Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
Matteo Tescione wrote: > Leroy, drbd folks, > > After a while of collecting and profiling my systems i discovered that our > poor performance problems were not related of processor, raid controller or > kernel configuration. > It's all about raid5/6 level configurations that is absolutely unreliable. > > In details reading and writing directly to the raid disk, with an ext3 > partition for example, gives more than 200 mbyte/sec with await and svc time > of approx 1.2 ms versus reading and writing with drbd (either syncing or > live i/o) gives extremely poor performance (i got 30-40 mbyte/sec with 3ware > 9650-8p configured in raid6 and i have 20 mbytes/sec with Compaq Smart Array > p400 configured in raid5 mode. > In both raid5/6 configurations, i/o seems stucked as i've reported in my > previous post with very high iowait values (await up to 5000 ms, svctime up > to 1000 ms) > > Switching to raid0 / raid10 configurations, totally solved our problems. > Sync its up to 200mbyte/sec, live i/o seems good as well but i'm still > testing the vmware infrastructure... > > If anyone has any idea of what's going on.... It seems we have the same problems :-) After you post, i checked my testing servers and i got surprises: with a new hp server with P200 controller and 4 disks in raid 5, i get max 20mb/s :-( I checked few things and i didn't find anything wrong in the conf. We have also another file server with 7 disks in raid 5 and a 3ware card (i think it's a 9550). On that server i got 170 cca mb/s. I know that hp E200 sure it's not as the 3ware card in term of performance, but so low i was not thinking. I tried different kernels (2.6.18-5 debian, 184.108.40.206 and 220.127.116.11) but all the same. This is a test server and the production servers will have P400 cards with 512mbyte of cache and i hope this will solve the problem. I'll try to make some other tests....hope to find find something. Pier