Hello, I have one more issue with degraded RAID6 array with left-symmetric layout. When I am reading from RAID6 with 3 active drives from 4 the operation is CPU bound on decent CPU and I get max seq read cca 50 MB/s. Drives are modern 150 MB/s HDDs. I did not look into how hard it is to compute data from P / Q yet. Is it that hard that it needs to consume so much CPU performance or is it not optimal implementation in md? Thanks. Patrik -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
