| Message ID | 20220921204356.4336-1-logang@deltatee.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | Write Zeroes option for Creating Arrays | expand |
Hi Logan I like this idea, but I have a question. If we do discard against the member disks and then creating raid device with --assume-clean, it should work with the same result. The reason that you add --write-zero is for automatic doing this? Regards Xiao On Thu, Sep 22, 2022 at 4:44 AM Logan Gunthorpe <logang@deltatee.com> wrote: > > Hi, > > This is the next iteration of the patchset that added the discard > option to mdadm. Per feedback from Martin, it's more desirable > to use the write-zeroes functionality than rely on devices to zero > the data on a discard request. This is because standards typically > only require the device to do the best effort to discard data and > may not actually discard (and thus zero) it all in some circumstances. > > This version of the patch set adds the --write-zeroes option which > will imply --assume-clean and write zeros to the data region in > each disk before starting the array. This can take some time so > each disk is done in parallel in its own fork. To make the forking > code easier to understand this patch set also starts with some > cleanup of the existing Create code. > > We tested write-zeroes requests on a number of modern nvme drives of > various manufacturers and found most are not as optimized as the > discard path. A couple drives that were tested did not support > write-zeroes at all but still performed similarly with the kernel > falling back to writing zero pages. Typically we see it take on the > order of one minute per 100GB of data zeroed. > > One reason write-zeroes is slower than discard is that today's NVMe > devices only allow about 2MB to be zeroed in one command where as > the entire drive can typically be discarded in one command. Partly, > this is a limitation of the spec as there are only 16 bits avalaible > in the write-zeros command size but drives still don't max this out. > Hopefully, in the future this will all be optimized a bit more > and this work will be able to take advantage of that. > > Logan > > -- > > Changes since v2: > > * Use write-zeroes instead of discard to zero the disks (per > Martin) > * Due to the time required to zero the disks, each disk is > now done in parallel with separate forks of the process. > * In order to add the forking some refactoring was done on the > Create() function to make it easier to understand > * Added a pr_info() call so that some prints can be done > to stdout instead of stdour (per Mariusz) > * Added KIB_TO_BYTES and SEC_TO_BYTES helpers (per Mariusz) > * Added a test to the mdadm test suite to test the option > works. > * Fixed up how the size and offset are calculated with some > great information from Xiao. > > Changes since v1: > > * Discard the data in the devices later in the create process > while they are already open. This requires treating the > s.discard option the same as the s.assume_clean option. > Per Mariusz. > * A couple other minor cleanup changes from Mariusz. > > -- > > Logan Gunthorpe (7): > Create: goto abort_locked instead of return 1 in error path > Create: remove safe_mode_delay local variable > Create: Factor out add_disks() helpers > mdadm: Introduce pr_info() > mdadm: Add --write-zeros option for Create > tests/00raid5-zero: Introduce test to exercise --write-zeros. > manpage: Add --write-zeroes option to manpage > > Create.c | 476 ++++++++++++++++++++++++++++----------------- > ReadMe.c | 2 + > mdadm.8.in | 16 ++ > mdadm.c | 9 + > mdadm.h | 9 + > tests/00raid5-zero | 12 ++ > 6 files changed, 349 insertions(+), 175 deletions(-) > create mode 100644 tests/00raid5-zero > > > base-commit: 171e9743881edf2dfb163ddff483566fbf913ccd > -- > 2.30.2 >
On 2022-09-29 23:26, Xiao Ni wrote: > Hi Logan > > I like this idea, but I have a question. If we do discard against the > member disks > and then creating raid device with --assume-clean, it should work with the same > result. The reason that you add --write-zero is for automatic doing this? Yes, that is correct. Logan
Hi, This is the next iteration of the patchset that added the discard option to mdadm. Per feedback from Martin, it's more desirable to use the write-zeroes functionality than rely on devices to zero the data on a discard request. This is because standards typically only require the device to do the best effort to discard data and may not actually discard (and thus zero) it all in some circumstances. This version of the patch set adds the --write-zeroes option which will imply --assume-clean and write zeros to the data region in each disk before starting the array. This can take some time so each disk is done in parallel in its own fork. To make the forking code easier to understand this patch set also starts with some cleanup of the existing Create code. We tested write-zeroes requests on a number of modern nvme drives of various manufacturers and found most are not as optimized as the discard path. A couple drives that were tested did not support write-zeroes at all but still performed similarly with the kernel falling back to writing zero pages. Typically we see it take on the order of one minute per 100GB of data zeroed. One reason write-zeroes is slower than discard is that today's NVMe devices only allow about 2MB to be zeroed in one command where as the entire drive can typically be discarded in one command. Partly, this is a limitation of the spec as there are only 16 bits avalaible in the write-zeros command size but drives still don't max this out. Hopefully, in the future this will all be optimized a bit more and this work will be able to take advantage of that. Logan -- Changes since v2: * Use write-zeroes instead of discard to zero the disks (per Martin) * Due to the time required to zero the disks, each disk is now done in parallel with separate forks of the process. * In order to add the forking some refactoring was done on the Create() function to make it easier to understand * Added a pr_info() call so that some prints can be done to stdout instead of stdour (per Mariusz) * Added KIB_TO_BYTES and SEC_TO_BYTES helpers (per Mariusz) * Added a test to the mdadm test suite to test the option works. * Fixed up how the size and offset are calculated with some great information from Xiao. Changes since v1: * Discard the data in the devices later in the create process while they are already open. This requires treating the s.discard option the same as the s.assume_clean option. Per Mariusz. * A couple other minor cleanup changes from Mariusz. -- Logan Gunthorpe (7): Create: goto abort_locked instead of return 1 in error path Create: remove safe_mode_delay local variable Create: Factor out add_disks() helpers mdadm: Introduce pr_info() mdadm: Add --write-zeros option for Create tests/00raid5-zero: Introduce test to exercise --write-zeros. manpage: Add --write-zeroes option to manpage Create.c | 476 ++++++++++++++++++++++++++++----------------- ReadMe.c | 2 + mdadm.8.in | 16 ++ mdadm.c | 9 + mdadm.h | 9 + tests/00raid5-zero | 12 ++ 6 files changed, 349 insertions(+), 175 deletions(-) create mode 100644 tests/00raid5-zero base-commit: 171e9743881edf2dfb163ddff483566fbf913ccd -- 2.30.2