slowdown in notmuch perf suite with xapian 1.3.5
David Bremner
david at tethera.net
Thu Apr 7 18:14:24 PDT 2016
Olly Betts <olly at survex.com> writes:
> Non-cached reads/writes are arguably the most useful sort to measure, but the
> reads at least will be sensitive to OS caching, which means a repeat run will
> generally show lower numbers of reads, e.g.:
>
> $ /usr/bin/time -f '%I/%O' wc randomfile
> 240 2908 96780 randomfile
> 192/0
> $ /usr/bin/time -f '%I/%O' wc randomfile
> 240 2908 96780 randomfile
> 0/0
>
> So those numbers may not be entirely comparable, depending what order your
> tests were done in, and whether you'd run the tests (or cloned the repo or some
> other operation which read or wrote the files used) recently enough that their
> data might still be cached.
Here are the number from second glass run. The order was glass / chert /
glass
T00-new.sh: Testing notmuch new [0.4 large]
Wall(s) Usr(s) Sys(s) Res(K) In/Out(512B)
Initial notmuch new 920.53 698.96 207.02 245188 3528/22442096
notmuch new #2 0.55 0.00 0.01 8048 6960/160
notmuch new #3 0.01 0.00 0.00 8112 0/8
notmuch new #4 0.01 0.01 0.00 8136 0/8
notmuch new #5 0.01 0.00 0.00 8140 0/8
notmuch new #6 0.01 0.00 0.00 8116 0/8
T01-dump-restore.sh: Testing dump and restore [0.4 large]
Wall(s) Usr(s) Sys(s) Res(K) In/Out(512B)
load nmbug tags 8.89 4.23 3.88 11648 368/40072
dump * 7.37 6.29 1.08 25268 72/27928
restore * 7.60 7.16 0.43 8624 0/0
T02-tag.sh: Testing tagging [0.4 large]
Wall(s) Usr(s) Sys(s) Res(K) In/Out(512B)
tag * +new_tag 474.16 274.89 191.52 34820 16/1920240
tag * +existing_tag 0.01 0.01 0.00 8480 152/0
tag * -existing_tag 438.62 239.02 195.44 34928 0/1970160
tag * -missing_tag 0.00 0.00 0.00 8264 0/0
It's a bit faster overall, but not radically so. So I think cache
effects are not the main issue here.
More information about the notmuch
mailing list