Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On 24/12/12 12:03, Prater, James K. wrote: > Hello Adam, > > You issue is that your secondary peer is running 8Mbyte behind and you could not make it primary without dumping the original primary. > Right, but it's only for a couple of seconds.... ie, it falls behind for a maximum period of 20seconds, (usually 3 - 5 seconds) about 20 times per day. So what I want to know, is how can I "tune" DRBD to buffer an additional 8M of data instead of falling behind? ie, I just need an extra 8M (ok, probably 16M would do it), of write cache on the secondary between DRBD and the drives. Sure, ultimately, buying another 5 x SSD's would resolve the issue, but that just isn't likely to happen any time soon... On 24/12/12 17:49, Christof.r wrote: > In our production environment this works out as expected and using the cluster this way around (SSD as primary) delivers around 5-10x the performance as vice versa. We did test this with loading mdir mailboxes with 20k+ messages in a webmail interface that fetches ALL the messages from the server and then sorts in in the frontend afterwards. > The loading time of such boxes, while SSD is primary, are by magnitudes faster....i.e. 3-4 seconds vs 20-30 (of course while system was in production and thousands of users online) Yep, I want the primary to provide better performance (because of the reads) than the secondary. This shouldn't be a problem, just my secondary is a bit too slow to keep up.... Potentially, upgrading to 6 x 2TB drives in RAID10 would resolve the issue, I can do that with existing hardware, but then I'm wasting 4TB instead of only 2TB, and I lose other options with the extra drives (like setting up a 3rd DRBD server to backup the secondary in a remote location, and just letting it get out of sync every day, and resync each night)... Thanks for your advise, I do appreciate it. Regards, Adam -- Adam Goryachev Website Managers www.websitemanagers.com.au