean_time_seconds, stddev_exec_time / 1000 as 
stddev_time_seconds, rows, shared_blks_hit, shared_blks_read, 
shared_blks_dirtied, shared_blks_written, local_blks_hit, local_blks_read, 
local_blks_dirtied, local_blks_written, temp_blks_read, temp_blk [...]
-  master: true
-  metrics:
-    - rolname:
-        usage: "LABEL"
-        description: "Name of user"
-    - datname:
-        usage: "LABEL"
-        description: "Name of database"
-    - query:
-        usage: "LABEL"
-        description: "Query"
-    - calls:
-        usage: "COUNTER"
-        description: "Number of times executed"
-    - total_time_seconds:
-        usage: "COUNTER"
-        description: "Total time spent in the statement, in seconds"
-    - min_time_seconds:
-        usage: "GAUGE"
-        description: "Minimum time spent in the statement, in seconds"
-    - max_time_seconds:
-        usage: "GAUGE"
-        description: "Maximum time spent in the statement, in seconds"
-    - mean_time_seconds:
-        usage: "GAUGE"
-        description: "Mean time spent in the statement, in seconds"
-    - stddev_time_seconds:
-        usage: "GAUGE"
-        description: "Population standard deviation of time spent in the 
statement, in seconds"
-    - rows:
-        usage: "COUNTER"
-        description: "Total number of rows retrieved or affected by the 
statement"
-    - shared_blks_hit:
-        usage: "COUNTER"
-        description: "Total number of shared block cache hits by the statement"
-    - shared_blks_read:
-        usage: "COUNTER"
-        description: "Total number of shared blocks read by the statement"
-    - shared_blks_dirtied:
-        usage: "COUNTER"
-        description: "Total number of shared blocks dirtied by the statement"
-    - shared_blks_written:
-        usage: "COUNTER"
-        description: "Total number of shared blocks written by the statement"
-    - local_blks_hit:
-        usage: "COUNTER"
-        description: "Total number of local block cache hits by the statement"
-    - local_blks_read:
-        usage: "COUNTER"
-        description: "Total number of local blocks read by the statement"
-    - local_blks_dirtied:
-        usage: "COUNTER"
-        description: "Total number of local blocks dirtied by the statement"
-    - local_blks_written:
-        usage: "COUNTER"
-        description: "Total number of local blocks written by the statement"
-    - temp_blks_read:
-        usage: "COUNTER"
-        description: "Total number of temp blocks read by the statement"
-    - temp_blks_written:
-        usage: "COUNTER"
-        description: "Total number of temp blocks written by the statement"
-    - blk_read_time_seconds:
-        usage: "COUNTER"
-        description: "Total time the statement spent reading blocks, in 
seconds (if track_io_timing is enabled, otherwise zero)"
-    - blk_write_time_seconds:
-        usage: "COUNTER"
-        description: "Total time the statement spent writing blocks, in 
seconds (if track_io_timing is enabled, otherwise zero)"
-
+#pg_stat_statements:
+#  query: "SELECT t2.rolname, t3.datname, queryid, calls, total_exec_time / 
1000 as total_time_seconds, min_exec_time / 1000 as min_time_seconds, 
max_exec_time / 1000 as max_time_seconds, mean_exec_time / 1000 as 
mean_time_seconds, stddev_exec_time / 1000 as stddev_time_seconds, rows, 
shared_blks_hit, shared_blks_read, shared_blks_dirtied, shared_blks_written, 
local_blks_hit, local_blks_read, local_blks_dirtied, local_blks_written, 
temp_blks_read, temp_blks_written, blk_read_time / 1000  [...]
+#  master: true
+#  metrics:
+#    - rolname:
+#        usage: "LABEL"
+#        description: "Name of user"
+#    - datname:
+#        usage: "LABEL"
+#        description: "Name of database"
+#    - queryid:
+#        usage: "LABEL"
+#        description: "Query"
+#    - calls:
+#        usage: "COUNTER"
+#        description: "Number of times executed"
+#    - total_time_seconds:
+#        usage: "COUNTER"
+#        description: "Total time spent in the statement, in seconds"
+#    - min_time_seconds:
+#        usage: "GAUGE"
+#        description: "Minimum time spent in the statement, in seconds"
+#    - max_time_seconds:
+#        usage: "GAUGE"
+#        description: "Maximum time spent in the statement, in seconds"
+#    - mean_time_seconds:
+#        usage: "GAUGE"
+#        description: "Mean time spent in the statement, in seconds"
+#    - stddev_time_seconds:
+#        usage: "GAUGE"
+#        description: "Population standard deviation of time spent in the 
statement, in seconds"
+#    - rows:
+#        usage: "COUNTER"
+#        description: "Total number of rows retrieved or affected by the 
statement"
+#    - shared_blks_hit:
+#        usage: "COUNTER"
+#        description: "Total number of shared block cache hits by the 
statement"
+#    - shared_blks_read:
+#        usage: "COUNTER"
+#        description: "Total number of shared blocks read by the statement"
+#    - shared_blks_dirtied:
+#        usage: "COUNTER"
+#        description: "Total number of shared blocks dirtied by the statement"
+#    - shared_blks_written:
+#        usage: "COUNTER"
+#        description: "Total number of shared blocks written by the statement"
+#    - local_blks_hit:
+#        usage: "COUNTER"
+#        description: "Total number of local block cache hits by the statement"
+#    - local_blks_read:
+#        usage: "COUNTER"
+#        description: "Total number of local blocks read by the statement"
+#    - local_blks_dirtied:
+#        usage: "COUNTER"
+#        description: "Total number of local blocks dirtied by the statement"
+#    - local_blks_written:
+#        usage: "COUNTER"
+#        description: "Total number of local blocks written by the statement"
+#    - temp_blks_read:
+#        usage: "COUNTER"
+#        description: "Total number of temp blocks read by the statement"
+#    - temp_blks_written:
+#        usage: "COUNTER"
+#        description: "Total number of temp blocks written by the statement"
+#    - blk_read_time_seconds:
+#        usage: "COUNTER"
+#        description: "Total time the statement spent reading blocks, in 
seconds (if track_io_timing is enabled, otherwise zero)"
+#    - blk_write_time_seconds:
+#        usage: "COUNTER"
+#        description: "Total time the statement spent writing blocks, in 
seconds (if track_io_timing is enabled, otherwise zero)"
+#
 #pg_process_idle:
 #  query: |
 #    WITH
diff --git a/configs/etc/monitor/promtail.yaml 
b/configs/etc/monitor/promtail.yaml
index 172f098..94d98c7 100644
--- a/configs/etc/monitor/promtail.yaml
+++ b/configs/etc/monitor/promtail.yaml
@@ -32,23 +32,43 @@ scrape_configs:
        selector: '{job="proxy"}'
        stages:
        - regex:
-           expression: 
'.*uri=/(?P<ep>[a-zA-Z]+)(?:/\w+)?(?:/(?P<act>[a-zA-Z]+))? 
s=(?P<status>\d{3}).*'
+           expression: 
'.*uri=/(?P<ep>[a-zA-Z]+)(?:/\w+)?(?:/(?P<act>[a-zA-Z]+))? 
s=(?P<status>\d{3}).*rt=(?P<response_time>\d+\.\d+) rl=(?P<request_length>\d+) 
bs=(?P<bytes_sent>\d+).*'
        - template:
            source: endpoint
            template: '{{ printf "%s-%s" .ep .act | trimSuffix "-" }}'
        - labels:
            endpoint:
            status:
-    - match:
-       selector: '{job="proxy"} |~ "s=200" |~ "(/withdraw|/deposit)"'
-       stages:
        - metrics:
-           tps:
+           total_requests:
+             prefix: 'taler_requests_'
              type: Counter
-             description: "Transactions per Second (successful requests to 
/withdraw and /deposit)"
+             description: "Total Requests"
              config:
                match_all: true
                action: inc
+           # 
https://www.robustperception.io/how-does-a-prometheus-histogram-work
+           request_length:
+             prefix: 'taler_requests_'
+             type: Histogram
+             description: "Request Length reported from Nginx"
+             source: request_length
+             config:
+               buckets: [1,10,50,100,200,500,1000,2000,5000] 
+           bytes_sent:
+             prefix: 'taler_requests_'
+             type: Histogram
+             description: "Number of bytes sent, reported from Nginx"
+             source: bytes_sent
+             config:
+               buckets: [1,10,50,100,200,500,1000,2000,5000] 
+           response_time_hist:
+             prefix: 'taler_requests_'
+             type: Histogram
+             description: "Time taken for Nginx to respond"
+             source: response_time
+             config:
+               buckets: 
[0.001,0.0025,0.005,0.010,0.025,0.050,0.1,0.25,0.5,1,2,5]
 - job_name: wallet
   syslog:
     listen_address: 0.0.0.0:1516

-- 
To stop receiving notification emails like this one, please contact
gnunet@gnunet.org.