Servers: Sun Fire X4240 (both servers) Network: 1Gbps Ethernet Disk: Intel X25-E 32GB SLC
Attempt 1: server1# zpool create X25E c1t15d0 server1# zfs set sharenfs=rw X25E server1# chmod a+w /X25E server2# /bin/time gtar zxf /var/tmp/emacs-22.3.tar.gz real 1:21.5 user 1.4 sys 2.0 + Plenty of SCSI errors that I mentioned in another thread: Jul 7 23:22:38 merope Error for Command: write Error Level: Retryable Jul 7 23:22:38 merope scsi: Requested Block: 98608 Error Block: 98608 Jul 7 23:22:38 merope scsi: Vendor: ATA Serial Number: CVEM849300BM Jul 7 23:22:38 merope scsi: Sense Key: Unit Attention Jul 7 23:22:38 merope scsi: ASC: 0x29 (power on, reset, or bus reset occurred), ASCQ: 0x0, FRU: Attempt 2: server1# format (make two partitions on that SSD disk, s0=4G, s1=16G) server1# zpool create X25E c1t15d0s1 +same commands above server2# /bin/time gtar zxf /var/tmp/emacs-22.3.tar.gz real 35.7 user 1.4 sys 2.0 Same SCSI errors on the console of server1... Hmm... Attempt 3: server1# metainit d0 c1t15d0s0 server1# metainit d1 c1t15d0s1 server1# zpool create X25E /dev/md/dsk/d1 +same commands server2# /bin/time gtar zxf /var/tmp/emacs-22.3.tar.gz real 11.7 user 1.4 sys 2.0 *No* SCSI errors this time. Flawless execution of all commands... Attempt 4 (just add a slog to the same zpool): server1# zpool add X25E log /dev/md/dsk/d0 server2# /bin/time gtar zxf /var/tmp/emacs-22.3.tar.gz real 11.2 user 1.4 sys 1.9 (No SCSI errors here either) -- This message posted from opensolaris.org _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
