Hello, On Sun, 09 Nov 2014 00:15:56 -0800 Zac Medico wrote: > On 11/08/2014 10:53 PM, Andrew Savchenko wrote: [...] > > On old hardware it may take dozens of minutes of CPU time. I have > > that *.pickle files, I have sqlite metadata cache, I have 100% CPU > > usage. It's not an I/O problem. Just take into account that due to > > instruction set, Lx cache, frequency and memory speed difference > > old CPU-based system may be 20x times slower than recent one. > > It could be useful for us to collect profiling data generated on old > hardware. If you'd like to help, you can use python's cProfile module to > generate statistics for us to analyze. The statistics can be nicely > visualized as a shaded call graph by using gprof2dot and graphviz [1].
Sorry for delay, I generated samples on two old hosts. Tarball contains per host directories. Each one contains: - pstats file; - generated pdf with call graphs and timing; - host-related information: * emerge --info * /proc/cpuinfo * /proc/memnifo *.pstats and *.pdf filename should describe command unambiguously, e.g. emerge-pv_python:2.7_python:3.3-python-3.3.5-r1 means: emerge -pv python:2.7 python:3.3 while using python-3.3.5-r1 as interpreter. hitomi system was not fully updated for a bit more than a year, while another one for about half a year. So dependency calculations may be of different intencities. Sets of packages installed are similar but not the same: 2502 on hitomi 2953 on desktop I understand that most interesting data will be from emerge -DNupv output, but to obtain it I must first fix all blockers and conflicts, this really takes a lot of time, so please be patient. And last but not the list: on both systems portage is configured to use sqlite3 cache for metadata, so there was no I/O delays (CPU usage about 100% according to top). In order not to abuse mail list with large attachments, data is available here: ftp://brunestud.info/gentoo/portage.tar.xz Best regards, Andrew Savchenko
pgp0dhtoPFabv.pgp
Description: PGP signature
