time spent writing history..

Fabien Tassin fta at sofaraway.org
Mon Jan 22 01:16:12 UTC 2001


Code region              Time    Pct    Invoked   Min(ms)    Avg(ms)    Max(ms)
article cleanup  01:03:22.687   4.4%    1349312     1.207      2.818      4.229
article write    03:38:32.563  15.2%    1316215     4.628      9.962     14.299
history lookup   01:33:00.892   6.5%   15994074     0.008      0.349      2.731
history sync     00:00:09.114   0.0%      26704     0.000      0.341     76.367
history write    03:35:37.066  15.0%    1327232     8.507      9.747     21.893

I wonder why innd spend so much time to write into the history.
These numbers are for a full feed (1.3M articles and 220 GB that day).

-rw-r--r--    1 news     news     838524872 Jan 22 01:51 history
-rw-r--r--    1 news     news           120 Jan 22 01:51 history.dir
-rw-r--r--    1 news     news     138755592 Jan 22 01:24 history.hash
-rw-r--r--    1 news     news     185007456 Jan 22 01:51 history.index

dbz 6 23125932 14 66
13873931 15256489 15278039 15417288 15365094 15274162 15181981 14958734
14714421 14766787 14689412

"article write" looks ok for U3 SCSI disks + Raid0. I've quickly read
the code of HISwrite() and HISremember() and the hardest part
seems to be dbzstore(). Looks like it is not a tagged-hash issue as I'm
running with largefiles enabled.

Any idea ?

-- 
Fabien Tassin -+- fta at sofaraway.org



More information about the inn-workers mailing list