Date: Sat, 7 Dec 1996 21:19:54 +0100 (MET) From: J Wunsch <j@uriah.heep.sax.de> To: freebsd-current@FreeBSD.org (FreeBSD-current users) Cc: croot@btp1da.phy.uni-bayreuth.de (Werner Griessl) Subject: Re: rdump slow Message-ID: <199612072019.VAA22287@uriah.heep.sax.de> In-Reply-To: <199612041026.KAA00900@btp1da.phy.uni-bayreuth.de> from Werner Griessl at "Dec 4, 96 10:26:09 am"
next in thread | previous in thread | raw e-mail | index | archive | help
As Werner Griessl wrote: > rdump in current is very slow, should be ~5 times faster : > > Wed Dec 4 09:57:01 1996 start btp1da:system_save to btp1x5:/dev/nrmt0h > Wed Dec 4 09:57:01 1996 rewinding tape > Wed Dec 4 09:57:07 1996 #1 rdump / ... > DUMP: DUMP: 21409 tape blocks on 1 volumes(s) > > DUMP: finished in 430 seconds, throughput 49 KBytes/sec > ^^^^^^^^^^^^^ !!!!! I can't confirm this. What's your blocksize? What system is the remote TCP peer? Is the tape streaming? That's what i get here: j@uriah 1523% /sbin/dump 0Bbf 5000000 32 localhost:/dev/rst0 / ... DUMP: DUMP: 20154 tape blocks on 1 volumes(s) DUMP: finished in 53 seconds, throughput 380 KBytes/sec ... j@uriah 1524% /sbin/dump 0Bbf 5000000 32 /dev/rst0 / ... DUMP: DUMP: 20154 tape blocks on 1 volumes(s) DUMP: finished in 53 seconds, throughput 380 KBytes/sec So of course, it's been the loopback device, but as long as the Ethernet card in question can handle 380 KB/s (which is not very much), the limiting factor is obviously the tape here. (It's a QIC-2.5GB w/ compression in a Tandberg drive. The 380 KB/s is a normal rate there.) -- cheers, J"org joerg_wunsch@uriah.heep.sax.de -- http://www.sax.de/~joerg/ -- NIC: JW11-RIPE Never trust an operating system you don't have sources for. ;-)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199612072019.VAA22287>