mirror/haproxy
1
0
Fork 0
mirror of http://git.haproxy.org/git/haproxy.git synced 2026-02-20 19:13:37 +02:00
Code Issues Packages Projects Releases Wiki Activity

MINOR: activity: report the average loop time in "show activity"

Browse Source 
Since we know the time it takes to process everything between two poll()
calls, we can use this as the max latency measurement any task will
experience and average it.

This code does this, and reports in "show activity" the average of this
loop time over the last 1024 poll() loops, for each thread. It will vary
quickly at high loads and slowly under low to moderate loads, depending
on the rate at which poll() is called. The latency a task experiences
is expected to be half of this on average.
This commit is contained in:
Willy Tarreau
2018-11-22 08:42:42 +01:00
parent 609aad9e73
commit baba82fe70
3 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/cli.c
View File

@@ -1004,6 +1004,7 @@ static int cli_io_handler_show_activity(struct appctx *appctx)
chunk_appendf(&trash, "\ncpust_tot:"); for (thr = 0; thr < global.nbthread; thr++) chunk_appendf(&trash, " %u", activity[thr].cpust_total/2);
chunk_appendf(&trash, "\ncpust_1s:"); for (thr = 0; thr < global.nbthread; thr++) chunk_appendf(&trash, " %u", read_freq_ctr(&activity[thr].cpust_1s)/2);
chunk_appendf(&trash, "\ncpust_15s:"); for (thr = 0; thr < global.nbthread; thr++) chunk_appendf(&trash, " %u", read_freq_ctr_period(&activity[thr].cpust_15s, 15000)/2);
chunk_appendf(&trash, "\navg_loop_us:"); for (thr = 0; thr < global.nbthread; thr++) chunk_appendf(&trash, " %u", swrate_avg(activity[thr].avg_loop_us, TIME_STATS_SAMPLES));
chunk_appendf(&trash, "\n");