log☇︎
600+ entries in 0.293s
asciilifeform: ACHTUNG, panzers! lobbes , diana_coman , et al : reader.py on dulap updated to lobbes's raw-export-fix. vtree page updated w/ lobbes patch and lobbes , asciilifeform , sigs.
asciilifeform: mircea_popescu: we'll snapshot the os a la dulap/smg so can be done reasonably quickly, when disk goes.
asciilifeform: mircea_popescu: looked for evidence of outages, but on neither dulap or own console , found any yet ( no disconnects of bot ; nor drop of shell from dulap to own chair, it's been standing for month+ )
snsabot: Logged on 2019-05-02 09:56:16 asciilifeform: http://btcbase.org/log/2019-05-02#1910633 << there's actually not 1 but 2 'standard os' available in piz ( 'rk' and 'dulap' tarballs ) but both are stone age gentoos, they are obsoleted by cuntoo (when the latter is pronounced baked, but really even nao, it is impossible to e.g. 'emerge' packages on the vintage gentoo, the upstream package repos went full tard year ago )
asciilifeform: ( on dulap, where deployed -- 10.3 )
asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-24#1930756 << ftr, right nao it loox like : pg_dump nsalog | gzip > /home/nsabot/log_db.gz; and on dulap , eats <8sec . ( getting the output to other boxes, however... )
asciilifeform: ftr , on dulap itself : time curl http://127.0.0.1:5002/log/trilema/2018-10-12 > /dev/null yields 0.161s .
asciilifeform: trinque: atm the bot on dulap is 'naked' <-> fleanode
snsabot: Logged on 2019-08-19 21:20:26 asciilifeform: ftr gets ~80kB/s avg. from dulap, there.
asciilifeform: ^ dulap incidentally performs considerably better , unsurprisingly, than the pseudo-sadmachine, in re actual page generation on local end.
asciilifeform: ftr gets ~80kB/s avg. from dulap, there.
asciilifeform: BingoBoingo, lobbes , et al : i'ma leave the rubbish box to run until further notice, and give it cron job that eats db from dulap erry day .
asciilifeform did not bother to sync the clock, so times on shit mirror will vary vs. dulap's
asciilifeform: i suppose for completeness will mention an alt-hypothesis -- somehow nic on dulap is culprit.
asciilifeform: lobbes: let it eat the #u archive, then run reader.py, take a look at the known barf lines from before. if it ate correctly, make again vpatch (from current leaf of tree) and i'ma sign, then eat on dulap.
asciilifeform: deployed to dulap.
asciilifeform: mp_en_viaje: 0 eggog on dulap-side log.
asciilifeform digging through barfology log on dulap, will brb
asciilifeform: the other side of this, is q of 'what is canonical log' . i.e. is it mp_en_viaje's terminal (runs for 3-4 hrs / d ? and where did not even notice index off, asciilifeform had to notice and ring alarm ) ? asciilifeform's term ? (runs 24/7, but down for maybe 10min / yr ) ? or dulap 's ?
asciilifeform: ( from asciilifeform's chair ; 0.9 when executed locally on dulap , via ng i.e. the public url )
asciilifeform: it aint best possible pipe, but pretty good; and , as i pointed out already, effect persists ~without~ it ( i.e. operating curl within dulap shaves only 200msec vs to my chair; and has same peculiar 'burst' pattern and wild variance in total time )
asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-13#1928224 << ftr i routinely get 1-2 MB/s from my chair to dulap and reverse
asciilifeform: if somebody's sat for ~minute~ , sounds like sslism ( not in use on dulap and never will be )
asciilifeform: ( and if cures, move dulap entirely to classic apache. back in the old days went w/ 'nginx' because slightly moar miserly re memory )
asciilifeform: dulap aint currently swamped with loads, either
asciilifeform: soo, in strange findings: on dulap, 'time curl http://logs.nosuchlabs.com/log' yields 2.342s; ( from my chair, same -- 2.455s ); but on identical (3m ago) clone of db , running locally, on substantially slower box, 0.252s !
asciilifeform: and on dulap.
asciilifeform: mircea_popescu: it lives on dulap
asciilifeform: mircea_popescu: after genesis will be pretty easy to stand up local copy. so in fact if you like can set the colours in person and vpatch, i will read, sign, upload to dulap..
asciilifeform: trinque: are you having a 'dulap-I'-style problem ??
asciilifeform: mp_en_viaje: rk and dulap 4.x , but heavily hand-cut. ( and i suspect can be cut further still . ) i dun operate kernels other than hand-cut.
a111: Logged on 2018-07-26 03:58 mod6: !!invoice mircea_popescu 0.22505299 S.NSA colocation (dulap) through June 2019
asciilifeform: BingoBoingo: you may be interested to know that my shell to dulap bumped after 132d. ( for no detectable reason, either on this end or the other )
BingoBoingo: asciilifeform: The thing is we have one pipe. That your dulap scroll continued has an element of luck. DDoS lab requires more routing than we have implemented.
asciilifeform: the shell i've had scrolling dulap log since 11 feb, didnt skip a beat, fwiw.
asciilifeform: BingoBoingo: as i said, dulap was entirely reachable last time.
asciilifeform: BingoBoingo: did they do this last time around also? cuz to date i have not once observed any problem accessing dulap
asciilifeform: dulap , interestingly, unaffected, loox like it's just uy1 that is bogged
asciilifeform: ( i.e. cat tape.peh | ./bin/peh 32768 32 100000 0 dulap_1m.bin , in this scheme all '?' output is taken from the supplied file )
a111: Logged on 2019-06-03 18:52 asciilifeform: mircea_popescu: the snsa pair is (dulap & spare-dulap) are snsa boxen
asciilifeform: mircea_popescu: the snsa pair is (dulap & spare-dulap) are snsa boxen ☟︎
BingoBoingo: Dulap's year is coming up soon http://pizarroisp.net/pizarro-records/#selection-83.1615-83.2338 but much simpler math (colo base rate of 141.7*monthstorenew)
BingoBoingo: asciilifeform: The dulap spare was yet another monthly, that one strictly billed as a colo, which hanbot played with cuntoo and then the subscription was canceled when that experiment was aborted. The S.NSA spare is cold at present.
asciilifeform: BingoBoingo: 1 of them is the dulap spare, and goes for colo rate ☝︎
asciilifeform digs though log, but still not certain which 2 boxes were spoken of. if indeed these 2, then price is diff, cuz dulap is a colo box, owned by snsa, whereas smg is leased box
asciilifeform: ( as i understand , boxes in question were dulap & smg ? )
asciilifeform: interestingly, loads from dulap
asciilifeform: to be maximally pedantic : both 'dulap' and 'rk' gentoo tarballs were created by literally tarring up the contents of two respective boxes where asciilifeform hand-sewed a gentoo based on the classic 2015-era 'kill list' gentoo recipe.
asciilifeform: ( dulap-gentoo does not boot from stick, it requires working hdd to install )
asciilifeform: iirc hanbot was ~not~ working from dulap-gentoo tho, but from an even older bootstick image.
asciilifeform: dulap-gentoo is essentially same item as rk gentoo, and is installed same way.
asciilifeform: it's what's on s.mg an' dulap. but defo obsolete, it's a stone age glibc-based gentoo.
diana_coman: asciilifeform: re dulap-tarball, does that mean that it's in fact *that* the gentoo image hanbot was looking for as stepping stone towards cuntoo? i.e. deploy that first and then from there move on to cuntoo?
asciilifeform: http://btcbase.org/log/2019-05-02#1910633 << there's actually not 1 but 2 'standard os' available in piz ( 'rk' and 'dulap' tarballs ) but both are stone age gentoos, they are obsoleted by cuntoo (when the latter is pronounced baked, but really even nao, it is impossible to e.g. 'emerge' packages on the vintage gentoo, the upstream package repos went full tard year ago ) ☝︎
asciilifeform: BingoBoingo: currently i'm thinking, 2 x dulap-style, 2 x 1u w/ ea. 4 x apu1 'amd g' where cuntoo in write-protected rom . ( i have a rom booter for the latter, built on ancient 'coreboot' )
asciilifeform: http://btcbase.org/log/2019-05-01#1910415 << diana_coman would dulap-style box suffice ? there is one. ( mp_en_viaje pointed out downthread, same 1 as hanbot worked on ) ☝︎
asciilifeform: http://p.bvulpes.com/pastes/fJa7Z/?raw=true << from dulap.
asciilifeform: dun ping from swampistan or from dulap
asciilifeform: mircea_popescu: my ( dulap & rk ) trees, eat 'n' re subj w/out choking
asciilifeform: having said this, i'm all for setting up a not-fleanode . and will put relay on dulap as soon as the matter of 'which ircd' is settled.
mod6: <+asciilifeform> we also host owner-operated iron (e.g. dulap is still snsa ; and trinque has some, and mod6 ) << The Foundation's 2nd box ("lovelace") is with ben_vulpes, currently. He's going to find a home for it in his new area, last we had talked about it. I don't have any machines on-hand that are waiting to go to .uy. However, I might be interested in buying a UY1 style machine from alf...
asciilifeform: we also host owner-operated iron (e.g. dulap is still snsa ; and trinque has some, and mod6 )
asciilifeform: ( and of course the snsa-operated dulap )
asciilifeform: hrm you defo dun want to build a kernel for a dulap-style machine with 'apu2' config
asciilifeform: re capacity : also needs discussion. currently considering rk array (1u), two x64 boxen of dulap type, and additionally a set of apu1d4 (see logs, or https://archive.is/8JBbH ) .
asciilifeform: really this whole thing oughta take ~30m on dulap ( 32 cpu )
a111: Logged on 2019-02-18 03:18 asciilifeform set up a rebuild of ave1 gnat (june) on dulap, with http://bvt-trace.net/2019/02/gnat-zero-cost-exceptions-and-asynchronous-task-aborting-part-2/comment-page-1/#selection-163.2-167.52 . tomorrow will see what came out of this.
asciilifeform set up a rebuild of ave1 gnat (june) on dulap, with http://bvt-trace.net/2019/02/gnat-zero-cost-exceptions-and-asynchronous-task-aborting-part-2/comment-page-1/#selection-163.2-167.52 . tomorrow will see what came out of this. ☟︎
asciilifeform: shinohai: mirrored nao at dulap, http://nosuchlabs.com/pub/liquishit/btcotclogs.tar.gz .
asciilifeform: http://btcbase.org/log/2019-02-11#1895021 << i saw nearly half MB of these in dulap log not long ago. iirc they're pill for ciscoisms ☝︎
asciilifeform: for instance asciilifeform has a known-working config for all dulap-like boxen; presently in use by diana_coman on iirc both diana_coman units; another for rkisms
BingoBoingo: asciilifeform: I am going to head down to the basement to put two old RK drives in dulap for zeroing and to retrieve the USB to SATA cable for zeroing the rust
asciilifeform: the standard color rate we get dulap for
asciilifeform: mircea_popescu do you want this mirrored on dulap ?
asciilifeform: BingoBoingo: when you're there, plox to stuff a new disk into dulap so i can breathe life into it
asciilifeform: ( of same type as dulap-iii and the s.mg machines )
a111: Logged on 2018-08-08 16:58 asciilifeform: BingoBoingo: i'ma test new kernel today, then tomorrow will ask BingoBoingo to power down rk-c and put disk in dulap to i can snap new master img, then it will go into service ( and can reimage BingoBoingo also ) .
asciilifeform: mircea_popescu: keep in mind this was a ben_vulpes-baked box, i never saw inside of it ( dulap-III, dulap-spare, s-mg, s-mg-spare -- i cleaned with own hands )
asciilifeform: for comparison, the 1 time dulap-III rebooted without sanction, was in may, when BingoBoingo elbowed the mains cable
asciilifeform: i ask because i have a 9GB disk image from that bolix 'macivory' ( recorded using the 'alpha' from earlier thrd ) but am reluctant to simply put on dulap, soaking up bw for errybody
asciilifeform: in other lulz, asciilifeform recently disasmed a raid card fw turd ( of the type found in dulap, s.mg, and several other boxes asciilifeform built ) ; turned out that it's ~little-endian ppc~, which i had nfi even existed; and on top of this, built in ~cpp~, which is also a 1st on my watch in re fwturds
asciilifeform: BingoBoingo: at your earliest convenience, plz route all packets having unassigned ip as destionation, to the 2nd nic on dulap, i'd like to make 'radiotelescope' for martian udp there
BingoBoingo: <asciilifeform> ( if BingoBoingo determines 'we need 4 dulap-class boxes by feb', asciilifeform will obtain, fly'em in, etc ) << I suspect more hardware is part of the solution. The Mocky mission to Qatar was a disappointment in the orc non-responsiveness.
asciilifeform: ( if BingoBoingo determines 'we need 4 dulap-class boxes by feb', asciilifeform will obtain, fly'em in, etc )
asciilifeform looks on dulap-III, 'up 210 days' -- i.e. ever since i taught BingoBoingo how to not elbow the mains plug
asciilifeform: the thread provoked by reading dulap l0gz this morning, and asciilifeform noticed a mysterious upsurge of heathen interest in ye olde http://btcbase.org/log/2016-06-28#1491985 turd collection. by all rights they oughta be seeing it as jpeg encrusted with tmsr ad banners etc ☝︎
asciilifeform: BingoBoingo: fwiw postgres doesn't, 'out of the box', have the runaway ram problem. ( it had exact opposite -- i had to coax it into actually making constructive use of dulap III's very plentiful ram )
asciilifeform: make sure plox that it's the only drive plugged into dulap
a111: Logged on 2018-11-11 16:00 BingoBoingo: <asciilifeform> prior to pizarro, i pictured 'tmsr isp' as a moar 'noncontact' item, where heathen contract is signed and robotic 'bring server into gossip net' item is installed immediately. but FG / we-want-custom-irons etc changed this picture << This and those surprise power cycling of dulap I/II (I forget the dulap version history)
asciilifeform: http://btcbase.org/log/2018-11-11#1871157 << ftr BingoBoingo's history is correct, dulap I and II perished by orc hand ☝︎
BingoBoingo: <asciilifeform> prior to pizarro, i pictured 'tmsr isp' as a moar 'noncontact' item, where heathen contract is signed and robotic 'bring server into gossip net' item is installed immediately. but FG / we-want-custom-irons etc changed this picture << This and those surprise power cycling of dulap I/II (I forget the dulap version history) ☟︎
asciilifeform: loox like finding answer might add up to costing some penies ( or not, lessee, if dulap dun suffice, i'ma lease some cycles on lulazon cluster )
asciilifeform: i expect the gaussation itself could take coupla wks on dulap, once the req'd pieces are cut and glued
asciilifeform: but, for instance, i dun have php on dulap, and like it that way
a111: Logged on 2018-10-03 00:38 asciilifeform: diana_coman , lobbes : your old drives are currently in dulap, lemme know when you're ready to have'em reformatted ( so your boxen dun try an' boot from'em instead of the primary ) and reissued to you as secondary disks.
asciilifeform: diana_coman , lobbes : your old drives are currently in dulap, lemme know when you're ready to have'em reformatted ( so your boxen dun try an' boot from'em instead of the primary ) and reissued to you as secondary disks. ☟︎
asciilifeform: BingoBoingo: when you get to the dc, feel free to pull lobbes's drive from dulap ( label it ) and insert 1) first, diana_coman's 2) 30sec later, the new
BingoBoingo: Could be done, but not while fitting another drive in dulap
asciilifeform: BingoBoingo: then power down lobbes's unit and put its disk in dulap, i'ma snapshot
BingoBoingo: asciilifeform: Drive for C placed in dulap as well