Thus spake swsnyder@snydernet.net (swsnyder@snydernet.net):
FYI, this is a profile of my Tor v0.2.2.30-rc relay, taken in a 10-minute sampling:
CPU: CPU with timer interrupt, speed 0 MHz (estimated)
Profiling through timer interrupt
samples % linenr info symbol name
3126 29.7290 cast-586.s:9 CAST_encrypt
Can you attach gdb to your relay and set a breakpoint for
CAST_encrypt? We have no idea why this function should be called at
all (unless it is for something like reading keyfiles off disk?) let
alone dominate your profile output.
gdb -p <tor_pid>
(gdb) break CAST_encrypt
(gdb) cont
You may need to stick a 'file /usr/bin/tor' or similar in there.
If you get no hits, try to do it on startup:
gdb /usr/bin/tor
(gdb) break CAST_encrypt
Function "CAST_encrypt" not defined.
Make breakpoint pending on future shared library load? (y or [n]) y
(gdb) run [<tor args>]
If you get any hits, run 'backtrace' and give us the output. You may
need to install some debuginfo packages, but gdb should tell you this
if so.
If anyone playing along at home gets any hits on either of these
breakpoints, let us know.
1677 15.9486 sha256-586.s:8 sha256_block_data_order
1149 10.9272 aes-586.s:424 _x86_AES_encrypt
844 8.0266 sha1-586.s:8 sha1_block_data_order
273 2.5963 crypto.c:1649 crypto_digest_get_digest
221 2.1018 md32_common.h:283 SHA1_Update
182 1.7309 encode.c:190 EVP_EncodeBlock
171 1.6262 OpenBSD_malloc_Linux.c:1793 ifree
136 1.2934 cast-586.s:379 CAST_decrypt
130 1.2363 md32_common.h:348 SHA1_Final
127 1.2078 obj_lib.c:66 OBJ_dup
122 1.1602 memarea.c:221 memarea_alloc
110 1.0461 aes-586.s:1610 _x86_AES_decrypt
After running for 14 hours, the Tor relay has consumed 1.6% of CPU time. It is now using 45MB of RAM, servicing 112 active connections.
According to http://torstatus.blutmagie.de my Max/Burst/Observed (Bps) bandwidth is:
153600 / 307200 / 127170
Environment:
CPU: Pentium-M (Dothan) @ 1.80 GHz
RAM: 1.0 GB DDR1
Net: Fast Ethernet connected to a Surfboard cable modem
CentOS v5.6
Tor v0.2.2.30-rc
libevent 2.0.12-stable
openssl 1.0.0d
zlib 1.2.5
glibc 2.5-58
Just another data point.
_______________________________________________
tor-relays mailing list
tor-relays@lists.torproject.org
https://lists.torproject.org/cgi-bin/mailman/listinfo/tor-relays
--
Mike Perry
Mad Computer Scientist
fscked.org evil labs
Mike Perry