[ewg] Translation Soft 6 by Sys+ran 153, Pc or mac at 88%`discount
virtual pc 7.0 for mac - 49 autodesk autocad 2008 - 129 virtualdj 4.3 for mac - 39 php maker 5 - 39 adobe encore dvd 2 - 49 quarkxpress passport 7.3 - 79 adobe indesign cs3 - 79 media tools professional 5 - 39 ` goto `xpfreeoemdownload .com` in Internet Explorer Remove ` before you goto in Internet Explorer ` In Hunting the Tiger, journalist Christopher S. Stewart tells the story of how Zeljko Raznatovic, a petty criminal, rose to head one of Serbia's most notorious death squads. U.N.'s Man in Darfur Addresses New Crisis ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Post OFED-1.3 teleconference today
Friendly reminder: the OFED teleconference is today (Monday, March 10, 2008). ***REMINDER: the US changed time yesterday. The teleconference is still at noon US eastern / 9am US Pacific, but has changed to ***6pm Israel***. Next few teleconferences: - All are at noon US eastern / 9am US Pacific. 1. Monday, March 24 (tentative; not scheduled yet) 6pm Israel 2. Monday, April 7 (tentative; not scheduled yet) ***7pm Israel*** Dial-in information: US/Canada: +1.866.432.9903 India: +91.80.4103.3979 Israel: +972.9.892.7026 Others: http://cisco.com/en/US/about/doing_business/conferencing/ -- Jeff Squyres Cisco Systems -- Jeff Squyres Cisco Systems ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] SRP performance in SCST
Hi, I'm trying to test SRP performance in SCST. I used the following configuration: Both, target and initiator are x86-64 machines. Both have OFED-1.3 GA installed. The HCAs are 20 Gb/sec (4X DDR). Target: Sles 10. 4GB RAM srpt installed. SCST installed. Initiator: Redhat 5. 2GB RAM. srp initiator (from OFED) is installed. On the target I set a virtual device: dd if=/dev/zero of=/tmp/tempfile bs=64k count=100 echo open vdisk0 /tmp/tempfile NULLIO /proc/scsi_tgt/vdisk/vdisk echo add vdisk0 0 /proc/scsi_tgt/groups/Default/devices cat /proc/scsi_tgt/vdisk/vdisk Name Size(MB)Block size Options File name vdisk01572864 512 NIO /tmp/tempfile I used the following commands: for write commands: sgp_dd of=/dev/sg1 if=/dev/zero bs=512 bpt=from 2-512 thr=8 time=1 count=20M for read commands sgp_dd if=/dev/sg1 of=/dev/null bs=512 bpt=from 2-512 thr=8 time=1 count=20M And the results are (all in MB/s): bpt:2 4 8 16 32 64 128 256 512 Write 22.541.480.6160 275 443 570 740 810 Read42 80 170 313 550 940 12001312 1300 What can be the reason for such difference between the bandwidth of Read and Write commands? Thanks, Doron ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [Scst-devel] SRP performance in SCST
On Mon, Mar 10, 2008 at 3:20 PM, Doron Shoham [EMAIL PROTECTED] wrote: I used the following commands: for write commands: sgp_dd of=/dev/sg1 if=/dev/zero bs=512 bpt=from 2-512 thr=8 time=1 count=20M for read commands sgp_dd if=/dev/sg1 of=/dev/null bs=512 bpt=from 2-512 thr=8 time=1 count=20M And the results are (all in MB/s): bpt:2 4 8 16 32 64 128 256 512 Write 22.541.480.6160 275 443 570 740 810 Read42 80 170 313 550 940 12001312 1300 What can be the reason for such difference between the bandwidth of Read and Write commands? Can you please try to use direct I/O instead of buffered I/O ? Bart. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [Scst-devel] SRP performance in SCST
Bart Van Assche wrote: On Mon, Mar 10, 2008 at 3:20 PM, Doron Shoham [EMAIL PROTECTED] wrote: I used the following commands: for write commands: sgp_dd of=/dev/sg1 if=/dev/zero bs=512 bpt=from 2-512 thr=8 time=1 count=20M for read commands sgp_dd if=/dev/sg1 of=/dev/null bs=512 bpt=from 2-512 thr=8 time=1 count=20M And the results are (all in MB/s): bpt:2 4 8 16 32 64 128 256 512 Write 22.541.480.6160 275 443 570 740 810 Read42 80 170 313 550 940 1200 13121300 What can be the reason for such difference between the bandwidth of Read and Write commands? Can you please try to use direct I/O instead of buffered I/O ? Bart. I have tried to use dio but when the bpt was 128 (or higher) I got the following error: echo 1 /proc/scsi/sg/allow_dio sgp_dd if=/dev/sg1 of=/dev/null bs=512 bpt=128 thr=8 time=1 count=5M dio=1 time to transfer data was 2.236290 secs, 1200.36 MB/sec 5242880+0 records in 5242880+0 records out Direct IO requested but incomplete 40960 times Doron ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] Re: [Scst-devel] SRP performance in SCST
On Mon, Mar 10, 2008 at 3:42 PM, Doron Shoham [EMAIL PROTECTED] wrote: Bart Van Assche wrote: Can you please try to use direct I/O instead of buffered I/O ? Bart. I have tried to use dio but when the bpt was 128 (or higher) I got the following error: echo 1 /proc/scsi/sg/allow_dio sgp_dd if=/dev/sg1 of=/dev/null bs=512 bpt=128 thr=8 time=1 count=5M dio=1 time to transfer data was 2.236290 secs, 1200.36 MB/sec 5242880+0 records in 5242880+0 records out Direct IO requested but incomplete 40960 times I'm not familiar with the /proc/scsi/sg/allow_dio entry. I was referring to options like iflag=direct or oflag=direct for dd -- all performance tests I have performed in the past were with dd and xdd. Without direct I/O, read tests use Linux' buffering. If the amount of data being read is less than the available RAM, buffered I/O tests only measure how fast Linux can copy data in RAM. Bart. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Post OFED-1.3 teleconference today
Jeff Squyres wrote: Friendly reminder: the OFED teleconference is today (Monday, March 10, 2008). ***REMINDER: the US changed time yesterday. The teleconference is still at noon US eastern / 9am US Pacific, but has changed to ***6pm Israel***. What is the meeting ID? Next few teleconferences: - All are at noon US eastern / 9am US Pacific. 1. Monday, March 24 (tentative; not scheduled yet) 6pm Israel 2. Monday, April 7 (tentative; not scheduled yet) ***7pm Israel*** Dial-in information: US/Canada: +1.866.432.9903 India: +91.80.4103.3979 Israel: +972.9.892.7026 Others: http://cisco.com/en/US/about/doing_business/conferencing/ --Jeff Squyres Cisco Systems --Jeff Squyres Cisco Systems ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
Re: [ewg] Post OFED-1.3 teleconference today
Oops! Sorry, the meeting ID today is the same that is has been: 210020028 On Mar 10, 2008, at 10:28 AM, Tziporet Koren wrote: Jeff Squyres wrote: Friendly reminder: the OFED teleconference is today (Monday, March 10, 2008). ***REMINDER: the US changed time yesterday. The teleconference is still at noon US eastern / 9am US Pacific, but has changed to ***6pm Israel***. What is the meeting ID? Next few teleconferences: - All are at noon US eastern / 9am US Pacific. 1. Monday, March 24 (tentative; not scheduled yet) 6pm Israel 2. Monday, April 7 (tentative; not scheduled yet) ***7pm Israel*** Dial-in information: US/Canada: +1.866.432.9903 India: +91.80.4103.3979 Israel: +972.9.892.7026 Others: http://cisco.com/en/US/about/doing_business/conferencing/ --Jeff Squyres Cisco Systems --Jeff Squyres Cisco Systems ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg -- Jeff Squyres Cisco Systems ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
[ewg] OFED meeting agenda for today (March 10)
OFED meeting agenda: 1. Feedback on OFED 1.3 release 2. Decide on fix release criteria and process (see suggestion below) 3. When do we need to have a new kernel branch for OFED 1.4 (based on kernel 2.6.25) 4. OFED meeting frequency - do we wish to continue with bi-weekly, or move to monthly meeting for this period Fix/point release criteria and process: --- Changes type: 1. No changes to kernel base (we should stay with 2.6.24) 2. No API changes (both in kernel and in user libs) 3. Low level driver changes - in the responsibility of the HW vendor, meaning: The HW vendor can enhance/fix bugs in the low level driver The QA for the change is the responsibility of the HW vendor 4. Core and ULPs: Critical and high priority bug fixes only 5. Add backports to support a new OS (e.g. SLES10 SP2, FC8, etc.) 6. Replace MPI revision - I am not sure here - need MPI people to respond on this Release frequency: 1. Every 4-6 weeks (unless a blocker bug arises) Release verification: 1. All vendors should run at least basic QA/verification cycle 2. If there is a change in a low level driver it's the responsibility of the HW vendor to run full QA with this HW. ___ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
