Project

General

Profile

Actions
Copy link

Bug #15010

closed

simple->async peer got "failed lossy con, dropping message"

Added by Sage Weil about 8 years ago. Updated about 8 years ago.

Status:
Can't reproduce
Priority:
High
Assignee:
Haomai Wang
Category:
-
Target version:
-
% Done:

0%

Source:
Q/A
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

2016-03-08 05:42:17.669564 7f26b1d12700  0 -- 172.21.15.47:6805/2508 >> 172.21.15.64:6801/3976 pipe(0x7f26ee3b7400 sd=70 :6805 s=0 pgs=0 cs=0 l=0 c=0x7f26ee341000).injecting socket failure
2016-03-08 05:42:17.669651 7f26b1d12700 10 osd.4 3  new session 0x7f26ee083ee0 con=0x7f26ee341000 addr=172.21.15.64:6801/3976
2016-03-08 05:42:17.669672 7f26b1d12700 10 osd.4 3  session 0x7f26ee083ee0 osd.0 has caps osdcap[grant(*)] 'allow *'
...
2016-03-08 05:42:17.671738 7f26cd767700  1 -- 172.21.15.47:6805/2508 --> 172.21.15.64:6801/3976 -- pg_query(0.15 epoch 3) v3 -- ?+0 0x7f26ee2b6e00 con 0x7f26ee341000
2016-03-08 05:42:17.671747 7f26cd767700  0 -- 172.21.15.47:6805/2508 submit_message pg_query(0.15 epoch 3) v3 remote, 172.21.15.64:6801/3976, failed lossy con, dropping message 0x7f26ee2b6e00

and on the other end (async),

2016-03-08 05:42:17.672869 7fa2ed769700  1 -- 172.21.15.64:6801/3976 >> 172.21.15.47:6805/2508 conn(0x7fa30c9b8800 sd=-1 :-1 s=STATE_CONNECTING pgs=0 cs=0 l=0). == tx == 0x7fa30c8d4600 pg_query(0.c epoch 3) v3
2016-03-08 05:42:17.673922 7fa2f9102700  1 -- 172.21.15.64:6801/3976 >> 172.21.15.47:6805/2508 conn(0x7fa30c9b8800 sd=69 :-1 s=STATE_CONNECTING_WAIT_CONNECT_REPLY pgs=0 cs=0 l=0).read_bulk peer close file descriptor 69
2016-03-08 05:42:17.673944 7fa2f9102700  1 -- 172.21.15.64:6801/3976 >> 172.21.15.47:6805/2508 conn(0x7fa30c9b8800 sd=69 :-1 s=STATE_CONNECTING_WAIT_CONNECT_REPLY pgs=0 cs=0 l=0).read_until read failed
2016-03-08 05:42:17.673957 7fa2f9102700  1 -- 172.21.15.64:6801/3976 >> 172.21.15.47:6805/2508 conn(0x7fa30c9b8800 sd=69 :-1 s=STATE_CONNECTING_WAIT_CONNECT_REPLY pgs=0 cs=0 l=0)._process_connection read connect reply failed

Actions
Copy link

Also available in: Atom PDF