log☇︎
102200+ entries in 0.029s
asciilifeform: that only takes care of block fetches
asciilifeform: but it has nfi re files !
asciilifeform: a good raid card will aggregate BLOCK accesses
asciilifeform: nope.
asciilifeform: nor has any means for bolting on such a thing
asciilifeform: it doesn't aggregate accesses
asciilifeform: i suspect fs-as-db will have same problem as the ancient shitdb
asciilifeform: (b) is where i ended up earlier.
asciilifeform: and i did not bother to vpatchify it.
asciilifeform: but it had 0 measurable effect
asciilifeform: dbenv.set_cachesize(4, 0, 1); // 4GB of contiguous cache ☟︎
asciilifeform: i also have a test going where :
asciilifeform: all i got is a stopwatch. the idea is, mod6 et al can run same stopwatch, on other boxes, with other types of disk
asciilifeform: and i will point out, none of my findings so far contradict mircea_popescu's original 'it sits and waits for the disk.' only question was, where.
asciilifeform: http://btcbase.org/log/2016-12-29#1592898 ☝︎
asciilifeform: mno, we had a thread where i cut'em up into classes
asciilifeform: mircea_popescu: if you, using my patch or similar, determined that type1 (verification) blackhole consists of any substantial portion of something other than db wait -- i'm all ears
asciilifeform: sadly i have 0 solutions, only moar problemz
asciilifeform: seems to consist ~entirely of db.
asciilifeform: mircea_popescu: that was in re the verification blackhole (the most common type observed on dulap)
asciilifeform: the 'type 2' (non-verification) blackhole goes right back to the fundamental question of 'something to all comers', how much disk thrashing does a derp get to invoke simply by coming up with a not-yet-banned ip and a pseudonode. ☟︎
asciilifeform: incidentally, rationing by ip is a nonstarter, notice that the requests come from a multitude of 'nodes'.
asciilifeform: for as long as the enemy is able to keep up the 'gimme, gimme, gimme' flood of 'ahahaha, you're giving something to allcomers! well where's mine'
asciilifeform: this is the mega-prize, folx, the blackhole that can carry on unabated for hours, days, weeks.
asciilifeform: (grep for 'received getdata for: block')
asciilifeform: instead we see what appears to be a node simply pecked to death by queued-up getdata-for-block flood
asciilifeform: grep for 'received block' -- it does not appear again in this log. because we are blackholed OUTSIDE of the verification delays.
asciilifeform: we start with where 454862 was received, and (in record time, as it was tiny) accepted.
asciilifeform: a blackhole certifiably NOT connected with block verification.
asciilifeform: finally caught this beast in the wild, in real time
asciilifeform: behold!
asciilifeform: http://nosuchlabs.com/pub/nonblockverifying_blackhole.txt
asciilifeform: in VERY other noose,
asciilifeform: lol block 454862 , 91.61kB ! >> ProcessBlock (res == 1) took : 11081ms; db write wait: 2402ms; db read wait: 597ms
asciilifeform: in very other lulz, http://www.metzdowd.com/pipermail/cryptography/2017-February/031615.html ( https://archive.is/jLUGT ) << 'Bruce Schneier has recently published an impassioned plea for a United States Federal Internet Security Agency, which would likely gain control of civilian cryptography, among many other munitions.'
asciilifeform: ^ ... hardcoded check for the published example !!
asciilifeform: ^ guess what the 'fix' was.
asciilifeform: 'Thursday's watershed attack on the widely used SHA1 hashing function has claimed its first casualty: the version control system used by the WebKit browser engine, which became completely corrupted after someone uploaded two proof-of-concept PDF files that have identical message digests.'
asciilifeform: in other lulz: https://arstechnica.com/security/2017/02/watershed-sha1-collision-just-broke-the-webkit-repository-others-may-follow
asciilifeform: [BTC-dev] (EXPERIMENTAL) Blackhole Read Timings, and the Verdict.
asciilifeform: http://therealbitcoin.org/ml/btc-dev/2017-February/000256.html
asciilifeform: mircea_popescu, ben_vulpes , mod6 , et al :
asciilifeform: ACHTUNG, PANZERS! ☟︎
asciilifeform: 'Rules to receive the up-to-$10,000 award from Project Veritas - Project Veritas only offers awards for valuable video or other media types which was legally obtained. It is important for the submitter to follow all local, state and federal laws while obtaining video or other media for submission.' << snoar
asciilifeform: 'race to the bottom'
asciilifeform: easy to undercut
asciilifeform: and 'nodes charge' probably isn't practical
asciilifeform: http://btcbase.org/log/2017-02-25#1618589 << was spot on ☝︎
asciilifeform: antecedents-in-existing-block or bust.
asciilifeform: danielpbarron: O(n^2) -- with orphanages etc. - tx verification-- suxx.
asciilifeform bbl; meat.
asciilifeform: miners get one hell of a free ride, while node operators get such a thick shaft, that there are -- contrary to appearances - virtually none left.
asciilifeform: mircea_popescu nails it.
asciilifeform: (ssd ain't cheap, and its price is ~rising~, don't take my word for it, go and see)
asciilifeform: danielpbarron: it ain't 'a cost', like buying a hammer, it's a monotonically-increasing bleed
asciilifeform: node -- bleeds and bleeds. and -- turns out -- operating proper nodes, ain't cheap, esp. with bitcoin's retarded non-O(1) verification, with the db idiocy
asciilifeform: ^^
asciilifeform: but why there are 0fees mined ~today~, is beyond me
asciilifeform: forced measure then.
asciilifeform: hmm,ok
asciilifeform: ( can mircea_popescu or any other oldtimer even explain to me why 0fee ever existed?? )
asciilifeform: are same, for this purpose, as nulls, neh
asciilifeform: for instance -- any and all 0fee tx
asciilifeform: not so expensive, apparently, if it sits vacant so regularly
asciilifeform: *yours
asciilifeform: ( today a miner can occupy as much of youts and my disk with shit tx, as he wants )
asciilifeform: suddenly, spamola becomes very questionable proposition.
asciilifeform: the transition from zero-cost to positive epsilon -- matters
asciilifeform: who dun give a shit about fees
asciilifeform: and for all i know, most tx are fake, generated by miner himself, or cartel
asciilifeform: and i see some ~every day
asciilifeform: there ever being any, is a perversion
asciilifeform: punishments are beneficial, even if a beheading does not grow a corresponding new head on somebody else, or undo the crime which led to the sentence
asciilifeform: possibly it makes more sense to think of the hypothetical 'god fee' as a ~punishment~ of tx-ignoring miners, rather than a payment to relayers.
asciilifeform: proper implement. eats file on stdin, hash out.
asciilifeform hands full
asciilifeform: might help if somebody did the chore, implemented mp's algo
asciilifeform: lul
asciilifeform: mircea_popescu: answrd
asciilifeform: mircea_popescu: if 'a' can shit out tx, 'b' shoulders the cost, but unrelated 'c' is paid by a, you have socialistleak.
asciilifeform: danielpbarron: a block, just occupying its 1MB on my disk, costs something.
asciilifeform: the only practical way to 'pay all users' is by burning some coin.
asciilifeform: it is laughable
asciilifeform: aha
asciilifeform: no practical way, afaik, to do such a thing
asciilifeform: trinque: ttl?
asciilifeform: *relaying
asciilifeform: fees, in turn , do zilch to offset the cost of relating tx
asciilifeform: *of cpu
asciilifeform: and he is even paid, the moterfucker, for this
asciilifeform: when miner makes empty block, he imposes a cost of cou and disk on every current and future user of the coin
asciilifeform: trinque: consider the base case : empty block
asciilifeform: wtf, why
asciilifeform: if anyone-can-steal it
asciilifeform: but why would you do that
asciilifeform: what means 'smallest unspent output'
asciilifeform: danielpbarron: elaborate?
asciilifeform: this is one of the ingredients in the 'debottling' from earlier.
asciilifeform: a null seat in a block, IS, i argue, a type of junk tx
asciilifeform: gotta disincentivize junk tx. ~including those created or abetted by malicious miners~.