Re: [Networker] Compress ASM Theory.
2005-02-14 10:45:31
Hi Shawn
ASMs are executed on the client. So compressasm will be executed on
Server1.
tl
Terry Lemons
CLARiiON Applications Integration Engineering
EMC²
where information lives
4400 Computer Drive, MS D239
Westboro MA 01580
Phone: 508 898 7312
Email: Lemons_Terry AT emc DOT com
-----Original Message-----
From: Legato NetWorker discussion [mailto:NETWORKER AT LISTSERV.TEMPLE DOT EDU]
On
Behalf Of Shawn Cox
Sent: Monday, February 14, 2005 10:32 AM
To: NETWORKER AT LISTSERV.TEMPLE DOT EDU
Subject: [Networker] Compress ASM Theory.
Would like a little input fromt he community re the compressasm
o-Server1 with very fast disks(approx 60MB/sec), and very large (100GB)
uncompressed (but highly comressable) files.
o-Legato Server v7.1.3 server with DBO option. DBO disks are very fast as
well(60MB/sec)
o-compressasm in the directive to which Server1 is a member.
o-Dual teamed Gigabit network on same subnet between Server1 and Legato
Server. Network is the Transport for the savesets from Server1 to the
Legato Server. Normal network throughput is about 20 MB/sec.
No tape hardware in this secnario as tape doesn't come into play until stage
off the DBO disks.
My question is which server does the compression? Is it save.exe on Server1
compressing the data then sending across the wire? Or is the uncompressed
data getting sent across the wire and being comressed at the Legao server
before being written to the DBO disk? My metrics show that the file is
being read at 45-50 MB/sec on Server1, but only being written at 9 MB/sec to
the DBO disks on the Legato Server. I don't see any significant processor
usage by either server during the backup that would indicate a compression
process running.
Any input appreciated.
--Shawn
--
Note: To sign off this list, send a "signoff networker" command via email
to listserv AT listserv.temple DOT edu or visit the list's Web site at
http://listserv.temple.edu/archives/networker.html where you can
also view and post messages to the list. Questions regarding this list
should be sent to stan AT temple DOT edu
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=
--
Note: To sign off this list, send a "signoff networker" command via email
to listserv AT listserv.temple DOT edu or visit the list's Web site at
http://listserv.temple.edu/archives/networker.html where you can
also view and post messages to the list. Questions regarding this list
should be sent to stan AT temple DOT edu
=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=
|
<Prev in Thread] |
Current Thread |
[Next in Thread> |
- Re: [Networker] Compress ASM Theory.,
Terry Lemons <=
|
|
|