Hi,
We observe high apply_latency(ms) and poor write performance I believe.
In logs there are repetitive slow request warnings related different OSDs and servers.
ceph versions 12.2.2
Cluster HW description:
9x Dell PowerEdge R730xd
1x Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz (10C/20T)
256 GB 2133 MHz DDR4
PERC H730 Mini 1GB cache
12x 4TB TOSHIBA MG04ACA400N (each disk configured as RAID 0 for single OSD)
2x 480GB SSDSC2BB480G7R (in RAID 1 for operating system)
1x NVMe PCIe SSD - Intel SSD DC D3700 Series for journaling, one for 12 OSDs
1x QLogic 57800 2x 10Gb DAC SFP+ and 2x 1Gb (configured as 2x10Gb in 802.3ad Dynamic link aggregation)
/etc/ceph/ceph.conf
[global]
fsid = 1023c49f-3b10-42de-9f62-9b122db32a9a
mon_initial_members = host01,host02,host03
mon_host = 10.212.32.18,10.212.32.19,10.212.32.20
auth_supported = cephx
public_network = 10.212.32.0/24
cluster_network = 10.212.14.0/24
rgw thread pool size = 256
[client.rgw.host01]
rgw host = host01
rgw enable usage log = true
[client.rgw.host02]
rgw host = host02
rgw enable usage log = true
[client.rgw.host03]
rgw host = host03
rgw enable usage log = true
[osd]
filestore xattr use omap = true
osd journal size = 10240
osd mount options xfs = noatime,inode64,logbsize=256k,logbufs=8
osd crush location hook = /usr/bin/ceph-crush-location.sh
osd pool default size = 3
[mon]
mon compact on start = true
mon compact on trim = true
OSDs topology as below. Actually I wonder why some OSDs have "hdd" class assigned.
ID CLASS WEIGHT REWEIGHT SIZE USE AVAIL %USE VAR PGS TYPE NAME
-1 392.73273 - 385T 236T 149T 61.24 1.00 - root default
-6 392.73273 - 385T 236T 149T 61.24 1.00 - region region01
-5 392.73273 - 385T 236T 149T 61.24 1.00 - datacenter dc01
-4 392.73273 - 385T 236T 149T 61.24 1.00 - room room01
-8 43.63699 - 44684G 26573G 18111G 59.47 0.97 - rack rack01
-7 43.63699 - 44684G 26573G 18111G 59.47 0.97 - host host01
0 3.63599 1.00000 3723G 2405G 1318G 64.59 1.05 210 osd.0
2 3.63599 1.00000 3723G 2004G 1719G 53.82 0.88 190 osd.2
4 3.63599 1.00000 3723G 2460G 1262G 66.08 1.08 214 osd.4
6 3.63599 1.00000 3723G 2474G 1249G 66.45 1.09 203 osd.6
8 3.63599 1.00000 3723G 2308G 1415G 61.99 1.01 220 osd.8
11 3.63599 1.00000 3723G 2356G 1367G 63.28 1.03 214 osd.11
12 3.63599 1.00000 3723G 2303G 1420G 61.86 1.01 206 osd.12
14 3.63599 1.00000 3723G 1920G 1803G 51.57 0.84 178 osd.14
16 3.63599 1.00000 3723G 2236G 1486G 60.07 0.98 203 osd.16
18 3.63599 1.00000 3723G 2203G 1520G 59.17 0.97 193 osd.18
20 3.63599 1.00000 3723G 1904G 1819G 51.15 0.84 179 osd.20
22 3.63599 1.00000 3723G 1995G 1728G 53.58 0.88 192 osd.22
-3 43.63699 - 44684G 27090G 17593G 60.63 0.99 - rack rack02
-2 43.63699 - 44684G 27090G 17593G 60.63 0.99 - host host02
1 hdd 3.63599 1.00000 3723G 2447G 1275G 65.74 1.07 213 osd.1
3 hdd 3.63599 1.00000 3723G 2696G 1027G 72.41 1.18 210 osd.3
5 hdd 3.63599 1.00000 3723G 2290G 1433G 61.51 1.00 188 osd.5
7 hdd 3.63599 1.00000 3723G 2171G 1551G 58.33 0.95 194 osd.7
9 hdd 3.63599 1.00000 3723G 2129G 1594G 57.18 0.93 204 osd.9
10 hdd 3.63599 1.00000 3723G 2153G 1570G 57.82 0.94 184 osd.10
13 hdd 3.63599 1.00000 3723G 2142G 1580G 57.55 0.94 188 osd.13
15 hdd 3.63599 1.00000 3723G 2147G 1576G 57.66 0.94 192 osd.15
17 hdd 3.63599 1.00000 3723G 2093G 1630G 56.21 0.92 201 osd.17
19 hdd 3.63599 1.00000 3723G 2079G 1643G 55.86 0.91 192 osd.19
21 hdd 3.63599 1.00000 3723G 2266G 1457G 60.87 0.99 201 osd.21
23 hdd 3.63599 1.00000 3723G 2472G 1251G 66.39 1.08 197 osd.23
-10 43.63699 - 44684G 27247G 17436G 60.98 1.00 - rack rack03
-9 43.63699 - 44684G 27247G 17436G 60.98 1.00 - host host03
24 3.63599 1.00000 3723G 2289G 1433G 61.49 1.00 195 osd.24
25 3.63599 1.00000 3723G 2584G 1138G 69.42 1.13 217 osd.25
26 3.63599 1.00000 3723G 2183G 1539G 58.65 0.96 198 osd.26
28 3.63599 1.00000 3723G 2540G 1182G 68.23 1.11 215 osd.28
30 3.63599 1.00000 3723G 2134G 1589G 57.31 0.94 207 osd.30
32 3.63599 1.00000 3723G 1715G 2008G 46.06 0.75 183 osd.32
34 3.63599 1.00000 3723G 2576G 1146G 69.20 1.13 219 osd.34
36 3.63599 1.00000 3723G 2166G 1557G 58.18 0.95 208 osd.36
38 3.63599 1.00000 3723G 2050G 1673G 55.06 0.90 191 osd.38
40 3.63599 1.00000 3723G 2542G 1181G 68.28 1.11 223 osd.40
42 3.63599 1.00000 3723G 2063G 1660G 55.42 0.90 181 osd.42
44 3.63599 1.00000 3723G 2399G 1324G 64.44 1.05 197 osd.44
-12 43.63699 - 44684G 27152G 17531G 60.76 0.99 - rack rack04
-11 43.63699 - 44684G 27152G 17531G 60.76 0.99 - host host04
27 3.63599 1.00000 3723G 2479G 1243G 66.60 1.09 212 osd.27
29 3.63599 1.00000 3723G 2646G 1077G 71.07 1.16 214 osd.29
31 3.63599 1.00000 3723G 2217G 1506G 59.55 0.97 202 osd.31
33 3.63599 1.00000 3723G 2073G 1650G 55.68 0.91 198 osd.33
35 3.63599 1.00000 3723G 2661G 1061G 71.48 1.17 205 osd.35
37 3.63599 1.00000 3723G 2097G 1626G 56.32 0.92 181 osd.37
39 3.63599 1.00000 3723G 1949G 1774G 52.35 0.85 196 osd.39
41 3.63599 1.00000 3723G 2205G 1518G 59.23 0.97 188 osd.41
43 3.63599 1.00000 3723G 2417G 1306G 64.92 1.06 214 osd.43
45 3.63599 1.00000 3723G 1925G 1798G 51.71 0.84 189 osd.45
46 3.63599 1.00000 3723G 2235G 1488G 60.03 0.98 208 osd.46
47 3.63599 1.00000 3723G 2243G 1480G 60.24 0.98 195 osd.47
-14 43.63699 - 37236G 25721G 11515G 69.08 1.13 - rack rack05
-13 43.63699 - 37236G 25721G 11515G 69.08 1.13 - host host05
48 3.63599 1.00000 3723G 2160G 1563G 58.01 0.95 213 osd.48
49 3.63599 1.00000 3723G 2603G 1120G 69.91 1.14 216 osd.49
50 3.63599 1.00000 3723G 2497G 1225G 67.08 1.10 220 osd.50
51 3.63599 1.00000 3723G 2613G 1110G 70.17 1.15 223 osd.51
52 3.63599 0 0 0 0 0 0 0 osd.52
53 3.63599 1.00000 3723G 2869G 854G 77.05 1.26 235 osd.53
54 3.63599 1.00000 3723G 3021G 702G 81.14 1.32 245 osd.54
55 3.63599 1.00000 3723G 2190G 1533G 58.83 0.96 209 osd.55
56 3.63599 0 0 0 0 0 0 0 osd.56
57 3.63599 1.00000 3723G 2651G 1072G 71.21 1.16 223 osd.57
58 3.63599 1.00000 3723G 2413G 1310G 64.81 1.06 198 osd.58
59 3.63599 1.00000 3723G 2701G 1021G 72.56 1.18 226 osd.59
-16 43.63699 - 44684G 28445G 16238G 63.66 1.04 - rack rack06
-15 43.63699 - 44684G 28445G 16238G 63.66 1.04 - host host06
60 hdd 3.63599 1.00000 3723G 1994G 1728G 53.57 0.87 175 osd.60
61 hdd 3.63599 1.00000 3723G 2531G 1192G 67.97 1.11 216 osd.61
62 hdd 3.63599 1.00000 3723G 2472G 1251G 66.40 1.08 217 osd.62
63 hdd 3.63599 1.00000 3723G 2588G 1135G 69.50 1.13 195 osd.63
64 hdd 3.63599 1.00000 3723G 2804G 919G 75.30 1.23 216 osd.64
65 hdd 3.63599 1.00000 3723G 2534G 1188G 68.08 1.11 208 osd.65
66 hdd 3.63599 1.00000 3723G 2362G 1361G 63.44 1.04 204 osd.66
67 hdd 3.63599 1.00000 3723G 2497G 1225G 67.08 1.10 214 osd.67
68 hdd 3.63599 1.00000 3723G 1291G 2432G 34.68 0.57 157 osd.68
69 hdd 3.63599 1.00000 3723G 2325G 1397G 62.46 1.02 192 osd.69
70 hdd 3.63599 1.00000 3723G 2590G 1133G 69.57 1.14 210 osd.70
71 hdd 3.63599 1.00000 3723G 2451G 1272G 65.83 1.08 207 osd.71
-18 43.63699 - 44684G 28525G 16158G 63.84 1.04 - rack rack07
-17 43.63699 - 44684G 28525G 16158G 63.84 1.04 - host host07
72 3.63599 1.00000 3723G 2415G 1307G 64.88 1.06 197 osd.72
73 3.63599 1.00000 3723G 2216G 1507G 59.52 0.97 188 osd.73
74 3.63599 1.00000 3723G 2421G 1301G 65.04 1.06 220 osd.74
75 3.63599 1.00000 3723G 2642G 1080G 70.97 1.16 207 osd.75
76 3.63599 1.00000 3723G 2307G 1416G 61.97 1.01 204 osd.76
77 3.63599 1.00000 3723G 2341G 1381G 62.89 1.03 200 osd.77
78 3.63599 1.00000 3723G 2312G 1410G 62.12 1.01 188 osd.78
79 3.63599 1.00000 3723G 2166G 1557G 58.18 0.95 183 osd.79
80 3.63599 1.00000 3723G 2458G 1264G 66.03 1.08 221 osd.80
81 3.63599 1.00000 3723G 2126G 1596G 57.12 0.93 182 osd.81
82 3.63599 1.00000 3723G 2442G 1281G 65.58 1.07 189 osd.82
83 3.63599 1.00000 3723G 2672G 1051G 71.76 1.17 214 osd.83
-20 87.27377 - 89368G 50955G 38412G 57.02 0.93 - rack rack08
-19 43.63699 - 44684G 25780G 18903G 57.70 0.94 - host host08
84 3.63599 1.00000 3723G 2084G 1638G 55.99 0.91 179 osd.84
85 3.63599 1.00000 3723G 2121G 1602G 56.96 0.93 193 osd.85
86 3.63599 1.00000 3723G 2131G 1591G 57.25 0.93 186 osd.86
87 3.63599 1.00000 3723G 2343G 1380G 62.94 1.03 200 osd.87
88 3.63599 1.00000 3723G 2120G 1603G 56.94 0.93 166 osd.88
89 3.63599 1.00000 3723G 2175G 1548G 58.43 0.95 161 osd.89
90 3.63599 1.00000 3723G 1974G 1749G 53.02 0.87 184 osd.90
91 3.63599 1.00000 3723G 1942G 1781G 52.17 0.85 171 osd.91
92 3.63599 1.00000 3723G 2281G 1442G 61.27 1.00 169 osd.92
93 3.63599 1.00000 3723G 2103G 1620G 56.48 0.92 190 osd.93
94 3.63599 1.00000 3723G 2326G 1397G 62.48 1.02 206 osd.94
95 3.63599 1.00000 3723G 2175G 1548G 58.42 0.95 186 osd.95
-21 43.63678 - 44684G 25175G 19508G 56.34 0.92 - host host09
96 hdd 3.63640 1.00000 3723G 2434G 1289G 65.38 1.07 191 osd.96
97 hdd 3.63640 1.00000 3723G 2175G 1547G 58.44 0.95 183 osd.97
98 hdd 3.63640 1.00000 3723G 1771G 1951G 47.59 0.78 171 osd.98
99 hdd 3.63640 1.00000 3723G 2433G 1290G 65.34 1.07 201 osd.99
100 hdd 3.63640 1.00000 3723G 2098G 1625G 56.35 0.92 175 osd.100
101 hdd 3.63640 1.00000 3723G 2175G 1547G 58.43 0.95 188 osd.101
102 hdd 3.63640 1.00000 3723G 1741G 1982G 46.77 0.76 172 osd.102
103 hdd 3.63640 1.00000 3723G 2123G 1600G 57.02 0.93 173 osd.103
104 hdd 3.63640 1.00000 3723G 1967G 1755G 52.85 0.86 177 osd.104
105 hdd 3.63640 1.00000 3723G 2283G 1440G 61.32 1.00 162 osd.105
106 hdd 3.63640 1.00000 3723G 2021G 1702G 54.29 0.89 184 osd.106
107 hdd 3.63640 1.00000 3723G 1947G 1776G 52.30 0.85 194 osd.107
TOTAL 385T 236T 149T 61.24
MIN/MAX VAR: 0.57/1.32 STDDEV: 7.11
Output of "ceph osd perf" when "ceph status" shows traffic like "client: 679 MB/s rd, 186 MB/s wr, 1200 op/s rd, 790 op/s wr". Most of this traffic goes via RGW.
osd commit_latency(ms) apply_latency(ms)
107 0 22
106 0 1
105 0 0
104 0 22
103 0 13
102 0 8
101 0 2
100 0 28
99 0 25
98 0 542
97 0 418
45 0 23
44 0 26
43 0 1
42 0 9
41 0 27
40 0 0
39 0 1189
38 0 9
37 0 4
36 0 625
35 0 43
34 0 4
33 0 143
32 0 8
31 0 1
30 0 21
29 0 33
28 0 11
27 0 40
26 0 7
25 0 6
24 0 20
23 0 5
22 0 6
9 0 2
8 0 71
7 0 2
6 0 35
5 0 549
4 0 6
0 0 861
1 0 15
2 0 19
3 0 2
10 0 4
11 0 378
12 0 19
13 0 1
14 0 6
15 0 4
16 0 1040
17 0 7
18 0 8
19 0 185
20 0 32
21 0 855
46 0 32
47 0 4
48 0 7
49 0 4
50 0 7
51 0 18
53 0 3
54 0 87
55 0 4
56 0 0
57 0 1
58 0 49
59 0 6
60 0 5
61 0 19
62 0 67
63 0 0
64 0 423
65 0 26
66 0 30
67 0 74
68 0 6
69 0 4
70 0 48
71 0 1900
72 0 24
73 0 7
74 0 379
75 0 4
76 0 9
77 0 19
78 0 14
79 0 135
80 0 1736
81 0 6
82 0 2504
83 0 24
84 0 8
85 0 10
86 0 13
87 0 142
88 0 68
89 0 28
90 0 3
91 0 14
92 0 14
93 0 12
94 0 47
95 0 39
96 0 8
All OSDs report slow requests
# zgrep 'slow request' /var/log/ceph/ceph.log* | egrep -io ' osd\.[0-9]*' |sort |uniq -c
1538 osd.0
1292 osd.1
752 osd.10
640 osd.100
10456 osd.101
2058 osd.102
2174 osd.103
1898 osd.104
1556 osd.105
2332 osd.106
786 osd.107
2408 osd.11
5222 osd.12
224 osd.13
2858 osd.14
238 osd.15
1880 osd.16
566 osd.17
120 osd.18
284 osd.19
896 osd.2
1840 osd.20
1466 osd.21
1218 osd.22
1066 osd.23
2470 osd.24
1640 osd.25
3584 osd.26
10912 osd.27
2954 osd.28
1736 osd.29
570 osd.3
1266 osd.30
298 osd.31
30 osd.32
4528 osd.33
4260 osd.34
4542 osd.35
374 osd.36
2820 osd.37
158 osd.38
748 osd.39
26816 osd.4
3378 osd.40
628 osd.41
16358 osd.42
454 osd.43
2798 osd.44
11378 osd.45
2280 osd.46
1374 osd.47
1660 osd.48
1122 osd.49
174 osd.5
1212 osd.50
1542 osd.51
2366 osd.53
2930 osd.54
196 osd.55
2008 osd.57
1796 osd.58
1644 osd.59
12974 osd.6
208 osd.60
644 osd.61
1230 osd.62
1018 osd.63
1446 osd.64
430 osd.65
512 osd.66
1782 osd.67
96 osd.68
1054 osd.69
596 osd.7
760 osd.70
1160 osd.71
648 osd.72
638 osd.73
752 osd.74
2196 osd.75
568 osd.76
1540 osd.77
944 osd.78
400 osd.79
516 osd.8
2494 osd.80
152 osd.81
1528 osd.82
846 osd.83
1218 osd.84
676 osd.85
1500 osd.86
630 osd.87
618 osd.88
106 osd.89
282 osd.9
972 osd.90
2442 osd.91
1056 osd.92
996 osd.93
1366 osd.94
1112 osd.95
474 osd.96
990 osd.97
342 osd.98
4906 osd.99
Example log
2018-01-30 10:31:39.865054 mon.host01 mon.0 10.212.32.18:6789/0 695886 : cluster [WRN] Health check update: 57 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:31:44.865536 mon.host01 mon.0 10.212.32.18:6789/0 695887 : cluster [WRN] Health check update: 56 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:31:43.408679 osd.85 osd.85 10.212.32.25:6810/142783 4357 : cluster [WRN] 56 slow requests, 2 included below; oldest blocked for > 54.329588 secs
2018-01-30 10:31:43.408683 osd.85 osd.85 10.212.32.25:6810/142783 4358 : cluster [WRN] slow request 30.391140 seconds old, received at 2018-01-30 10:31:13.017492: osd_op(client.612334.0:119664853 3.3cca000a 3.3cca000a (undecoded) ack+ondisk+write+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:31:43.408686 osd.85 osd.85 10.212.32.25:6810/142783 4359 : cluster [WRN] slow request 30.359503 seconds old, received at 2018-01-30 10:31:13.049129: osd_op(client.612334.0:119664855 3.3cca000a 3.3cca000a (undecoded) ack+ondisk+write+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:31:50.891971 mon.host01 mon.0 10.212.32.18:6789/0 695888 : cluster [INF] Health check cleared: REQUEST_SLOW (was: 56 slow requests are blocked > 32 sec)
2018-01-30 10:31:50.892042 mon.host01 mon.0 10.212.32.18:6789/0 695889 : cluster [INF] Cluster is now healthy
2018-01-30 10:31:52.947008 mon.host01 mon.0 10.212.32.18:6789/0 695890 : cluster [WRN] Health check failed: 1 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:31:54.125045 mon.host01 mon.0 10.212.32.18:6789/0 695891 : cluster [INF] mon.1 10.212.32.19:6789/0
2018-01-30 10:31:54.125098 mon.host01 mon.0 10.212.32.18:6789/0 695892 : cluster [INF] mon.2 10.212.32.20:6789/0
2018-01-30 10:31:56.146267 mon.host01 mon.0 10.212.32.18:6789/0 695893 : cluster [WRN] overall HEALTH_WARN 1 slow requests are blocked > 32 sec
2018-01-30 10:31:59.866730 mon.host01 mon.0 10.212.32.18:6789/0 695894 : cluster [WRN] Health check update: 3 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:32:04.867163 mon.host01 mon.0 10.212.32.18:6789/0 695896 : cluster [WRN] Health check update: 6 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:32:05.722529 osd.11 osd.11 10.212.32.18:6812/94831 5792 : cluster [WRN] 3 slow requests, 3 included below; oldest blocked for > 30.713577 secs
2018-01-30 10:32:05.722536 osd.11 osd.11 10.212.32.18:6812/94831 5793 : cluster [WRN] slow request 30.023513 seconds old, received at 2018-01-30 10:31:35.698959: osd_op(client.858110.0:109814110 3.6a6d3d03 3.6a6d3d03 (undecoded) ack+ondisk+write+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:05.722539 osd.11 osd.11 10.212.32.18:6812/94831 5794 : cluster [WRN] slow request 30.188061 seconds old, received at 2018-01-30 10:31:35.534411: osd_op(client.858110.0:109814108 3.6a6d3d03 3.6a6d3d03 (undecoded) ack+ondisk+write+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:05.722542 osd.11 osd.11 10.212.32.18:6812/94831 5795 : cluster [WRN] slow request 30.713577 seconds old, received at 2018-01-30 10:31:35.008895: osd_op(client.864319.0:1526442 20.21bs0 20.da47561b (undecoded) ondisk+read+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:08.722925 osd.11 osd.11 10.212.32.18:6812/94831 5796 : cluster [WRN] 4 slow requests, 1 included below; oldest blocked for > 33.713980 secs
2018-01-30 10:32:08.722930 osd.11 osd.11 10.212.32.18:6812/94831 5797 : cluster [WRN] slow request 30.132129 seconds old, received at 2018-01-30 10:31:38.590746: osd_op(client.864319.0:1526720 20.21bs0 20.2af5361b (undecoded) ondisk+read+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:11.723286 osd.11 osd.11 10.212.32.18:6812/94831 5798 : cluster [WRN] 5 slow requests, 1 included below; oldest blocked for > 36.714352 secs
2018-01-30 10:32:11.723290 osd.11 osd.11 10.212.32.18:6812/94831 5799 : cluster [WRN] slow request 30.963475 seconds old, received at 2018-01-30 10:31:40.759772: osd_op(client.834441.0:1569804 20.21bs0 20.cf3c321b (undecoded) ondisk+read+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:13.723602 osd.11 osd.11 10.212.32.18:6812/94831 5800 : cluster [WRN] 6 slow requests, 1 included below; oldest blocked for > 38.714655 secs
2018-01-30 10:32:13.723607 osd.11 osd.11 10.212.32.18:6812/94831 5801 : cluster [WRN] slow request 30.933479 seconds old, received at 2018-01-30 10:31:42.790071: osd_op(client.612286.0:59425229 3.e2431d03 3.e2431d03 (undecoded) ack+ondisk+write+known_if_redirected e5269) currently queued_for_pg
2018-01-30 10:32:23.857767 mon.host01 mon.0 10.212.32.18:6789/0 695897 : cluster [INF] Health check cleared: REQUEST_SLOW (was: 6 slow requests are blocked > 32 sec)
2018-01-30 10:32:23.857841 mon.host01 mon.0 10.212.32.18:6789/0 695898 : cluster [INF] Cluster is now healthy
2018-01-30 10:32:25.105695 mon.host01 mon.0 10.212.32.18:6789/0 695899 : cluster [WRN] Health check failed: 4 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:32:34.869380 mon.host01 mon.0 10.212.32.18:6789/0 695900 : cluster [WRN] Health check update: 6 slow requests are blocked > 32 sec (REQUEST_SLOW)
2018-01-30 10:32:30.812261 osd.97 osd.97 10.212.32.26:6822/9220 3691 : cluster [WRN] 1 slow requests, 1 included below; oldest blocked for > 30.393065 secs
2018-01-30 10:32:30.812265 osd.97 osd.97 10.212.32.26:6822/9220 3692 : cluster [WRN] slow request 30.393065 seconds old, received at 2018-01-30 10:32:00.419168: osd_op(client.1010840.0:1005983 20.13fs0 20.4245d13f (undecoded) ondisk+read+known_if_redirected e5269) currently queued_for_pg
Any not default ceph.conf options to make better use of cluster configuration?
So far we increased value for "rgw thread pool size = 256"
What throughput can I expect from above configuration ? I see peaks like 2GBps reads and 100MBps writes.
Thanks
Jakub
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
