AoEForEmbeddedLinuxDevEnvEngText - Revision history

Jsujjava: Add category description

2011-05-05T14:08:45Z

Add category description

Peter Huewe: spellcheck

2011-04-11T20:56:28Z

spellcheck

Ikoma: /* (slide 17)Consideration */

2009-06-02T09:42:46Z

‎(slide 17)Consideration

Ikoma: /* (slide 16)Evaluation of AoE Use (Behavior) */

2009-06-02T09:41:58Z

‎(slide 16)Evaluation of AoE Use (Behavior)

Ikoma: /* (slide 15)Evaluation of AoE Use (Size/Memory Usage) */

2009-06-02T09:40:49Z

‎(slide 15)Evaluation of AoE Use (Size/Memory Usage)

Ikoma: /* (slide 14)Evaluation of AoE Use */

2009-06-02T09:37:57Z

‎(slide 14)Evaluation of AoE Use

Ikoma: /* (slide 11)Use of rootfs with each Method */

2009-06-02T09:37:01Z

‎(slide 11)Use of rootfs with each Method

Ikoma: /* (slide 6)ATA over Ethernet (AoE) Overview */

2009-06-02T09:34:59Z

‎(slide 6)ATA over Ethernet (AoE) Overview

Ikoma: /* (slide 2)Background */

2009-06-02T09:34:21Z

‎(slide 2)Background

Ikoma: /* (slide 4)Issues when using NFS */

2009-06-02T09:33:43Z

‎(slide 4)Issues when using NFS

← Older revision		Revision as of 14:08, 5 May 2011
Line 327:		Line 327:

	* http://nbd.sourceforge.net/		* http://nbd.sourceforge.net/
		+	[[Category:Presentations]]

@@ Line 22: / Line 22: @@
-ATA over Ethernet for Embedded Linux Developmnet Environment
+ATA over Ethernet for Embedded Linux Development Environment
 Tomohiko Shigeoka
@@ Line 32: / Line 32: @@
-* NFS is typically used to share files (rootfs) between the host and the target in embedded Linux development enviroment
+* NFS is typically used to share files (rootfs) between the host and the target in embedded Linux development environment
 * When burnt onto devices, file systems are built on flash memory
@@ Line 43: / Line 43: @@
 [http://www.example.com link title]
-==(slide 3)Typical Development Environemnt using NFS==
+==(slide 3)Typical Development Environment using NFS==
 * Developing software on host system using cross tool chain
@@ Line 56: / Line 56: @@
 * NFS has prove track record(+) and it is convenient to develop under NFS environment, but there are issues ...
-** Different software configuration in operation (after development) may cause misterious behavior
+** Different software configuration in operation (after development) may cause mysterious behavior
 ** Debugging problems attributed to file system is impossible/hard
@@ Line 95: / Line 95: @@
    # vblade 0 0 eth0 image_file
-* AoE driver on client presents an image publised on server as a block device to file system layer
+* AoE driver on client presents an image published on server as a block device to file system layer
    # mount -t ext2 /dev/etherd/e0.0 /mnt
@@ Line 104: / Line 104: @@
 ==(slide 8)iSCSI Overview==
-* SAN technology gettin popular in enterprise arena
+* SAN technology getting popular in enterprise arena
 * Protocol to communicate by loading SCSI commands/data on TCP/IP
@@ Line 110: / Line 110: @@
 * Client side driver (initiator) mainlined since kernel 2.6.12 (drivers/scsi/iscsi_tcp.c)
-* Block devices can be used with the same interface with ordinaly SCSI devices (/dev/sda etc.)
+* Block devices can be used with the same interface with ordinary SCSI devices (/dev/sda etc.)
 * On client side, configuration with userland tool (Open-iSCSI) is required
@@ Line 128: / Line 128: @@
 * Treats server data via TCP/IP as block device
-* Protocol irelevalent to ATA (compression supported)
+* Protocol irrelevant to ATA (compression supported)
 * Client side driver mainlined since kernel 2.1.101 (drivers/block/nbd.c)
@@ Line 145: / Line 145: @@
 * Only AoE support the same style as NFS
 ** AoE root patch required(http://support.coraid.com/support/linux/contrib/mcmullan/aoeroot-2.6.15.diff)
-** With this patch, AoE server to be root must be specifed in kernel config
+** With this patch, AoE server to be root must be specified in kernel config
 ** Can not be specified in kernel command line (root=???)
 ** Setting with command (aoetools) is not required
@@ Line 160: / Line 160: @@
 * jffs2 etc. assumes MTD, not block devices
-* MTD inteface can be used with block2mtd
+* MTD interface can be used with block2mtd
    # insmod block2mtd.ko block2mtd=/dev/hda1
    # mount -t jffs2 /dev/mtdblock0 /mnt
@@ Line 184: / Line 184: @@
 ** Memory usage at boot with identical rootfs
 ** Comparison of behavior with compression file system (cramfs)
-*** read time of a highly compressionable file (all zero) and a less compressionable file (random data) of the same data volume
+*** read time of a highly compressible file (all zero) and a less compressible file (random data) of the same data volume
 * Evaluation environment
@@ Line 217: / Line 217: @@
 * Memory usage comparison
-** After booting up with an identical rootfs (busybox), logging in and executing free commaand
+** After booting up with an identical rootfs (busybox), logging in and executing free command
 +-------+--------+--------+--------+---------+
@@ Line 302: / Line 302: @@
 ** In case of NFS, it is independent of data contents as there is no expanding (data transfer volume is also uniform)
-* Data transfer volume is reflects the data contens to be transferred
+* Data transfer volume is reflects the data contents to be transferred
 ** Transferring compressed data causes highly compressible data is transferred as less volume
 ** NFS does not compress data, so data transfer volume is constant
@@ Line 310: / Line 310: @@
 * AoE is usable even for embedded Linux systems
-* AoE make some debuging impossible with NFS possible
+* AoE make some debugging impossible with NFS possible
 * Object size is smaller with AoE than with NFS

@@ Line 299: / Line 299: @@
 * Kernel CPU time reflects the difference of compression processing
-  - Expanding highly compressible data (all zero) does not use CPU as much as random data (Assuming that data transfer does not need so much CPU power; if data transfer needs much CPU power, volume of memory copy would be also reflected)
+** Expanding highly compressible data (all zero) does not use CPU as much as random data (Assuming that data transfer does not need so much CPU power; if data transfer needs much CPU power, volume of memory copy would be also reflected)
+** In case of NFS, it is independent of data contents as there is no expanding (data transfer volume is also uniform)
-  - In case of NFS, it is independent of data contents as there is no expanding (data transfer volume is also uniform)
 * Data transfer volume is reflects the data contens to be transferred
-  - Transferring compressed data causes highly compressible data is transferred as less volume
+** Transferring compressed data causes highly compressible data is transferred as less volume
-  - NFS does not compress data, so data transfer volume is constant
+** NFS does not compress data, so data transfer volume is constant
-−
 ==(slide 18)Summary==

@@ Line 242: / Line 242: @@
 * File read time (CPU time)
-  - "echo 3 > /proc/sys/vm/drop_caches", then read out with "time wc -c"
+** "echo 3 > /proc/sys/vm/drop_caches", then read out with "time wc -c"
 +-------+--------------------+--------------------+
@@ Line 266: / Line 266: @@
 +-------+------+------+------+------+------+------+
-        unit: second (read 5MB; avarage of 10 trials)
+:        unit: second (read 5MB; avarage of 10 trials)
 * Data transfer volume
-  - Measured as the difference between /proc/diskstats and /proc/net/dev
+** Measured as the difference between /proc/diskstats and /proc/net/dev
 +-------+--------------------------+--------------------------+
@@ Line 294: / Line 294: @@
 +-------+------------+-------------+------------+-------------+
-                                     unit: byte (when read 5MB)
+:                                    unit: byte (when read 5MB)
 ==(slide 17)Consideration==

@@ Line 214: / Line 214: @@
 +----------------------+---------+---------------------+
-               size of build-in.o in each directory (bytes)
+:              size of build-in.o in each directory (bytes)
 * Memory usage comparison
+** After booting up with an identical rootfs (busybox), logging in and executing free commaand
-  - After booting up with an identical rootfs (busybox), logging in and executing free commaand
 +-------+--------+--------+--------+---------+
@@ Line 238: / Line 237: @@
 +-------+--------+--------+--------+---------+
-                  free command output (Kbytes)
+:                  free command output (Kbytes)
-−
 ==(slide 16)Evaluation of AoE Use (Behavior)==

@@ Line 181: / Line 181: @@
 * Evaluation items (Comparison among AoE/NFS/Flash memory)
-  - Object size of target kernel
+** Object size of target kernel
-  - Memory usage at boot with identical rootfs
+** Memory usage at boot with identical rootfs
-  - Comparison of behavior with compression file system (cramfs)
+** Comparison of behavior with compression file system (cramfs)
-    -- read time of a highly compressionable file (all zero) and a less compressionable file (random data) of the same data volume
+*** read time of a highly compressionable file (all zero) and a less compressionable file (random data) of the same data volume
 * Evaluation environment
-  - Target: OSK (TI OMAP 192MHz, RAM 32M), kernel 2.6.20.20, 10BASE-T
+** Target: OSK (TI OMAP 192MHz, RAM 32M), kernel 2.6.20.20, 10BASE-T
-  - Host: x86_64(3.4GHz), kernel 2.4.21(RHEL3), 1000BASE-T
+** Host: x86_64(3.4GHz), kernel 2.4.21(RHEL3), 1000BASE-T
-−
 ==(slide 15)Evaluation of AoE Use (Size/Memory Usage)==

@@ Line 144: / Line 144: @@
 * Only AoE support the same style as NFS
-  - AoE root patch required
+** AoE root patch required(http://support.coraid.com/support/linux/contrib/mcmullan/aoeroot-2.6.15.diff)
-    (http://support.coraid.com/support/linux/contrib/mcmullan/aoeroot-2.6.15.diff
+** With this patch, AoE server to be root must be specifed in kernel config
+** Can not be specified in kernel command line (root=???)
-  - With this patch, AoE server to be root must be specifed in kernel config
+** Setting with command (aoetools) is not required
-  - Can not be specified in kernel command line (root=???)
-  - Setting with command (aoetools) is not required
 * Setting up with command is required for iSCSI or NBD
-  - Setting up using initramfs/initrd
+** Setting up using initramfs/initrd
-  - Direct mounting as rootfs is not possible; must add initramfs/initrd with setting up
+** Direct mounting as rootfs is not possible; must add initramfs/initrd with setting up
-    --> this is why we use AoE here
+:    --> this is why we use AoE here
 ==(slide 12)MTD Emulation==

@@ Line 83: / Line 83: @@
 * Server side is special hardware or software implementation - userland daemon, kernel driver etc.
+**vblade, kvblade, qaoed, etc.
-  - vblade, kvblade, qaoed, etc.
 * Server side is not required to be an ATA

@@ Line 35: / Line 35: @@
 * When burnt onto devices, file systems are built on flash memory
 **File system other than extN is often used
 **cramfs/squashfs/jffs2/ubifs/ etc.
 * Modifying files placed on flash memory is not easy (in many cases)
 **Writing with ROM Writer, JTAG-ICE etc. is cumbersome
 **If failed, further troublesome
 ==(slide 3)Typical Development Environemnt using NFS==