1 |
swift 08/05/19 20:56:20 |
2 |
|
3 |
Modified: hpc-howto.xml |
4 |
Log: |
5 |
Coding style (sorry, length on uris not fixable) |
6 |
|
7 |
Revision Changes Path |
8 |
1.14 xml/htdocs/doc/en/hpc-howto.xml |
9 |
|
10 |
file : http://sources.gentoo.org/viewcvs.py/gentoo/xml/htdocs/doc/en/hpc-howto.xml?rev=1.14&view=markup |
11 |
plain: http://sources.gentoo.org/viewcvs.py/gentoo/xml/htdocs/doc/en/hpc-howto.xml?rev=1.14&content-type=text/plain |
12 |
diff : http://sources.gentoo.org/viewcvs.py/gentoo/xml/htdocs/doc/en/hpc-howto.xml?r1=1.13&r2=1.14 |
13 |
|
14 |
Index: hpc-howto.xml |
15 |
=================================================================== |
16 |
RCS file: /var/cvsroot/gentoo/xml/htdocs/doc/en/hpc-howto.xml,v |
17 |
retrieving revision 1.13 |
18 |
retrieving revision 1.14 |
19 |
diff -u -r1.13 -r1.14 |
20 |
--- hpc-howto.xml 18 Dec 2006 21:47:19 -0000 1.13 |
21 |
+++ hpc-howto.xml 19 May 2008 20:56:20 -0000 1.14 |
22 |
@@ -1,5 +1,5 @@ |
23 |
<?xml version='1.0' encoding="UTF-8"?> |
24 |
-<!-- $Header: /var/cvsroot/gentoo/xml/htdocs/doc/en/hpc-howto.xml,v 1.13 2006/12/18 21:47:19 nightmorph Exp $ --> |
25 |
+<!-- $Header: /var/cvsroot/gentoo/xml/htdocs/doc/en/hpc-howto.xml,v 1.14 2008/05/19 20:56:20 swift Exp $ --> |
26 |
<!DOCTYPE guide SYSTEM "/dtd/guide.dtd"> |
27 |
|
28 |
<guide link="/doc/en/hpc-howto.xml"> |
29 |
@@ -28,7 +28,7 @@ |
30 |
permission to distribute this document as-is and update it when appropriate |
31 |
as long as the adelie linux R&D notice stays |
32 |
--> |
33 |
- |
34 |
+ |
35 |
<abstract> |
36 |
This document was written by people at the Adelie Linux R&D Center |
37 |
<http://www.adelielinux.com> as a step-by-step guide to turn a Gentoo |
38 |
@@ -44,22 +44,22 @@ |
39 |
<body> |
40 |
|
41 |
<p> |
42 |
-Gentoo Linux, a special flavor of Linux that can be automatically optimized |
43 |
-and customized for just about any application or need. Extreme performance, |
44 |
+Gentoo Linux, a special flavor of Linux that can be automatically optimized |
45 |
+and customized for just about any application or need. Extreme performance, |
46 |
configurability and a top-notch user and developer community are all hallmarks |
47 |
of the Gentoo experience. |
48 |
</p> |
49 |
|
50 |
<p> |
51 |
-Thanks to a technology called Portage, Gentoo Linux can become an ideal secure |
52 |
+Thanks to a technology called Portage, Gentoo Linux can become an ideal secure |
53 |
server, development workstation, professional desktop, gaming system, embedded |
54 |
-solution or... a High Performance Computing system. Because of its |
55 |
+solution or... a High Performance Computing system. Because of its |
56 |
near-unlimited adaptability, we call Gentoo Linux a metadistribution. |
57 |
</p> |
58 |
|
59 |
<p> |
60 |
-This document explains how to turn a Gentoo system into a High Performance |
61 |
-Computing system. Step by step, it explains what packages one may want to |
62 |
+This document explains how to turn a Gentoo system into a High Performance |
63 |
+Computing system. Step by step, it explains what packages one may want to |
64 |
install and helps configure them. |
65 |
</p> |
66 |
|
67 |
@@ -86,10 +86,10 @@ |
68 |
|
69 |
<p> |
70 |
During the installation process, you will have to set your USE variables in |
71 |
-<path>/etc/make.conf</path>. We recommended that you deactivate all the |
72 |
+<path>/etc/make.conf</path>. We recommended that you deactivate all the |
73 |
defaults (see <path>/etc/make.profile/make.defaults</path>) by negating them in |
74 |
-make.conf. However, you may want to keep such use variables as x86, 3dnow, gpm, |
75 |
-mmx, nptl, nptlonly, sse, ncurses, pam and tcpd. Refer to the USE documentation |
76 |
+make.conf. However, you may want to keep such use variables as x86, 3dnow, gpm, |
77 |
+mmx, nptl, nptlonly, sse, ncurses, pam and tcpd. Refer to the USE documentation |
78 |
for more information. |
79 |
</p> |
80 |
|
81 |
@@ -114,8 +114,8 @@ |
82 |
</note> |
83 |
|
84 |
<p> |
85 |
-In step 15 ("Installing the kernel and a System Logger") for stability |
86 |
-reasons, we recommend the vanilla-sources, the official kernel sources |
87 |
+In step 15 ("Installing the kernel and a System Logger") for stability |
88 |
+reasons, we recommend the vanilla-sources, the official kernel sources |
89 |
released on <uri>http://www.kernel.org/</uri>, unless you require special |
90 |
support such as xfs. |
91 |
</p> |
92 |
@@ -125,7 +125,7 @@ |
93 |
</pre> |
94 |
|
95 |
<p> |
96 |
-When you install miscellaneous packages, we recommend installing the |
97 |
+When you install miscellaneous packages, we recommend installing the |
98 |
following: |
99 |
</p> |
100 |
|
101 |
@@ -140,35 +140,35 @@ |
102 |
<body> |
103 |
|
104 |
<p> |
105 |
-A cluster requires a communication layer to interconnect the slave nodes to |
106 |
-the master node. Typically, a FastEthernet or GigaEthernet LAN can be used |
107 |
-since they have a good price/performance ratio. Other possibilities include |
108 |
-use of products like <uri link="http://www.myricom.com/">Myrinet</uri>, <uri |
109 |
+A cluster requires a communication layer to interconnect the slave nodes to |
110 |
+the master node. Typically, a FastEthernet or GigaEthernet LAN can be used |
111 |
+since they have a good price/performance ratio. Other possibilities include |
112 |
+use of products like <uri link="http://www.myricom.com/">Myrinet</uri>, <uri |
113 |
link="http://quadrics.com/">QsNet</uri> or others. |
114 |
</p> |
115 |
|
116 |
<p> |
117 |
-A cluster is composed of two node types: master and slave. Typically, your |
118 |
+A cluster is composed of two node types: master and slave. Typically, your |
119 |
cluster will have one master node and several slave nodes. |
120 |
</p> |
121 |
|
122 |
<p> |
123 |
-The master node is the cluster's server. It is responsible for telling the |
124 |
-slave nodes what to do. This server will typically run such daemons as dhcpd, |
125 |
-nfs, pbs-server, and pbs-sched. Your master node will allow interactive |
126 |
+The master node is the cluster's server. It is responsible for telling the |
127 |
+slave nodes what to do. This server will typically run such daemons as dhcpd, |
128 |
+nfs, pbs-server, and pbs-sched. Your master node will allow interactive |
129 |
sessions for users, and accept job executions. |
130 |
</p> |
131 |
|
132 |
<p> |
133 |
-The slave nodes listen for instructions (via ssh/rsh perhaps) from the master |
134 |
-node. They should be dedicated to crunching results and therefore should not |
135 |
+The slave nodes listen for instructions (via ssh/rsh perhaps) from the master |
136 |
+node. They should be dedicated to crunching results and therefore should not |
137 |
run any unnecessary services. |
138 |
</p> |
139 |
|
140 |
<p> |
141 |
-The rest of this documentation will assume a cluster configuration as per the |
142 |
-hosts file below. You should maintain on every node such a hosts file |
143 |
-(<path>/etc/hosts</path>) with entries for each node participating node in the |
144 |
+The rest of this documentation will assume a cluster configuration as per the |
145 |
+hosts file below. You should maintain on every node such a hosts file |
146 |
+(<path>/etc/hosts</path>) with entries for each node participating node in the |
147 |
cluster. |
148 |
</p> |
149 |
|
150 |
@@ -185,7 +185,7 @@ |
151 |
</pre> |
152 |
|
153 |
<p> |
154 |
-To setup your cluster dedicated LAN, edit your <path>/etc/conf.d/net</path> |
155 |
+To setup your cluster dedicated LAN, edit your <path>/etc/conf.d/net</path> |
156 |
file on the master node. |
157 |
</p> |
158 |
|
159 |
@@ -202,7 +202,7 @@ |
160 |
|
161 |
|
162 |
<p> |
163 |
-Finally, setup a DHCP daemon on the master node to avoid having to maintain a |
164 |
+Finally, setup a DHCP daemon on the master node to avoid having to maintain a |
165 |
network configuration on each slave node. |
166 |
</p> |
167 |
|
168 |
@@ -239,22 +239,22 @@ |
169 |
<body> |
170 |
|
171 |
<p> |
172 |
-The Network File System (NFS) was developed to allow machines to mount a disk |
173 |
+The Network File System (NFS) was developed to allow machines to mount a disk |
174 |
partition on a remote machine as if it were on a local hard drive. This allows |
175 |
for fast, seamless sharing of files across a network. |
176 |
</p> |
177 |
|
178 |
<p> |
179 |
There are other systems that provide similar functionality to NFS which could |
180 |
-be used in a cluster environment. The <uri |
181 |
-link="http://www.openafs.org">Andrew File System |
182 |
-from IBM</uri>, recently open-sourced, provides a file sharing mechanism with |
183 |
-some additional security and performance features. The <uri |
184 |
-link="http://www.coda.cs.cmu.edu/">Coda File System</uri> is still in |
185 |
-development, but is designed to work well with disconnected clients. Many |
186 |
+be used in a cluster environment. The <uri |
187 |
+link="http://www.openafs.org">Andrew File System |
188 |
+from IBM</uri>, recently open-sourced, provides a file sharing mechanism with |
189 |
+some additional security and performance features. The <uri |
190 |
+link="http://www.coda.cs.cmu.edu/">Coda File System</uri> is still in |
191 |
+development, but is designed to work well with disconnected clients. Many |
192 |
of the features of the Andrew and Coda file systems are slated for inclusion |
193 |
in the next version of <uri link="http://www.nfsv4.org">NFS (Version 4)</uri>. |
194 |
-The advantage of NFS today is that it is mature, standard, well understood, |
195 |
+The advantage of NFS today is that it is mature, standard, well understood, |
196 |
and supported robustly across a variety of platforms. |
197 |
</p> |
198 |
|
199 |
@@ -277,8 +277,8 @@ |
200 |
</pre> |
201 |
|
202 |
<p> |
203 |
-On the master node, edit your <path>/etc/hosts.allow</path> file to allow |
204 |
-connections from slave nodes. If your cluster LAN is on 192.168.1.0/24, |
205 |
+On the master node, edit your <path>/etc/hosts.allow</path> file to allow |
206 |
+connections from slave nodes. If your cluster LAN is on 192.168.1.0/24, |
207 |
your <path>hosts.allow</path> will look like: |
208 |
</p> |
209 |
|
210 |
@@ -287,7 +287,7 @@ |
211 |
</pre> |
212 |
|
213 |
<p> |
214 |
-Edit the <path>/etc/exports</path> file of the master node to export a work |
215 |
+Edit the <path>/etc/exports</path> file of the master node to export a work |
216 |
directory structure (/home is good for this). |
217 |
</p> |
218 |
|
219 |
@@ -304,8 +304,8 @@ |
220 |
</pre> |
221 |
|
222 |
<p> |
223 |
-To mount the nfs exported filesystem from the master, you also have to |
224 |
-configure your salve nodes' <path>/etc/fstab</path>. Add a line like this |
225 |
+To mount the nfs exported filesystem from the master, you also have to |
226 |
+configure your salve nodes' <path>/etc/fstab</path>. Add a line like this |
227 |
one: |
228 |
</p> |
229 |
|
230 |
@@ -314,7 +314,7 @@ |
231 |
</pre> |
232 |
|
233 |
<p> |
234 |
-You'll also need to set up your nodes so that they mount the nfs filesystem by |
235 |
+You'll also need to set up your nodes so that they mount the nfs filesystem by |
236 |
issuing this command: |
237 |
</p> |
238 |
|
239 |
@@ -329,15 +329,15 @@ |
240 |
<body> |
241 |
|
242 |
<p> |
243 |
-SSH is a protocol for secure remote login and other secure network services |
244 |
-over an insecure network. OpenSSH uses public key cryptography to provide |
245 |
-secure authorization. Generating the public key, which is shared with remote |
246 |
-systems, and the private key which is kept on the local system, is done first |
247 |
+SSH is a protocol for secure remote login and other secure network services |
248 |
+over an insecure network. OpenSSH uses public key cryptography to provide |
249 |
+secure authorization. Generating the public key, which is shared with remote |
250 |
+systems, and the private key which is kept on the local system, is done first |
251 |
to configure OpenSSH on the cluster. |
252 |
</p> |
253 |
|
254 |
<p> |
255 |
-For transparent cluster usage, private/public keys may be used. This process |
256 |
+For transparent cluster usage, private/public keys may be used. This process |
257 |
has two steps: |
258 |
</p> |
259 |
|
260 |
@@ -374,12 +374,12 @@ |
261 |
</pre> |
262 |
|
263 |
<note> |
264 |
-Host keys must have an empty passphrase. RSA is required for host-based |
265 |
+Host keys must have an empty passphrase. RSA is required for host-based |
266 |
authentication. |
267 |
</note> |
268 |
|
269 |
<p> |
270 |
-For host based authentication, you will also need to edit your |
271 |
+For host based authentication, you will also need to edit your |
272 |
<path>/etc/ssh/shosts.equiv</path>. |
273 |
</p> |
274 |
|
275 |
@@ -397,7 +397,7 @@ |
276 |
# $OpenBSD: sshd_config,v 1.42 2001/09/20 20:57:51 mouring Exp $ |
277 |
# This sshd was compiled with PATH=/usr/bin:/bin:/usr/sbin:/sbin |
278 |
|
279 |
-# This is the sshd server system-wide configuration file. See sshd(8) |
280 |
+# This is the sshd server system-wide configuration file. See sshd(8) |
281 |
# for more information. |
282 |
|
283 |
# HostKeys for protocol version 2 |
284 |
@@ -405,7 +405,7 @@ |
285 |
</pre> |
286 |
|
287 |
<p> |
288 |
-If your application require RSH communications, you will need to emerge |
289 |
+If your application require RSH communications, you will need to emerge |
290 |
net-misc/netkit-rsh and sys-apps/xinetd. |
291 |
</p> |
292 |
|
293 |
@@ -417,7 +417,7 @@ |
294 |
</pre> |
295 |
|
296 |
<p> |
297 |
-Then configure the rsh deamon. Edit your <path>/etc/xinet.d/rsh</path> file. |
298 |
+Then configure the rsh deamon. Edit your <path>/etc/xinet.d/rsh</path> file. |
299 |
</p> |
300 |
|
301 |
<pre caption="rsh"> |
302 |
@@ -456,7 +456,7 @@ |
303 |
|
304 |
<pre caption="hosts.allow"> |
305 |
# Adelie Linux Research & Development Center |
306 |
-# /etc/hosts.allow |
307 |
+# /etc/hosts.allow |
308 |
|
309 |
ALL:192.168.1.0/255.255.255.0 |
310 |
</pre> |
311 |
@@ -489,20 +489,20 @@ |
312 |
<body> |
313 |
|
314 |
<p> |
315 |
-The Network Time Protocol (NTP) is used to synchronize the time of a computer |
316 |
-client or server to another server or reference time source, such as a radio |
317 |
-or satellite receiver or modem. It provides accuracies typically within a |
318 |
-millisecond on LANs and up to a few tens of milliseconds on WANs relative to |
319 |
-Coordinated Universal Time (UTC) via a Global Positioning Service (GPS) |
320 |
+The Network Time Protocol (NTP) is used to synchronize the time of a computer |
321 |
+client or server to another server or reference time source, such as a radio |
322 |
+or satellite receiver or modem. It provides accuracies typically within a |
323 |
+millisecond on LANs and up to a few tens of milliseconds on WANs relative to |
324 |
+Coordinated Universal Time (UTC) via a Global Positioning Service (GPS) |
325 |
receiver, for example. Typical NTP configurations utilize multiple redundant |
326 |
-servers and diverse network paths in order to achieve high accuracy and |
327 |
+servers and diverse network paths in order to achieve high accuracy and |
328 |
reliability. |
329 |
</p> |
330 |
|
331 |
<p> |
332 |
-Select a NTP server geographically close to you from <uri |
333 |
-link="http://www.eecis.udel.edu/~mills/ntp/servers.html">Public NTP Time |
334 |
-Servers</uri>, and configure your <path>/etc/conf.d/ntp</path> and |
335 |
+Select a NTP server geographically close to you from <uri |
336 |
+link="http://www.eecis.udel.edu/~mills/ntp/servers.html">Public NTP Time |
337 |
+Servers</uri>, and configure your <path>/etc/conf.d/ntp</path> and |
338 |
<path>/etc/ntp.conf</path> files on the master node. |
339 |
</p> |
340 |
|
341 |
@@ -549,7 +549,7 @@ |
342 |
</pre> |
343 |
|
344 |
<p> |
345 |
-Edit your <path>/etc/ntp.conf</path> file on the master to setup an external |
346 |
+Edit your <path>/etc/ntp.conf</path> file on the master to setup an external |
347 |
synchronization source: |
348 |
</p> |
349 |
|
350 |
@@ -565,7 +565,7 @@ |
351 |
restrict ntp2.cmc.ec.gc.ca |
352 |
stratum 10 |
353 |
driftfile /etc/ntp.drift.server |
354 |
-logfile /var/log/ntp |
355 |
+logfile /var/log/ntp |
356 |
broadcast 192.168.1.255 |
357 |
restrict default kod |
358 |
restrict 127.0.0.1 |
359 |
@@ -573,7 +573,7 @@ |
360 |
</pre> |
361 |
|
362 |
<p> |
363 |
-And on all your slave nodes, setup your synchronization source as your master |
364 |
+And on all your slave nodes, setup your synchronization source as your master |
365 |
node. |
366 |
</p> |
367 |
|
368 |
@@ -594,7 +594,7 @@ |
369 |
restrict master |
370 |
stratum 11 |
371 |
driftfile /etc/ntp.drift.server |
372 |
-logfile /var/log/ntp |
373 |
+logfile /var/log/ntp |
374 |
restrict default kod |
375 |
restrict 127.0.0.1 |
376 |
</pre> |
377 |
@@ -608,7 +608,7 @@ |
378 |
</pre> |
379 |
|
380 |
<note> |
381 |
-NTP will not update the local clock if the time difference between your |
382 |
+NTP will not update the local clock if the time difference between your |
383 |
synchronization source and the local clock is too great. |
384 |
</note> |
385 |
|
386 |
@@ -691,10 +691,10 @@ |
387 |
<body> |
388 |
|
389 |
<p> |
390 |
-The Portable Batch System (PBS) is a flexible batch queueing and workload |
391 |
+The Portable Batch System (PBS) is a flexible batch queueing and workload |
392 |
management system originally developed for NASA. It operates on networked, |
393 |
-multi-platform UNIX environments, including heterogeneous clusters of |
394 |
-workstations, supercomputers, and massively parallel systems. Development of |
395 |
+multi-platform UNIX environments, including heterogeneous clusters of |
396 |
+workstations, supercomputers, and massively parallel systems. Development of |
397 |
PBS is provided by Altair Grid Technologies. |
398 |
</p> |
399 |
|
400 |
@@ -703,12 +703,12 @@ |
401 |
</pre> |
402 |
|
403 |
<note> |
404 |
-OpenPBS ebuild does not currently set proper permissions on var-directories |
405 |
+OpenPBS ebuild does not currently set proper permissions on var-directories |
406 |
used by OpenPBS. |
407 |
</note> |
408 |
|
409 |
<p> |
410 |
-Before starting using OpenPBS, some configurations are required. The files |
411 |
+Before starting using OpenPBS, some configurations are required. The files |
412 |
you will need to personalize for your system are: |
413 |
</p> |
414 |
|
415 |
@@ -762,10 +762,10 @@ |
416 |
</pre> |
417 |
|
418 |
<p> |
419 |
-To submit a task to OpenPBS, the command <c>qsub</c> is used with some |
420 |
-optional parameters. In the example below, "-l" allows you to specify |
421 |
+To submit a task to OpenPBS, the command <c>qsub</c> is used with some |
422 |
+optional parameters. In the example below, "-l" allows you to specify |
423 |
the resources required, "-j" provides for redirection of standard out and |
424 |
-standard error, and the "-m" will e-mail the user at beginning (b), end (e) |
425 |
+standard error, and the "-m" will e-mail the user at beginning (b), end (e) |
426 |
and on abort (a) of the job. |
427 |
</p> |
428 |
|
429 |
@@ -775,8 +775,8 @@ |
430 |
</pre> |
431 |
|
432 |
<p> |
433 |
-Normally jobs submitted to OpenPBS are in the form of scripts. Sometimes, you |
434 |
-may want to try a task manually. To request an interactive shell from OpenPBS, |
435 |
+Normally jobs submitted to OpenPBS are in the form of scripts. Sometimes, you |
436 |
+may want to try a task manually. To request an interactive shell from OpenPBS, |
437 |
use the "-I" parameter. |
438 |
</p> |
439 |
|
440 |
@@ -802,16 +802,16 @@ |
441 |
<body> |
442 |
|
443 |
<p> |
444 |
-Message passing is a paradigm used widely on certain classes of parallel |
445 |
-machines, especially those with distributed memory. MPICH is a freely |
446 |
-available, portable implementation of MPI, the Standard for message-passing |
447 |
+Message passing is a paradigm used widely on certain classes of parallel |
448 |
+machines, especially those with distributed memory. MPICH is a freely |
449 |
+available, portable implementation of MPI, the Standard for message-passing |
450 |
libraries. |
451 |
</p> |
452 |
|
453 |
<p> |
454 |
-The mpich ebuild provided by Adelie Linux allows for two USE flags: |
455 |
-<e>doc</e> and <e>crypt</e>. <e>doc</e> will cause documentation to be |
456 |
-installed, while <e>crypt</e> will configure MPICH to use <c>ssh</c> instead |
457 |
+The mpich ebuild provided by Adelie Linux allows for two USE flags: |
458 |
+<e>doc</e> and <e>crypt</e>. <e>doc</e> will cause documentation to be |
459 |
+installed, while <e>crypt</e> will configure MPICH to use <c>ssh</c> instead |
460 |
of <c>rsh</c>. |
461 |
</p> |
462 |
|
463 |
@@ -821,7 +821,7 @@ |
464 |
</pre> |
465 |
|
466 |
<p> |
467 |
-You may need to export a mpich work directory to all your slave nodes in |
468 |
+You may need to export a mpich work directory to all your slave nodes in |
469 |
<path>/etc/exports</path>: |
470 |
</p> |
471 |
|
472 |
@@ -830,15 +830,15 @@ |
473 |
</pre> |
474 |
|
475 |
<p> |
476 |
-Most massively parallel processors (MPPs) provide a way to start a program on |
477 |
-a requested number of processors; <c>mpirun</c> makes use of the appropriate |
478 |
+Most massively parallel processors (MPPs) provide a way to start a program on |
479 |
+a requested number of processors; <c>mpirun</c> makes use of the appropriate |
480 |
command whenever possible. In contrast, workstation clusters require that each |
481 |
-process in a parallel job be started individually, though programs to help |
482 |
-start these processes exist. Because workstation clusters are not already |
483 |
-organized as an MPP, additional information is required to make use of them. |
484 |
-Mpich should be installed with a list of participating workstations in the |
485 |
-file <path>machines.LINUX</path> in the directory |
486 |
-<path>/usr/share/mpich/</path>. This file is used by <c>mpirun</c> to choose |
487 |
+process in a parallel job be started individually, though programs to help |
488 |
+start these processes exist. Because workstation clusters are not already |
489 |
+organized as an MPP, additional information is required to make use of them. |
490 |
+Mpich should be installed with a list of participating workstations in the |
491 |
+file <path>machines.LINUX</path> in the directory |
492 |
+<path>/usr/share/mpich/</path>. This file is used by <c>mpirun</c> to choose |
493 |
processors to run on. |
494 |
</p> |
495 |
|
496 |
@@ -848,11 +848,11 @@ |
497 |
|
498 |
<pre caption="/usr/share/mpich/machines.LINUX"> |
499 |
# Change this file to contain the machines that you want to use |
500 |
-# to run MPI jobs on. The format is one host name per line, with either |
501 |
+# to run MPI jobs on. The format is one host name per line, with either |
502 |
# hostname |
503 |
# or |
504 |
# hostname:n |
505 |
-# where n is the number of processors in an SMP. The hostname should |
506 |
+# where n is the number of processors in an SMP. The hostname should |
507 |
# be the same as the result from the command "hostname" |
508 |
master |
509 |
node01 |
510 |
@@ -863,18 +863,18 @@ |
511 |
</pre> |
512 |
|
513 |
<p> |
514 |
-Use the script <c>tstmachines</c> in <path>/usr/sbin/</path> to ensure that |
515 |
-you can use all of the machines that you have listed. This script performs |
516 |
-an <c>rsh</c> and a short directory listing; this tests that you both have |
517 |
-access to the node and that a program in the current directory is visible on |
518 |
-the remote node. If there are any problems, they will be listed. These |
519 |
+Use the script <c>tstmachines</c> in <path>/usr/sbin/</path> to ensure that |
520 |
+you can use all of the machines that you have listed. This script performs |
521 |
+an <c>rsh</c> and a short directory listing; this tests that you both have |
522 |
+access to the node and that a program in the current directory is visible on |
523 |
+the remote node. If there are any problems, they will be listed. These |
524 |
problems must be fixed before proceeding. |
525 |
</p> |
526 |
|
527 |
<p> |
528 |
-The only argument to <c>tstmachines</c> is the name of the architecture; this |
529 |
-is the same name as the extension on the machines file. For example, the |
530 |
-following tests that a program in the current directory can be executed by |
531 |
+The only argument to <c>tstmachines</c> is the name of the architecture; this |
532 |
+is the same name as the extension on the machines file. For example, the |
533 |
+following tests that a program in the current directory can be executed by |
534 |
all of the machines in the LINUX machines list. |
535 |
</p> |
536 |
|
537 |
@@ -883,7 +883,7 @@ |
538 |
</pre> |
539 |
|
540 |
<note> |
541 |
-This program is silent if all is well; if you want to see what it is doing, |
542 |
+This program is silent if all is well; if you want to see what it is doing, |
543 |
use the -v (for verbose) argument: |
544 |
</note> |
545 |
|
546 |
@@ -905,24 +905,24 @@ |
547 |
</pre> |
548 |
|
549 |
<p> |
550 |
-If <c>tstmachines</c> finds a problem, it will suggest possible reasons and |
551 |
+If <c>tstmachines</c> finds a problem, it will suggest possible reasons and |
552 |
solutions. In brief, there are three tests: |
553 |
</p> |
554 |
|
555 |
<ul> |
556 |
<li> |
557 |
- <e>Can processes be started on remote machines?</e> tstmachines attempts |
558 |
- to run the shell command true on each machine in the machines files by |
559 |
+ <e>Can processes be started on remote machines?</e> tstmachines attempts |
560 |
+ to run the shell command true on each machine in the machines files by |
561 |
using the remote shell command. |
562 |
</li> |
563 |
<li> |
564 |
- <e>Is current working directory available to all machines?</e> This |
565 |
- attempts to ls a file that tstmachines creates by running ls using the |
566 |
+ <e>Is current working directory available to all machines?</e> This |
567 |
+ attempts to ls a file that tstmachines creates by running ls using the |
568 |
remote shell command. |
569 |
</li> |
570 |
<li> |
571 |
<e>Can user programs be run on remote systems?</e> This checks that shared |
572 |
- libraries and other components have been properly installed on all |
573 |
+ libraries and other components have been properly installed on all |
574 |
machines. |
575 |
</li> |
576 |
</ul> |
577 |
@@ -939,7 +939,7 @@ |
578 |
</pre> |
579 |
|
580 |
<p> |
581 |
-For further information on MPICH, consult the documentation at <uri |
582 |
+For further information on MPICH, consult the documentation at <uri |
583 |
link="http://www-unix.mcs.anl.gov/mpi/mpich/docs/mpichman-chp4/mpichman-chp4.htm">http://www-unix.mcs.anl.gov/mpi/mpich/docs/mpichman-chp4/mpichman-chp4.htm</uri>. |
584 |
</p> |
585 |
|
586 |
@@ -973,44 +973,44 @@ |
587 |
<body> |
588 |
|
589 |
<p> |
590 |
-The original document is published at the <uri |
591 |
-link="http://www.adelielinux.com">Adelie Linux R&D Centre</uri> web site, |
592 |
-and is reproduced here with the permission of the authors and <uri |
593 |
-link="http://www.cyberlogic.ca">Cyberlogic</uri>'s Adelie Linux R&D |
594 |
+The original document is published at the <uri |
595 |
+link="http://www.adelielinux.com">Adelie Linux R&D Centre</uri> web site, |
596 |
+and is reproduced here with the permission of the authors and <uri |
597 |
+link="http://www.cyberlogic.ca">Cyberlogic</uri>'s Adelie Linux R&D |
598 |
Centre. |
599 |
</p> |
600 |
|
601 |
<ul> |
602 |
<li><uri>http://www.gentoo.org</uri>, Gentoo Foundation, Inc.</li> |
603 |
<li> |
604 |
- <uri link="http://www.adelielinux.com">http://www.adelielinux.com</uri>, |
605 |
+ <uri link="http://www.adelielinux.com">http://www.adelielinux.com</uri>, |
606 |
Adelie Linux Research and Development Centre |
607 |
</li> |
608 |
<li> |
609 |
- <uri link="http://nfs.sourceforge.net/">http://nfs.sourceforge.net</uri>, |
610 |
+ <uri link="http://nfs.sourceforge.net/">http://nfs.sourceforge.net</uri>, |
611 |
Linux NFS Project |
612 |
</li> |
613 |
<li> |
614 |
- <uri link="http://www-unix.mcs.anl.gov/mpi/mpich/">http://www-unix.mcs.anl.gov/mpi/mpich/</uri>, |
615 |
+ <uri link="http://www-unix.mcs.anl.gov/mpi/mpich/">http://www-unix.mcs.anl.gov/mpi/mpich/</uri>, |
616 |
Mathematics and Computer Science Division, Argonne National Laboratory |
617 |
</li> |
618 |
<li> |
619 |
<uri link="http://www.ntp.org/">http://ntp.org</uri> |
620 |
</li> |
621 |
<li> |
622 |
- <uri link="http://www.eecis.udel.edu/~mills/">http://www.eecis.udel.edu/~mills/</uri>, |
623 |
+ <uri link="http://www.eecis.udel.edu/~mills/">http://www.eecis.udel.edu/~mills/</uri>, |
624 |
David L. Mills, University of Delaware |
625 |
</li> |
626 |
<li> |
627 |
- <uri link="http://www.ietf.org/html.charters/secsh-charter.html">http://www.ietf.org/html.charters/secsh-charter.html</uri>, |
628 |
+ <uri link="http://www.ietf.org/html.charters/secsh-charter.html">http://www.ietf.org/html.charters/secsh-charter.html</uri>, |
629 |
Secure Shell Working Group, IETF, Internet Society |
630 |
</li> |
631 |
<li> |
632 |
- <uri link="http://www.linuxsecurity.com/">http://www.linuxsecurity.com/</uri>, |
633 |
+ <uri link="http://www.linuxsecurity.com/">http://www.linuxsecurity.com/</uri>, |
634 |
Guardian Digital |
635 |
</li> |
636 |
<li> |
637 |
- <uri link="http://www.openpbs.org/">http://www.openpbs.org/</uri>, |
638 |
+ <uri link="http://www.openpbs.org/">http://www.openpbs.org/</uri>, |
639 |
Altair Grid Technologies, LLC. |
640 |
</li> |
641 |
</ul> |
642 |
|
643 |
|
644 |
|
645 |
-- |
646 |
gentoo-doc-cvs@l.g.o mailing list |