[ceph-users] Re: extract disk usage stats from running ceph cluster
Hello MJ, Perhaps your PGs are a unbalanced? Ceph osd df tree Greetz Mehmet Am 10. Februar 2020 14:58:25 MEZ schrieb lists : >Hi, > >We would like to replace the current seagate ST4000NM0034 HDDs in our >ceph cluster with SSDs, and before doing that, we would like to >checkout >the typical usage of our current drives, over the last years, so we can > >select the best (price/performance/endurance) SSD to replace them with. > >I am trying to extract this info from the fields "Blocks received from >initiator" / "blocks sent to initiator", as these are the fields >smartctl gets from the seagate disks. But the numbers seem strange, and > >I would like to request feedback here. > >Three nodes, all equal, 8 OSDs per node, all 4TB ST4000NM0034 >(filestore) HDDs with SSD-based journals: > >> root@node1:~# ceph osd crush tree >> ID CLASS WEIGHT TYPE NAME >> -1 87.35376 root default >> -2 29.11688 host node1 >> 0 hdd 3.64000 osd.0 >> 1 hdd 3.64000 osd.1 >> 2 hdd 3.63689 osd.2 >> 3 hdd 3.64000 osd.3 >> 12 hdd 3.64000 osd.12 >> 13 hdd 3.64000 osd.13 >> 14 hdd 3.64000 osd.14 >> 15 hdd 3.64000 osd.15 >> -3 29.12000 host node2 >> 4 hdd 3.64000 osd.4 >> 5 hdd 3.64000 osd.5 >> 6 hdd 3.64000 osd.6 >> 7 hdd 3.64000 osd.7 >> 16 hdd 3.64000 osd.16 >> 17 hdd 3.64000 osd.17 >> 18 hdd 3.64000 osd.18 >> 19 hdd 3.64000 osd.19 >> -4 29.11688 host node3 >> 8 hdd 3.64000 osd.8 >> 9 hdd 3.64000 osd.9 >> 10 hdd 3.64000 osd.10 >> 11 hdd 3.64000 osd.11 >> 20 hdd 3.64000 osd.20 >> 21 hdd 3.64000 osd.21 >> 22 hdd 3.64000 osd.22 >> 23 hdd 3.63689 osd.23 > >We are looking at the numbers from smartctl, and basing our >calculations >on this output for each individual various OSD: >> Vendor (Seagate) cache information >> Blocks sent to initiator = 3783529066 >> Blocks received from initiator = 3121186120 >> Blocks read from cache and sent to initiator = 545427169 >> Number of read and write commands whose size <= segment size = >93877358 >> Number of read and write commands whose size > segment size = >2290879 > >I created the following spreadsheet: > >> blocks sent blocks received total blocks >> to initiatorfrom initiator calculated read% write% >> aka >> node1 >> osd0 905060564 1900663448 2805724012 32,26% 67,74% >> sda >> osd1 2270442418 3756215880 6026658298 37,67% 62,33% >> sdb >> osd2 3531938448 3940249192 7472187640 47,27% 52,73% >> sdc >> osd3 2824808123 3130655416 5955463539 47,43% 52,57% >> sdd >> osd121956722491 1294854032 3251576523 60,18% 39,82% >> sdg >> osd133410188306 1265443936 4675632242 72,94% 27,06% >> sdh >> osd143765454090 3115079112 6880533202 54,73% 45,27% >> sdi >> osd152272246730 2218847264 4491093994 50,59% 49,41% >> sdj >> >> node2 >> osd4 3974937107 740853712 4715790819 84,29% 15,71% >> sda >> osd5 1181377668 2109150744 3290528412 35,90% 64,10% >> sdb >> osd5 1903438106 608869008 2512307114 75,76% 24,24% >> sdc >> osd7 3511170043 724345936 4235515979 82,90% 17,10% >> sdd >> osd162642731906 3981984640 6624716546 39,89% 60,11% >> sdg >> osd173994977805 3703856288 7698834093 51,89% 48,11% >> sdh >> osd183992157229 2096991672 6089148901 65,56% 34,44% >> sdi >> osd19279766405 1053039640 1332806045 20,99% 79,01% >> sdj >> >> node3 >> osd8 3711322586 234696960 3946019546 94,05% 5,95% >> sda >> osd9 1203912715 313299 4336902715 27,76% 72,24% >> sdb >> osd10912356010 1681434416 2593790426 35,17% 64,83% >> sdc >> osd11810488345 2626589896 3437078241 23,58% 76,42% >> sdd >> osd201506879946 2421596680 3928476626 38,36% 61,64% >> sdg >> osd212991526593 7525120 2999051713 99,75% 0,25% >> sdh >> osd22295603373226114552 3255674889 0,91% 99,09% >> sdi >> osd232019195656 2563506320 4582701976 44,06% 55,94% >> s
[ceph-users] Re: extract disk usage stats from running ceph cluster
try from admin node ceph osd df ceph osd status thanks Joe >>> 2/10/2020 10:44 AM >>> Hello MJ, Perhaps your PGs are a unbalanced? Ceph osd df tree Greetz Mehmet Am 10. Februar 2020 14:58:25 MEZ schrieb lists : >Hi, > >We would like to replace the current seagate ST4000NM0034 HDDs in our >ceph cluster with SSDs, and before doing that, we would like to >checkout >the typical usage of our current drives, over the last years, so we can > >select the best (price/performance/endurance) SSD to replace them with. > >I am trying to extract this info from the fields "Blocks received from >initiator" / "blocks sent to initiator", as these are the fields >smartctl gets from the seagate disks. But the numbers seem strange, and > >I would like to request feedback here. > >Three nodes, all equal, 8 OSDs per node, all 4TB ST4000NM0034 >(filestore) HDDs with SSD-based journals: > >> root@node1:~# ceph osd crush tree >> ID CLASS WEIGHT TYPE NAME >> -1 87.35376 root default >> -2 29.11688 host node1 >> 0 hdd 3.64000 osd.0 >> 1 hdd 3.64000 osd.1 >> 2 hdd 3.63689 osd.2 >> 3 hdd 3.64000 osd.3 >> 12 hdd 3.64000osd.12 >> 13 hdd 3.64000osd.13 >> 14 hdd 3.64000osd.14 >> 15 hdd 3.64000osd.15 >> -3 29.12000 host node2 >> 4 hdd 3.64000 osd.4 >> 5 hdd 3.64000 osd.5 >> 6 hdd 3.64000 osd.6 >> 7 hdd 3.64000 osd.7 >> 16 hdd 3.64000osd.16 >> 17 hdd 3.64000osd.17 >> 18 hdd 3.64000osd.18 >> 19 hdd 3.64000osd.19 >> -4 29.11688 host node3 >> 8 hdd 3.64000 osd.8 >> 9 hdd 3.64000 osd.9 >> 10 hdd 3.64000osd.10 >> 11 hdd 3.64000osd.11 >> 20 hdd 3.64000osd.20 >> 21 hdd 3.64000osd.21 >> 22 hdd 3.64000osd.22 >> 23 hdd 3.63689osd.23 > >We are looking at the numbers from smartctl, and basing our >calculations >on this output for each individual various OSD: >> Vendor (Seagate) cache information >> Blocks sent to initiator = 3783529066 >> Blocks received from initiator = 3121186120 >> Blocks read from cache and sent to initiator = 545427169 >> Number of read and write commands whose size <= segment size = >93877358 >> Number of read and write commands whose size > segment size = >2290879 > >I created the following spreadsheet: > >> blocks sent blocks received total blocks >> to initiatorfrom initiatorcalculatedread%write% >> aka >> node1 >> osd0 905060564 1900663448 2805724012 32,26% 67,74% >> sda >> osd1 2270442418 3756215880 6026658298 37,67% 62,33% >> sdb >> osd2 3531938448 3940249192 7472187640 47,27% 52,73% >> sdc >> osd3 2824808123 3130655416 5955463539 47,43% 52,57% >> sdd >> osd121956722491 1294854032 3251576523 60,18% 39,82% >> sdg >> osd133410188306 1265443936 4675632242 72,94% 27,06% >> sdh >> osd143765454090 3115079112 6880533202 54,73% 45,27% >> sdi >> osd152272246730 2218847264 4491093994 50,59% 49,41% >> sdj >> >> node2 >> osd4 3974937107 740853712 4715790819 84,29% 15,71% >> sda >> osd5 1181377668 2109150744 3290528412 35,90% 64,10% >> sdb >> osd5 1903438106 608869008 2512307114 75,76% 24,24% >> sdc >> osd7 3511170043 724345936 4235515979 82,90% 17,10% >> sdd >> osd162642731906 3981984640 6624716546 39,89% 60,11% >> sdg >> osd173994977805 3703856288 7698834093 51,89% 48,11% >> sdh >> osd183992157229 2096991672 6089148901 65,56% 34,44% >> sdi >> osd19279766405 1053039640 1332806045 20,99% 79,01% >> sdj >> >> node3 >> osd8 3711322586 234696960 3946019546 94,05% 5,95% >> sda >> osd9 1203912715 313299 4336902715 27,76% 72,24% >> sdb >> osd10912356010 1681434416 2593790426 35,17% 64,83% >> sdc >> osd11810488345 2626589896 3437078241 23,58% 76,42% >> sdd >> osd201506879946 2421596680 3928476626 38,36% 61,64% >> sdg >> osd212991526593 7525120 2999051713 99,75% 0,25% >> sdh >> osd22295603373226114552 3255674889 0,91% 99
[ceph-users] Re: extract disk usage stats from running ceph cluster
Hi Joe and Mehmet! Thanks for your responses! The requested outputs at the end of the message. But to make my question more clear: What we are actually after, is not about CURRENT usage of our OSDs, but stats on total GBs written in the cluster, per OSD, and read/write ratio. With those numbers, we would be able to identify suitable replacement SSDs for our current HDDs, and select specifically for OUR typical use. (taking into account endurance, speed, price, etc, etc) And it seems smartctl on our seagate ST4000NM0034 drives do not give us data on total bytes written or read. (...or are we simply not looking in the right place..?) Requested outputs below: root@node1:~# ceph osd df tree ID CLASS WEIGHT REWEIGHT SIZEUSE AVAIL %USE VAR PGS TYPE NAME -1 87.35376- 87.3TiB 49.1TiB 38.2TiB 56.22 1.00 - root default -2 29.11688- 29.1TiB 16.4TiB 12.7TiB 56.23 1.00 - host node1 0 hdd 3.64000 1.0 3.64TiB 2.01TiB 1.62TiB 55.34 0.98 137 osd.0 1 hdd 3.64000 1.0 3.64TiB 2.09TiB 1.54TiB 57.56 1.02 141 osd.1 2 hdd 3.63689 1.0 3.64TiB 1.92TiB 1.72TiB 52.79 0.94 128 osd.2 3 hdd 3.64000 1.0 3.64TiB 2.07TiB 1.57TiB 56.90 1.01 143 osd.3 12 hdd 3.64000 1.0 3.64TiB 2.15TiB 1.48TiB 59.18 1.05 138 osd.12 13 hdd 3.64000 1.0 3.64TiB 1.99TiB 1.64TiB 54.80 0.97 131 osd.13 14 hdd 3.64000 1.0 3.64TiB 1.93TiB 1.70TiB 53.13 0.94 127 osd.14 15 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.10 1.07 143 osd.15 -3 29.12000- 29.1TiB 16.4TiB 12.7TiB 56.22 1.00 - host node2 4 hdd 3.64000 1.0 3.64TiB 2.11TiB 1.53TiB 57.97 1.03 142 osd.4 5 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.11 0.96 134 osd.5 6 hdd 3.64000 1.0 3.64TiB 2.12TiB 1.51TiB 58.40 1.04 142 osd.6 7 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.66TiB 54.28 0.97 128 osd.7 16 hdd 3.64000 1.0 3.64TiB 2.00TiB 1.64TiB 54.90 0.98 133 osd.16 17 hdd 3.64000 1.0 3.64TiB 2.33TiB 1.30TiB 64.14 1.14 153 osd.17 18 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.07 0.96 132 osd.18 19 hdd 3.64000 1.0 3.64TiB 1.89TiB 1.75TiB 51.93 0.92 124 osd.19 -4 29.11688- 29.1TiB 16.4TiB 12.7TiB 56.22 1.00 - host node3 8 hdd 3.64000 1.0 3.64TiB 1.79TiB 1.85TiB 49.24 0.88 123 osd.8 9 hdd 3.64000 1.0 3.64TiB 2.17TiB 1.47TiB 59.72 1.06 144 osd.9 10 hdd 3.64000 1.0 3.64TiB 2.40TiB 1.24TiB 65.88 1.17 157 osd.10 11 hdd 3.64000 1.0 3.64TiB 2.06TiB 1.58TiB 56.64 1.01 133 osd.11 20 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.23 1.07 148 osd.20 21 hdd 3.64000 1.0 3.64TiB 1.74TiB 1.90TiB 47.80 0.85 115 osd.21 22 hdd 3.64000 1.0 3.64TiB 2.05TiB 1.59TiB 56.27 1.00 138 osd.22 23 hdd 3.63689 1.0 3.64TiB 1.96TiB 1.67TiB 54.01 0.96 130 osd.23 TOTAL 87.3TiB 49.1TiB 38.2TiB 56.22 MIN/MAX VAR: 0.85/1.17 STDDEV: 4.08 root@node1:~# ceph osd status ++--+---+---++-++-+---+ | id | host | used | avail | wr ops | wr data | rd ops | rd data | state | ++--+---+---++-++-+---+ | 0 | node1 | 2061G | 1663G | 38 | 5168k |3 | 1491k | exists,up | | 1 | node1 | 2143G | 1580G |4 | 1092k |9 | 2243k | exists,up | | 2 | node1 | 1965G | 1758G | 20 | 3643k |5 | 1758k | exists,up | | 3 | node1 | 2119G | 1605G | 17 | 99.5k |4 | 3904k | exists,up | | 4 | node2 | 2158G | 1565G | 12 | 527k |1 | 2632k | exists,up | | 5 | node2 | 2014G | 1709G | 15 | 239k |0 | 889k | exists,up | | 6 | node2 | 2174G | 1549G | 11 | 1677k |5 | 1931k | exists,up | | 7 | node2 | 2021G | 1702G |2 | 597k |0 | 1638k | exists,up | | 8 | node3 | 1833G | 1890G |4 | 564k |4 | 5595k | exists,up | | 9 | node3 | 2223G | 1500G |6 | 1124k | 10 | 4864k | exists,up | | 10 | node3 | 2453G | 1270G |8 | 1257k |3 | 1447k | exists,up | | 11 | node3 | 2109G | 1614G | 14 | 2889k |3 | 1449k | exists,up | | 12 | node1 | 2204G | 1520G | 17 | 1596k |4 | 1806k | exists,up | | 13 | node1 | 2040G | 1683G | 15 | 2526k |0 | 819k | exists,up | | 14 | node1 | 1978G | 1745G | 11 | 1713k |8 | 3489k | exists,up | | 15 | node1 | 2238G | 1485G | 25 | 5151k |5 | 2715k | exists,up | | 16 | node2 | 2044G | 1679G |2 | 43.3k |1 | 3371k | exists,up | | 17 | node2 | 2388G | 1335G | 14 | 1736k |9 | 5315k | exists,up | | 18 | node2 | 2013G | 1710G |8 | 1907k |2 | 2004k | exists,up | | 19 | node2
[ceph-users] Re: extract disk usage stats from running ceph cluster
>>>And it seems smartctl on our seagate ST4000NM0034 drives do not give us data on total bytes written or read If it's a SAS device, it's not always obvious where to find this information. You can use Seagate's openseachest toolset. For any (SAS/SATA, HDD/SSD) device, the --deviceInfo will give you some of the info you are looking for; e.g. sudo ./openSeaChest_Info -d /dev/sg1 --deviceInfo | grep Total Total Bytes Read (TB): 82.46 Total Bytes Written (TB): 311.56 On Tue, Feb 11, 2020 at 3:10 AM lists wrote: > > Hi Joe and Mehmet! > > Thanks for your responses! > > The requested outputs at the end of the message. > > But to make my question more clear: > > What we are actually after, is not about CURRENT usage of our OSDs, but > stats on total GBs written in the cluster, per OSD, and read/write ratio. > > With those numbers, we would be able to identify suitable replacement > SSDs for our current HDDs, and select specifically for OUR typical use. > (taking into account endurance, speed, price, etc, etc) > > And it seems smartctl on our seagate ST4000NM0034 drives do not give us > data on total bytes written or read. (...or are we simply not looking in > the right place..?) > > Requested outputs below: > > > root@node1:~# ceph osd df tree > > ID CLASS WEIGHT REWEIGHT SIZEUSE AVAIL %USE VAR PGS TYPE NAME > > -1 87.35376- 87.3TiB 49.1TiB 38.2TiB 56.22 1.00 - root > > default > > -2 29.11688- 29.1TiB 16.4TiB 12.7TiB 56.23 1.00 - host > > node1 > > 0 hdd 3.64000 1.0 3.64TiB 2.01TiB 1.62TiB 55.34 0.98 137 > > osd.0 > > 1 hdd 3.64000 1.0 3.64TiB 2.09TiB 1.54TiB 57.56 1.02 141 > > osd.1 > > 2 hdd 3.63689 1.0 3.64TiB 1.92TiB 1.72TiB 52.79 0.94 128 > > osd.2 > > 3 hdd 3.64000 1.0 3.64TiB 2.07TiB 1.57TiB 56.90 1.01 143 > > osd.3 > > 12 hdd 3.64000 1.0 3.64TiB 2.15TiB 1.48TiB 59.18 1.05 138 > > osd.12 > > 13 hdd 3.64000 1.0 3.64TiB 1.99TiB 1.64TiB 54.80 0.97 131 > > osd.13 > > 14 hdd 3.64000 1.0 3.64TiB 1.93TiB 1.70TiB 53.13 0.94 127 > > osd.14 > > 15 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.10 1.07 143 > > osd.15 > > -3 29.12000- 29.1TiB 16.4TiB 12.7TiB 56.22 1.00 - host > > node2 > > 4 hdd 3.64000 1.0 3.64TiB 2.11TiB 1.53TiB 57.97 1.03 142 > > osd.4 > > 5 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.11 0.96 134 > > osd.5 > > 6 hdd 3.64000 1.0 3.64TiB 2.12TiB 1.51TiB 58.40 1.04 142 > > osd.6 > > 7 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.66TiB 54.28 0.97 128 > > osd.7 > > 16 hdd 3.64000 1.0 3.64TiB 2.00TiB 1.64TiB 54.90 0.98 133 > > osd.16 > > 17 hdd 3.64000 1.0 3.64TiB 2.33TiB 1.30TiB 64.14 1.14 153 > > osd.17 > > 18 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.07 0.96 132 > > osd.18 > > 19 hdd 3.64000 1.0 3.64TiB 1.89TiB 1.75TiB 51.93 0.92 124 > > osd.19 > > -4 29.11688- 29.1TiB 16.4TiB 12.7TiB 56.22 1.00 - host > > node3 > > 8 hdd 3.64000 1.0 3.64TiB 1.79TiB 1.85TiB 49.24 0.88 123 > > osd.8 > > 9 hdd 3.64000 1.0 3.64TiB 2.17TiB 1.47TiB 59.72 1.06 144 > > osd.9 > > 10 hdd 3.64000 1.0 3.64TiB 2.40TiB 1.24TiB 65.88 1.17 157 > > osd.10 > > 11 hdd 3.64000 1.0 3.64TiB 2.06TiB 1.58TiB 56.64 1.01 133 > > osd.11 > > 20 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.23 1.07 148 > > osd.20 > > 21 hdd 3.64000 1.0 3.64TiB 1.74TiB 1.90TiB 47.80 0.85 115 > > osd.21 > > 22 hdd 3.64000 1.0 3.64TiB 2.05TiB 1.59TiB 56.27 1.00 138 > > osd.22 > > 23 hdd 3.63689 1.0 3.64TiB 1.96TiB 1.67TiB 54.01 0.96 130 > > osd.23 > > TOTAL 87.3TiB 49.1TiB 38.2TiB 56.22 > > MIN/MAX VAR: 0.85/1.17 STDDEV: 4.08 > > root@node1:~# ceph osd status > > ++--+---+---++-++-+---+ > > | id | host | used | avail | wr ops | wr data | rd ops | rd data | state > > | > > ++--+---+---++-++-+---+ > > | 0 | node1 | 2061G | 1663G | 38 | 5168k |3 | 1491k | > > exists,up | > > | 1 | node1 | 2143G | 1580G |4 | 1092k |9 | 2243k | > > exists,up | > > | 2 | node1 | 1965G | 1758G | 20 | 3643k |5 | 1758k | > > exists,up | > > | 3 | node1 | 2119G | 1605G | 17 | 99.5k |4 | 3904k | > > exists,up | > > | 4 | node2 | 2158G | 1565G | 12 | 527k |1 | 2632k | > > exists,up | > > | 5 | node2 | 2014G | 1709G | 15 | 239k |0 | 889k | > > exists,up | > > | 6 | node2 | 2174G | 1549G | 11 | 1677k |5 | 1931k | > > exists,up | > > | 7 | node2 | 2021G | 1702G |2 | 597k |0 | 1638k | > > exists,up | > > | 8 | node3 | 1833G
[ceph-users] Re: extract disk usage stats from running ceph cluster
Hi Muhammad, Yes, that tool helps! Thank you for pointing it out! With a combination of openSeaChest_Info and smartctl I was able to extract the following stats of our cluster, and the numbers are very surprising to me. I hope someone here can explain the what we see below: node1 AnnualWrkload ReadWritten Power On Hours osd0 93.14 318.7919.48 31815.65 osd1 94.38 322.6720.11 31815.42 osd2 41.08 38.9511.33 10722.47new disk osd3 94.56 323.9819.45 31815.35 osd12 124.20 340.1120.09 25406.73 osd13 112.43 308.1817.88 25405.72 sdb14 120.67 330.9619.01 25405.65 osd15 105.59 287.7818.45 25405.90 ssd journal 0.46 1643.58 31813.00 node2 osd4697.75 2390 151.23 31864.88(2.39PB) osd5677.74 2320 144.94 31864.68(2.32PB) osd6687.13 2340 157.11 31865.05(2.34PB) osd7619.19 2100 151.08 31864.67(2.10PB) osd16 827.57 2260 142.81 25405.93(2.26PB) osd17 996.03 2720 167.97 25405.87(2.72PB) osd18 809.36 2210 137.96 25405.82(2.21PB) osd19 844.06 2300 146.84 25405.90(2.30PB) ssd journal 0.461637.60 31862.00 node3 osd8 75.30 258.7914.67 31813.67 osd9 77.30 264.8715.85 31813.68 osd1082.32 282.4316.53 31813.60 osd1182.26 282.7216.01 31813.73 osd2096.86 265.2515.65 25404.37 osd2193.18 256.1114.12 25404.22 osd22 108.43 298.2916.15 25404.23 osd2330.80 33.6110.78 12625.07new disk ssd journal 0.46 1644.83 31811.00 AnnualWrkload = Annualized Workload Rate (TB/year) Read = Total Bytes Read (TB) Written = Total Bytes Written (TB) Power On Hours = hours the drive has been used From the numbers above, it seems the OSDs on node2 are used INCREDIBLY much more than those on the other two nodes. The numbers for node2 are even reported in PB, and the other nodes in TB. (converted to TB using https://www.gbmb.org/pb-to-tb, to make sure there are no conversion errors) However, SSD journal usage across the three nodes looks similar. All OSDs have the same weight: root@node2:~# ceph osd tree ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF -1 87.35376 root default -2 29.11688 host pm1 0 hdd 3.64000 osd.0 up 1.0 1.0 1 hdd 3.64000 osd.1 up 1.0 1.0 2 hdd 3.63689 osd.2 up 1.0 1.0 3 hdd 3.64000 osd.3 up 1.0 1.0 12 hdd 3.64000 osd.12 up 1.0 1.0 13 hdd 3.64000 osd.13 up 1.0 1.0 14 hdd 3.64000 osd.14 up 1.0 1.0 15 hdd 3.64000 osd.15 up 1.0 1.0 -3 29.12000 host pm2 4 hdd 3.64000 osd.4 up 1.0 1.0 5 hdd 3.64000 osd.5 up 1.0 1.0 6 hdd 3.64000 osd.6 up 1.0 1.0 7 hdd 3.64000 osd.7 up 1.0 1.0 16 hdd 3.64000 osd.16 up 1.0 1.0 17 hdd 3.64000 osd.17 up 1.0 1.0 18 hdd 3.64000 osd.18 up 1.0 1.0 19 hdd 3.64000 osd.19 up 1.0 1.0 -4 29.11688 host pm3 8 hdd 3.64000 osd.8 up 1.0 1.0 9 hdd 3.64000 osd.9 up 1.0 1.0 10 hdd 3.64000 osd.10 up 1.0 1.0 11 hdd 3.64000 osd.11 up 1.0 1.0 20 hdd 3.64000 osd.20 up 1.0 1.0 21 hdd 3.64000 osd.21 up 1.0 1.0 22 hdd 3.64000 osd.22 up 1.0 1.0 23 hdd 3.63689 osd.23 up 1.0 1.0 Disk usage also looks ok: root@pm2:~# ceph osd df ID CLASS WEIGHT REWEIGHT SIZEUSE AVAIL %USE VAR PGS 0 hdd 3.64000 1.0 3.64TiB 2.01TiB 1.62TiB 55.34 0.98 137 1 hdd 3.64000 1.0 3.64TiB 2.09TiB 1.54TiB 57.56 1.02 141 2 hdd 3.63689 1.0 3.64TiB 1.92TiB 1.72TiB 52.79 0.94 128 3 hdd 3.64000 1.0 3.64TiB 2.07TiB 1.57TiB 56.90 1.01 143 12
[ceph-users] Re: extract disk usage stats from running ceph cluster
On 2/12/20 11:23 AM, mj wrote: Better layout for the disks usage stats: https://pastebin.com/8V5VDXNt ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
[ceph-users] Re: extract disk usage stats from running ceph cluster
Hi, I would like to understand why the OSD HDDs on node2 of my three identical ceph hosts claim to have processed 10 times more reads/writes than the other two nodes. OSD weights are all the similar, disk usage in space also, same disk sizes, same reported disk usage hours etc, etc. All data (QEMU VMs) is in one large 3/2 pool, called "ceph-storage". This is on ceph version 12.2.10. The spreadsheet with all the stats: https://docs.google.com/spreadsheets/d/1n8aOC1tpPPMi2iALhxfHzSQTRmfIz6wCERlagNShVss/edit?usp=sharing I hope the information is now both complete and readable, let me know if anything else is needed. Curious for any insights. The previously requested outputs below. root@node1:~# ceph osd df ID CLASS WEIGHT REWEIGHT SIZEUSE AVAIL %USE VAR PGS 0 hdd 3.64000 1.0 3.64TiB 2.01TiB 1.62TiB 55.35 0.98 137 1 hdd 3.64000 1.0 3.64TiB 2.09TiB 1.54TiB 57.56 1.02 141 2 hdd 3.63689 1.0 3.64TiB 1.92TiB 1.72TiB 52.80 0.94 128 3 hdd 3.64000 1.0 3.64TiB 2.07TiB 1.57TiB 56.91 1.01 143 12 hdd 3.64000 1.0 3.64TiB 2.15TiB 1.48TiB 59.19 1.05 138 13 hdd 3.64000 1.0 3.64TiB 1.99TiB 1.64TiB 54.81 0.97 131 14 hdd 3.64000 1.0 3.64TiB 1.93TiB 1.70TiB 53.14 0.94 127 15 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.11 1.07 143 4 hdd 3.64000 1.0 3.64TiB 2.11TiB 1.53TiB 57.98 1.03 142 5 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.11 0.96 134 6 hdd 3.64000 1.0 3.64TiB 2.12TiB 1.51TiB 58.41 1.04 142 7 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.66TiB 54.29 0.97 128 16 hdd 3.64000 1.0 3.64TiB 2.00TiB 1.64TiB 54.90 0.98 133 17 hdd 3.64000 1.0 3.64TiB 2.33TiB 1.30TiB 64.15 1.14 153 18 hdd 3.64000 1.0 3.64TiB 1.97TiB 1.67TiB 54.08 0.96 132 19 hdd 3.64000 1.0 3.64TiB 1.89TiB 1.75TiB 51.94 0.92 124 8 hdd 3.64000 1.0 3.64TiB 1.79TiB 1.85TiB 49.25 0.88 123 9 hdd 3.64000 1.0 3.64TiB 2.17TiB 1.46TiB 59.73 1.06 144 10 hdd 3.64000 1.0 3.64TiB 2.40TiB 1.24TiB 65.89 1.17 157 11 hdd 3.64000 1.0 3.64TiB 2.06TiB 1.58TiB 56.65 1.01 133 20 hdd 3.64000 1.0 3.64TiB 2.19TiB 1.45TiB 60.24 1.07 148 21 hdd 3.64000 1.0 3.64TiB 1.74TiB 1.90TiB 47.80 0.85 115 22 hdd 3.64000 1.0 3.64TiB 2.05TiB 1.59TiB 56.28 1.00 138 23 hdd 3.63689 1.0 3.64TiB 1.96TiB 1.67TiB 54.02 0.96 130 TOTAL 87.3TiB 49.1TiB 38.2TiB 56.23 MIN/MAX VAR: 0.85/1.17 STDDEV: 4.08 and root@node1:~# ceph osd tree ID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF -1 87.35376 root default -2 29.11688 host node1 0 hdd 3.64000 osd.0 up 1.0 1.0 1 hdd 3.64000 osd.1 up 1.0 1.0 2 hdd 3.63689 osd.2 up 1.0 1.0 3 hdd 3.64000 osd.3 up 1.0 1.0 12 hdd 3.64000 osd.12 up 1.0 1.0 13 hdd 3.64000 osd.13 up 1.0 1.0 14 hdd 3.64000 osd.14 up 1.0 1.0 15 hdd 3.64000 osd.15 up 1.0 1.0 -3 29.12000 host node2 4 hdd 3.64000 osd.4 up 1.0 1.0 5 hdd 3.64000 osd.5 up 1.0 1.0 6 hdd 3.64000 osd.6 up 1.0 1.0 7 hdd 3.64000 osd.7 up 1.0 1.0 16 hdd 3.64000 osd.16 up 1.0 1.0 17 hdd 3.64000 osd.17 up 1.0 1.0 18 hdd 3.64000 osd.18 up 1.0 1.0 19 hdd 3.64000 osd.19 up 1.0 1.0 -4 29.11688 host node3 8 hdd 3.64000 osd.8 up 1.0 1.0 9 hdd 3.64000 osd.9 up 1.0 1.0 10 hdd 3.64000 osd.10 up 1.0 1.0 11 hdd 3.64000 osd.11 up 1.0 1.0 20 hdd 3.64000 osd.20 up 1.0 1.0 21 hdd 3.64000 osd.21 up 1.0 1.0 22 hdd 3.64000 osd.22 up 1.0 1.0 23 hdd 3.63689 osd.23 up 1.0 1.0 MJ ___ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io