Message ID | ce94e108e049ac2b51ef197fa15b1dcf6600c9ca.1465112552.git.mjt@msgid.tls.msk.ru (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
On Sun 05 Jun 2016 09:43:01 AM CEST, Michael Tokarev wrote: > - Water leaks from the bucket at a rate of 100 IOPS. > - Water can be added to the bucket at a rate of 2000 IOPS. > - The size of the bucket is 2000 x 60 = 120000 > - - If 'iops-total-max-length' is unset then the bucket size is 100. > + - If 'iops-total-max' is unset then the bucket size is 100 x 60. Sorry, I should have noticed this here in the pull request, but this is wrong. If 'iops-total-max' is unset the bucket size is 100. It's not 100 x 60 because you can only set 'iops-total-max-length = 60' when 'iops-total-max' is set as well. I'll send a new patch fixing this. Berto
08.06.2016 12:00, Alberto Garcia wrote: > On Sun 05 Jun 2016 09:43:01 AM CEST, Michael Tokarev wrote: > >> - Water leaks from the bucket at a rate of 100 IOPS. >> - Water can be added to the bucket at a rate of 2000 IOPS. >> - The size of the bucket is 2000 x 60 = 120000 >> - - If 'iops-total-max-length' is unset then the bucket size is 100. >> + - If 'iops-total-max' is unset then the bucket size is 100 x 60. > > Sorry, I should have noticed this here in the pull request, but this is > wrong. This has been discussed before, and it looks like the original version which I applied was actually right... :) I can just drop this patch from the pull request, since it hasn't been applied yet. Esp. since the subject line is now wrong too :) Thanks, /mjt
On Wed 08 Jun 2016 11:44:35 AM CEST, Michael Tokarev wrote: > 08.06.2016 12:00, Alberto Garcia wrote: >> On Sun 05 Jun 2016 09:43:01 AM CEST, Michael Tokarev wrote: >> >>> - Water leaks from the bucket at a rate of 100 IOPS. >>> - Water can be added to the bucket at a rate of 2000 IOPS. >>> - The size of the bucket is 2000 x 60 = 120000 >>> - - If 'iops-total-max-length' is unset then the bucket size is 100. >>> + - If 'iops-total-max' is unset then the bucket size is 100 x 60. >> >> Sorry, I should have noticed this here in the pull request, but this is >> wrong. > > This has been discussed before, and it looks like the original version > which I applied was actually right... :) > > I can just drop this patch from the pull request, since it hasn't > been applied yet. Esp. since the subject line is now wrong too :) It's been applied already: https://github.com/qemu/qemu/commit/0bab0ebb17759c926bd48fd396bd8cbb2c8e4a3e I'll send a follow-up patch. Berto
diff --git a/docs/throttle.txt b/docs/throttle.txt index 06ed9b3..26d4d51 100644 --- a/docs/throttle.txt +++ b/docs/throttle.txt @@ -39,7 +39,7 @@ the parameters for both cases: | throttling.bps-write | bps_wr | |-----------------------+-----------------------| -It is possible to set limits for both IOPS and bps and the same time, +It is possible to set limits for both IOPS and bps at the same time, and for each case we can decide whether to have separate read and write limits or not, but note that if iops-total is set then neither iops-read nor iops-write can be set. The same applies to bps-total and @@ -235,7 +235,7 @@ consider the following values: - Water leaks from the bucket at a rate of 100 IOPS. - Water can be added to the bucket at a rate of 2000 IOPS. - The size of the bucket is 2000 x 60 = 120000 - - If 'iops-total-max-length' is unset then the bucket size is 100. + - If 'iops-total-max' is unset then the bucket size is 100 x 60. The bucket is initially empty, therefore water can be added until it's full at a rate of 2000 IOPS (the burst rate). Once the bucket is full