|
01:49
ilbot3 joined
04:46
KDr2_c joined
06:39
domidumont joined
06:45
domidumont joined
07:43
domidumont joined
07:50
TimToady joined
08:27
zakharyas joined
|
|||
| lizmat | hmmm...notice of build breakage on CentOS6 | 11:49 | |
| github.com/MoarVM/MoarVM/issues/587 | |||
| timotimo | thanks | 11:50 | |
|
13:05
AlexDaniel joined
|
|||
| stmuk_ | timotimo: see my comment on that issue | 13:43 | |
| timotimo | stmuk_: can you help me get the rdtscp configure-time probe working? | 13:59 | |
| oh | |||
| i think i know what's wrong | |||
| Geth | MoarVM/configure-telemeh-probe-rdtscp: e7e46332d8 | (Timo Paulssen)++ | src/profiler/telemeh.c we always define MVM_RDTSCP, but sometimes with 0 instead of 1. |
14:01 | |
| stmuk_ | timotimo: sure | 14:05 | |
| shall I test now or wait a bit? | |||
| timotimo | now | 14:06 | |
| stmuk_ | timotimo: gist.github.com/stmuk/5a09e2438498...c59ca29fbb | 14:07 | |
| timotimo | interesting | ||
| i'll reproduce locally by just setting RDTSCP to 0 in the makefile | 14:08 | ||
| huh | 14:09 | ||
| Geth | MoarVM/configure-telemeh-probe-rdtscp: bcd8b59c81 | (Timo Paulssen)++ | src/profiler/telemeh.c give __rdtscp a more proper stub implementation |
14:10 | |
| timotimo | should be bettern ow | ||
| stmuk_ | works fine on Centos 6 (I can test on OpenBSD later) | 14:12 | |
| timotimo++ | 14:13 | ||
| timotimo | fantastic | ||
| Geth | MoarVM/master: 7 commits pushed by (Timo Paulssen)++
|
14:52 | |
| Zoffix | How do you pronounce "telemeh"? "t-eh-l-eh-m-eh"? | 14:55 | |
| stmuk_ | tele meh | 14:58 | |
| timotimo | tell-uh-meh | 15:19 | |
| robertle | jsut like telomere | 15:21 | |
|
16:00
geekosaur joined
16:04
geekosaur joined
16:40
domidumont joined
16:56
geekosaur joined
|
|||
| timotimo | hm. i still don't know how we could cause all other threads to be interrupted reliably so that we can slurp up their profile data | 17:21 | |
| MasterDuke_ | that would be awesome though... | 17:22 | |
| timotimo | i mean, normally when we exit we just have the other threads killed dead in their tracks by the process just ending | 17:23 | |
| we could probably abuse the gc signaling mechanism, but instead of doing gc, we do our profile stuff | 17:33 | ||
| the thing is ... we probably need to GC multiple times inside the process of creating the data structures from the profile data | 17:42 | ||
| however | |||
| hm | 17:43 | ||
| i thought perhaps we can just recursively memcpy stuff away so the gc doesn't touch it any more, but that sounds like recipe for absolute disaster | |||
|
17:47
AlexDaniel joined
|
|||
| timotimo | though of course by turning on gen2-allocatoin-by-default gets us out of "having to gc a bunch" trouble | 18:32 | |
| samcv | good * | 18:55 | |
| timotimo | nood goon | ||
| that came out strange | |||
| samcv | heh | 18:57 | |
| timotimo | the cat really likes the upper left edge of my laptop screen | 19:42 | |
| lizmat | timotimo: perhaps that's the warmest part ? | 19:47 | |
| lizmat remembers our cats liking to sleep on top of a monitor | 19:48 | ||
| but that was in the pre-flatscreen days :-) | |||
| timotimo | heh | 19:52 | |
| nah, he's rubbing his flew on it | |||
|
19:59
geekosaur joined
|
|||
| Zoffix wonders what a flew of a cat is :) | 20:10 | ||
| timotimo | the dictionary spat that word out | 20:13 | |
| hm, seems like that's reserved for canines | 20:14 | ||
| Zoffix | face? | ||
| whiskers? | |||
| timotimo | "upper lip" | ||
| basically "where the whiskers come out, or below there" | |||
| Zoffix | ah | ||
| I looked at the first def in dictionary and it was something about tubes and fire boilers :) | 20:15 | ||
| timotimo | which also causes the corner of the laptop lid ends up inside the mouth one time out of three | ||
| MasterDuke_: could you give me that little set of sql queries again? the ones that you made to give the same results as the html profiler? | 20:24 | ||
| MasterDuke_ | timotimo: i put some examples in the PR comments github.com/perl6/nqp/pull/354. let me know if those don't get you what you need | 20:25 | |
| timotimo | ah, *there* it was | 20:26 | |
| timotimo is briefly fascinated by zmodem | 20:43 | ||
|
21:32
geekosaur joined
|
|||
| timotimo | i ran a profile of a thing and it's totally killed my puter | 22:01 | |
| MasterDuke_ | creating the profile did? or accessing it? | 22:03 | |
| timotimo | creating | 22:04 | |
| tried to build it with the sql mode. i'm not sure if it even reached the perl6 part of the code, though | |||
| wonder when my system will be resurrected ... | 22:05 | ||
| we might really want to turn on gen2-by-default allocation during the call graph dumping | 22:06 | ||
| japhb | timotimo: Ragnarok? | 22:07 | |
| MasterDuke_ | should probably batch writing out the sql lines. it's simpler not to, but our IO is slow | 22:08 | |
| timotimo | have you profiled that? :) | 22:09 | |
| MasterDuke_ | heh, yes and no. i've timed the json and the sql output, and json is faster | 22:10 | |
| timotimo | mhm | ||
| MasterDuke_ | for the exact same profile (i.e., i hacked it to write both) | ||
| timotimo | i'd like to use my desktop again please | 22:12 | |
| MasterDuke_ | i guess i can't be sure the reason to_sql is slower is because of how it does IO, but that's my guess | 22:13 | |
| timotimo | i wonder why this particular profile is so explosive | 22:15 | |
| MasterDuke_ | what's the perl6 code? | 22:18 | |
| timotimo | it's my brownian tree implementation off of rosettacode | 22:19 | |
| MasterDuke_ | ha, taking longer than the 25s mentioned in the description? | 22:21 | |
| timotimo | depends on what size and particle count you're using | 22:22 | |
| my run was 55 seconds | |||
| and since then it's been trying to build the profile | |||
| MasterDuke_ | is the output file being written to? | 22:24 | |
| timotimo | how am i supposed to find out? | ||
| MasterDuke_ | it's getting bigger/has more lines? | 22:25 | |
| timotimo | well, yeah, but how am i supposed to find out how big it is? | ||
| i'm telling you i can not use the device | 22:26 | ||
| at. all. | |||
| no mouse cursor movement, no ssh connection | |||
| the clock hasn't updated since 23:56, now it's 00:26 | |||
| MasterDuke_ | oh! | ||
| that...does make it harder... | 22:27 | ||
| timotimo | a little bit | 22:28 | |
| i might kill the machine | |||
| if i can, that is | |||
| i pressed a few combinations and pushed the power button | 22:29 | ||
| don't think anything's happening | |||
| i held the power button and it did a hard shut-off | 22:30 | ||
| MasterDuke_ | hate when i have to do that | 22:31 | |
| timotimo | yeah | 22:32 | |
| not sure how to make it unnecessary | |||
| hm | 22:34 | ||
| the numbers in the calls table are reaching 80k | |||
| when i have only size=10 and particlenum=30 | |||
| MasterDuke_ | seems a lot | 22:35 | |
| timotimo | i think so, too | ||
| rec_depth goes up to 280 | 22:41 | ||
| i have not written any sql in far too long | 22:43 | ||
| MasterDuke_: since the callees table was renamed calls, maybe we should rename callee_id to call_id? | 22:54 | ||
| or just id, like routines has a column named "id" | 22:55 | ||
| huh | |||
| why does allocations have both a caller_id and a call_id? | 22:56 | ||
| sorry, callee_id | |||
| MasterDuke_ | heh. yeah, i wasn't sure at first which was needed, so i just added both (caller and callee to allocations) | 23:02 | |
| and yeah, renaming callee_id would probably make sense | |||
| timotimo | DBIish is not happy with me | 23:04 | |
| yeah, user error | 23:05 | ||
| poor dot | 23:09 | ||
| has to handle 80k nodes for this particular document | |||
| Error: <stdin>: syntax error in line 83954 near '' | 23:10 | ||
| MasterDuke_ | in the sql output? | 23:14 | |
| timotimo | no, in my dot transformation of it | 23:15 | |
| it was some bad escaping or something | 23:16 | ||
|
23:24
geekosaur joined
|
|||
| timotimo | well, it's still trying to render | 23:27 | |
| not sure if it's layouting or what | |||
| it shouldn't be terribly hard to do for dot, the graph should be perfectly tree-like | 23:29 | ||
| i'll suspend my computer so i can sleep (it's noisy), but i'll leave dot running so it'll maybe finish tomorrow %) | 23:41 | ||
| MasterDuke_ | i've used dot a bunch before, but always on tiny graphs, no idea how well it handles large things | 23:42 | |