xref: /freebsd/sys/dev/isp/Hardware.txt (revision a35d88931c87cfe6bd38f01d7bad22140b3b38f3)
1/* $FreeBSD$ */
2
3	Hardware that is Known To or Should Work with This Driver
4
5
60. Intro
7
8	This is not an endorsement for hardware vendors (there will be
9	no "where to buy" URLs here with a couple of exception). This
10	is simply a list of things I know work, or should work, plus
11	maybe a couple of notes as to what you should do to make it
12	work. Corrections accepted. Even better would be to send me
13	hardware to I can test it.
14
15	I'll put a rough range of costs in US$ that I know about. No doubt
16	it'll differ from your expectations.
17
181. HBAs
19
20Qlogic	2100, 2102
21	2200, 2202, 2204
22
23	There are various suffices that indicate copper or optical
24	connectors, or 33 vs. 66MHz PCI bus operation. None of these
25	have a software impact.
26
27	Approx cost: 1K$ for a 2200
28
29Qlogic	2300, 2312
30
31	These are the new 2-Gigabit cards. Optical only.
32
33	Approx cost: ??????
34
35
36Antares	P-0033, P-0034, P-0036
37
38	There many other vendors that use the Qlogic 2X00 chipset. Some older
39	2100 boards (not on this list) have a bug in the ROM that causes a
40	failure to download newer firmware that is larger than 0x7fff words.
41
42	Approx cost: 850$ for a P-0036
43
44
45
46	In general, the 2200 class chip is to be preferred.
47
48
492. Hubs
50
51Vixel 1000
52Vixel 2000
53	Of the two, the 1000 (7 ports, vs. 12 ports) has had fewer problems-
54	it's an old workhorse.
55
56
57	Approx cost: 1.5K$ for Vixel 1000, 2.5K$ for 2000
58
59Gadzoox Cappellix 3000
60	Don't forget to use telnet to configure the Cappellix ports
61	to the role you're using them for- otherwise things don't
62	work well at all.
63
64	(cost: I have no idea... certainly less than a switch)
65
663. Switches
67
68Brocade Silkworm II
69Brocade 2400
70(other brocades should be fine)
71
72	Especially with revision 2 or higher f/w, this is now best
73	of breed for fabrics or segmented loop (which Brocade
74	calls "QuickLoop").
75
76	For the Silkworm II, set operating mode to "Tachyon" (mode 3).
77
78	The web interace isn't good- but telnet is what I prefer anyhow.
79
80	You can't connect a Silkworm II and the other Brocades together
81	as E-ports to make a large fabric (at least with the f/w *I*
82	had for the Silkworm II).
83
84	Approx cost of a Brocade 2400 with no GBICs is about 8K$ when
85	I recently checked the US Government SEWP price list- no doubt
86	it'll be a bit more for others. I'd assume around 10K$.
87
88ANCOR SA-8
89
90	This also is a fine switch, but you have to use a browser
91	with working java to manage it- which is a bit of a pain.
92	This also supports fabric and segmented loop.
93
94	These switches don't form E-ports with each other for a larger
95	fabric.
96
97	(cost: no idea)
98
99McData (model unknown)
100
101	I tried one exactly once for 30 minutes. Seemed to work once
102	I added the "register FC4 types" command to the driver.
103
104	(cost: very very expensive, 40K$ plus)
105
1064. Cables/GBICs
107
108	Multimode optical is adequate for Fibre Channel- the same cable is
109	used for Gigabit Ethernet.
110
111	Copper DB-9 and Copper HSS-DC connectors are also fine. Copper &&
112	Optical both are rated to 1.026Gbit- copper is naturally shorter
113	(the longest I've used is a 15meter cable but it's supposed to go
114	longer).
115
116	The reason to use copper instead of optical is that if step on one of
117	the really fat DB-9 cables you can get, it'll survive. Optical usually
118	dies quickly if you step on it.
119
120	Approx cost: I don't know what optical is- you can expect to pay maybe
121	a 100$ for a 3m copper cable.
122
123GBICs-
124
125	I use Finisar copper and IBM Opticals.
126
127	Approx Cost: Copper GBICs are 70$ each. Opticals are twice that or more.
128
129
130Vendor: (this is the one exception I'll make because it turns out to be
131	an incredible pain to find FC copper cabling and GBICs- the source I
132	use for GBICs and copper cables is http://www.scsi-cables.com)
133
134
135Other:
136	There now is apparently a source for little connector boards
137	to connect to bare drives: http://www.cinonic.com.
138
139
1405. Storage JBODs/RAID
141
142JMR 4-Bay
143
144	Rinky-tink, but a solid 4 bay loop only entry model.
145
146	I paid 1000$ for mine- overprice, IMO.
147
148JMR Fortra
149
150	I rather like this box. The blue LEDs are a very nice touch- you
151	can see them very clearly from 50 feet away.
152
153	I paid 2000$ for one used.
154
155Sun A5X00
156
157	Very expensive (in my opinion) but well crafted. Has two SES
158	instances, so you can use the ses driver (and the example
159	code in /usr/share/examples) for power/thermal/slot monitoring.
160
161	Approx Cost: The last I saw for a price list item on this was 22K$
162	for an unpopulated (no disk drive) A5X00.
163
164
165DataDirect E1000 RAID
166
167	Don't connect both SCSI and FC interfaces at the same time- a SCSI
168	reset will cause the DataDirect to think you want to use the SCSI
169	interface and a LIP on the FC interface will cause it to think you
170	want to use the FC interface. Use only one connector at a time so
171	both you and the DataDirect are sure about what you want.
172
173	Cost: I have no idea.
174
175Veritas ServPoint
176
177	This is a software storage virtualization engine that
178	runs on Sparc/Solaris in target mode for frontend
179	and with other FC or SCSI as the backend storage. FreeBSD
180	has been used extensively to test it.
181
182
183	Cost: I have no idea.
184
1856. Disk Drives
186
187	I have used lots of different Seagate and a few IBM drives and
188	typically have had few problems with them. These are the bare
189	drives with 40-pin SCA connectors in back. They go into the JBODs
190	you assemble.
191
192	Seagate does make, but I can no longer find, a little paddleboard
193	single drive connector that goes from DB-9 FC to the 40-pin SCA
194	connector- primarily for you to try and evaluate a single FC drive.
195
196	All FC-AL disk drives are dual ported (i.e., have separte 'A' and
197	'B' ports- which are completely separate loops). This seems to work
198	reasonably enough, but I haven't tested it much. It really depends
199	on the JBOD you put them to carry this dual port to the outside
200	world. The JMR boxes have it. The Sun A5X00 you have to pay for
201	an extra IB card to carry it out.
202
203	Approx Cost: You'll find that FC drives are the same cost if not
204	slightly cheaper than the equivalent Ultra3 SCSI drives.
205
2067. Recommended Configurations
207
208These are recommendations that are biased toward the cautious side. They
209do not represent formal engineering commitments- just suggestions as to
210what I would expect to work.
211
212A. The simpletst form of a connection topology I can suggest for
213a small SAN (i.e., replacement for SCSI JBOD/RAID):
214
215HOST
2162xxx <----------> Single Unit of Storage (JBOD, RAID)
217
218This is called a PL_DA (Private Loop, Direct Attach) topology.
219
220B. The next most simple form of a connection topology I can suggest for
221a medium local SAN (where you do not plan to do dynamic insertion
222and removal of devices while I/Os are active):
223
224HOST
2252xxx <----------> +--------
226                  | Vixel |
227                  | 1000  |
228                  |       +<---> Storage
229                  |       |
230                  |       +<---> Storage
231                  |       |
232                  |       +<---> Storage
233                  --------
234
235This is a Private Loop topology. Remember that this can get very unstable
236if you make it too long. A good practice is to try it in a staged fashion.
237
238It is possible with some units to "daisy chain", e.g.:
239
240HOST
2412xxx <----------> (JBOD, RAID) <--------> (JBOD, RAID)
242
243In practice I have had poor results with these configurations. They *should*
244work fine, but for both the JMR and the Sun A5X00 I tend to get LIP storms
245and so the second unit just isn't seen and the loop isn't stable.
246
247Now, this could simply be my lack of clean, newer, h/w (or, in general,
248a lack of h/w), but I would recommend the use of a hub if you want to
249stay with Private Loop and have more than one FC target.
250
251You should also note this can begin to be the basis for a shared SAN
252solution. For example, the above configuration can be extended to be:
253
254HOST
2552xxx <----------> +--------
256                  | Vixel |
257                  | 1000  |
258                  |       +<---> Storage
259                  |       |
260                  |       +<---> Storage
261                  |       |
262                  |       +<---> Storage
263HOST              |       |
2642xxx <----------> +--------
265
266However, note that there is nothing to mediate locking of devices, and
267it is also conceivable that the reboot of one host can, by causing
268a LIP storm, cause problems with the I/Os from the other host.
269(in other words, this topology hasn't really been made safe yet for
270this driver).
271
272D. You can repeat the topology in #B with a switch that is set to be
273in segmented loop mode. This avoids LIPs propagating where you don't
274want them to- and this makes for a much more reliable, if more expensive,
275SAN.
276
277E. The next level of complexity is a Switched Fabric. The following topology
278is good when you start to begin to get to want more performance. Private
279and Public Arbitrated Loop, while 100MB/s, is a shared medium. Direct
280connections to a switch can run full-duplex at full speed.
281
282HOST
2832xxx <----------> +---------
284                  | Brocade|
285                  | 2400   |
286                  |        +<---> Storage
287                  |        |
288                  |        +<---> Storage
289                  |        |
290                  |        +<---> Storage
291HOST              |        |
2922xxx <----------> +---------
293
294
295I would call this the best configuration available now. It can expand
296substantially if you cascade switches.
297
298There is a hard limit of about 253 devices for each Qlogic HBA- and the
299fabric login policy is simplistic (log them in as you find them). If
300somebody actually runs into a configuration that's larger, let me know
301and I'll work on some tools that would allow you some policy choices
302as to which would be interesting devices to actually connect to.
303
304
305