log☇︎
22600+ entries in 0.013s
lobbes: will do. yeah, I didn't get the bot portion running on my local test box, nor did I do port forwarding, but the reader.py and database portions were up and running pretty smoothly
asciilifeform: lobbes: it aint a very 'hungry' proggy -- e.g. the db presently weighs <70MB
lobbes: meanwhile, I've been looking at some dedicated server options, primarily for a second trb node on a proper ssd, but I will stand up a 'production' copy of asciilifeform's logotron as well
asciilifeform: interesting that there's an entire 150ms b/w austria & frankfurt
asciilifeform: lobbes: ty. moar or less what i'd expect to see.
snsabot: Logged on 2019-08-20 18:31:09 asciilifeform: diana_coman, mp_en_viaje , spyked , et al : http://18.195.64.227/log << copy of 'rubbish mirror', identical (same 'dollar store' pseudo-isp) but this one in frankfurt. try the same timing w/ it.
lobbes: http://logs.nosuchlabs.com/log/trilema/2019-08-20#1929816 << on heavy page test, I get the following: NC : 0m1.711s, Austria VPS : 0m0.379s, Piz Rkchp : 0m2.054s
lobbes: http://logs.nosuchlabs.com/log/trilema/2019-08-20#1929767 << tyvm
asciilifeform: BingoBoingo: i'm skeptical that we're already outta pipe. but if this persists we will have to actually meter folx.
snsabot: Logged on 2019-08-20 11:52:47 asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929749 << today <50kB/s...
asciilifeform: also worrisome is that http://logs.nosuchlabs.com/log/trilema/2019-08-20#1929804 thing
asciilifeform: not a properly threaded one
asciilifeform: meanwhile : BingoBoingo rk3328 seems to be back in print ! 50bux for the 4 GB, for 2 GB -- 35.
bvt: hi, sorry for delay on the linux rng post, it is in fact ~ready, but i need one more day for proofreading
asciilifeform: the mirrors are identical to the orig ( in re pythonism, nginx, etc ) and in fact considerably slower boxen, and laden with shitlinux ('centos') iirc . geography is the killer, imho satisfactorily proven .
asciilifeform: ( granted there aint a fiber through the diameter. but. )
asciilifeform: # of hops via buggered switches i suspect matters moar than km of fiber
mp_en_viaje: course land distance to frankfurt is ~1k km
asciilifeform: mp_en_viaje if you've 1s, time curl http://18.195.64.227/log/trilema/2018-04-18#1802801 > /dev/null
asciilifeform: ftr i get ~1.00s ('heavy page' test) from washingtonistan
mp_en_viaje is writing an article and then hopping on a plane, but in principle.
asciilifeform: diana_coman, mp_en_viaje , spyked , et al : http://18.195.64.227/log << copy of 'rubbish mirror', identical (same 'dollar store' pseudo-isp) but this one in frankfurt. try the same timing w/ it.
asciilifeform: atm it seems quite impossible even to say which ~generates~ the pgs faster -- the diff, if any, is entirely dwarfed by pipe effects
asciilifeform: ( spoiler : rubbish-mirror actually loads slightly faster, from europistan, than phf's orig., for 'heavy page' test )
snsabot: Logged on 2019-08-19 21:20:26 asciilifeform: ftr gets ~80kB/s avg. from dulap, there.
asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929749 << today <50kB/s...
asciilifeform: ( and, interestingly, specifically fucked re tcp. )
snsabot: Logged on 2019-08-20 08:48:36 mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929711 << this is possible if the intercontinental interchange's fucked. which...
asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-20#1929795 << the measurements strongly suggest this.
snsabot: Logged on 2019-08-19 21:55:06 asciilifeform: i expect at some pt mp will say to anyone in l1 who aint running a logger, 'партбилет на стол!'(tm)(r)
mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929757 << certainly seems to go with historical practice
mp_en_viaje is too lazy to try and dust off ye olde netcraft toolset an' look
snsabot: Logged on 2019-08-19 17:35:50 asciilifeform: BingoBoingo: hard to say for fact, but seems to add up to a picture where's there's a ~0.5s bottleneck b/w south amer. and errywhere else.
mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929711 << this is possible if the intercontinental interchange's fucked. which...
snsabot: Logged on 2019-08-19 16:52:17 asciilifeform: this experiment also reveals that asciilifeform's logotron will in fact stand up, with no modifications, on a python, flask, pg, etc. plucked out of arbitrary rubbish bin.
mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929705 << now that's pretty cool.
mp_en_viaje: on the first pass it appears as a complete disinterest in "feelings", but it fundamentally is a method for the valuation of human activity. and therefore complete ethics and a set of morals. co
mp_en_viaje: THE. METHOD. the one thing that unites "What do you mean how ?" and the reporting "who cares who it damages" and the engineering "who cares what business models/political arrangements this renders obsolete" is [http://trilema.com/2017/is-it-still-rape-if-i-write
mp_en_viaje: ~any woman'd rather read me write in defense of rape than watch charlie branson-sheen derp about like little bois. the reason is ~THE METHOD~, not the subject, not "oh mp is rich" -- seriously, wtf -- not anything else.
mp_en_viaje: an't be interesting even when discussing interesting topics.
mp_en_viaje: "traditional" (no they aren't) heuristic valuations of activity imported from the practices and intellectual habits of the herd of idiots are NOT USEFUL. how "boring" or "interesting" or "sexy" or whatever things seem, truly the on;ly saviour is the method ; which is why trilema can be interesting whatever i discuss, be it defecation or obscure byzantine minutia, whereas the herd of idiots c
mp_en_viaje: meaning that all prediction as to the future is to be based on METHODOLOGICAL considerations. how well the method was applied, and how uniformly, over how homogenous a sample with how good expected coverage. that's all.
mp_en_viaje: but the important point is, METHODOLOGY. science, not as "the profession" nor as "the professional activity", but as the occupation, science as in, productive, not science as in, socially acceptable -- IS A BEHAVIOUR. that's all it is, applying a method systematically.
snsabot: Logged on 2019-08-20 07:47:16 mp_en_viaje: would like to take the time to point this out re ye olde discussion of "is something to learn / is nothing to learn", coming up oft re gosspid but generally always there. "to learn" is insanely vague an operator. just because you don't learn anything useful [about programming] while doing, say, python, it still dun mean you don't learn anything useful about your girflriend, or the tcp infrastructure, or router har
mp_en_viaje: (amusingly, there was an article i ran into that made the exact point, in a list of four. meanwhile (superficially) reviewed the complete list of trilema articles i looked at this month (on this mchine), >6k lines, did not find it anymore. fuck me. and then of course there's http://trilema.com/2019/pizd-atrage-da-curu-trage-ca-n-viata-tragic/ )
mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-20#1929777 < this, obviously is the exact complement to the oft-repeated "now that i write article 2, i find article 1 useful ; there was no way to evaluate this utility at the time decision to write article 1 was to be made" re blogwriting.
mp_en_viaje: shrysr, what the heck are you doing, anyways ?
mp_en_viaje was going to propose http://trilema.com/2015/the-four-points-of-this-morning-in-color-any-questions/ to the younghands summarization project ; then went over and checked what exactly the pinging article was doing, decided.... best not to.
mp_en_viaje would like to take the time to point this out re ye olde discussion of "is something to learn / is nothing to learn", coming up oft re gosspid but generally always there. "to learn" is insanely vague an operator. just because you don't learn anything useful [about programming] while doing, say, python, it still dun mean you don't learn anything useful about your girflriend, or the tcp infrastructure, or router hardware, or the difference be
snsabot: Logged on 2019-08-19 14:04:28 asciilifeform: diana_alt: i have plan to move the box to traditional apache, but yet not figured out how to do so w/out unacceptably long disruption of service .
mp_en_viaje: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929650 << if nothing else, will tell us some things, similar to your point before. mystery delay will de-mystify through usage.
snsabot: Logged on 2019-08-19 13:50:01 asciilifeform: diana_alt: fwiw i was not, to date, able to rule out mp's 'overworked pipe' hypothesis .
spyked: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929659 <-- PM works for L1 and L2; in-channel is limited to L1.
asciilifeform: ^ dulap incidentally performs considerably better , unsurprisingly, than the pseudo-sadmachine, in re actual page generation on local end.
asciilifeform: i.e. takes ~0.068s to travel the 50km or so to asciilifeform's chair from said pseudobox.
asciilifeform: (i.e. all on top of this, is transmission delay from east amerireich, where thing sits.)
snsabot: Logged on 2019-08-19 16:38:17 asciilifeform: other folx welcome to try. e.g. the 'heavy page' : curl http://54.209.217.34/log/trilema/2018-04-18#1802801 > /dev/null
asciilifeform: btw for thread-completeness, heavy page loaded locally on the shitbox consumes avg. of 0.2s.
asciilifeform: i expect at some pt mp will say to anyone in l1 who aint running a logger, 'партбилет на стол!'(tm)(r)
asciilifeform: rly what we oughta have is 7+ ~active~ bots/logotrons on 7 continents, then no one will have to grumble 'wai slow'
asciilifeform: BingoBoingo: from this pt i'ma follow the prescription mp gave during last 'wai slow' thrd -- leave it alone, there aint much to be done re to speed it up ( as imho conclusively showed that the pipe is to blame ). will move on to other matters ( import of historic logs ; fix of reported catastrophic bugs, incl. the resync of numeration mp asked for ; and then to get back to ffa ! )
snsabot: Logged on 2019-08-19 13:52:44 asciilifeform: diana_alt: however, if accessed from localhost on ~public port~ (80) then yes same delay
asciilifeform: BingoBoingo: this remains a mystery. i gotta wonder if there's something peculiar re our routing, which gives this effect.
asciilifeform: for n00bz : the cron job script which powers this ; the cron job itself .
asciilifeform: the 'db snapshot' link nao worx. this box will do duty as an (unauthoritative!) 'fast' mirror of db snapshot also, until someone comes up with better.
asciilifeform: keep in mind that bot will not echo log lines cited from rubbish mirror. it is fit strictly for timing experimentation.
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: ty for the timings lobbes . seems to match up with asciilifeform's and BingoBoingo's pictures
lobbes: trinque: ^ I may have been too quick on the draw when deedbot came back online. plox to lemme know if I should re-issue the above !!v
lobbes: Numbers for the 'heavy log' as follows: NC chair 0m1.055s ; Euro VPS 0m0.971s ; Piz Rkchp 0m1.435s
snsabot: Logged on 2019-08-19 16:37:04 asciilifeform: time curl http://54.209.217.34/log > /dev/null from my chair yields 0.063s.
deedbot: Invoiced trinque 0.01645328 << Colocation + Shared August 2019
BingoBoingo: !!invoice trinque 0.01645328 Colocation + Shared August 2019
deedbot: Invoiced jurov 0.01445328 << TBF Colocation August 2019
BingoBoingo: !!invoice jurov 0.01445328 TBF Colocation August 2019
deedbot: Invoiced diana_coman 0.10429931 << Rockchip w/ FUCKGOATS, Annual, Through July 2020
BingoBoingo: !!invoice diana_coman 0.10429931 Rockchip w/ FUCKGOATS, Annual, Through July 2020
snsabot: Logged on 2019-08-19 16:13:02 BingoBoingo: I remember a thread from last year where trinque saw long pings doing something at the same time MP was enjoying incredibly fast ping to Eulora server
asciilifeform: http://logs.nosuchlabs.com/log/trilema/2019-08-19#1929694 << this is worth expanding on. asciilifeform also gets very fast pings ( never moar than 200msec, to date ) and fast udp. what i suspect is, usg's snoop gear that sits as parasitic toad on south amer's pipe, specifically slows down tcp.
asciilifeform: ( the rest -- largely, hand-copying configs )
asciilifeform: other folx btw are encouraged to perform similar experiment ; whole thing took me approx 35min of meat time, from revving up heathen pseudo-box to posting link here.
asciilifeform: ( in the mirror example, we get it in the reverse direction, but seems to be that same ~0.5s ! )
asciilifeform: BingoBoingo: hard to say for fact, but seems to add up to a picture where's there's a ~0.5s bottleneck b/w south amer. and errywhere else.
BingoBoingo: From the rack gives 0m0.561s
asciilifeform: BingoBoingo, diana_coman, et al ^ as time permits , plox to post load times of this ^ log.
asciilifeform: i'ma switch this thing off in coupla days, once errybody's taken the offered measurement and is satisfied ( i dun want a 'fossilized' logger sitting for idiots to find and think 'they're dead' )
asciilifeform: this experiment also reveals that asciilifeform's logotron will in fact stand up, with no modifications, on a python, flask, pg, etc. plucked out of arbitrary rubbish bin.
asciilifeform: all knobs aside from 'download snapshot' work, so feel free to e.g. walk the 'random' pages etc.
asciilifeform did not bother to sync the clock, so times on shit mirror will vary vs. dulap's
asciilifeform: errybody's welcome to play with the mirror ( it's a '1st month -- phreeee!' pseudo-machine , i'ma leave it up for a spell, tho it will , obv., grow no new log lines )
asciilifeform: this suggests that culprit of 'mystery delay' is in fact piz pipe.
asciilifeform: deliberately this setup uses nginx and same (as far as could replicate on the heathen box) stack of proggies as the orig.
asciilifeform: other folx welcome to try. e.g. the 'heavy page' : curl http://54.209.217.34/log/trilema/2018-04-18#1802801 > /dev/null
asciilifeform: oook here's an experiment : asciilifeform set up a mirror of the logotron on a cheap heathen host. ( one of the most rubbish hosters known, lulazon's . hence cannot in fact stand up copy of bot there, fleanode bans conns from it unless sslized. but the db is current. )
BingoBoingo: I remember a thread from last year where trinque saw long pings doing something at the same time MP was enjoying incredibly fast ping to Eulora server
BingoBoingo: <asciilifeform> ( and imho further suggests that pipe is culprit ) << My desk offers "0m0.073s" suggesting geography may be at play
asciilifeform: ^ the log bot itself, for instance, thus far has only reconnected when asciilifeform manually cycled it, to update to new ver (last such time, to put phf's uniturd pill in production)
snsabot: asciilifeform: time since my last reconnect : 3d 4h 43m
asciilifeform: ... and typically they die on acct of connectivity pause on asciilifeform's end, rather than piz