Re: slowdown in notmuch perf suite with xapian 1.3.5

[David Bremner <david@tethera.net>]

Olly Betts <olly@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.