similar to: [storage-discuss] SAN arrays with NVRAM cache : ZIL and zfs_nocacheflush

Hi, I read some articles on solarisinternals.com like "ZFS_Evil_Tuning_Guide" on http://www.solarisinternals.com/wiki/index.php/ZFS_Evil_Tuning_Guide . They clearly suggest to disable cache flush http://www.solarisinternals.com/wiki/index.php/ZFS_Evil_Tuning_Guide#FLUSH . It seems to be the only serious article on the net about this subject. Could someone here state on this

-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 hi, i have a system connected to an external DAS (SCSI) array, using ZFS. the array has an nvram write cache, but it honours SCSI cache flush commands by flushing the nvram to disk. the array has no way to disable this behaviour. a well-known behaviour of ZFS is that it often issues cache flush commands to storage in order to ensure data

Hi, I''m running SunOS Release 5.10 Version Generic_118855-36 64-bit and in [b]/etc/system[/b] I put: [b]set zfs:zfs_nocacheflush = 1[/b] And after rebooting, I get the message: [b]sorry, variable ''zfs_nocacheflush'' is not defined in the ''zfs'' module[/b] So is this variable not available in the Solaris kernel? I''m getting really poor

A question regarding zfs_nocacheflush: The Evil Tuning Guide says to only enable this if every device is protected by NVRAM. However, is it safe to enable zfs_nocacheflush when I also have local drives (the internal system drives) using ZFS, in particular if the write cache is disabled on those drives? What I have is a local zfs pool from the free space on the internal drives, so I''m

I have found the following opinion on Vorbis' talk page at wikipedia. It might be something interesting to consider, I suppose. ~*~ "Quality settings run from -1 to 10 and are an arbitrary metric; files encoded at -q5, for example, should have the same quality of sound in all versions of the encoder, but newer versions should be able to achieve that quality with a lower

Hi Derek, Here''s the latest email I''ve received from the zfs-discuss alias. ------------- Begin Forwarded Message ------------- Date: Mon, 18 Sep 2006 23:55:27 -0400 From: Jonathan Edwards <Jonathan.Edwards@sun.com> Subject: Re: [zfs-discuss] ZFS and HDS ShadowImage To: Eric Schrock <eric.schrock@sun.com> Cc: zfs-discuss@opensolaris.org, Torrey McMahon

Hi, With dovecot 1.0.2, depending on the client I can only see inbox, or all the folders. I see all the folders with pine and balsa, but can see only the inbox with squirel mail and thunderbird. Any idea what's going on here ? Thanks. Yves. ---- Yves Dorfsman yves at zioup.com

Is it true that Solaris 10 u4 does not have any of the nice ZIL controls that exist in the various recent Open Solaris flavors? I would like to move my ZIL to solid state storage, but I fear I can''t do it until I have another update. Heck, I would be happy to just be able to turn the ZIL off to see how my NFS on ZFS performance is effected before spending the $''s. Anyone

I will be out of the office starting 06/30/2005 and will not return until 07/06/2005. Please call Ken Milberg at 718-312-5070 or Steve Goldman at 718-312-5075 if you have a midrange issue. Otherwise, I will respond to your note upon my return. "WellChoice, Inc." made the following annotations on 06/30/05 08:02:11

Hi! Even on midrange-systems it's necessary to set "ulimit -n" to a higher value then the system default of 1024. I'd prefer having this already prepared: In /etc/defaults/dovecot we should add: # Set amount of "open files" / ulimit -n ULIMIT_OPEN_FILES=16884 In /etc/init.d/dovecot we should add: # Set amount of open files / ulimit -n [ -n

hi, am trying speex on TI c54x dsp. does anyone has any idea whether we can make both the coder AND decoder run in about 10ms for a 20ms frame for this dsp, looking at narrowband, no VAD/CNG/VBR, using a low complexity, say 1, for a midrange bitrate, say 15kbps? was the c55 dsp able to run real-time on speex for the above configuration? can someone share their timings? tia! oh yes, just

https://bugzilla.samba.org/show_bug.cgi?id=8508 Summary: out of memory in glob_expand_module Product: rsync Version: 3.0.8 Platform: All OS/Version: SunOS Status: NEW Severity: major Priority: P5 Component: core AssignedTo: wayned at samba.org ReportedBy: david at midrange.com

Hello there everybody! Terrific... a mailing-list for compiz with David on board! Ok, I started off with writing some functions using cairo to draw me the needed elements for drop-shadows (atm stand-alone to focus on the proper generation of the shadow-parts) and currently still fiddle with the tweakable parameters. Right now I have... shadow-radius (e.g. 20 pixels) 2D-offset vector (e.g. 10

I'm amazed by how low the artifacts are when encoding with Vorbis, but I found problems (Vorbis version 1.00) on equalization (high vs midrange vs low pitches balance) when encoding my benchmark audio track, problems which are hard to go away even at very high bitrates. My benchmark audio track is composed by me and you can find it here http://www.trombettworks.com/drumswork.php in losslessly

I have a dialplan that looks like this: [dorecord] exten => _*99XX,1,Verbose(2,Doing custom record) exten => _*99XX,n,Answer() exten => _*99XX,n,Verbose(2,Doing custom record - before wait) exten => _*99XX,n,Wait(0.5) exten => _*99XX,n,Verbose(2,Doing custom record - before record) exten => _*99XX,n,Record(/tmp/prompt${EXTEN:3}.gsm) exten => _*99XX,n,Verbose(2,Doing custom

As a matter of interest I tested the quality at -1 which has a nominal bitrate of 45 but the 2 tracks I encoded both averaged out to exactly 48kb/s. I noticed the lowpass defaulted to 15.1khz like -q0 so that may need addressing at some stage. I used a lowpass of 13khz which overall sounded better with less artifacts. I found it sharper & clearer than a lame encoded mp3 encoded with

<FONT face="Default Sans Serif, Verdana, Arial, Helvetica, sans-serif" size=2><DIV>I''m getting requests in increasing regularity for secure file transfers.&nbsp; We''ve been a happy wu-ftpd user for a couple of years, and although wu-ftpd offers a rock solid ftp server, it doesn''t appear to have hooks for secure/encrypted transfers.&nbsp;

Ah, the midrange noise was not entirely the psychoacoustics... I have a mode 0 (effectively a short block) bug. Forcing all short blocks int he encoder (Change the last line of the info_A struct in include/vorbis/modes.h to 64,0,2) makes it very obvious. I'll be hunting/killing that tonight. Greg Maxwell also found that the bitrarte is not dropping to 0kbps in digital silence like it should

I have just tried to rsync a file of 2147500032 bytes (2.0000152587Gb) and got the following error: rsync -Wvaz /db/edwp/temp/edwp_temp_09.dbf klingon::Dest/db/edwp/temp/ building file list ... link_stat /db/edwp/temp/edwp_temp_09.dbf : Value too large for defined data type done wrote 81 bytes read 40 bytes 80.67 bytes/sec total size is 0 speedup is 0.00 Source and

Issue: Vista reads slowly from a samba server. This appears to pop up periodically here and elsewhere. My samba.conf file has: [homes] ... vfs objects = readahead As suggested elsewhere. Writes are approximately 17-18MB/s which is acceptable. Reads are in the 8MB/s range which is appalingly slow. Using linux smbclient and windows XP clients I can read at 25+MB/s. I've enabled vfs