[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20091026095516.02f1cb49@nehalam>
Date: Mon, 26 Oct 2009 09:55:16 -0700
From: Stephen Hemminger <shemminger@...tta.com>
To: Octavian Purdila <opurdila@...acom.com>
Cc: Eric Dumazet <eric.dumazet@...il.com>,
Krishna Kumar2 <krkumar2@...ibm.com>,
Hagen Paul Pfeifer <hagen@...u.net>, netdev@...r.kernel.org
Subject: Re: [PATCH next-next-2.6] netdev: better dev_name_hash
Added more algorithms to test...
Time is in seconds for 10000000 entries with hashbits = 8
Ratio is number of probes / ideal hash probes
Result sorted by distribution:
Algorithm Time Ratio Max StdDev
string10 1.434087 1.00 39064 0.01
SuperFastHash 1.469511 1.00 40497 2.17
string_hash17 1.472544 1.00 39497 1.50
jhash_string 1.501508 1.00 39669 1.04
crc 2.826795 1.00 39088 0.07
md5_string 3.608253 1.00 39605 0.98
djb2 1.462722 1.15 60681 76.16
string_hash31 1.457253 1.21 64950 91.12
sdbm 1.566174 2.38 129900 232.22
pjw 1.527306 2.45 99990 237.86
elf 1.576096 2.45 99990 237.86
kr_hash 1.400072 7.80 468451 515.52
fletcher 1.449671 7.80 468451 515.52
full_name_hash 1.487707 13.09 562501 687.24
xor 1.400403 13.36 583189 694.98
lastchar 1.348798 25.60 1000000 980.27
Another run sorted by speed:
Algorithm Time Ratio Max StdDev
lastchar 1.338545 25.60 1000000 980.27
kr_hash 1.398453 7.80 468451 515.52
xor 1.398843 13.36 583189 694.98
string10 1.432756 1.00 39064 0.01
fletcher 1.448499 7.80 468451 515.52
string_hash31 1.457524 1.21 64950 91.12
string_hash17 1.462548 1.00 39497 1.50
djb2 1.462956 1.15 60681 76.16
SuperFastHash 1.469907 1.00 40497 2.17
full_name_hash 1.486465 13.09 562501 687.24
jhash_string 1.500959 1.00 39669 1.04
pjw 1.526097 2.45 99990 237.86
sdbm 1.566533 2.38 129900 232.22
elf 1.576470 2.45 99990 237.86
crc 2.811210 1.00 39088 0.07
md5_string 3.604675 1.00 39605 0.98
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists