Actions
Bug #41754
openUse dump_stream() instead of dump_float() for floats where max precision isn't helpful
Status:
New
Priority:
Normal
Assignee:
David Zafman
Category:
-
Target version:
-
% Done:
0%
Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(RADOS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
Some examples from osd dump are below. The full_ratio is .95, backfill_ratio .90 and nearfull_ratio .85.
"full_ratio": 0.949999988079071, "backfillfull_ratio": 0.8999999761581421, "nearfull_ratio": 0.8500000238418579,
Some fields from osd dump I'm not sure about.
"weight": 0.904632568359375, "primary_affinity": 0.451995849609375,
Another example of useless precision:
$ ceph daemon osd.0 compact { "elapsed_time": 0.087996230999999994 }
Actions