Very slow at the end (>=1.30) - Printable Version +- hashcat Forum (https://hashcat.net/forum) +-- Forum: Deprecated; Previous versions (https://hashcat.net/forum/forum-29.html) +--- Forum: Old oclHashcat Support (https://hashcat.net/forum/forum-38.html) +--- Thread: Very slow at the end (>=1.30) (/thread-3878.html) |
Very slow at the end (>=1.30) - passlab - 12-06-2014 I have a problem: ocl64 and cuda64 v.130 and 1.31 Sometimes for attack methods Combinator and Hybryd (1 dict smaller then 2-nd or mask keyspace; MD5, NTLM about 100 hashes) (may be another too) at the end of work (after ~96-97%) very power decrease of speed (last 1% especially). Fore example sometimes i have time of 95% work smaller then time of last 5 % work. (and 1.01 total time very smaller then total time 1.31) At listing i have this string: INFO: approaching final keyspace, workload adjusted I used all combinations of workload_profile, gpu_accel and gpu_loops. Can I deside this bug? Can I block "workload adjusted" ? RE: Very slow at the end (>=1.30) - epixoip - 12-06-2014 That's just the way it works. GPUs work on massively parallel problems, therefore you have to give them lots of work to do in order to gain acceleration. Once you start to run out of work, you start to lose acceleration. It's completely expected that it will slow down at the end. This used to be much more dramatic in previous versions of oclHashcat, before atom added some code to adjust the workload once the final keyspace is approached. So you definitely don't want to "block" this, as the slow-down at the end would be much more dramatic without it. RE: Very slow at the end (>=1.30) - passlab - 12-06-2014 But for example in 1.01 total time was 20 min, in 1.31 - 45 min (at 4 GPU) (at the end only 1 GPU work at very slaw speed) RE: Very slow at the end (>=1.30) - epixoip - 12-06-2014 how are you measuring this? or is this from memory only. RE: Very slow at the end (>=1.30) - passlab - 12-06-2014 listings i can publish later RE: Very slow at the end (>=1.30) - epixoip - 12-07-2014 ok... RE: Very slow at the end (>=1.30) - passlab - 12-08-2014 1.31: instead of 10 min --> 28 min ./oclHashcat64.bin -a 6 -m 1000 --markov-disable --status --status-timer=240 --logfile-disable --restore-disable --potfile-disable NT.txt 76.dict ?a?a?a?a oclHashcat v1.31 starting... Generating dictionary stats for 76.dict: 28396 bytes (100.00%), 3000 words, 244351875000 keyspace Generated dictionary stats for 76.dict: 28396 bytes, 3000 words, 244351875000 keyspace INFO: approaching final keyspace, workload adjusted [s]tatus [p]ause [r]esume [b]ypass [q]uit => Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (3 mins, 59 secs) Time.Estimated.: Fri Dec 5 13:12:27 2014 (5 mins, 44 secs) Speed.GPU.#1...: 105.0 MH/s Speed.GPU.#2...: 107.8 MH/s Speed.GPU.#3...: 106.4 MH/s Speed.GPU.#4...: 106.0 MH/s Speed.GPU.#*...: 425.3 MH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 100260335616/244351875000 (41.03%) Skipped........: 0/100260335616 (0.00%) Rejected.......: 0/100260335616 (0.00%) HWMon.GPU.#1...: 90% Util, 40c Temp, 80% Fan HWMon.GPU.#2...: 89% Util, 46c Temp, 80% Fan HWMon.GPU.#3...: 90% Util, 40c Temp, 80% Fan HWMon.GPU.#4...: 89% Util, 44c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (7 mins, 59 secs) Time.Estimated.: Fri Dec 5 13:12:24 2014 (1 min, 41 secs) Speed.GPU.#1...: 106.2 MH/s Speed.GPU.#2...: 106.4 MH/s Speed.GPU.#3...: 106.4 MH/s Speed.GPU.#4...: 106.2 MH/s Speed.GPU.#*...: 425.1 MH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 201526185984/244351875000 (82.47%) Skipped........: 0/201526185984 (0.00%) Rejected.......: 0/201526185984 (0.00%) HWMon.GPU.#1...: 91% Util, 42c Temp, 80% Fan HWMon.GPU.#2...: 89% Util, 47c Temp, 80% Fan HWMon.GPU.#3...: 91% Util, 41c Temp, 80% Fan HWMon.GPU.#4...: 89% Util, 44c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (12 mins, 0 secs) Time.Estimated.: Fri Dec 5 13:15:25 2014 (42 secs) Speed.GPU.#1...: 33141.1 kH/s Speed.GPU.#2...: 1228.8 kH/s Speed.GPU.#3...: 1074.5 kH/s Speed.GPU.#4...: 1402.1 kH/s Speed.GPU.#*...: 36846.5 kH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 230825953472/244351875000 (94.46%) Skipped........: 0/230825953472 (0.00%) Rejected.......: 0/230825953472 (0.00%) HWMon.GPU.#1...: 79% Util, 41c Temp, 80% Fan HWMon.GPU.#2...: 79% Util, 46c Temp, 80% Fan HWMon.GPU.#3...: 78% Util, 39c Temp, 80% Fan HWMon.GPU.#4...: 79% Util, 43c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (16 mins, 0 secs) Time.Estimated.: Fri Dec 5 13:19:02 2014 (19 secs) Speed.GPU.#1...: 33768.6 kH/s Speed.GPU.#2...: 1248.5 kH/s Speed.GPU.#3...: 1094.2 kH/s Speed.GPU.#4...: 1404.5 kH/s Speed.GPU.#*...: 37515.8 kH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 239607251392/244351875000 (98.06%) Skipped........: 0/239607251392 (0.00%) Rejected.......: 0/239607251392 (0.00%) HWMon.GPU.#1...: 90% Util, 41c Temp, 80% Fan HWMon.GPU.#2...: 91% Util, 46c Temp, 80% Fan HWMon.GPU.#3...: 90% Util, 39c Temp, 80% Fan HWMon.GPU.#4...: 90% Util, 43c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (20 mins, 0 secs) Time.Estimated.: Fri Dec 5 13:22:45 2014 (2 secs) Speed.GPU.#1...: 1312.2 kH/s Speed.GPU.#2...: 0 H/s Speed.GPU.#3...: 0 H/s Speed.GPU.#4...: 0 H/s Speed.GPU.#*...: 1312.2 kH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 243867829168/244351875000 (99.80%) Skipped........: 0/243867829168 (0.00%) Rejected.......: 0/243867829168 (0.00%) HWMon.GPU.#1...: 92% Util, 40c Temp, 80% Fan HWMon.GPU.#2...: 0% Util, 32c Temp, 80% Fan HWMon.GPU.#3...: 0% Util, 29c Temp, 80% Fan HWMon.GPU.#4...: 0% Util, 30c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Running Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (24 mins, 0 secs) Time.Estimated.: Fri Dec 5 13:26:45 2014 (1 sec) Speed.GPU.#1...: 1288.8 kH/s Speed.GPU.#2...: 0 H/s Speed.GPU.#3...: 0 H/s Speed.GPU.#4...: 0 H/s Speed.GPU.#*...: 1288.8 kH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 244179280816/244351875000 (99.93%) Skipped........: 0/244179280816 (0.00%) Rejected.......: 0/244179280816 (0.00%) HWMon.GPU.#1...: 90% Util, 40c Temp, 80% Fan HWMon.GPU.#2...: 0% Util, 31c Temp, 80% Fan HWMon.GPU.#3...: 0% Util, 28c Temp, 80% Fan HWMon.GPU.#4...: 0% Util, 29c Temp, 80% Fan Session.Name...: oclHashcat Status.........: Exhausted Input.Base.....: File (76.dict) Input.Mod......: Mask (?a?a?a?a) [4] Hash.Target....: File (NT.txt) Hash.Type......: NTLM Time.Started...: Fri Dec 5 13:02:41 2014 (26 mins, 15 secs) Time.Estimated.: 0 secs Speed.GPU.#1...: 1281.7 kH/s Speed.GPU.#2...: 0 H/s Speed.GPU.#3...: 0 H/s Speed.GPU.#4...: 0 H/s Speed.GPU.#*...: 1281.7 kH/s Recovered......: 0/65 (0.00%) Digests, 0/1 (0.00%) Salts Progress.......: 244351875000/244351875000 (100.00%) Skipped........: 0/244351875000 (0.00%) Rejected.......: 0/244351875000 (0.00%) HWMon.GPU.#1...: 85% Util, 40c Temp, 80% Fan HWMon.GPU.#2...: 0% Util, 31c Temp, 80% Fan HWMon.GPU.#3...: 0% Util, 28c Temp, 80% Fan HWMon.GPU.#4...: 0% Util, 29c Temp, 80% Fan RE: Very slow at the end (>=1.30) - iRuser - 12-28-2014 I just got two new GTX980's today and running my old 580ti via 1x to 16x riser. PLaying around with hashcat and came across an issue relating to this post, let me know if i should put elsewhere. I get the theory on why things slow down at as we reduce the workload, but out of the three cards to choose from cudaHashcat v1.31 keeps seemingly choosing to finish the last leg on the weakest card of the 3 making it painfully slow. Why? Is there any way I can change this or can you consider making a small tweak to the logic in a future update? Code: $ ./cudaHashcat64.bin -m 2811 -a 0 nothing2seehere.hashes cracked_pass.txt -r ../customRules/1.rule -o nothing2seehere.cracked --remove --gpu-async --gpu-accel=80 --gpu-loops=1024 |