Hi, We’ve observed some suspicious memory leak problems of MGR since upgraded to Nautilus. Yesterday I upgrade our cluster to the latest 14.2.10 and this problem seems still reproducible. According to the monitoring chart (memory usage of the active mgr node), the memory consumption started to increase with higher velocity at about 21:40pm. Up to now the reserved memory of mgr is about 8.3G according to top. I also checked the log of mgr and found that from 21:38:40, a message "client.0 ms_handle_reset on v2:10.3.1.3:6800/6” was produced every second:
2020-06-29 21:38:24.173 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9979: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 8.1 MiB/s rd, 21 MiB/s wr, 673 op/s 2020-06-29 21:38:26.180 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9980: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 9.6 MiB/s rd, 26 MiB/s wr, 764 op/s 2020-06-29 21:38:28.183 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9981: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 9.3 MiB/s rd, 23 MiB/s wr, 667 op/s 2020-06-29 21:38:30.186 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9982: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 9.3 MiB/s rd, 22 MiB/s wr, 661 op/s 2020-06-29 21:38:32.191 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9983: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 8.1 MiB/s rd, 21 MiB/s wr, 683 op/s 2020-06-29 21:38:34.195 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9984: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 4.0 MiB/s rd, 17 MiB/s wr, 670 op/s 2020-06-29 21:38:36.200 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9985: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 2.4 MiB/s rd, 15 MiB/s wr, 755 op/s 2020-06-29 21:38:38.203 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9986: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.2 MiB/s rd, 12 MiB/s wr, 668 op/s 2020-06-29 21:38:40.207 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9987: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.1 MiB/s rd, 12 MiB/s wr, 681 op/s 2020-06-29 21:38:40.887 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:41.887 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:42.213 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9988: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.2 MiB/s rd, 13 MiB/s wr, 735 op/s 2020-06-29 21:38:42.887 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:43.887 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:44.216 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9989: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 982 KiB/s rd, 12 MiB/s wr, 687 op/s 2020-06-29 21:38:44.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:45.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:46.222 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9990: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.2 MiB/s rd, 17 MiB/s wr, 789 op/s 2020-06-29 21:38:46.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:47.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:48.225 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9991: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.2 MiB/s rd, 15 MiB/s wr, 684 op/s 2020-06-29 21:38:48.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:49.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:50.228 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9992: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 940 KiB/s rd, 16 MiB/s wr, 674 op/s 2020-06-29 21:38:50.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:51.888 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:52.235 7f2ecab7a700 0 log_channel(cluster) log [DBG] : pgmap v9993: 1824 pgs: 3 active+clean+scrubbing+deep, 1821 active+clean; 54 TiB data, 169 TiB used, 153 TiB / 322 TiB avail; 1.3 MiB/s rd, 19 MiB/s wr, 752 op/s 2020-06-29 21:38:52.889 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6 2020-06-29 21:38:53.889 7f2edbec3700 0 client.0 ms_handle_reset on v2:10.3.1.3:6800/6
I enable the debug log of another cluster which has the same problem, the log is attached
Any thoughts about this issue? BR, Xu Yun
_______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
