12018-08-25T00:00:16 <gmaxwell> right. well there is also no need to discard bytes from K_2 but it does that too. the performance hit is especially gratitious for lengths.
22018-08-25T00:02:00 *** goatpig has joined #bitcoin-core-dev
32018-08-25T00:03:57 *** intcat has quit IRC
42018-08-25T00:04:33 *** AaronvanW has quit IRC
52018-08-25T00:04:44 <gmaxwell> sipa: oh geesh, for every message we do _another_ chacha20 run to derrive the poly key.
62018-08-25T00:05:30 <gmaxwell> so encrypting a single small message requires 3 runs of the chacha20 function, one to encrypt the length, one to establsh the poly1305 key, and one to encrypt the payload.
72018-08-25T00:06:02 <gmaxwell> this seems pants on head stupid.
82018-08-25T00:06:28 *** intcat has joined #bitcoin-core-dev
92018-08-25T00:07:42 <gmaxwell> The polykey needs to be per packet for poly1305's requirements, so I suppose it's only throwing out 32 bytes of chacha output.
102018-08-25T00:14:09 <gmaxwell> https://www.ietf.org/mail-archive/web/secsh/current/msg01224.html seems other people have suggested combining the poly1305 chacha block with the length encryption.
112018-08-25T00:14:46 <gmaxwell> and it seems that they didn't so that you could just use a RFC5116 implementation of it.
122018-08-25T00:14:49 * gmaxwell cries
132018-08-25T00:16:32 *** plankers has joined #bitcoin-core-dev
142018-08-25T00:24:32 <gmaxwell> So encrypting a 12 byte message will run on the order of 109 cycles/byte... which means that for small messages a straighforward implementation of AES-GCM would likely be faster, even on hardware without AES instructions.
152018-08-25T00:24:46 <gmaxwell> (109 cycles/byte for the chacha20 part alone)
162018-08-25T00:28:01 *** d9b4bef9 has quit IRC
172018-08-25T00:29:08 *** d9b4bef9 has joined #bitcoin-core-dev
182018-08-25T00:30:02 *** d9b4bef9 has quit IRC
192018-08-25T00:30:39 *** IGHOR has quit IRC
202018-08-25T00:31:09 *** d9b4bef9 has joined #bitcoin-core-dev
212018-08-25T00:31:29 <sipa> gmaxwell: but what is the average message length for us?
222018-08-25T00:32:09 *** IGHOR has joined #bitcoin-core-dev
232018-08-25T00:34:20 <sipa> it seems we don't keep stats on message counts
242018-08-25T00:42:24 *** promag has quit IRC
252018-08-25T00:59:24 *** meshcollider_ has quit IRC
262018-08-25T01:03:10 *** profmac has joined #bitcoin-core-dev
272018-08-25T01:09:43 *** promag has joined #bitcoin-core-dev
282018-08-25T01:14:54 *** promag has quit IRC
292018-08-25T01:24:08 <cfields> luke-jr: hmm?
302018-08-25T01:24:44 <cfields> luke-jr: if qt's copy is missing the files that need patching, what's to patch?
312018-08-25T01:36:21 *** Chris_Stewart_5 has quit IRC
322018-08-25T01:47:35 *** Chris_Stewart_5 has joined #bitcoin-core-dev
332018-08-25T01:55:28 <luke-jr> cfields: libpng has optimisations for ARM and POWER in separate files missing in Qt, but Qt's copy of the normal files still tries to link them
342018-08-25T01:57:38 <cfields> luke-jr: armhf/aarch64 build fine, what's different about power?
352018-08-25T01:58:03 <luke-jr> cfields: I don't know how ARM works
362018-08-25T01:58:05 <cfields> (not arguing, just trying to understand)
372018-08-25T01:59:54 <cfields> luke-jr: anyway, breaking out libpng is fine with me. IIRC I didn't do that because it requires zlib, as does qt, so that would've meant 2 copies of zlib. But we've since broken zlib out anyway I believe.
382018-08-25T02:00:31 <luke-jr> yeah
392018-08-25T02:01:03 <cfields> luke-jr: while you're at it, feel free to flip -qt-jpeg to -disable-jpeg too
402018-08-25T02:01:16 <cfields> something like those options, anyway
412018-08-25T02:01:46 <cfields> I think we've had no need for jpegs for a long time
422018-08-25T02:04:56 <luke-jr> did we ever? O.o
432018-08-25T02:05:32 <cfields> pretty sure we had some at some point
442018-08-25T02:10:58 <midnightmagic> /w 39
452018-08-25T02:11:46 <cfields> luke-jr: https://github.com/bitcoin/bitcoin/commit/f9124587ccea723dbd743e3877a7071fbb6c5732
462018-08-25T02:12:20 <cfields> 0.8, heh
472018-08-25T02:16:47 <gmaxwell> sipa: the most common message by far is transaction inv.
482018-08-25T02:18:53 <gmaxwell> sipa: it's just so weird that it uses 3 chacha runs, the poly1305 run has 32 bytes totally unused.
492018-08-25T02:28:35 *** Krellan has quit IRC
502018-08-25T02:31:42 *** davex__ has quit IRC
512018-08-25T02:32:53 *** pierre_rochard has joined #bitcoin-core-dev
522018-08-25T02:41:19 *** jimpo has joined #bitcoin-core-dev
532018-08-25T02:42:46 *** promag has joined #bitcoin-core-dev
542018-08-25T02:48:24 *** promag has quit IRC
552018-08-25T03:32:57 *** Chris_Stewart_5 has quit IRC
562018-08-25T03:55:47 *** Chris_Stewart_5 has joined #bitcoin-core-dev
572018-08-25T03:55:57 *** Rootsudo has joined #bitcoin-core-dev
582018-08-25T04:01:27 *** Jmabsd has joined #bitcoin-core-dev
592018-08-25T04:01:47 <Jmabsd> wait, so Bitcoin has the tendency to print (256 & 160bit) hashes in *reverse* order, right - block hashes, transaction hashes and merkle root hashes.
602018-08-25T04:02:12 <Jmabsd> What about pubkey hashes (20B), pubkeys (32B) and signatures (64B) - are those printed in normal or reverse byte order? so, I have a P2SH pubkey script, say. in there is a 20B hash of my redeemscript, right. when I use Bitcoin Core's script disassembly function, will it print that hash in byte or normal order? i mean there is an outer extent to what Core prints in reverse order - for instance, binary transaction dumps (in hex) are in
612018-08-25T04:02:14 <Jmabsd> *normal* order, not reverse.
622018-08-25T04:06:46 <sipa> Jmabsd: that's just printing the bytes one by one
632018-08-25T04:07:08 <sipa> it's only when a hash is interested as a number the printing gets reversed
642018-08-25T04:07:46 <sipa> because the bytes are interpreted as little-endian number, but then printed in big endian for human consumption (humans want to see numbers in big endian)
652018-08-25T04:07:58 <sipa> but a script is a number
662018-08-25T04:08:05 <luke-jr> isn't*
672018-08-25T04:08:11 <Jmabsd> gotcha.
682018-08-25T04:08:45 <sipa> *indeed, isn't
692018-08-25T04:11:16 <Jmabsd> aha. so let's see - if you print a hex dump of a signature (71/72/73B), that's not a hash and hence printed in normal order
702018-08-25T04:11:37 <Jmabsd> a P2SH hash, for instance when printing the disassembly of a P2SH pubkey script - will the 20B hash there be printed in reverse ordeR?
712018-08-25T04:12:06 <Jmabsd> also if a pubkey (32B) is printed out, could that ever be in reverse order?
722018-08-25T04:13:02 <luke-jr> why don't you just try it and see? -.-
732018-08-25T04:14:33 <sipa> Jmabsd: pubkeys are not 32 bytes, and they're not hashes
742018-08-25T04:15:02 *** vexbuy has quit IRC
752018-08-25T04:15:10 <Jmabsd> sipa: so the hex printer for other byte structures are never printed in reverse orders.
762018-08-25T04:15:17 <sipa> indeed
772018-08-25T04:15:32 <sipa> only for things that are internally treated as numbers
782018-08-25T04:15:33 <Jmabsd> but.. a P2SH 20B hash, that's a hash right. for printing purposes, is it considered a hash or a byte blob?
792018-08-25T04:15:37 *** vexbuy has joined #bitcoin-core-dev
802018-08-25T04:15:39 <sipa> nope!
812018-08-25T04:15:48 <sipa> because the printer cannot know it is a hash
822018-08-25T04:16:02 <sipa> you'd need to execute the script to know it is treated as such
832018-08-25T04:16:12 <sipa> the script opcode is just "put some bytes on the stack"
842018-08-25T04:17:48 <sipa> so, not reversed there
852018-08-25T04:20:18 *** vexbuy has quit IRC
862018-08-25T04:20:34 *** Jmabsd has quit IRC
872018-08-25T04:21:20 *** Jmabsd has joined #bitcoin-core-dev
882018-08-25T04:21:25 <Jmabsd> (sorry disconnect)
892018-08-25T04:21:30 <Jmabsd> last, > interesting. except for the HD wallet root seed (160b=20B), there is no instance ever where a 20B hash e.g. in P2SH pubkeyscript, is printed in reverse order.
902018-08-25T04:21:35 <Jmabsd> > sipa, right and when getting a disassembly printout in Bitcoin Core and related tools, those 20B:s are printed in normal order
912018-08-25T04:28:18 *** vexbuy has joined #bitcoin-core-dev
922018-08-25T04:32:02 *** d9b4bef9 has quit IRC
932018-08-25T04:33:10 *** d9b4bef9 has joined #bitcoin-core-dev
942018-08-25T04:40:18 *** Chris_Stewart_5 has quit IRC
952018-08-25T05:36:53 *** promag has joined #bitcoin-core-dev
962018-08-25T05:41:58 *** promag has quit IRC
972018-08-25T05:49:07 *** vexbuy has quit IRC
982018-08-25T06:07:11 *** vexbuy has joined #bitcoin-core-dev
992018-08-25T06:16:30 <Jmabsd> the proper way to phrase Core's reversing policy is something like, "any hash that is not part of another binary blob or produced as script data, is hex-serialized in reverse byte order."
1002018-08-25T06:17:07 <Jmabsd> i'd hope any hash values introduced in the future will not be reversed though.
1012018-08-25T06:26:19 <sipa> i don't see why not
1022018-08-25T06:26:32 <sipa> we've always treated hash outputs as numbers and printed them as such
1032018-08-25T06:26:56 <sipa> if byte swapping is the hardest problem to deal with, i'm not very worried :)
1042018-08-25T06:43:42 *** Jmabsd has quit IRC
1052018-08-25T06:53:32 *** vexbuy has quit IRC
1062018-08-25T06:54:08 *** vexbuy has joined #bitcoin-core-dev
1072018-08-25T06:58:39 *** vexbuy has quit IRC
1082018-08-25T07:00:33 *** sipa has quit IRC
1092018-08-25T07:00:53 *** sipa has joined #bitcoin-core-dev
1102018-08-25T07:18:38 *** Lauda has joined #bitcoin-core-dev
1112018-08-25T07:29:26 *** vexbuy has joined #bitcoin-core-dev
1122018-08-25T07:37:20 *** murrayn has quit IRC
1132018-08-25T07:39:00 *** promag has joined #bitcoin-core-dev
1142018-08-25T07:39:24 *** wxss has joined #bitcoin-core-dev
1152018-08-25T07:43:36 *** promag has quit IRC
1162018-08-25T07:53:27 *** Rootsudo has quit IRC
1172018-08-25T07:54:53 *** Rootsudo has joined #bitcoin-core-dev
1182018-08-25T07:55:39 *** Rootsudo has joined #bitcoin-core-dev
1192018-08-25T07:57:11 *** Rootsudo has joined #bitcoin-core-dev
1202018-08-25T08:04:50 *** Krellan has joined #bitcoin-core-dev
1212018-08-25T08:05:43 *** vexbuy has quit IRC
1222018-08-25T08:07:20 *** vexbuy has joined #bitcoin-core-dev
1232018-08-25T08:08:55 *** SopaXorzTaker has joined #bitcoin-core-dev
1242018-08-25T08:11:27 *** plankers has quit IRC
1252018-08-25T08:12:26 *** vexbuy has quit IRC
1262018-08-25T08:34:02 *** d9b4bef9 has quit IRC
1272018-08-25T08:35:08 *** d9b4bef9 has joined #bitcoin-core-dev
1282018-08-25T08:40:50 *** SopaXorzTaker has quit IRC
1292018-08-25T08:42:10 *** vexbuy has joined #bitcoin-core-dev
1302018-08-25T08:42:29 *** SopaXorzTaker has joined #bitcoin-core-dev
1312018-08-25T09:08:08 *** csknk has joined #bitcoin-core-dev
1322018-08-25T09:22:01 *** promag has joined #bitcoin-core-dev
1332018-08-25T09:22:04 *** promag has quit IRC
1342018-08-25T09:37:03 *** Krellan has quit IRC
1352018-08-25T10:03:25 *** AaronvanW has joined #bitcoin-core-dev
1362018-08-25T10:03:46 *** AaronvanW has quit IRC
1372018-08-25T10:06:22 *** AaronvanW has joined #bitcoin-core-dev
1382018-08-25T10:22:42 *** profmac has quit IRC
1392018-08-25T10:30:03 *** promag has joined #bitcoin-core-dev
1402018-08-25T10:35:30 *** promag has quit IRC
1412018-08-25T10:45:24 *** cdecker has quit IRC
1422018-08-25T11:27:14 *** vexbuy has quit IRC
1432018-08-25T11:34:54 *** goatpig has quit IRC
1442018-08-25T11:40:17 *** vexbuy has joined #bitcoin-core-dev
1452018-08-25T11:42:05 *** promag has joined #bitcoin-core-dev
1462018-08-25T11:42:32 *** IGHOR has quit IRC
1472018-08-25T11:43:45 *** IGHOR has joined #bitcoin-core-dev
1482018-08-25T11:46:19 *** vexbuy has quit IRC
1492018-08-25T11:46:32 *** promag has quit IRC
1502018-08-25T12:04:56 *** promag has joined #bitcoin-core-dev
1512018-08-25T12:11:57 *** vexbuy has joined #bitcoin-core-dev
1522018-08-25T12:36:02 *** d9b4bef9 has quit IRC
1532018-08-25T12:37:09 *** d9b4bef9 has joined #bitcoin-core-dev
1542018-08-25T12:41:51 *** as1nc has joined #bitcoin-core-dev
1552018-08-25T12:41:56 *** vexbuy has quit IRC
1562018-08-25T12:42:33 *** vexbuy has joined #bitcoin-core-dev
1572018-08-25T12:46:48 *** vexbuy has quit IRC
1582018-08-25T12:47:37 *** promag has quit IRC
1592018-08-25T12:48:47 *** vexbuy has joined #bitcoin-core-dev
1602018-08-25T12:56:43 *** esotericnonsense has quit IRC
1612018-08-25T13:25:10 *** Chris_Stewart_5 has joined #bitcoin-core-dev
1622018-08-25T13:39:13 *** promag has joined #bitcoin-core-dev
1632018-08-25T13:40:50 *** Chris_Stewart_5 has quit IRC
1642018-08-25T13:43:29 *** Victorsueca has quit IRC
1652018-08-25T13:44:12 *** promag has quit IRC
1662018-08-25T13:44:42 *** Victorsueca has joined #bitcoin-core-dev
1672018-08-25T13:55:41 *** Chris_Stewart_5 has joined #bitcoin-core-dev
1682018-08-25T13:56:21 *** AaronvanW has quit IRC
1692018-08-25T13:58:42 *** owowo has quit IRC
1702018-08-25T14:06:42 *** AaronvanW has joined #bitcoin-core-dev
1712018-08-25T14:08:42 *** Chris_Stewart_5 has quit IRC
1722018-08-25T14:11:37 *** AaronvanW has quit IRC
1732018-08-25T14:13:03 *** Chris_Stewart_5 has joined #bitcoin-core-dev
1742018-08-25T14:23:36 *** owowo has joined #bitcoin-core-dev
1752018-08-25T14:30:20 *** promag has joined #bitcoin-core-dev
1762018-08-25T14:43:43 *** promag has quit IRC
1772018-08-25T15:03:44 *** vexbuy has quit IRC
1782018-08-25T15:04:22 *** vexbuy has joined #bitcoin-core-dev
1792018-08-25T15:04:46 *** bsm117532 has joined #bitcoin-core-dev
1802018-08-25T15:07:43 *** AaronvanW has joined #bitcoin-core-dev
1812018-08-25T15:08:41 *** Chris_Stewart_5 has quit IRC
1822018-08-25T15:12:00 *** AaronvanW has quit IRC
1832018-08-25T15:17:08 *** vexbuy_ has joined #bitcoin-core-dev
1842018-08-25T15:20:51 *** vexbuy has quit IRC
1852018-08-25T15:22:20 *** ossifrage has quit IRC
1862018-08-25T15:23:39 *** ossifrage has joined #bitcoin-core-dev
1872018-08-25T15:40:47 *** Chris_Stewart_5 has joined #bitcoin-core-dev
1882018-08-25T16:16:47 *** drexl has joined #bitcoin-core-dev
1892018-08-25T16:33:11 *** Zenton has quit IRC
1902018-08-25T16:38:01 *** d9b4bef9 has quit IRC
1912018-08-25T16:39:08 *** d9b4bef9 has joined #bitcoin-core-dev
1922018-08-25T16:41:48 *** Krellan has joined #bitcoin-core-dev
1932018-08-25T16:49:21 *** Krellan has quit IRC
1942018-08-25T16:55:03 *** CubicEarth has quit IRC
1952018-08-25T17:02:32 *** AaronvanW has joined #bitcoin-core-dev
1962018-08-25T17:13:44 *** Krellan has joined #bitcoin-core-dev
1972018-08-25T17:15:02 *** spinza has quit IRC
1982018-08-25T17:26:03 *** spinza has joined #bitcoin-core-dev
1992018-08-25T17:35:58 *** Taifta has joined #bitcoin-core-dev
2002018-08-25T17:45:31 *** jhfrontz has quit IRC
2012018-08-25T17:48:24 *** plankers has joined #bitcoin-core-dev
2022018-08-25T17:49:32 *** jhfrontz has joined #bitcoin-core-dev
2032018-08-25T18:08:14 *** Chris_Stewart_5 has quit IRC
2042018-08-25T18:20:02 *** drexl has quit IRC
2052018-08-25T18:29:31 *** csknk has quit IRC
2062018-08-25T18:51:57 *** SopaXorzTaker has quit IRC
2072018-08-25T18:58:45 *** davex__ has joined #bitcoin-core-dev
2082018-08-25T19:03:20 *** hebasto has joined #bitcoin-core-dev
2092018-08-25T19:07:42 *** SopaXorzTaker has joined #bitcoin-core-dev
2102018-08-25T19:10:42 *** ken2812221 has quit IRC
2112018-08-25T19:21:02 *** d9b4bef9 has quit IRC
2122018-08-25T19:22:08 *** d9b4bef9 has joined #bitcoin-core-dev
2132018-08-25T19:32:08 *** SopaXorzTaker has quit IRC
2142018-08-25T19:32:53 *** wumpus has joined #bitcoin-core-dev
2152018-08-25T20:39:07 *** vexbuy_ has quit IRC
2162018-08-25T20:39:22 *** vexbuy has joined #bitcoin-core-dev
2172018-08-25T20:39:36 <jamesob> re: memory usage increase: preliminary bisections are in and MarcoFalke and I are betting it's the leveldb changes. https://i.imgur.com/8aXRzwe.png
2182018-08-25T20:41:33 *** intcat has quit IRC
2192018-08-25T20:42:31 <gmaxwell> jamesob: wait. how are we measuring memory usage in that benchmark?
2202018-08-25T20:42:52 <jamesob> gmaxwell: time -f %M (ie resident set size)
2212018-08-25T20:49:08 <jamesob> https://github.com/chaincodelabs/bitcoinperf/blob/master/runner/main.py#L659-L668
2222018-08-25T20:53:40 <sipa> so every mmap causes 150 kB RSS increase? :s
2232018-08-25T20:54:31 <gmaxwell> no because we're not actually using the new maximum.
2242018-08-25T20:54:48 <gmaxwell> (I mean not using all of)
2252018-08-25T20:54:49 <sipa> aha.
2262018-08-25T20:54:57 <gmaxwell> So even MOAR.
2272018-08-25T20:55:00 <gmaxwell> which is suspect
2282018-08-25T20:55:09 <sipa> mmap by default will prefetch mapped pages into memory
2292018-08-25T20:55:19 *** plankers has quit IRC
2302018-08-25T20:55:24 <sipa> by default, 31 4kB blocks
2312018-08-25T20:55:54 <gmaxwell> oh interesting. but those pages are clean they'll just get evicted, they really shouldn't be counted bt RSS :(
2322018-08-25T20:57:37 <gmaxwell> so MADV_RANDOM
2332018-08-25T20:57:38 <gmaxwell> ...
2342018-08-25T20:57:48 <sipa> madvice(MADV_DONTNEED) will disable the reading entirely
2352018-08-25T20:58:08 <sipa> which may be useful to diagnose the issue
2362018-08-25T20:58:44 <jamesob> (for those following along at home: https://github.com/bitcoin/bitcoin/pull/13925/files)
2372018-08-25T20:58:46 *** AaronvanW has quit IRC
2382018-08-25T20:59:20 *** AaronvanW has joined #bitcoin-core-dev
2392018-08-25T20:59:26 *** Chris_Stewart_5 has joined #bitcoin-core-dev
2402018-08-25T20:59:58 <gmaxwell> Also setting the maximum maps really low, like..2 might be interesting.
2412018-08-25T21:02:21 <gmaxwell> but if this is the problem, MADV_RANDOM is probably the fix to the extent that its an actual problem at all.
2422018-08-25T21:02:42 <gmaxwell> Though we should do a reindex benchmark to make sure MADV_RANDOM doesn't hurt performance.
2432018-08-25T21:03:29 <wumpus> PSA: if after the latest merge you get a linker error "/usr/local/include/boost/smart_ptr/shared_ptr.hpp:728: undefined reference to `translationInterface", you need to do a 'make clean' and re-do the make and it will work
2442018-08-25T21:03:53 *** AaronvanW has quit IRC
2452018-08-25T21:04:25 <luke-jr> wumpus: is there a reason the gitian linux yml has g++-riscv64-linux-gnu as a dep? seems to pull in GCC 7 when we're using GCC 8 now?
2462018-08-25T21:04:51 <luke-jr> wumpus: if `make clean` ever fixes something, that means there's a bug in the build system :/
2472018-08-25T21:06:05 <sipa> gmaxwell, jamesob: LMDB uses MADV_RANDOM it seems
2482018-08-25T21:06:22 <sipa> (though its design is different, i don't know their access patterns)
2492018-08-25T21:06:36 <wumpus> luke-jr: yes, it must be missing some changes in dependency detection between source and header files (another one is if you change something in univalue, it won't detect it)
2502018-08-25T21:06:55 <sipa> jamesob: try this:
2512018-08-25T21:06:56 <sipa> void* base = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0);
2522018-08-25T21:06:56 <sipa> if (base != MAP_FAILED) {
2532018-08-25T21:06:56 <sipa> + madvise(base, size, MADV_DONTNEED);
2542018-08-25T21:07:07 <sipa> in src/leveldb/util/env_posix.cc
2552018-08-25T21:07:32 <sipa> (and/or MADV_RANDOM)
2562018-08-25T21:07:37 <wumpus> luke-jr: it pulls in both gcc 7 and 8, I think that's necessary due to some strangeness with the packages (some symlink will only exist when g++-riscv64-linux-gnu is also installed)
2572018-08-25T21:07:41 <luke-jr> DONTNEED sounds wrong?
2582018-08-25T21:07:51 <luke-jr> wumpus: ah, weird
2592018-08-25T21:08:08 <wumpus> luke-jr: you might be able to get around it, but I noticed and tried as well and ran into a dead end
2602018-08-25T21:08:20 <sipa> luke-jr: to diagnoze
2612018-08-25T21:08:48 <sipa> luke-jr: it would be interesting to see what the effect on RSS is with DONTNEED, to have an idea to what extent our memory usage is due to mmap caching
2622018-08-25T21:09:30 <jamesob> sipa: giving it a shot now
2632018-08-25T21:09:52 <wumpus> luke-jr: at least it's not MADV_HWPOISON!
2642018-08-25T21:10:09 *** BashCo has joined #bitcoin-core-dev
2652018-08-25T21:10:21 *** intcat has joined #bitcoin-core-dev
2662018-08-25T21:10:40 *** plankers has joined #bitcoin-core-dev
2672018-08-25T21:10:47 <luke-jr> wumpus: lol
2682018-08-25T21:11:06 <gmaxwell> It's plausable to me that MADV_RANDOM will help performance or at least be neutral.
2692018-08-25T21:11:39 <wumpus> yes, to me too
2702018-08-25T21:11:48 <wumpus> our access pattern is more or less random
2712018-08-25T21:12:15 <gmaxwell> I don't recall now, though I know I researched this before... does leveldb's bisection interpolate assuming keys are uniform and that their values are uniformly sized or does it plain bisect?
2722018-08-25T21:12:51 <wumpus> (except in the rare times it's iterating over the whole utxo set in order, like when computing statistics)
2732018-08-25T21:13:15 <gmaxwell> esp in the case of plain bisection, prefetching is a bad behavior.
2742018-08-25T21:13:22 <wumpus> I don't know
2752018-08-25T21:13:44 *** vexbuy has quit IRC
2762018-08-25T21:14:19 *** vexbuy has joined #bitcoin-core-dev
2772018-08-25T21:15:44 <sipa> gmaxwell: there is an index at the end of each ldb file
2782018-08-25T21:15:59 <sipa> i assume it bisects in that index in a naive way, but i'm not sure
2792018-08-25T21:21:05 <jamesob> sipa: bench is running; we'll know how your change works in about six hours
2802018-08-25T21:22:06 <sipa> jamesob: awesome
2812018-08-25T21:22:15 <luke-jr> hm, I think I will regret relatime when I try to prune gitian caches
2822018-08-25T21:53:25 *** meshcollider_ has joined #bitcoin-core-dev
2832018-08-25T21:54:31 *** Amuza has joined #bitcoin-core-dev
2842018-08-25T21:55:36 *** vexbuy_ has joined #bitcoin-core-dev
2852018-08-25T21:56:07 *** vexbuy has quit IRC
2862018-08-25T22:02:32 *** jhfrontz has quit IRC
2872018-08-25T22:08:18 *** AaronvanW has joined #bitcoin-core-dev
2882018-08-25T22:09:15 *** BashCo has quit IRC
2892018-08-25T22:11:10 *** BashCo has joined #bitcoin-core-dev
2902018-08-25T22:17:18 *** plankers has quit IRC
2912018-08-25T22:29:41 *** BashCo has quit IRC
2922018-08-25T22:32:12 *** plankers has joined #bitcoin-core-dev
2932018-08-25T22:32:38 *** BashCo has joined #bitcoin-core-dev
2942018-08-25T22:33:39 *** Amuza has quit IRC
2952018-08-25T22:48:21 *** esotericnonsense has joined #bitcoin-core-dev
2962018-08-25T22:57:51 *** spinza has quit IRC
2972018-08-25T23:07:35 *** sipa has quit IRC
2982018-08-25T23:11:03 *** sipa has joined #bitcoin-core-dev
2992018-08-25T23:18:44 *** dcousens has quit IRC
3002018-08-25T23:23:02 *** d9b4bef9 has quit IRC
3012018-08-25T23:24:08 *** d9b4bef9 has joined #bitcoin-core-dev
3022018-08-25T23:24:58 *** spinza has joined #bitcoin-core-dev
3032018-08-25T23:31:53 *** Chris_Stewart_5 has quit IRC
3042018-08-25T23:40:48 *** Krellan has quit IRC
3052018-08-25T23:41:28 *** Krellan has joined #bitcoin-core-dev