Hi,
In the meantime I already tried with upgrading the cluster to 0.84, to see if that made a difference, and it seems it does.
I can't reproduce the crashing osds by doing a 'rados -p ecdata ls' anymore.
But now the cluster detect it is inconsistent:
cluster 82766e04-585b-49a6-a0ac-c13d9ffd0a7d
health HEALTH_ERR 40 pgs inconsistent; 40 scrub errors; too
few pgs per osd (4 < min 20); mon.ceph002 low disk space
monmap e3: 3 mons at
{ceph001=10.141.8.180:6789/0,ceph002=10.141.8.181:6789/0,ceph003=10.141.8.182:6789/0}, election epoch 30, quorum 0,1,2
ceph001,ceph002,ceph003
mdsmap e78951: 1/1/1 up {0=ceph003.cubone.os=up:active}, 3 up:standby
osdmap e145384: 78 osds: 78 up, 78 in
pgmap v247095: 320 pgs, 4 pools, 15366 GB data, 3841 kobjects
1502 GB used, 129 TB / 131 TB avail
279 active+clean
40 active+clean+inconsistent
1 active+clean+scrubbing+deep
I tried to do ceph pg repair for all the inconsistent pgs:
cluster 82766e04-585b-49a6-a0ac-c13d9ffd0a7d
health HEALTH_ERR 40 pgs inconsistent; 1 pgs repair; 40 scrub
errors; too few pgs per osd (4 < min 20); mon.ceph002 low disk space
monmap e3: 3 mons at
{ceph001=10.141.8.180:6789/0,ceph002=10.141.8.181:6789/0,ceph003=10.141.8.182:6789/0}, election epoch 30, quorum 0,1,2
ceph001,ceph002,ceph003
mdsmap e79486: 1/1/1 up {0=ceph003.cubone.os=up:active}, 3 up:standby
osdmap e146452: 78 osds: 78 up, 78 in
pgmap v248520: 320 pgs, 4 pools, 15366 GB data, 3841 kobjects
1503 GB used, 129 TB / 131 TB avail
279 active+clean
39 active+clean+inconsistent
1 active+clean+scrubbing+deep
1 active+clean+scrubbing+deep+inconsistent+repair
I let it recovering through the night, but this morning the mons were
all gone, nothing to see in the log files.. The osds were all still up!
cluster 82766e04-585b-49a6-a0ac-c13d9ffd0a7d
health HEALTH_ERR 36 pgs inconsistent; 1 pgs repair; 36 scrub
errors; too few pgs per osd (4 < min 20)
monmap e7: 3 mons at
{ceph001=10.141.8.180:6789/0,ceph002=10.141.8.181:6789/0,ceph003=10.141.8.182:6789/0}, election epoch 44, quorum 0,1,2
ceph001,ceph002,ceph003
mdsmap e109481: 1/1/1 up {0=ceph003.cubone.os=up:active}, 3 up:standby
osdmap e203410: 78 osds: 78 up, 78 in
pgmap v331747: 320 pgs, 4 pools, 15251 GB data, 3812 kobjects
1547 GB used, 129 TB / 131 TB avail
1 active+clean+scrubbing+deep+inconsistent+repair
284 active+clean
35 active+clean+inconsistent
I restarted the monitors now, I will let you know when I see something more..
----- Message from Haomai Wang <haomaiw...@gmail.com> ---------
Date: Sun, 24 Aug 2014 12:51:41 +0800
From: Haomai Wang <haomaiw...@gmail.com>
Subject: Re: [ceph-users] ceph cluster inconsistency?
To: Kenneth Waegeman <kenneth.waege...@ugent.be>,
ceph-users@lists.ceph.com
It's really strange! I write a test program according the key ordering you provided and parse the corresponding value. It's true! I have no idea now. If free, could you add this debug code to "src/os/GenericObjectMap.cc" and insert *before* "assert(start <= header.oid);": dout(0) << "start: " << start << "header.oid: " << header.oid << dendl; Then you need to recompile ceph-osd and run it again. The output log can help it! On Tue, Aug 19, 2014 at 10:19 PM, Haomai Wang <haomaiw...@gmail.com> wrote:I feel a little embarrassed, 1024 rows still true for me. I was wondering if you could give your all keys via ""ceph-kvstore-tool /var/lib/ceph/osd/ceph-67/current/ list _GHOBJTOSEQ_ > keys.log“. thanks! On Tue, Aug 19, 2014 at 4:58 PM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:----- Message from Haomai Wang <haomaiw...@gmail.com> --------- Date: Tue, 19 Aug 2014 12:28:27 +0800 From: Haomai Wang <haomaiw...@gmail.com> Subject: Re: [ceph-users] ceph cluster inconsistency? To: Kenneth Waegeman <kenneth.waege...@ugent.be> Cc: Sage Weil <sw...@redhat.com>, ceph-users@lists.ceph.comOn Mon, Aug 18, 2014 at 7:32 PM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:----- Message from Haomai Wang <haomaiw...@gmail.com> --------- Date: Mon, 18 Aug 2014 18:34:11 +0800 From: Haomai Wang <haomaiw...@gmail.com> Subject: Re: [ceph-users] ceph cluster inconsistency? To: Kenneth Waegeman <kenneth.waege...@ugent.be> Cc: Sage Weil <sw...@redhat.com>, ceph-users@lists.ceph.comOn Mon, Aug 18, 2014 at 5:38 PM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:Hi, I tried this after restarting the osd, but I guess that was not the aim ( # ceph-kvstore-tool /var/lib/ceph/osd/ceph-67/current/ list _GHOBJTOSEQ_| grep 6adb1100 -A 100 IO error: lock /var/lib/ceph/osd/ceph-67/current//LOCK: Resource temporarily unavailable tools/ceph_kvstore_tool.cc: In function 'StoreTool::StoreTool(const string&)' thread 7f8fecf7d780 time 2014-08-18 11:12:29.551780 tools/ceph_kvstore_tool.cc: 38: FAILED assert(!db_ptr->open(std::cerr)) .. ) When I run it after bringing the osd down, it takes a while, but it has no output.. (When running it without the grep, I'm getting a huge list )Oh, sorry for it! I made a mistake, the hash value(6adb1100) will be reversed into leveldb. So grep "benchmark_data_ceph001.cubone.os_5560_object789734" should be help it.this gives: [root@ceph003 ~]# ceph-kvstore-tool /var/lib/ceph/osd/ceph-67/current/ list _GHOBJTOSEQ_ | grep 5560_object789734 -A 100 _GHOBJTOSEQ_:3%e0s0_head!0011BDA6!!3!!benchmark_data_ceph001%ecubone%eos_5560_object789734!head _GHOBJTOSEQ_:3%e0s0_head!0011C027!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1330170!head _GHOBJTOSEQ_:3%e0s0_head!0011C6FD!!3!!benchmark_data_ceph001%ecubone%eos_4919_object227366!head _GHOBJTOSEQ_:3%e0s0_head!0011CB03!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1363631!head _GHOBJTOSEQ_:3%e0s0_head!0011CDF0!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1573957!head _GHOBJTOSEQ_:3%e0s0_head!0011D02C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1019282!head _GHOBJTOSEQ_:3%e0s0_head!0011E2B5!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1283563!head _GHOBJTOSEQ_:3%e0s0_head!0011E511!!3!!benchmark_data_ceph001%ecubone%eos_4919_object273736!head _GHOBJTOSEQ_:3%e0s0_head!0011E547!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1170628!head _GHOBJTOSEQ_:3%e0s0_head!0011EAAB!!3!!benchmark_data_ceph001%ecubone%eos_4919_object256335!head _GHOBJTOSEQ_:3%e0s0_head!0011F446!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1484196!head _GHOBJTOSEQ_:3%e0s0_head!0011FC59!!3!!benchmark_data_ceph001%ecubone%eos_5560_object884178!head _GHOBJTOSEQ_:3%e0s0_head!001203F3!!3!!benchmark_data_ceph001%ecubone%eos_5560_object853746!head _GHOBJTOSEQ_:3%e0s0_head!001208E3!!3!!benchmark_data_ceph001%ecubone%eos_5560_object36633!head _GHOBJTOSEQ_:3%e0s0_head!00120B37!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1235337!head _GHOBJTOSEQ_:3%e0s0_head!001210B6!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1661351!head _GHOBJTOSEQ_:3%e0s0_head!001210CB!!3!!benchmark_data_ceph001%ecubone%eos_5560_object238126!head _GHOBJTOSEQ_:3%e0s0_head!0012184C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object339943!head _GHOBJTOSEQ_:3%e0s0_head!00121916!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1047094!head _GHOBJTOSEQ_:3%e0s0_head!001219C1!!3!!benchmark_data_ceph001%ecubone%eos_31461_object520642!head _GHOBJTOSEQ_:3%e0s0_head!001222BB!!3!!benchmark_data_ceph001%ecubone%eos_5560_object639565!head _GHOBJTOSEQ_:3%e0s0_head!001223AA!!3!!benchmark_data_ceph001%ecubone%eos_4919_object231080!head _GHOBJTOSEQ_:3%e0s0_head!0012243C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object858050!head _GHOBJTOSEQ_:3%e0s0_head!0012289C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object241796!head _GHOBJTOSEQ_:3%e0s0_head!00122D28!!3!!benchmark_data_ceph001%ecubone%eos_4919_object7462!head _GHOBJTOSEQ_:3%e0s0_head!00122DFE!!3!!benchmark_data_ceph001%ecubone%eos_5560_object243798!head _GHOBJTOSEQ_:3%e0s0_head!00122EFC!!3!!benchmark_data_ceph001%ecubone%eos_8961_object109512!head _GHOBJTOSEQ_:3%e0s0_head!001232D7!!3!!benchmark_data_ceph001%ecubone%eos_31461_object653973!head _GHOBJTOSEQ_:3%e0s0_head!001234A3!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1378169!head _GHOBJTOSEQ_:3%e0s0_head!00123714!!3!!benchmark_data_ceph001%ecubone%eos_5560_object512925!head _GHOBJTOSEQ_:3%e0s0_head!001237D9!!3!!benchmark_data_ceph001%ecubone%eos_4919_object23289!head _GHOBJTOSEQ_:3%e0s0_head!00123854!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1108852!head _GHOBJTOSEQ_:3%e0s0_head!00123971!!3!!benchmark_data_ceph001%ecubone%eos_5560_object704026!head _GHOBJTOSEQ_:3%e0s0_head!00123F75!!3!!benchmark_data_ceph001%ecubone%eos_8961_object250441!head _GHOBJTOSEQ_:3%e0s0_head!00124083!!3!!benchmark_data_ceph001%ecubone%eos_31461_object706178!head _GHOBJTOSEQ_:3%e0s0_head!001240FA!!3!!benchmark_data_ceph001%ecubone%eos_5560_object316952!head _GHOBJTOSEQ_:3%e0s0_head!0012447D!!3!!benchmark_data_ceph001%ecubone%eos_5560_object538734!head _GHOBJTOSEQ_:3%e0s0_head!001244D9!!3!!benchmark_data_ceph001%ecubone%eos_31461_object789215!head _GHOBJTOSEQ_:3%e0s0_head!001247CD!!3!!benchmark_data_ceph001%ecubone%eos_8961_object265993!head _GHOBJTOSEQ_:3%e0s0_head!00124897!!3!!benchmark_data_ceph001%ecubone%eos_31461_object610597!head _GHOBJTOSEQ_:3%e0s0_head!00124BE4!!3!!benchmark_data_ceph001%ecubone%eos_31461_object691723!head _GHOBJTOSEQ_:3%e0s0_head!00124C9B!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1306135!head _GHOBJTOSEQ_:3%e0s0_head!00124E1D!!3!!benchmark_data_ceph001%ecubone%eos_5560_object520580!head _GHOBJTOSEQ_:3%e0s0_head!0012534C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object659767!head _GHOBJTOSEQ_:3%e0s0_head!00125A81!!3!!benchmark_data_ceph001%ecubone%eos_5560_object184060!head _GHOBJTOSEQ_:3%e0s0_head!00125E77!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1292867!head _GHOBJTOSEQ_:3%e0s0_head!00126562!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1201410!head _GHOBJTOSEQ_:3%e0s0_head!00126B34!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1657326!head _GHOBJTOSEQ_:3%e0s0_head!00127383!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1269787!head _GHOBJTOSEQ_:3%e0s0_head!00127396!!3!!benchmark_data_ceph001%ecubone%eos_31461_object500115!head _GHOBJTOSEQ_:3%e0s0_head!001277F8!!3!!benchmark_data_ceph001%ecubone%eos_31461_object394932!head _GHOBJTOSEQ_:3%e0s0_head!001279DD!!3!!benchmark_data_ceph001%ecubone%eos_4919_object252963!head _GHOBJTOSEQ_:3%e0s0_head!00127B40!!3!!benchmark_data_ceph001%ecubone%eos_31461_object936811!head _GHOBJTOSEQ_:3%e0s0_head!00127BAC!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1481773!head _GHOBJTOSEQ_:3%e0s0_head!0012894E!!3!!benchmark_data_ceph001%ecubone%eos_5560_object999885!head _GHOBJTOSEQ_:3%e0s0_head!00128D05!!3!!benchmark_data_ceph001%ecubone%eos_31461_object943667!head _GHOBJTOSEQ_:3%e0s0_head!0012908A!!3!!benchmark_data_ceph001%ecubone%eos_5560_object212990!head _GHOBJTOSEQ_:3%e0s0_head!00129519!!3!!benchmark_data_ceph001%ecubone%eos_5560_object437596!head _GHOBJTOSEQ_:3%e0s0_head!00129716!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1585330!head _GHOBJTOSEQ_:3%e0s0_head!00129798!!3!!benchmark_data_ceph001%ecubone%eos_5560_object603505!head _GHOBJTOSEQ_:3%e0s0_head!001299C9!!3!!benchmark_data_ceph001%ecubone%eos_31461_object808800!head _GHOBJTOSEQ_:3%e0s0_head!00129B7A!!3!!benchmark_data_ceph001%ecubone%eos_31461_object23193!head _GHOBJTOSEQ_:3%e0s0_head!00129B9A!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1158397!head _GHOBJTOSEQ_:3%e0s0_head!0012A932!!3!!benchmark_data_ceph001%ecubone%eos_5560_object542450!head _GHOBJTOSEQ_:3%e0s0_head!0012B77A!!3!!benchmark_data_ceph001%ecubone%eos_8961_object195480!head _GHOBJTOSEQ_:3%e0s0_head!0012BE8C!!3!!benchmark_data_ceph001%ecubone%eos_4919_object312911!head _GHOBJTOSEQ_:3%e0s0_head!0012BF74!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1563783!head _GHOBJTOSEQ_:3%e0s0_head!0012C65C!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1123980!head _GHOBJTOSEQ_:3%e0s0_head!0012C6FE!!3!!benchmark_data_ceph001%ecubone%eos_3411_object913!head _GHOBJTOSEQ_:3%e0s0_head!0012CCAD!!3!!benchmark_data_ceph001%ecubone%eos_31461_object400863!head _GHOBJTOSEQ_:3%e0s0_head!0012CDBB!!3!!benchmark_data_ceph001%ecubone%eos_5560_object789667!head _GHOBJTOSEQ_:3%e0s0_head!0012D14B!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1020723!head _GHOBJTOSEQ_:3%e0s0_head!0012D95B!!3!!benchmark_data_ceph001%ecubone%eos_8961_object106293!head _GHOBJTOSEQ_:3%e0s0_head!0012E3C8!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1355526!head _GHOBJTOSEQ_:3%e0s0_head!0012E5B3!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1491348!head _GHOBJTOSEQ_:3%e0s0_head!0012F2BB!!3!!benchmark_data_ceph001%ecubone%eos_8961_object338872!head _GHOBJTOSEQ_:3%e0s0_head!0012F374!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1337264!head _GHOBJTOSEQ_:3%e0s0_head!0012FBE5!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1512395!head _GHOBJTOSEQ_:3%e0s0_head!0012FCE3!!3!!benchmark_data_ceph001%ecubone%eos_8961_object298610!head _GHOBJTOSEQ_:3%e0s0_head!0012FEB6!!3!!benchmark_data_ceph001%ecubone%eos_4919_object120824!head _GHOBJTOSEQ_:3%e0s0_head!001301CA!!3!!benchmark_data_ceph001%ecubone%eos_5560_object816326!head _GHOBJTOSEQ_:3%e0s0_head!00130263!!3!!benchmark_data_ceph001%ecubone%eos_5560_object777163!head _GHOBJTOSEQ_:3%e0s0_head!00130529!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1413173!head _GHOBJTOSEQ_:3%e0s0_head!001317D9!!3!!benchmark_data_ceph001%ecubone%eos_31461_object809510!head _GHOBJTOSEQ_:3%e0s0_head!0013204F!!3!!benchmark_data_ceph001%ecubone%eos_31461_object471416!head _GHOBJTOSEQ_:3%e0s0_head!00132400!!3!!benchmark_data_ceph001%ecubone%eos_5560_object695087!head _GHOBJTOSEQ_:3%e0s0_head!00132A19!!3!!benchmark_data_ceph001%ecubone%eos_31461_object591945!head _GHOBJTOSEQ_:3%e0s0_head!00132BF8!!3!!benchmark_data_ceph001%ecubone%eos_31461_object302000!head _GHOBJTOSEQ_:3%e0s0_head!00132F5B!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1645443!head _GHOBJTOSEQ_:3%e0s0_head!00133B8B!!3!!benchmark_data_ceph001%ecubone%eos_5560_object761911!head _GHOBJTOSEQ_:3%e0s0_head!0013433E!!3!!benchmark_data_ceph001%ecubone%eos_31461_object1467727!head _GHOBJTOSEQ_:3%e0s0_head!00134446!!3!!benchmark_data_ceph001%ecubone%eos_31461_object791960!head _GHOBJTOSEQ_:3%e0s0_head!00134678!!3!!benchmark_data_ceph001%ecubone%eos_31461_object677078!head _GHOBJTOSEQ_:3%e0s0_head!00134A96!!3!!benchmark_data_ceph001%ecubone%eos_31461_object254923!head _GHOBJTOSEQ_:3%e0s0_head!001355D0!!3!!benchmark_data_ceph001%ecubone%eos_31461_object321528!head _GHOBJTOSEQ_:3%e0s0_head!00135690!!3!!benchmark_data_ceph001%ecubone%eos_4919_object36935!head _GHOBJTOSEQ_:3%e0s0_head!00135B62!!3!!benchmark_data_ceph001%ecubone%eos_5560_object1228272!head _GHOBJTOSEQ_:3%e0s0_head!00135C72!!3!!benchmark_data_ceph001%ecubone%eos_4812_object2180!head _GHOBJTOSEQ_:3%e0s0_head!00135DEE!!3!!benchmark_data_ceph001%ecubone%eos_5560_object425705!head _GHOBJTOSEQ_:3%e0s0_head!00136366!!3!!benchmark_data_ceph001%ecubone%eos_5560_object141569!head _GHOBJTOSEQ_:3%e0s0_head!00136371!!3!!benchmark_data_ceph001%ecubone%eos_5560_object564213!head100 rows seemed true for me. I found the min list objects is 1024. Please could you run "ceph-kvstore-tool /var/lib/ceph/osd/ceph-67/current/ list _GHOBJTOSEQ_| grep 6adb1100 -A 1024"I got the output in attachmentOr should I run this immediately after the osd is crashed, (because it maybe rebalanced? I did already restarted the cluster) I don't know if it is related, but before I could all do that, I had to fix something else: A monitor did run out if disk space, using 8GB for his store.db folder (lot of sst files). Other monitors are also near that level. Never had that problem on previous setups before. I recreated a monitor and now it uses 3.8GB.It exists some duplicate data which needed to be compacted.Another idea, maybe you can make KeyValueStore's stripe size align with EC stripe size.How can I do that? Is there some documentation about that?ceph --show-config | grep keyvaluestoredebug_keyvaluestore = 0/0 keyvaluestore_queue_max_ops = 50 keyvaluestore_queue_max_bytes = 104857600 keyvaluestore_debug_check_backend = false keyvaluestore_op_threads = 2 keyvaluestore_op_thread_timeout = 60 keyvaluestore_op_thread_suicide_timeout = 180 keyvaluestore_default_strip_size = 4096 keyvaluestore_max_expected_write_size = 16777216 keyvaluestore_header_cache_size = 4096 keyvaluestore_backend = leveldb keyvaluestore_default_strip_size is the wantedI haven't think deeply and maybe I will try it later.Thanks! Kenneth ----- Message from Sage Weil <sw...@redhat.com> --------- Date: Fri, 15 Aug 2014 06:10:34 -0700 (PDT) From: Sage Weil <sw...@redhat.com> Subject: Re: [ceph-users] ceph cluster inconsistency? To: Haomai Wang <haomaiw...@gmail.com> Cc: Kenneth Waegeman <kenneth.waege...@ugent.be>, ceph-users@lists.ceph.comOn Fri, 15 Aug 2014, Haomai Wang wrote:Hi Kenneth, I don't find valuable info in your logs, it lack of the necessary debug output when accessing crash code. But I scan the encode/decode implementation in GenericObjectMap and find something bad. For example, two oid has same hash and their name is: A: "rb.data.123" B: "rb-123" In ghobject_t compare level, A < B. But GenericObjectMap encode "." to "%e", so the key in DB is: A: _GHOBJTOSEQ_:blah!51615000!!none!!rb%edata%e123!head B: _GHOBJTOSEQ_:blah!51615000!!none!!rb-123!head A > B And it seemed that the escape function is useless and should be disabled. I'm not sure whether Kenneth's problem is touching this bug. Because this scene only occur when the object set is very large and make the two object has same hash value. Kenneth, could you have time to run "ceph-kv-store [path-to-osd] list _GHOBJTOSEQ_| grep 6adb1100 -A 100". ceph-kv-store is a debug tool which can be compiled from source. You can clone ceph repo and run "./authongen.sh; ./configure; cd src; make ceph-kvstore-tool". "path-to-osd" should be "/var/lib/ceph/osd-[id]/current/". "6adb1100" is from your verbose log and the next 100 rows should know necessary infos.You can also get ceph-kvstore-tool from the 'ceph-tests' package.Hi sage, do you think we need to provided with upgrade function to fix it?Hmm, we might. This only affects the key/value encoding right? The FileStore is using its own function to map these to file names? Can you open a ticket in the tracker for this? Thanks! sageOn Thu, Aug 14, 2014 at 7:36 PM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:----- Message from Haomai Wang <haomaiw...@gmail.com> --------- Date: Thu, 14 Aug 2014 19:11:55 +0800 From: Haomai Wang <haomaiw...@gmail.com> Subject: Re: [ceph-users] ceph cluster inconsistency? To: Kenneth Waegeman <kenneth.waege...@ugent.be>Could you add config "debug_keyvaluestore = 20/20" to the crashed osd and replay the command causing crash? I would like to get more debug infos! Thanks.I included the log in attachment! Thanks!On Thu, Aug 14, 2014 at 4:41 PM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:I have: osd_objectstore = keyvaluestore-dev in the global section of my ceph.conf [root@ceph002 ~]# ceph osd erasure-code-profile get profile11 directory=/usr/lib64/ceph/erasure-code k=8 m=3 plugin=jerasure ruleset-failure-domain=osd technique=reed_sol_van the ecdata pool has this as profile pool 3 'ecdata' erasure size 11 min_size 8 crush_ruleset 2 object_hash rjenkins pg_num 128 pgp_num 128 last_change 161 flags hashpspool stripe_width 4096 ECrule in crushmap rule ecdata { ruleset 2 type erasure min_size 3 max_size 20 step set_chooseleaf_tries 5 step take default-ec step choose indep 0 type osd step emit } root default-ec { id -8 # do not change unnecessarily # weight 140.616 alg straw hash 0 # rjenkins1 item ceph001-ec weight 46.872 item ceph002-ec weight 46.872 item ceph003-ec weight 46.872 ... Cheers! Kenneth ----- Message from Haomai Wang <haomaiw...@gmail.com> --------- Date: Thu, 14 Aug 2014 10:07:50 +0800 From: Haomai Wang <haomaiw...@gmail.com> Subject: Re: [ceph-users] ceph cluster inconsistency? To: Kenneth Waegeman <kenneth.waege...@ugent.be> Cc: ceph-users <ceph-users@lists.ceph.com>Hi Kenneth, Could you give your configuration related to EC and KeyValueStore? Not sure whether it's bug on KeyValueStore On Thu, Aug 14, 2014 at 12:06 AM, Kenneth Waegeman <kenneth.waege...@ugent.be> wrote:Hi, I was doing some tests with rados bench on a Erasure Coded pool (using keyvaluestore-dev objectstore) on 0.83, and I see some strangs things: [root@ceph001 ~]# ceph status cluster 82766e04-585b-49a6-a0ac-c13d9ffd0a7d health HEALTH_WARN too few pgs per osd (4 < min 20) monmap e1: 3 mons at {ceph001=10.141.8.180:6789/0,ceph002=10.141.8.181:6789/0,ceph003=10.141.8.182:6789/0}, election epoch 6, quorum 0,1,2 ceph001,ceph002,ceph003 mdsmap e116: 1/1/1 up {0=ceph001.cubone.os=up:active}, 2 up:standby osdmap e292: 78 osds: 78 up, 78 in pgmap v48873: 320 pgs, 4 pools, 15366 GB data, 3841 kobjects 1381 GB used, 129 TB / 131 TB avail 320 active+clean There is around 15T of data, but only 1.3 T usage. This is also visible in rados: [root@ceph001 ~]# rados df pool name category KB objects clones degraded unfound rd rd KB wr wr KB data - 0 0 0 0 0 0 0 ecdata - 16113451009 3933959 0 0 1 1 3935632 16116850711 metadata - 2 20 0 0 33 36 21 8 rbd - 0 0 0 0 0 0 0 total used 1448266016 3933979 total avail 139400181016 total space 140848447032 Another (related?) thing: if I do rados -p ecdata ls, I trigger osd shutdowns (each time): I get a list followed by an error: ... benchmark_data_ceph001.cubone.os_8961_object243839 benchmark_data_ceph001.cubone.os_5560_object801983 benchmark_data_ceph001.cubone.os_31461_object856489 benchmark_data_ceph001.cubone.os_8961_object202232 benchmark_data_ceph001.cubone.os_4919_object33199 benchmark_data_ceph001.cubone.os_5560_object807797 benchmark_data_ceph001.cubone.os_4919_object74729 benchmark_data_ceph001.cubone.os_31461_object1264121 benchmark_data_ceph001.cubone.os_5560_object1318513 benchmark_data_ceph001.cubone.os_5560_object1202111 benchmark_data_ceph001.cubone.os_31461_object939107 benchmark_data_ceph001.cubone.os_31461_object729682 benchmark_data_ceph001.cubone.os_5560_object122915 benchmark_data_ceph001.cubone.os_5560_object76521 benchmark_data_ceph001.cubone.os_5560_object113261 benchmark_data_ceph001.cubone.os_31461_object575079 benchmark_data_ceph001.cubone.os_5560_object671042 benchmark_data_ceph001.cubone.os_5560_object381146 2014-08-13 17:57:48.736150 7f65047b5700 0 -- 10.141.8.180:0/1023295 >> 10.141.8.182:6839/4471 pipe(0x7f64fc019b20 sd=5 :0 s=1 pgs=0 cs=0 l=1 c=0x7f64fc019db0).fault And I can see this in the log files: -25> 2014-08-13 17:52:56.323908 7f8a97fa4700 1 -- 10.143.8.182:6827/64670 <== osd.57 10.141.8.182:0/15796 51 ==== osd_ping(ping e220 stamp 2014-08-13 17:52:56.323092) v2 ==== 47+0+0 (3227325175 0 0) 0xf475940 con 0xee89fa0 -24> 2014-08-13 17:52:56.323938 7f8a97fa4700 1 -- 10.143.8.182:6827/64670 --> 10.141.8.182:0/15796 -- osd_ping(ping_reply e220 stamp 2014-08-13 17:52:56.323092) v2 -- ?+0 0xf815b00 con 0xee89fa0 -23> 2014-08-13 17:52:56.324078 7f8a997a7700 1 -- 10.141.8.182:6840/64670 <== osd.57 10.141.8.182:0/15796 51 ==== osd_ping(ping e220 stamp 2014-08-13 17:52:56.323092) v2 ==== 47+0+0 (3227325175 0 0) 0xf132bc0 con 0xee8a680 -22> 2014-08-13 17:52:56.324111 7f8a997a7700 1 -- 10.141.8.182:6840/64670 --> 10.141.8.182:0/15796 -- osd_ping(ping_reply e220 stamp 2014-08-13 17:52:56.323092) v2 -- ?+0 0xf811a40 con 0xee8a680 -21> 2014-08-13 17:52:56.584461 7f8a997a7700 1 -- 10.141.8.182:6840/64670 <== osd.29 10.143.8.181:0/12142 47 ==== osd_ping(ping e220 stamp 2014-08-13 17:52:56.583010) v2 ==== 47+0+0 (3355887204 0 0) 0xf655940 con 0xee88b00 -20> 2014-08-13 17:52:56.584486 7f8a997a7700 1 -- 10.141.8.182:6840/64670 --> 10.143.8.181:0/12142 -- osd_ping(ping_reply e220 stamp 2014-08-13 17:52:56.583010) v2 -- ?+0 0xf132bc0 con 0xee88b00 -19> 2014-08-13 17:52:56.584498 7f8a97fa4700 1 -- 10.143.8.182:6827/64670 <== osd.29 10.143.8.181:0/12142 47 ==== osd_ping(ping e220 stamp 2014-08-13 17:52:56.583010) v2 ==== 47+0+0 (3355887204 0 0) 0xf20e040 con 0xee886e0 -18> 2014-08-13 17:52:56.584526 7f8a97fa4700 1 -- 10.143.8.182:6827/64670 --> 10.143.8.181:0/12142 -- osd_ping(ping_reply e220 stamp 2014-08-13 17:52:56.583010) v2 -- ?+0 0xf475940 con 0xee886e0 -17> 2014-08-13 17:52:56.594448 7f8a798c7700 1 -- 10.141.8.182:6839/64670 >> :/0 pipe(0xec15f00 sd=74 :6839 s=0 pgs=0 cs=0 l=0 c=0xee856a0).accept sd=74 10.141.8.180:47641/0 -16> 2014-08-13 17:52:56.594921 7f8a798c7700 1 -- 10.141.8.182:6839/64670 <== client.7512 10.141.8.180:0/1018433 1 ==== osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) v4 ==== 151+0+39 (1972163119 4174233976) 0xf3bca40 con 0xee856a0 -15> 2014-08-13 17:52:56.594957 7f8a798c7700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.594874, event: header_read, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -14> 2014-08-13 17:52:56.594970 7f8a798c7700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.594880, event: throttled, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -13> 2014-08-13 17:52:56.594978 7f8a798c7700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.594917, event: all_read, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -12> 2014-08-13 17:52:56.594986 7f8a798c7700 5 -- op tracker -- , seq: 299, time: 0.000000, event: dispatched, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -11> 2014-08-13 17:52:56.595127 7f8a90795700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.595104, event: reached_pg, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -10> 2014-08-13 17:52:56.595159 7f8a90795700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.595153, event: started, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -9> 2014-08-13 17:52:56.602179 7f8a90795700 1 -- 10.141.8.182:6839/64670 --> 10.141.8.180:0/1018433 -- osd_op_reply(1 [pgls start_epoch 0] v164'30654 uv30654 ondisk = 0) v6 -- ?+0 0xec16180 con 0xee856a0 -8> 2014-08-13 17:52:56.602211 7f8a90795700 5 -- op tracker -- , seq: 299, time: 2014-08-13 17:52:56.602205, event: done, op: osd_op(client.7512.0:1 [pgls start_epoch 0] 3.0 ack+read+known_if_redirected e220) -7> 2014-08-13 17:52:56.614839 7f8a798c7700 1 -- 10.141.8.182:6839/64670 <== client.7512 10.141.8.180:0/1018433 2 ==== osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) v4 ==== 151+0+89 (3460833343 2600845095) 0xf3bcec0 con 0xee856a0 -6> 2014-08-13 17:52:56.614864 7f8a798c7700 5 -- op tracker -- , seq: 300, time: 2014-08-13 17:52:56.614789, event: header_read, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) -5> 2014-08-13 17:52:56.614874 7f8a798c7700 5 -- op tracker -- , seq: 300, time: 2014-08-13 17:52:56.614792, event: throttled, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) -4> 2014-08-13 17:52:56.614884 7f8a798c7700 5 -- op tracker -- , seq: 300, time: 2014-08-13 17:52:56.614835, event: all_read, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) -3> 2014-08-13 17:52:56.614891 7f8a798c7700 5 -- op tracker -- , seq: 300, time: 0.000000, event: dispatched, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) -2> 2014-08-13 17:52:56.614972 7f8a92f9a700 5 -- op tracker -- , seq: 300, time: 2014-08-13 17:52:56.614958, event: reached_pg, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) -1> 2014-08-13 17:52:56.614993 7f8a92f9a700 5 -- op tracker -- , seq: 300, time: 2014-08-13 17:52:56.614986, event: started, op: osd_op(client.7512.0:2 [pgls start_epoch 220] 3.0 ack+read+known_if_redirected e220) 0> 2014-08-13 17:52:56.617087 7f8a92f9a700 -1 os/GenericObjectMap.cc: In function 'int GenericObjectMap::list_objects(const coll_t&, ghobject_t, int, std::vector<ghobject_t>*, ghobject_t*)' thread 7f8a92f9a700 time 2014-08-13 17:52:56.615073 os/GenericObjectMap.cc: 1118: FAILED assert(start <= header.oid) ceph version 0.83 (78ff1f0a5dfd3c5850805b4021738564c36c92b8) 1: (GenericObjectMap::list_objects(coll_t const&, ghobject_t, int, std::vector<ghobject_t, std::allocator<ghobject_t> >*, ghobject_t*)+0x474) [0x98f774] 2: (KeyValueStore::collection_list_partial(coll_t, ghobject_t, int, int, snapid_t, std::vector<ghobject_t, std::allocator<ghobject_t>*,ghobject_t*)+0x274) [0x8c5b54] 3: (PGBackend::objects_list_partial(hobject_t const&, int, int, snapid_t, std::vector<hobject_t, std::allocator<hobject_t> >*, hobject_t*)+0x1c9) [0x862de9] 4: (ReplicatedPG::do_pg_op(std::tr1::shared_ptr<OpRequest>)+0xea5) [0x7f67f5] 5: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x1f3) [0x8177b3] 6: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x5d5) [0x7b8045] 7: (OSD::dequeue_op(boost::intrusive_ptr<PG>, std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x47d) [0x62bf8d] 8: (OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*)+0x35c) [0x62c56c] 9: (ShardedThreadPool::shardedthreadpool_worker(unsigned int)+0x8cd) [0xa776fd] 10: (ShardedThreadPool::WorkThreadSharded::entry()+0x10) [0xa79980] 11: (()+0x7df3) [0x7f8aac71fdf3] 12: (clone()+0x6d) [0x7f8aab1963dd] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. ceph version 0.83 (78ff1f0a5dfd3c5850805b4021738564c36c92b8) 1: /usr/bin/ceph-osd() [0x99b466] 2: (()+0xf130) [0x7f8aac727130] 3: (gsignal()+0x39) [0x7f8aab0d5989] 4: (abort()+0x148) [0x7f8aab0d7098] 5: (__gnu_cxx::__verbose_terminate_handler()+0x165) [0x7f8aab9e89d5] 6: (()+0x5e946) [0x7f8aab9e6946] 7: (()+0x5e973) [0x7f8aab9e6973] 8: (()+0x5eb9f) [0x7f8aab9e6b9f] 9: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x1ef) [0xa8805f] 10: (GenericObjectMap::list_objects(coll_t const&, ghobject_t, int, std::vector<ghobject_t, std::allocator<ghobject_t> >*, ghobject_t*)+0x474) [0x98f774] 11: (KeyValueStore::collection_list_partial(coll_t, ghobject_t, int, int, snapid_t, std::vector<ghobject_t, std::allocator<ghobject_t>*,ghobject_t*)+0x274) [0x8c5b54] 12: (PGBackend::objects_list_partial(hobject_t const&, int, int, snapid_t, std::vector<hobject_t, std::allocator<hobject_t> >*, hobject_t*)+0x1c9) [0x862de9] 13: (ReplicatedPG::do_pg_op(std::tr1::shared_ptr<OpRequest>)+0xea5) [0x7f67f5] 14: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x1f3) [0x8177b3] 15: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x5d5) [0x7b8045] 16: (OSD::dequeue_op(boost::intrusive_ptr<PG>, std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x47d) [0x62bf8d] 17: (OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*)+0x35c) [0x62c56c] 18: (ShardedThreadPool::shardedthreadpool_worker(unsigned int)+0x8cd) [0xa776fd] 19: (ShardedThreadPool::WorkThreadSharded::entry()+0x10) [0xa79980] 20: (()+0x7df3) [0x7f8aac71fdf3] 21: (clone()+0x6d) [0x7f8aab1963dd] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. --- begin dump of recent events --- 0> 2014-08-13 17:52:56.714214 7f8a92f9a700 -1 *** Caught signal (Aborted) ** in thread 7f8a92f9a700 ceph version 0.83 (78ff1f0a5dfd3c5850805b4021738564c36c92b8) 1: /usr/bin/ceph-osd() [0x99b466] 2: (()+0xf130) [0x7f8aac727130] 3: (gsignal()+0x39) [0x7f8aab0d5989] 4: (abort()+0x148) [0x7f8aab0d7098] 5: (__gnu_cxx::__verbose_terminate_handler()+0x165) [0x7f8aab9e89d5] 6: (()+0x5e946) [0x7f8aab9e6946] 7: (()+0x5e973) [0x7f8aab9e6973] 8: (()+0x5eb9f) [0x7f8aab9e6b9f] 9: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x1ef) [0xa8805f] 10: (GenericObjectMap::list_objects(coll_t const&, ghobject_t, int, std::vector<ghobject_t, std::allocator<ghobject_t> >*, ghobject_t*)+0x474) [0x98f774] 11: (KeyValueStore::collection_list_partial(coll_t, ghobject_t, int, int, snapid_t, std::vector<ghobject_t, std::allocator<ghobject_t>*,ghobject_t*)+0x274) [0x8c5b54] 12: (PGBackend::objects_list_partial(hobject_t const&, int, int, snapid_t, std::vector<hobject_t, std::allocator<hobject_t> >*, hobject_t*)+0x1c9) [0x862de9] 13: (ReplicatedPG::do_pg_op(std::tr1::shared_ptr<OpRequest>)+0xea5) [0x7f67f5] 14: (ReplicatedPG::do_op(std::tr1::shared_ptr<OpRequest>)+0x1f3) [0x8177b3] 15: (ReplicatedPG::do_request(std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x5d5) [0x7b8045] 16: (OSD::dequeue_op(boost::intrusive_ptr<PG>, std::tr1::shared_ptr<OpRequest>, ThreadPool::TPHandle&)+0x47d) [0x62bf8d] 17: (OSD::ShardedOpWQ::_process(unsigned int, ceph::heartbeat_handle_d*)+0x35c) [0x62c56c] 18: (ShardedThreadPool::shardedthreadpool_worker(unsigned int)+0x8cd) [0xa776fd] 19: (ShardedThreadPool::WorkThreadSharded::entry()+0x10) [0xa79980] 20: (()+0x7df3) [0x7f8aac71fdf3] 21: (clone()+0x6d) [0x7f8aab1963dd] NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this. I guess this has something to do with using the dev Keyvaluestore? Thanks! Kenneth _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com-- Best Regards, Wheat----- End message from Haomai Wang <haomaiw...@gmail.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman-- Best Regards, Wheat----- End message from Haomai Wang <haomaiw...@gmail.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman-- Best Regards, Wheat _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com----- End message from Sage Weil <sw...@redhat.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman-- Best Regards, Wheat----- End message from Haomai Wang <haomaiw...@gmail.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman-- Best Regards, Wheat----- End message from Haomai Wang <haomaiw...@gmail.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman-- Best Regards, Wheat-- Best Regards, Wheat
----- End message from Haomai Wang <haomaiw...@gmail.com> ----- -- Met vriendelijke groeten, Kenneth Waegeman _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
