On 30/03/17 09:53, NeilBrown wrote:
On Thu, Mar 30 2017, Brad Campbell wrote:
[==============>......] recovery = 72.0% (4222847296/5860391360)
finish=541.6min speed=50382K/sec
...
[==============>......] recovery = 73.3% (4297641980/5860391360)
finish=284.7min speed=91465K/sec
So that has significantly increased the rebuild speed, as you would expect.
Not quite twice as fast, but close!
It's actually more than twice as fast.
[================>....] recovery = 84.1% (4933147664/5860391360)
finish=151.4min speed=102062K/sec
That sample was taken at an inopportune moment when things were just
getting up to speed. We're progressing towards slower parts of the disk,
and it's still twice as fast as it was.
Everyone has been suffering with that poor speed for years and nobody
noticed until you did. Thanks for being thorough! And thanks for
confirming the patch.
I'm baffled it has been around this long and it hasn't come up previously.
Again, I really appreciate you taking a look at this.
Regards,
Brad
--
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
