找回密码
 新注册用户
搜索
楼主: maxzong

[分享] 再议 bigadv 装备 及 重要性(Native Linux下的简易教程)

  [复制链接]
发表于 2010-6-2 11:41:32 | 显示全部楼层
观望中
回复

使用道具 举报

发表于 2010-6-2 12:09:29 | 显示全部楼层
好热闹啊。

eqzero,晚上上旺旺联系吧。
回复

使用道具 举报

发表于 2010-6-2 13:00:03 | 显示全部楼层
回复 32# shouldbe


    ok
回复

使用道具 举报

发表于 2010-6-19 20:13:49 | 显示全部楼层
回复 1# maxzong


    请问兄弟都是i7+4G内存跑linux的bigadv吗?不知道内存4G购不?准备再加一台机器,要是4g能稳定跑得话就不要买内存了.......
回复

使用道具 举报

发表于 2010-6-19 23:17:00 | 显示全部楼层
回复  maxzong


    请问兄弟都是i7+4G内存跑linux的bigadv吗?不知道内存4G购不?准备再加一台机器,要 ...
eqzero 发表于 2010-6-19 20:13


以前在沧者极限看到有几个成功在4G下顺畅跑BIGADV的分享(貌似纯CPU系统),估计4G有戏

期待这个问题兄弟你、 maxzong 以及其他高手能搞出一个解决方案
回复

使用道具 举报

 楼主| 发表于 2010-6-19 23:51:33 | 显示全部楼层
回复 34# eqzero

我前2周跑 860 + 4G 内存的情况是 Native Ubuntu Linux, 上虚拟机4G是不够的。

但4G的话,2684 跑A3 核心一直出错,但其实A3核心跑2684时用的内存只有2G左右,比2681-2683 都少,所以一直不是很明白到底是不是4G内存不够还是其他什么问题。为简单起见,这周给2台 860 都加到6G内存了,但加好之后就没碰到过 2684,所以也不敢确认。

但至少 930 + 6G 内存 跑VM Linux +GPU2 , 2684是没有问题的。

860 + 4G  跑 2681-2683 也是确认没问题的。

评分

参与人数 1基本分 +15 收起 理由
金鹏 + 15 原创内容

查看全部评分

回复

使用道具 举报

发表于 2010-6-20 01:12:19 | 显示全部楼层
天天也在以4GB RAM跑Native Linux啊!

但說實在的在過去的一兩星期內成功提交過十次以上的BigAdv當中,
幸運地,兩組i7(920@4.1G與930@4G)只遇過一次2684這個大魔頭
,大約5日前...可能是Console Screen首次出現Temperture Over therehold
字樣那天,i7-930那組確實遇過一次Unstable Machine的「2684」惡夢啊~!
又幸運地,惡夢很快就甦醒過來,因為那一次2684連1%也做不成就自動報銷,
棄暗投明回到2681的懷抱了。之後也沒有考究原由,以下是當時一段Log的節錄
有興趣的讀者請自行參詳一下.....


[05:07:30] Folding@home Core Shutdown: FINISHED_UNIT
[05:09:51] CoreStatus = 64 (100)
[05:09:51] Sending work to server
[05:09:51] Project: 2681 (Run 8, Clone 0, Gen 90)


[05:09:51] + Attempting to send results [June 15 05:09:51 UTC]
[05:16:43] + Results successfully sent
[05:16:43] Thank you for your contribution to Folding@Home.
[05:16:43] + Number of Units Completed: 4

[05:16:55] - Preparing to get new work unit...
[05:16:55] Cleaning up work directory
[05:16:55] + Attempting to get work packet
[05:16:55] Passkey found
[05:16:55] - Connecting to assignment server
[05:16:56] - Successful: assigned to (171.67.108.22).
[05:16:56] + News From Folding@Home: Welcome to Folding@Home
[05:16:56] Loaded queue successfully.
[05:18:05] + Closed connections
[05:18:05]
[05:18:05] + Processing work unit
[05:18:05] Core required: FahCore_a3.exe
[05:18:05] Core found.
[05:18:05] Working on queue slot 04 [June 15 05:18:05 UTC]
[05:18:05] + Working ...
[05:18:05]
[05:18:05] *------------------------------*
[05:18:05] Folding@Home Gromacs SMP Core
[05:18:05] Version 2.21 (May 10, 2010)
[05:18:06]
[05:18:06] Preparing to commence simulation
[05:18:06] - Looking at optimizations...
[05:18:06] - Created dyn
[05:18:06] - Files status OK
[05:18:07] - Expanded 24824116 -> 30791309 (decompressed 124.0 percent)
[05:18:07] Called DecompressByteArray: compressed_data_size=24824116 data_size=30791309, decompressed_data_size=30791309 diff=0
[05:18:07] - Digital signature verified
[05:18:07]
[05:18:07] Project: 2684 (Run 8, Clone 1, Gen 5) *****[惡魔現身了!]*****
[05:18:07]
[05:18:07] Assembly optimizations on if available.
[05:18:07] Entering M.D.
[05:18:19] Completed 0 out of 250000 steps (0%)
[05:18:21] mdrun returned 255 *****[惡有惡報啊!]*****
[05:18:21] Going to send back what have done -- stepsTotalG=250000
[05:18:21] Work fraction=1249927.2500 steps=250000.
[05:18:25] logfile size=12544 infoLength=12544 edr=25 trr=1
[05:18:25] logfile size: 12544 info=12544 bed=25 hdr=1
[05:18:25] - Writing 13082 bytes of core data to disk...
[05:18:26] ... Done.
[05:18:40]
[05:18:40] Folding@home Core Shutdown: UNSTABLE_MACHINE *****[Oh........]*****
[05:18:41] CoreStatus = 7A (122)
[05:18:41] Sending work to server
[05:18:41] Project: 2684 (Run 8, Clone 1, Gen 5)


[05:18:41] + Attempting to send results [June 15 05:18:41 UTC]
[05:18:42] + Results successfully sent
[05:18:42] Thank you for your contribution to Folding@Home.
[05:18:42] - Preparing to get new work unit...
[05:18:42] Cleaning up work directory
[05:18:42] + Attempting to get work packet
[05:18:42] Passkey found
[05:18:42] - Connecting to assignment server
[05:18:43] - Successful: assigned to (171.67.108.22).
[05:18:43] + News From Folding@Home: Welcome to Folding@Home
[05:18:43] Loaded queue successfully.
[05:20:50] + Closed connections
[05:20:55]
[05:20:55] + Processing work unit
[05:20:55] Core required: FahCore_a2.exe
[05:20:55] Core found.
[05:20:55] Working on queue slot 05 [June 15 05:20:55 UTC]
[05:20:55] + Working ...

[05:20:55] Preparing to commence simulation
[05:20:55] - Ensuring status. Please wait.
[05:20:55] Working with standard loops on this execution.
[05:20:55] - Files status OK
[05:20:58] - Expanded 30Called DecompressByteArray: compressed_data_size=Called DecompressByteArray: compressed_data_size=30331739 data_size=159726549, decompressed_data_size=159726549 diff=0
[05:20:59] 2, Clone 15, Gen 101)
[05:20:59]
[05:20:59] ified
[05:20:59]
[05:20:59] Project: 2681 (Run 2, Clone 15, Gen 101)
[05:20:59]
[05:20:59] Entering M.D.
[05:21:09] one 15, Gen 101)
[05:21:09]
[05:21:09] Entering M.D. *****[重投Normal BigAdv工作了]*****
[05:21:28] (0%)
[05:52:00] Completed 2500 out of 250000 steps (1%)

评分

参与人数 1基本分 +15 收起 理由
金鹏 + 15 原创内容

查看全部评分

回复

使用道具 举报

发表于 2010-6-20 02:29:33 | 显示全部楼层
回复 36# maxzong


    看来要试下了。
回复

使用道具 举报

发表于 2010-6-20 02:30:31 | 显示全部楼层
回复 37# OverFold


    非常感谢!可能要过段时间试下了,前阵子出错太多了,不敢试验了,怕<80%......
回复

使用道具 举报

发表于 2010-6-20 03:02:29 | 显示全部楼层
何止80後.....90後來個Core Status=7A也試過,返魂無術呵!
心痛+肉痛(電費~)
回复

使用道具 举报

发表于 2010-6-20 14:08:24 | 显示全部楼层
本帖最后由 金鹏 于 2010-6-20 14:45 编辑

回复 36# maxzong
回复 39# eqzero
回复 37# OverFold

昨天RP爆发,接到2684毒包,速度下降不少内存占用感觉4G足够吃了

捕获.PNG 捕获.PNG


[07:18:54] + Processing work unit
[07:18:54] Core required: FahCore_a3.exe
[07:18:54] Core found.
[07:18:54] Working on queue slot 07 [June 19 07:18:54 UTC]
[07:18:54] + Working ...
[07:18:54]
[07:18:54] *------------------------------*
[07:18:54] Folding@Home Gromacs SMP Core
[07:18:54] Version 2.22 (June 10, 2010)
[07:18:54]
[07:18:54] Preparing to commence simulation
[07:18:54] - Looking at optimizations...
[07:18:54] - Created dyn
[07:18:54] - Files status OK
[07:18:56] - Expanded 24884920 -> 30791309 (decompressed 123.7 percent)
[07:18:56] Called DecompressByteArray: compressed_data_size=24884920 data_size=30791309, decompressed_data_size=30791309 diff=0
[07:18:56] - Digital signature verified
[07:18:56]
[07:18:56] Project: 2684 (Run 5, Clone 18, Gen 4)
[07:18:56]
[07:18:56] Assembly optimizations on if available.
[07:18:56] Entering M.D.
[07:19:17] Completed 0 out of 250000 steps  (0%)
[07:19:20] CoreStatus = 0 (0)
[07:19:20] Sending work to server
[07:19:20] Project: 2684 (Run 5, Clone 18, Gen 4)
[07:19:20] - Error: Could not get length of results file work/wuresults_07.dat
[07:19:20] - Error: Could not read unit 07 file. Removing from queue.
[07:19:20] - Preparing to get new work unit...
[07:19:20] Cleaning up work directory
[07:19:22] + Attempting to get work packet
[07:19:22] Passkey found
[07:19:22] - Connecting to assignment server
[07:19:22] - Successful: assigned to (171.67.108.22).
[07:19:22] + News From Folding@Home: Welcome to Folding@Home
[07:19:23] Loaded queue successfully.
[07:19:54] + Closed connections
[07:19:59]
[07:19:59] + Processing work unit
[07:19:59] Core required: FahCore_a3.exe
[07:19:59] Core found.
[07:19:59] Working on queue slot 08 [June 19 07:19:59 UTC]
[07:19:59] + Working ...
[07:19:59]
[07:19:59] *------------------------------*
[07:19:59] Folding@Home Gromacs SMP Core
[07:19:59] Version 2.22 (June 10, 2010)
[07:19:59]
[07:19:59] Preparing to commence simulation
[07:19:59] - Ensuring status. Please wait.
[07:20:08] - Looking at optimizations...
[07:20:08] - Working with standard loops on this execution.
[07:20:08] - Created dyn
[07:20:08] - Files status OK
[07:20:10] - Expanded 24884920 -> 30791309 (decompressed 123.7 percent)
[07:20:10] Called DecompressByteArray: compressed_data_size=24884920 data_size=30791309, decompressed_data_size=30791309 diff=0
[07:20:10] - Digital signature verified
[07:20:10]
[07:20:10] Project: 2684 (Run 5, Clone 18, Gen 4)
[07:20:10]
[07:20:10] Entering M.D.
[07:20:23] Completed 0 out of 250000 steps  (0%)
[08:11:38] Completed 2500 out of 250000 steps  (1%)
[09:02:43] Completed 5000 out of 250000 steps  (2%)
[09:58:09] Completed 7500 out of 250000 steps  (3%)
[10:56:33] Completed 10000 out of 250000 steps  (4%)
[11:47:48] Completed 12500 out of 250000 steps  (5%)
[12:36:55] Completed 15000 out of 250000 steps  (6%)
[13:26:13] Completed 17500 out of 250000 steps  (7%)
[14:15:37] Completed 20000 out of 250000 steps  (8%)
[15:03:43] Completed 22500 out of 250000 steps  (9%)
[15:52:21] Completed 25000 out of 250000 steps  (10%)
[16:41:11] Completed 27500 out of 250000 steps  (11%)
[17:29:49] Completed 30000 out of 250000 steps  (12%)
[18:18:18] Completed 32500 out of 250000 steps  (13%)
[19:06:51] Completed 35000 out of 250000 steps  (14%)
[19:55:20] Completed 37500 out of 250000 steps  (15%)
[20:44:05] Completed 40000 out of 250000 steps  (16%)
[21:32:25] Completed 42500 out of 250000 steps  (17%)
[22:20:36] Completed 45000 out of 250000 steps  (18%)
[23:09:02] Completed 47500 out of 250000 steps  (19%)
[23:58:49] Completed 50000 out of 250000 steps  (20%)
回复

使用道具 举报

发表于 2010-6-20 14:34:06 | 显示全部楼层

日了2684,关闭一下后重开就爆了,已经21%进度了
###############################################################################
###############################################################################

Launch directory: /usr/local/fah
Executable: ./fah6
Arguments: -bigadv -smp 7

[06:23:20] - Ask before connecting: No
[06:23:20] - User name: husq (Team 3213)
[06:23:20] - User ID: 14ED88B87AC69495
[06:23:20] - Machine ID: 2
[06:23:20]
[06:23:20] Loaded queue successfully.
[06:23:20]
[06:23:20] + Processing work unit
[06:23:20] Core required: FahCore_a3.exe
[06:23:20] Core found.
[06:23:20] Working on queue slot 08 [June 20 06:23:20 UTC]
[06:23:20] + Working ...
[06:23:20]
[06:23:20] *------------------------------*
[06:23:20] Folding@Home Gromacs SMP Core
[06:23:20] Version 2.22 (June 10, 2010)
[06:23:20]
[06:23:20] Preparing to commence simulation
[06:23:20] - Ensuring status. Please wait.
[06:23:30] - Looking at optimizations...
[06:23:30] - Working with standard loops on this execution.
[06:23:30] - Previous termination of core was improper.
[06:23:30] - Files status OK
[06:23:32] - Expanded 24884920 -> 30791309 (decompressed 123.7 percent)
[06:23:32] Called DecompressByteArray: compressed_data_size=24884920 data_size=30791309, decompressed_data_size=30791309 diff=0
[06:23:32] - Digital signature verified
[06:23:32]
[06:23:32] Project: 2684 (Run 5, Clone 18, Gen 4)
[06:23:32]
[06:23:32] Entering M.D.
[06:23:39] Using Gromacs checkpoints
[06:23:47] Resuming from checkpoint
[06:23:50] Verified work/wudata_08.log
[06:23:50] Verified work/wudata_08.trr
[06:23:50] Verified work/wudata_08.xtc
[06:23:50] Verified work/wudata_08.edr
[06:23:53] Completed 54855 out of 250000 steps  (21%)
[06:23:54] mdrun returned 255
[06:23:54] Going to send back what have done -- stepsTotalG=250000
[06:23:54] Work fraction=18.2299 steps=250000.
[06:23:58] logfile size=53593 infoLength=53593 edr=25 trr=1
[06:23:58] logfile size: 53593 info=53593 bed=25 hdr=1
[06:23:58] - Writing 54131 bytes of core data to disk...
[06:23:59]   ... Done.
[06:24:14]
[06:24:14] Folding@home Core Shutdown: UNSTABLE_MACHINE
[06:24:15] CoreStatus = 7A (122)
[06:24:15] Sending work to server

[06:24:15] Project: 2684 (Run 5, Clone 18, Gen 4)


[06:24:15] + Attempting to send results [June 20 06:24:15 UTC]
[06:24:17] + Results successfully sent
[06:24:17] Thank you for your contribution to Folding@Home.
[06:24:17] - Preparing to get new work unit...
[06:24:17] Cleaning up work directory
[06:24:19] + Attempting to get work packet
[06:24:19] Passkey found
[06:24:19] - Connecting to assignment server
[06:24:20] - Successful: assigned to (171.67.108.22).
[06:24:20] + News From Folding@Home: Welcome to Folding@Home
[06:24:20] Loaded queue successfully.
[06:24:54] + Closed connections
[06:24:59]
[06:24:59] + Processing work unit
[06:24:59] Core required: FahCore_a3.exe
[06:24:59] Core found.
[06:24:59] Working on queue slot 09 [June 20 06:24:59 UTC]
[06:24:59] + Working ...
[06:24:59]
[06:24:59] *------------------------------*
[06:24:59] Folding@Home Gromacs SMP Core
[06:24:59] Version 2.22 (June 10, 2010)
[06:24:59]
[06:24:59] Preparing to commence simulation
[06:24:59] - Looking at optimizations...
[06:24:59] - Created dyn
[06:24:59] - Files status OK
[06:25:01] - Expanded 24884920 -> 30791309 (decompressed 123.7 percent)
[06:25:01] Called DecompressByteArray: compressed_data_size=24884920 data_size=30791309, decompressed_data_size=30791309 diff=0
[06:25:01] - Digital signature verified
[06:25:01]
[06:25:01] Project: 2684 (Run 5, Clone 18, Gen 4)
[06:25:01]
[06:25:01] Assembly optimizations on if available.
[06:25:01] Entering M.D.
[06:25:14] Completed 0 out of 250000 steps  (0%)
回复

使用道具 举报

发表于 2010-6-21 19:41:33 | 显示全部楼层
还是2684毒包,跑到33%了,这次绝不重启,但愿不要再爆包了


捕获.PNG
回复

使用道具 举报

发表于 2010-6-21 20:38:13 | 显示全部楼层
金版,你说的内存感觉4G足够,是用vm跑linux -bigadv,还是在win下跑 -bigadv呢?
回复

使用道具 举报

发表于 2010-6-21 21:54:33 | 显示全部楼层
回复 44# guihuo

回兄弟,是在WIN7下的VMware Player下的LINUX跑BIGADV
   从上面截图能看出来
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 新注册用户

本版积分规则

论坛官方淘宝店开业啦~
欢迎大家多多支持基金会~

Archiver|手机版|小黑屋|中国分布式计算总站 ( 沪ICP备05042587号 )

GMT+8, 2024-3-29 05:00

Powered by Discuz! X3.5

© 2001-2024 Discuz! Team.

快速回复 返回顶部 返回列表