Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Nate Carlson wrote: > > Hey all, > > I'm setting up DRBD between two identical boxes (Xeon 2.8ghz, 3ware > 8506-4LP's, 4 160gb SATA drives in RAID5), with a pair of GigE cards > bonded together (iptraf says I can get about 1.8gbits/sec across the > link). I'm running Debian Testing with a 2.6.10 kernel and drbd 0.7.10. > <SNIP> > I can start the disk ok, but I've been running mkfs.ext3 on it for 1h45m > now, and it's still not done: > > Writing inode tables: 2282/3434 > > Also, the sync is going very slow: > > 1: cs:SyncSource st:Primary/Secondary ld:Consistent > ns:22596892 nr:0 dw:4267388 dr:18345948 al:1947 bm:1133 lo:2 pe:74 ua:4096 ap:47 > [=>..................] sync'ed: 5.2% (402553/424334)M > finish: 13:28:15 speed: 8,448 (6,840) K/sec > > Both boxes are also showing a high load average (server1 is primary, and > is at ~2; server2 is secondary, and is at ~1). Brand new systems, fresh out of the box? A few quick questions: 1) have each of the raid 5 arrays gotten finished building themselves? The drive arrays I got first required time to do some kind of setup. After I told the drive array that it was raid 5, it took ~4 hours and the drives were unusable until it was finished. 2) did you know that when you setup drbd against the disks the first time it has to do a full sync between the drives to get them to the same state, i.e. all 424334M has to be transferred? This could mean your mkfs.ext3 is causing the disk to seek between where mkfs is writing and where drbd is reading (these might be quite a bit apart) and this slows both down. You might try putting the mkfs to sleep and see what the sync rate goes to. -- Todd Denniston Crane Division, Naval Surface Warfare Center (NSWC Crane) Harnessing the Power of Technology for the Warfighter