Hello
Conversation
Notices
-
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:36:07 JST :apa: スプリットショックウイルス † - † top dog :pedomustdie: likes this.
-
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:36:13 JST :apa: スプリットショックウイルス † @graf LIkewise, they haven't got to me yet.
† top dog :pedomustdie: likes this. -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Tuesday, 16-Jan-2024 12:36:14 JST :btrfly: anime graf mays 🛰️🪐 @splitshockvirus happens to the best of us friend. glad you're still around -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Tuesday, 16-Jan-2024 12:36:15 JST :btrfly: anime graf mays 🛰️🪐 @splitshockvirus Hello -
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:36:15 JST :apa: スプリットショックウイルス † @graf Pleromer ran out of space
-
† top dog :pedomustdie: (dcc@annihilation.social)'s status on Tuesday, 16-Jan-2024 12:36:30 JST † top dog :pedomustdie: @splitshockvirus @graf #itsover -
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:39:11 JST :apa: スプリットショックウイルス † I'm setting up external storage and moving the DB to it so this doesn't happen again (for a long time).
† top dog :pedomustdie: likes this. -
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:43:18 JST :apa: スプリットショックウイルス † Well... :nana_smug:
It should have similar IOPS right? Like 1000 is enough for pleroma right? :nana_smug:Or am I actually going to have to pony up money for a larger NVME?
-
† top dog :pedomustdie: (dcc@annihilation.social)'s status on Tuesday, 16-Jan-2024 12:43:18 JST † top dog :pedomustdie: @splitshockvirus @graf Mf'ers out here using nvme's while im using sata ssd's. -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Tuesday, 16-Jan-2024 12:43:19 JST :btrfly: anime graf mays 🛰️🪐 @splitshockvirus @dcc >db on external
oh no -
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:45:18 JST :apa: スプリットショックウイルス † Well that's what they advertise it as but Hetzner IOPS are limited to 7k IOPS on NVMEs so I actually get worse performance than your SATAs.
If I just had this shit on Danksquad it wouldn't be an issue, but I don't.
† top dog :pedomustdie: likes this. -
† top dog :pedomustdie: (dcc@annihilation.social)'s status on Tuesday, 16-Jan-2024 12:47:01 JST † top dog :pedomustdie: @graf @splitshockvirus I see, i have a raid 10 20tb array on hdd's but just a 4tb and 2tb sdd for the new main server. -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Tuesday, 16-Jan-2024 12:47:02 JST :btrfly: anime graf mays 🛰️🪐 @dcc @splitshockvirus poast database for your perusal, friend
Personalities : [raid10] md127 : active raid10 nvme0n1p2[0] nvme3n1p1[3] nvme2n1p1[2] nvme1n1p1[1] 3748384768 blocks super 1.2 512K chunks 2 near-copies [4/4] [UUUU] bitmap: 8/28 pages [32KB], 65536KB chunk/dev/md127: Version : 1.2 Creation Time : Mon Oct 23 21:38:52 2023 Raid Level : raid10 Array Size : 3748384768 (3.49 TiB 3.84 TB) Used Dev Size : 1874192384 (1787.37 GiB 1919.17 GB) Raid Devices : 4 Total Devices : 4 Persistence : Superblock is persistent Intent Bitmap : Internal Update Time : Tue Jan 16 03:43:41 2024 State : active Active Devices : 4 Working Devices : 4 Failed Devices : 0 Spare Devices : 0 Layout : near=2 Chunk Size : 512K Consistency Policy : bitmap Name : livecd:0 UUID : 9001ffa6:8f0d009c:ba814e3f:c93a2598 Events : 5670 Number Major Minor RaidDevice State 0 259 5 0 active sync set-A /dev/nvme0n1p2 1 259 8 1 active sync set-B /dev/nvme1n1p1 2 259 7 2 active sync set-A /dev/nvme2n1p1 3 259 6 3 active sync set-B /dev/nvme3n1p1 -
† top dog :pedomustdie: (dcc@annihilation.social)'s status on Tuesday, 16-Jan-2024 12:49:47 JST † top dog :pedomustdie: @graf @splitshockvirus >7tb
Less than i expected, i wont have any storage problems anytime soon then. -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Tuesday, 16-Jan-2024 12:49:48 JST :btrfly: anime graf mays 🛰️🪐 @dcc @splitshockvirus poast media:
md127 : active raid10 nvme4n1p1[4] nvme7n1p1[7] nvme3n1p1[3] nvme2n1p1[2] nvme5n1p1[5] nvme1n1p1[1] nvme0n1p1[0] nvme6n1p1[6] 7500963840 blocks super 1.2 512K chunks 2 near-copies [8/8] [UUUUUUUU] bitmap: 2/56 pages [8KB], 65536KB chunk/dev/md127: Version : 1.2 Creation Time : Tue Oct 24 04:04:50 2023 Raid Level : raid10 Array Size : 7500963840 (6.99 TiB 7.68 TB) Used Dev Size : 1875240960 (1788.37 GiB 1920.25 GB) Raid Devices : 8 Total Devices : 8 Persistence : Superblock is persistent Intent Bitmap : Internal Update Time : Tue Jan 16 03:48:23 2024 State : clean Active Devices : 8 Working Devices : 8 Failed Devices : 0 Spare Devices : 0 Layout : near=2 Chunk Size : 512K Consistency Policy : bitmap Name : livecd:0 UUID : c1e08cf9:1ec433fa:808457a1:3850d892 Events : 9362 Number Major Minor RaidDevice State 0 259 2 0 active sync set-A /dev/nvme0n1p1 1 259 3 1 active sync set-B /dev/nvme1n1p1 2 259 13 2 active sync set-A /dev/nvme2n1p1 3 259 10 3 active sync set-B /dev/nvme3n1p1 4 259 14 4 active sync set-A /dev/nvme4n1p1 5 259 11 5 active sync set-B /dev/nvme5n1p1 6 259 15 6 active sync set-A /dev/nvme6n1p1 7 259 12 7 active sync set-B /dev/nvme7n1p1 -
:apa: スプリットショックウイルス † (splitshockvirus@mstdn.starnix.network)'s status on Tuesday, 16-Jan-2024 12:51:03 JST :apa: スプリットショックウイルス † Just finished provisioning this one while listening to some cuck on YT rank im@s characters
[code]
root@cn56.sfo-ca:~# cat /proc/mdstat
Personalities : [raid10] [linear] [multipath] [raid0] [raid1] [raid6] [raid5] [raid4]
md1 : active raid10 nvme1n1p3[3] nvme3n1p3[1] nvme0n1p3[2] nvme2n1p3[0]
12500080640 blocks super 1.2 512K chunks 2 near-copies [4/4] [UUUU]
bitmap: 2/94 pages [8KB], 65536KB chunkmd0 : active raid10 nvme1n1p2[3] nvme3n1p2[1] nvme0n1p2[2] nvme2n1p2[0]
2093056 blocks super 1.2 512K chunks 2 near-copies [4/4] [UUUU]unused devices:
root@cn56.sfo-ca:~# mdadm --detail /dev/md1
/dev/md1:
Version : 1.2
Creation Time : Mon Jan 8 14:26:57 2024
Raid Level : raid10
Array Size : 12500080640 (11921.01 GiB 12800.08 GB)
Used Dev Size : 6250040320 (5960.50 GiB 6400.04 GB)
Raid Devices : 4
Total Devices : 4
Persistence : Superblock is persistentIntent Bitmap : Internal
Update Time : Mon Jan 15 22:48:56 2024
State : clean
Active Devices : 4
Working Devices : 4
Failed Devices : 0
Spare Devices : 0Layout : near=2
Chunk Size : 512KConsistency Policy : bitmap
Name : cn56:1 (local to host cn56)
UUID : 8dadefa4:0cc53826:eac8f188:b9e1678f
Events : 38176Number Major Minor RaidDevice State
0 259 8 0 active sync set-A /dev/nvme2n1p3
1 259 12 1 active sync set-B /dev/nvme3n1p3
2 259 5 2 active sync set-A /dev/nvme0n1p3
3 259 15 3 active sync set-B /dev/nvme1n1p3
[/code]† top dog :pedomustdie: likes this. -
:btrfly: anime graf mays 🛰️🪐 (graf@poa.st)'s status on Wednesday, 17-Jan-2024 02:25:24 JST :btrfly: anime graf mays 🛰️🪐 @splitshockvirus @dcc speaking from experience, on a slow instance with little/no users (<100 active) HDD speed (90-100MB/s r/w) is fine. the problem is the design of the pleroma database is just so bad. @p will agree with me and can explain it in maybe a more elegant way -
pistolero :thispersondoesnotexist: (p@freespeechextremist.com)'s status on Wednesday, 17-Jan-2024 02:25:24 JST pistolero :thispersondoesnotexist: @graf @splitshockvirus @dcc
> on a slow instance with little/no users (<100 active) HDD speed (90-100MB/s r/w) is fine.
It depends more on how many remote accounts have local followers and how many local accounts have remote followers than on the number of local accounts, but since small instances can run fine on shit-tier VMs with less than a gig of RAM, I'd say this is correct.
> the problem is the design of the pleroma database is just so bad. @p will agree with me and can explain it in maybe a more elegant way
Well, I wouldn't agree that it's bad, but there are some tradeoffs that were made for the sake of correctness/flexibility and efficiency was on the other end. For example, the indexes are bloated because of the URLs being used as keys, the URLs are used as keys because the raw AP JSON blobs are treated as canonical.
This gives a lot of advantages: the FE can just deal with AP objects, the backend just has to ship AP objects around between servers and occasionally send them to the FE. There are no transformation problems to debug because there are no transformations, and debugging is easier in general because what you keep in the DB matches what you put on the wire, learning how the protocol works and learning how the DB is structured are nearly the same thing.
The downside is that, you know, instead of looking up a 64-bit int in the DB, you're looking up 'https://poa.st/objects/78a0e635-cc57-4d91-a550-715790ce7acc', and there's non-zero overhead for that, especially in terms of on-disk representations for indexes, and that eventually piles up, you do more seeks because the data is bigger, etc. Indexes are taken off the JSON blobs directly (well, JSONB, but it's still got non-zero overhead) so there's a lot of packing/unpacking of fields, and because the data is kept as-is, there are a lot of queries that use COALESCE() and CASE/WHEN that you wouldn't need otherwise. But that is one of the reasons Pleroma has such great compatibility, even forward-compatibility in a lot of cases: when EmojiReact happened, instances that didn't support it only needed frontend changes to support the new Activity type and since the backend is relatively agnostic¹, adding frontend support magically made EmojiReact activities from the past appear. Mastodon can't do that sort of thing (though it doesn't really have to, because it's the majority of the network and decides what everyone *else* has to support).
¹ Ironically, given the software was named for a Gnostic concept.† top dog :pedomustdie: likes this. -
(mint@ryona.agency)'s status on Wednesday, 17-Jan-2024 03:04:56 JST @p @dcc @splitshockvirus @graf >when EmojiReact happened, instances that didn't support it only needed frontend changes to support the new Activity type and since the backend is relatively agnostic
Sounds like bullshit to me. Object validator rejects activities of unknown type, so to get them to federate you still need backend support on both sides. -
pistolero :thispersondoesnotexist: (p@freespeechextremist.com)'s status on Wednesday, 17-Jan-2024 05:47:33 JST pistolero :thispersondoesnotexist: @mint @dcc @graf @splitshockvirus
> Object validator rejects activities of unknown type,
Object types and Activity types are different, but you can dig through the database for old posts and see people finding EmojiReactions federating before they existed. Maybe this has changed.
I had to clear some of them from the DB because they started breaking some scripts I used to detect bots. (This was admittedly brittle design, but I had hard-coded the activity types way back when; this was emergency code written to cope with the Gabpocalypse.) There were some remarks lain made about adding new ActivityPub verbs (something like "People think you can't add new ActivityPub verbs, but you really can.") and that line managed to stick with me but no information on whether there was an accompanying blog post or any elaboration remain in my head. likes this. -
(mint@ryona.agency)'s status on Wednesday, 17-Jan-2024 05:49:31 JST @p @dcc @splitshockvirus @graf >Maybe this has changed.
Maybe. I was talking from experience upgrading my instance to support quoteposts and custom reacts; none of those appeared retroactively on older posts. -
pistolero :thispersondoesnotexist: (p@freespeechextremist.com)'s status on Wednesday, 17-Jan-2024 07:29:42 JST pistolero :thispersondoesnotexist: @mint @dcc @graf @splitshockvirus This is entirely plausible. Quoteposts are another thing entirely, but as I recall, the reactions arrived before FSE had support for them and they sort of sat there, inert. They didn't generate notifications. likes this.