mirrors/scst
1
0
Fork 0
mirror of https://github.com/SCST-project/scst.git synced 2026-05-14 09:11:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge with 1.0.1.x r731:

Browse Source 
Docs updated. Changes in iscsi-scst/doc/iscsi-scst-howto.txt made by Bart Van Assche



git-svn-id: http://svn.code.sf.net/p/scst/svn/trunk@732 d57e44dd-8a1f-0410-8b47-8ef2f437770f
This commit is contained in:
Vladislav Bolkhovitin
2009-04-01 12:12:41 +00:00
parent 4bc15527d2
commit 2580e6b17f
3 changed files with 60 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
doc/scst_user_spec.txt
View File

@@ -124,6 +124,9 @@ struct scst_user_opt
uint8_t queue_alg;
uint8_t tas;
uint8_t swp;
uint8_t d_sense;
uint8_t has_own_order_mgmt;
},
where:
@@ -192,8 +195,13 @@ where:
* SCST_USER_PARTIAL_TRANSFERS_SUPPORTED - the partial data transfers
are supported without limitations.
- tst, queue_alg, tas and swp - set values for TST, QUEUE ALGORITHM MODIFIER,
TAS and SWP fields from control mode page correspondingly, see SPC.
- tst, queue_alg, tas, swp, d_sense - set values for TST, QUEUE ALGORITHM MODIFIER,
TAS, SWP and D_SENSE fields from control mode page correspondingly,
see SPC.
- has_own_order_mgmt - true, if the user space handler has full
commands execution order management, i.e. guarantees commands execution
order as required by SAM. False otherwise.
Flags parse_type and on_free_cmd_type are designed to improve
performance by eliminating context switches to the user space handler,
@@ -328,7 +336,8 @@ struct scst_user_scsi_cmd_parse
uint64_t sess_h;
uint8_t cdb[SCST_MAX_CDB_SIZE];
int32_t cdb_len;
uint16_t cdb_len;
uint16_t ext_cdb_len;
uint32_t timeout;
int32_t bufflen;
@@ -351,6 +360,9 @@ where:
- cdb_len - SCSI CDB length
- ext_cdb_len - size of extended CDB, see SCST_USER_GET_EXTENDED_CDB
for more details
- timeout - CDB execution timeout
- bufflen - command's buffer length
@@ -403,7 +415,8 @@ struct scst_user_scsi_cmd_alloc_mem
uint64_t sess_h;
uint8_t cdb[SCST_MAX_CDB_SIZE];
int32_t cdb_len;
uint16_t cdb_len;
uint16_t ext_cdb_len;
int32_t alloc_len;
@@ -421,6 +434,9 @@ where:
- cdb_len - SCSI CDB length
- ext_cdb_len - size of extended CDB, see SCST_USER_GET_EXTENDED_CDB
for more details
- alloc_len - command's buffer length
- queue_type - SCSI task attribute (queue type )
@@ -508,7 +524,8 @@ struct scst_user_scsi_cmd_exec
uint64_t sess_h;
uint8_t cdb[SCST_MAX_CDB_SIZE];
int32_t cdb_len;
uint16_t cdb_len;
uint16_t ext_cdb_len;
int32_t data_len;
int32_t bufflen;
@@ -534,6 +551,9 @@ where:
- cdb_len - SCSI CDB length
- ext_cdb_len - size of extended CDB, see SCST_USER_GET_EXTENDED_CDB
for more details
- data_len - command's data length. Could be different from bufflen for
commands like VERIFY, which transfer different amount of data, than
process, or even none of them
@@ -843,6 +863,29 @@ SCST_USER_DEVICE_CAPACITY_CHANGED returns 0 on success or -1 in case of
error, and errno is set appropriately.
8. SCST_USER_GET_EXTENDED_CDB
SCST_USER_GET_EXTENDED_CDB - requests extended CDB, if CDB size is more
than SCST_MAX_CDB_SIZE bytes. In this case SCST_USER_GET_EXTENDED_CDB
returns additional CDB data beyond SCST_MAX_CDB_SIZE bytes.
SCST_USER_GET_EXTENDED_CDB has the following arguments:
struct scst_user_get_ext_cdb {
uint32_t cmd_h;
aligned_u64 ext_cdb_buffer;
},
where:
- cmd_h - command handle used to identify the command in the reply.
- ext_cdb_buffer - pointer to buffer, where extended CDB will be copied.
SCST_USER_GET_EXTENDED_CDB returns 0 on success or -1 in case of error,
and errno is set appropriately.
IV. Commands processing flow example.
As the example consider a simple synchronous VTL, which serves one

2
iscsi-scst/doc/iscsi-scst-howto.txt
View File

@@ -80,6 +80,8 @@ Replace the device names by names that apply to your system:
scstadmin -ClearConfig /etc/scst.conf
scstadmin -adddev disk01 -path /dev/ram0 -handler vdisk -options NV_CACHE
scstadmin -adddev disk02 -path /dev/ram1 -handler vdisk -options NV_CACHE
scstadmin -assigndev disk01 -group Default -lun 0
scstadmin -assigndev disk02 -group Default -lun 0
scstadmin -WriteConfig /etc/scst.conf
cat /etc/scst.conf

21
www/target_iscsi.html
View File

@@ -57,10 +57,10 @@
which doesn't touch the core code, could be merged, it is very unlikely that they will be merged in the main
<strong>IET</strong> trunk.</p>
<p><strong>ISCSI-SCST</strong> has the following major advantages over the mainline <strong>IET</strong>:
<p><strong>ISCSI-SCST</strong> has the following major advantages over <strong>IET</strong>:
<ul>
<li><span>It uses full power of <strong>SCST core</strong> without loosing any existing IET feature (except, maybe, illegal
from SCSI specifications point of view MPIO). Namely, you can additionally use with it:
<li><span>It uses full power of <strong>SCST core</strong> without loosing any existing IET feature.
Comparing to IET it has the following additional features:
<ul>
<li><span><strong>Pass-through mode with one to many relationship</strong>, i.e. when multiple initiators can connect to the
exported pass-through devices. For instance, you can safely export your parallel
@@ -74,7 +74,7 @@
of <strong>BLOCKIO</strong>, but also supports files on file systems. Sometimes, in the appropriate cases,
this mode can make performance difference in 100% or even more.</span></li>
<li><span>With <strong>4KB blocks</strong> you can forget about abysmal write performance caused by misaligned partitions.
All modern OS'es, including Windows starting from, at least, Windows 2000, work perfectly with 4KB block
All modern OS'es, including Windows starting from Windows 2000, work perfectly with 4KB block
devices without any additional storage or handling overhead.</span></li>
<li><span><strong>Virtual CD/DVD-ROMs</strong> without necessity for manual patching.</span></li>
<li><span>Ability to create target devices emulators in the <strong>user space</strong>.</span></li>
@@ -94,13 +94,12 @@
<li><span>Due to reworked I/O architecture and SCST backend iSCSI-SCST has
better performance in many cases. In future with upcoming improvements in SCST core, like <strong>zero-copy
with Linux cache FILEIO</strong>, the performance difference is going to be even bigger. Currently in
tests from a single initiator over a single connection on 1GbE hardware over FILEIO vdisk
iSCSI-SCST with default settings usually outperforms tuned for best
performance IET a on <strong>on up to 100%</strong>. The difference is especially noticeably with real storage,
not NULLIO or RAM disks.
On 10GbE hardware the performance difference is often as high as <strong>100-200%</strong> or even more.
With higher number of initiators the difference will be even bigger. This is because
with Linux cache FILEIO</strong>, the performance difference is going to be even bigger. For instance, in
tests from a single initiator over a single connection on 1GbE hardware using vdisk handler
iSCSI-SCST with default settings in many cases outperforms tuned for best
performance IET on <strong>more than 100%</strong>. See
<a href="http://lkml.org/lkml/2009/3/30/283">those measurements</a>, for example. The difference is especially
noticeably with real storage, not NULLIO or RAM disks. This is because
iSCSI-SCST has less commands processing overhead per command, hence has smaller processing
latency and puts less load on CPU.
</ul></p>