Message boards :
Number crunching :
Panic Mode On (106) Server Problems?
Message board moderation
Previous · 1 . . . 9 · 10 · 11 · 12 · 13 · 14 · 15 . . . 29 · Next
Author | Message |
---|---|
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Nothing is stuck ATM, but there are no Arecibo files loaded to be split so we're in for a guppy flood. . . Hi Wiggo, . . Oh well, the number of jobs per day is gonna take a dive :( Stephen :( |
betreger Send message Joined: 29 Jun 99 Posts: 11408 Credit: 29,581,041 RAC: 66 |
Nothing is stuck ATM, but there are no Arecibo files loaded to be split so we're in for a guppy flood. I'd rather crunch a guppy than a a vhar regardless of the credit/hr. I'm here for Seti not credit. |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . Yep there has been a high proportion of halflings in the Arecibo WUs of late and finding ET is the main priority, but it's still nice to be able to feel my gear is working at a high level of productivity and efficiency. Yet GBT work must also be processed :( . . However, it must be good for contributors like this new guy Juan Jimenez https://setiathome.berkeley.edu/show_user.php?userid=93982. Bringing nearly 7000 CPU cores (yep that's the right number of zeroes) to the project he must feel delighted about the current guppi deluge :) Stephen :( |
Jimbocous Send message Joined: 1 Apr 13 Posts: 1856 Credit: 268,616,081 RAC: 1,349 |
. . However, it must be good for contributors like this new guy Juan Jimenez https://setiathome.berkeley.edu/show_user.php?userid=93982. Bringing nearly 7000 CPU cores (yep that's the right number of zeroes) to the project he must feel delighted about the current guppi deluge :) Stephen :( New? Says he's been around since 1999? I'm pretty impressed with the 225 PCs he's running; wonder which Uni or Corp is footing the bill for that? As far as CPU count, that I'm a bit less impressed with. Not getting that much RAC per box. You can tell BOINC how many CPUs you want it to emulate; doesn't mean they're really there. And that can be a valid thing to do; I do it on my X5675 boxes to max out the usage on those Xeons. But at least in my experience, the most that gain you anything is actual cores (*2 for hyper-threading) - 1 per GPU. And there's a lot of debate as to whether hyper-threading really gains you anything at all. There's a few boxes where it looks as though he's way, way beyond that. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13835 Credit: 208,696,464 RAC: 304 |
And there's a lot of debate as to whether hyper-threading really gains you anything at all. It's (relatively) easy enough to figure out, it just involves a bit of rebooting when enabling and disabling it (just limiting the number of Cores used in BOINC wouldn't necessarily result in just the real cores being used). And like CUDA running 2 at a time, while it takes longer to crunch each WU, the overall throughput with Hyperthreading on is greater than with it off. That's certainly the case with my i7. On systems with smaller/slower caches it could be a very different story. Grant Darwin NT |
Wiggo Send message Joined: 24 Jan 00 Posts: 36322 Credit: 261,360,520 RAC: 489 |
The servers look to be having hiccups again. Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/mysql_connect_test oscar' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 326 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/mysql_connect_test carolyn' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 334 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/paddym_connect_test' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 342 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/marvin_connect_test' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 350 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/apache_running_on_host synergy' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 369 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/nginx_running_on_host georgem' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 386 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/nginx_running_on_host vader' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 392 Warning: shell_exec(): Unable to execute '/home/boincadm/projects/sah/bin/apache_running_on_host bruno' in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 406 Warning: exec(): Unable to fork [/usr/bin/ssh synergy /bin/ps ww 10388 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/bin/ps ww 1709 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/bin/ps ww 1889 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/bin/ps ww 2072 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh georgem /bin/ps ww 21836 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh georgem /bin/ps ww 21838 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh georgem /bin/ps ww 21840 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/bin/ps ww 2281 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh vader /bin/ps ww 30597 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh vader /bin/ps ww 30599 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 Warning: exec(): Unable to fork [/usr/bin/ssh vader /bin/ps ww 30601 ] in /disks/carolyn/b/home/boincadm/projects/sah/html/seti_boinc_html/sah_status.php on line 85 scheduling server synergy Disabled scheduler process synergy Running download server 1 georgem Disabled download server 2 vader Disabled upload server bruno Disabled Cheers. |
kittyman Send message Joined: 9 Jul 00 Posts: 51477 Credit: 1,018,363,574 RAC: 1,004 |
Dunno what's borking the SSP at the moment, but uploads, reporting, scheduler, and downloading are all still functioning. EDIT...... And as of this edit, the SSP seems to be reporting properly again as well. "Time is simply the mechanism that keeps everything from happening all at once." |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. . However, it must be good for contributors like this new guy Juan Jimenez https://setiathome.berkeley.edu/show_user.php?userid=93982. Bringing nearly 7000 CPU cores (yep that's the right number of zeroes) to the project he must feel delighted about the current guppi deluge :) Stephen :( . . OK, the user may not be new but the throng of hosts is new. This is why their RACs are still quite low, they have yet to establish their average properly. Not sure how far they will go though Stephen :) |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
. . However, it must be good for contributors like this new guy Juan Jimenez https://setiathome.berkeley.edu/show_user.php?userid=93982. Bringing nearly 7000 CPU cores (yep that's the right number of zeroes) to the project he must feel delighted about the current guppi deluge :) Stephen :( Each time I have tested HT or no HT I have always seen more work done with HT enabled. With my dual E5-2670 I am planning on doing a more detailed test of running fewer tasks than threads in steps of 2 until I get down to 16 again. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
EdwardPF Send message Joined: 26 Jul 99 Posts: 389 Credit: 236,772,605 RAC: 374 |
I have an old (Gen-1) Core I7. My tests on it indicate HT gives about a 20% boost in overall throughput. However I do not like to "starve" my GPU so I run with the CPU "opposite" it idle. (I.E. GPU WU feeder runs on cpu 0 and cpu 1 is idle). Ed F |
HAL9000 Send message Joined: 11 Sep 99 Posts: 6534 Credit: 196,805,888 RAC: 57 |
I have an old (Gen-1) Core I7. My tests on it indicate HT gives about a 20% boost in overall throughput. My old i7-860 showed an 11.1% increase in power consumption & a 27.7% increase in work output when running HT on with 8 tasks vs HT off with 4 tasks. Since it has 1600MHz DDR3 I'm not sure how much of a factor that plays vs a system with 1333MHz DDR3. SETI@home classic workunits: 93,865 CPU time: 863,447 hours Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[ |
Brent Norman Send message Joined: 1 Dec 99 Posts: 2786 Credit: 685,657,289 RAC: 835 |
Anyone have any idea why the Haveland graphs keeps randomly showing zero values for most of the entries. seeing non-reports or spaces is common, but everything going to zero is not. |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13835 Credit: 208,696,464 RAC: 304 |
Anyone have any idea why the Haveland graphs keeps randomly showing zero values for most of the entries. seeing non-reports or spaces is common, but everything going to zero is not. The current random seti server weirdness is being reflected there by those values would be my guess. Grant Darwin NT |
Grant (SSSF) Send message Joined: 19 Aug 99 Posts: 13835 Credit: 208,696,464 RAC: 304 |
I have an old (Gen-1) Core I7. My tests on it indicate HT gives about a 20% boost in overall throughput. I just use app_config.xml to reserve a CPU core for my GPU WU. Grant Darwin NT |
Wiggo Send message Joined: 24 Jan 00 Posts: 36322 Credit: 261,360,520 RAC: 489 |
Well my 1060's ran out of work as the temp here hit -3C so it's a bit on the cool side in my rooms this morning. But at least they're producing heat again now. Cheers. |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Well my 1060's ran out of work as the temp here hit -3C so it's a bit on the cool side in my rooms this morning. . . My two Linux machines ran out at 2:10am and 3:30am respectively. But they have been slaving away for E@H since then. My Seti room was at 16C when I got up this morning. But it is still nice to have new work before midnight UTC. . . But I have to say, I am no great fan of Linux ... but a big fan of Special sauce ... Stephen :) |
betreger Send message Joined: 29 Jun 99 Posts: 11408 Credit: 29,581,041 RAC: 66 |
. My two Linux machines ran out at 2:10am and 3:30am respectively. But they have been slaving away for E@H since then. My Seti room was at 16C when I got up this morning. But it is still nice to have new work before midnight UTC. You could run Einstein to keep warm, Seti owes them a lotta luv for allowing Seti to use their Atlas cluster to run Nebula. |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
. My two Linux machines ran out at 2:10am and 3:30am respectively. But they have been slaving away for E@H since then. My Seti room was at 16C when I got up this morning. But it is still nice to have new work before midnight UTC. . . Hi Betreger . . I think you may have misunderstood my message ... if you read the part that you quoted you will see than I AM running Einstein (E@H). Stephen :) |
betreger Send message Joined: 29 Jun 99 Posts: 11408 Credit: 29,581,041 RAC: 66 |
Sorry, it didn't register, the early stages of brain death have set in. |
Stephen "Heretic" Send message Joined: 20 Sep 12 Posts: 5557 Credit: 192,787,363 RAC: 628 |
Sorry, it didn't register, the early stages of brain death have set in. . . Sorry, who are you? :) Don't worry, it happens to us all ... :( But never give up ... Stephen :) |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.