| *** dev1990 <dev1990!~dev@78.10.71.240> has quit IRC (Quit: Konversation terminated!) | 00:01 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 00:33 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Read error: Connection reset by peer) | 00:34 | |
| *** camus1 is now known as camus | 00:34 | |
| *** leon-anavi <leon-anavi!~Leon@78.130.197.211> has quit IRC (Remote host closed the connection) | 00:55 | |
| *** sakoman <sakoman!~steve@rrcs-66-91-142-162.west.biz.rr.com> has quit IRC (Quit: Leaving.) | 02:36 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 02:58 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 265 seconds) | 02:59 | |
| *** camus1 is now known as camus | 02:59 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 05:16 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Read error: Connection reset by peer) | 05:17 | |
| *** camus1 is now known as camus | 05:17 | |
| *** alejandrohs <alejandrohs!~alejandro@user/alejandrohs> has quit IRC (Read error: Connection reset by peer) | 05:26 | |
| *** alejandrohs <alejandrohs!~alejandro@user/alejandrohs> has joined #oe | 05:27 | |
| *** ant__ <ant__!~ant@host-82-54-240-7.retail.telecomitalia.it> has quit IRC (Quit: Leaving) | 06:05 | |
| *** rsalveti <rsalveti!uid117878@id-117878.uxbridge.irccloud.com> has quit IRC (Quit: Connection closed for inactivity) | 06:17 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has joined #oe | 06:43 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has quit IRC (Ping timeout: 252 seconds) | 06:47 | |
| *** mckoan|away is now known as mckoan | 06:50 | |
| mckoan | good morning | 06:50 |
|---|---|---|
| *** dl9pf[m] <dl9pf[m]!~dl9pfmatr@2001:470:69fc:105::9a8> has joined #oe | 06:50 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has joined #oe | 07:01 | |
| *** rob_w <rob_w!~bob@host-82-135-31-73.customer.m-online.net> has joined #oe | 07:04 | |
| *** leon-anavi <leon-anavi!~Leon@78.130.197.211> has joined #oe | 07:08 | |
| marex | hi, maybe this is something known already, although I couldn't find anything in the MLs or elsewhere | 07:18 |
| marex | so | 07:18 |
| marex | I built oe-core/master (recent-ish, like from a day ago) for cortexa7thf-neon-vfpv4 (stm32mp1) core-image-base | 07:19 |
| marex | then I ran some ad-hoc python3 loop (i.e. not-really-good-benchmark provided by someone else) | 07:19 |
| marex | that loop took around 35% longer on that python 3.9.x interpreter in OE-core than it did in debian armhf testing/unstable hybrid rootfs with python 3.9.6 from debian package running the exact same kernel version on the exact same hardware | 07:20 |
| marex | I basically took the two rootfs images , chrooted into each, ran the test | 07:21 |
| marex | now, it is not new, I originally found it in oe-core dunfell with python 3.8.11, same problem there, it is slower than the debian one | 07:21 |
| marex | lmbench indicates no funny outliers /wrt the hardware or image, in fact, the lmbench run is generally faster on the OE built image because of better CPU tailored optimizations | 07:22 |
| marex | so this is likely isolated to python3 interpreter | 07:22 |
| marex | I also had a look at what debian configures there, they enable pthread support (OE does not for the cross compiled target) and computed gotos, but neither makes a difference | 07:23 |
| marex | am I missing anything obvious which would make such a huge performance difference ? | 07:24 |
| marex | RP: ^ | 07:24 |
| *** dgriego1 <dgriego1!~dgriego@user/dgriego> has quit IRC (Ping timeout: 252 seconds) | 07:30 | |
| *** dgriego <dgriego!~dgriego@user/dgriego> has joined #oe | 07:31 | |
| marex | well uh ... on aarch64 (ca53,zynqmp) it also runs slower compared to debian aarch64 build | 08:17 |
| *** florian <florian!~florian@port-217-146-132-69.static.as20676.net> has joined #oe | 08:21 | |
| RP | marex: try enabling profile guided optimisation (pgo) | 08:30 |
| RP | marex: you'll need to turn off reproducbility for python for that :/ | 08:31 |
| marex | RP: pgo is already enabled for class-target | 08:31 |
| marex | RP: I also tried LTO | 08:31 |
| RP | marex: hmm, don't know then | 08:31 |
| marex | pthread is missing when cross compiling, I force-enabled that | 08:31 |
| marex | I also added --with-computed-gotos | 08:32 |
| RP | would be good to track down the difference | 08:32 |
| marex | that should make the python interpretter configured close to what debian has there | 08:32 |
| marex | still nothing | 08:32 |
| marex | RP: yes | 08:32 |
| marex | RP: the odd thing is, it happens both on arm64 and arm32, which means it is some arch-independent config issue | 08:32 |
| marex | and I suspect if my base system(s) had problems, they would show up in lmbench, since the python interpreter should be mostly independent of the base system libs | 08:33 |
| RP | marex: did you disable reproducibility? | 08:43 |
| RP | marex: you've looked at the possibly_include_pgo() function? | 08:44 |
| marex | if bb.utils.contains('MACHINE_FEATURES', 'qemu-usermode', True, False, d) and d.getVar('BUILD_REPRODUCIBLE_BINARIES') != '1': | 08:48 |
| marex | this ? | 08:48 |
| marex | I do NOT have BUILD_REPRODUCIBLE_BINARIES set | 08:49 |
| marex | (so I get the PGO) | 08:49 |
| marex | I also verified the PGO configure flag is set, that --enable-optimizations one | 08:49 |
| *** dgriego <dgriego!~dgriego@user/dgriego> has quit IRC (Ping timeout: 252 seconds) | 09:01 | |
| *** dgriego <dgriego!~dgriego@user/dgriego> has joined #oe | 09:03 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 09:48 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 265 seconds) | 09:50 | |
| *** camus1 is now known as camus | 09:50 | |
| RP | marex: ok, good. reproducible builds are the default now | 10:08 |
| RP | marex: just wanted to double check | 10:08 |
| marex | RP: btw the same problem happens in dunfell LTS, there the reproducible builds are surely disabled | 10:55 |
| marex | so this isnt a new problem | 10:55 |
| RP | marex: we enabled there there I think too | 10:59 |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 11:05 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 245 seconds) | 11:07 | |
| *** camus1 is now known as camus | 11:07 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 245 seconds) | 12:01 | |
| *** camus <camus!~Instantbi@58.246.136.202> has joined #oe | 12:01 | |
| *** rber|res <rber|res!~rber|res@ppp-2-86-135-62.home.otenet.gr> has joined #oe | 12:08 | |
| marex | RP: lemme double-check | 12:11 |
| marex | bitbake -e python3 | grep ^PACKAGECONFIG | 12:27 |
| marex | PACKAGECONFIG="readline pgo gdbm" | 12:27 |
| marex | PACKAGECONFIG_class-target="readline pgo gdbm" | 12:27 |
| marex | RP: looks good to me ^ no ? | 12:27 |
| *** warpme_ <warpme_!uid391875@id-391875.helmsley.irccloud.com> has joined #oe | 12:32 | |
| RP | marex: as long as reproduciblity isn't enabled | 12:43 |
| *** leon-anavi <leon-anavi!~Leon@78.130.197.211> has quit IRC (Remote host closed the connection) | 13:42 | |
| *** leon-anavi <leon-anavi!~Leon@78.130.197.211> has joined #oe | 13:42 | |
| *** sakoman <sakoman!~steve@rrcs-66-91-142-162.west.biz.rr.com> has joined #oe | 14:00 | |
| *** rob_w <rob_w!~bob@host-82-135-31-73.customer.m-online.net> has quit IRC (Quit: Leaving) | 14:02 | |
| marex | RP: it is not | 14:22 |
| RP | marex: hmm, ok. I think I'm getting confused as we did start testing it for dunfell | 14:24 |
| *** dev1990 <dev1990!~dev@78.10.71.240> has joined #oe | 14:44 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 15:11 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Read error: Connection reset by peer) | 15:12 | |
| *** camus1 is now known as camus | 15:12 | |
| *** arr <arr!~ar@208.116.162.162> has joined #oe | 15:27 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 15:55 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 265 seconds) | 15:57 | |
| *** camus1 is now known as camus | 15:57 | |
| *** dl9pf[m] <dl9pf[m]!~dl9pfmatr@2001:470:69fc:105::9a8> has quit IRC (Quit: You have been kicked for being idle) | 16:00 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has quit IRC (Read error: Connection reset by peer) | 16:00 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has joined #oe | 16:00 | |
| *** mckoan is now known as mckoan|away | 16:21 | |
| *** leon-anavi <leon-anavi!~Leon@78.130.197.211> has quit IRC (Quit: Leaving) | 16:26 | |
| *** rsalveti <rsalveti!uid117878@id-117878.uxbridge.irccloud.com> has joined #oe | 16:29 | |
| *** frieder <frieder!~frieder@i59F4B6AF.versanet.de> has quit IRC (Ping timeout: 265 seconds) | 16:47 | |
| *** arr <arr!~ar@208.116.162.162> has quit IRC (Ping timeout: 265 seconds) | 16:47 | |
| *** arr <arr!~ar@208.116.162.162> has joined #oe | 16:51 | |
| *** florian <florian!~florian@port-217-146-132-69.static.as20676.net> has quit IRC (Quit: Ex-Chat) | 16:56 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 17:07 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 264 seconds) | 17:09 | |
| *** camus1 is now known as camus | 17:09 | |
| *** florian <florian!~florian@dynamic-002-243-097-197.2.243.pool.telefonica.de> has joined #oe | 18:01 | |
| *** ant__ <ant__!~ant@host-82-54-240-7.retail.telecomitalia.it> has joined #oe | 19:11 | |
| *** rber|res <rber|res!~rber|res@ppp-2-86-135-62.home.otenet.gr> has quit IRC (Ping timeout: 245 seconds) | 20:18 | |
| *** rber|res <rber|res!~rber|res@ppp-2-86-132-26.home.otenet.gr> has joined #oe | 20:21 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 264 seconds) | 20:24 | |
| *** camus <camus!~Instantbi@58.246.136.202> has joined #oe | 20:24 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 20:43 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 265 seconds) | 20:43 | |
| *** camus1 is now known as camus | 20:43 | |
| *** florian <florian!~florian@dynamic-002-243-097-197.2.243.pool.telefonica.de> has quit IRC (Ping timeout: 250 seconds) | 21:24 | |
| *** arr <arr!~ar@208.116.162.162> has quit IRC (Ping timeout: 265 seconds) | 22:06 | |
| *** sakoman <sakoman!~steve@rrcs-66-91-142-162.west.biz.rr.com> has quit IRC (Quit: Leaving.) | 22:14 | |
| *** sakoman <sakoman!~steve@rrcs-66-91-142-162.west.biz.rr.com> has joined #oe | 22:28 | |
| *** camus1 <camus1!~Instantbi@58.246.136.202> has joined #oe | 22:42 | |
| *** camus <camus!~Instantbi@58.246.136.202> has quit IRC (Ping timeout: 245 seconds) | 22:44 | |
| *** camus1 is now known as camus | 22:44 | |
| *** vmeson <vmeson!~rmacleod@198-48-226-187.cpe.pppoe.ca> has quit IRC (Quit: Konversation terminated!) | 22:45 | |
| *** vmeson <vmeson!~rmacleod@198-48-226-187.cpe.pppoe.ca> has joined #oe | 22:51 | |
| *** otavio <otavio!~otavio@201-34-65-230.user3p.brasiltelecom.net.br> has quit IRC (Remote host closed the connection) | 22:56 | |
| *** otavio <otavio!~otavio@201-34-65-230.user3p.brasiltelecom.net.br> has joined #oe | 23:04 | |
| *** florian <florian!~florian@dynamic-002-243-097-197.2.243.pool.telefonica.de> has joined #oe | 23:11 | |
| *** rber|res <rber|res!~rber|res@ppp-2-86-132-26.home.otenet.gr> has quit IRC (Remote host closed the connection) | 23:22 | |
| *** rber|res <rber|res!~rber|res@ppp-2-86-132-26.home.otenet.gr> has joined #oe | 23:22 | |
| *** florian <florian!~florian@dynamic-002-243-097-197.2.243.pool.telefonica.de> has quit IRC (Ping timeout: 250 seconds) | 23:24 | |
Generated by irclog2html.py 2.17.2 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!