Re: Speeding up garbage collection in RGW

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 

That helps a little bit, but overall the process would take years at this rate:

 

# for i in {1..3600}; do ceph df -f json-pretty |grep -A7 '".rgw.buckets"' |grep objects; sleep 60; done

                "objects": 1660775838

                "objects": 1660775733

                "objects": 1660775548

                "objects": 1660774825

                "objects": 1660774790

                "objects": 1660774735

 

This is on a hammer cluster.  Would upgrading to Jewel or Luminous speed up this process at all?

 

Bryan

 

From: Yehuda Sadeh-Weinraub <yehuda@xxxxxxxxxx>
Date: Wednesday, October 25, 2017 at 11:32 AM
To: Bryan Stillwell <bstillwell@xxxxxxxxxxx>
Cc: David Turner <drakonstein@xxxxxxxxx>, Ben Hines <bhines@xxxxxxxxx>, "ceph-users@xxxxxxxxxxxxxx" <ceph-users@xxxxxxxxxxxxxx>
Subject: Re: [ceph-users] Speeding up garbage collection in RGW

 

Some of the options there won't do much for you as they'll only affect

newer object removals. I think the default number of gc objects is

just inadequate for your needs. You can try manually running

'radosgw-admin gc process' concurrently (for the start 2 or 3

processes), see if it makes any dent there. I think one of the problem

is that the gc omaps grew so much that operations on them are too

slow.

 

Yehuda

 

On Wed, Oct 25, 2017 at 9:05 AM, Bryan Stillwell <bstillwell@xxxxxxxxxxx> wrote:

We tried various options like the one's Ben mentioned to speed up the garbage collection process and were unsuccessful.  Luckily, we had the ability to create a new cluster and move all the data that wasn't part of the POC which created our problem.

 

One of the things we ran into was the .rgw.gc pool became too large to handle drive failures without taking down the cluster.  We eventually had to move that pool to SSDs just to get the cluster healthy.  It was not obvious it was getting large though, because this is what it looked like in the 'ceph df' output:

 

     NAME                   ID     USED      %USED     MAX AVAIL     OBJECTS

     .rgw.gc                17         0         0          235G           2647

 

However, if you look at the SSDs we used (repurposed journal SSDs to get out of the disaster) in 'ceph osd df' you can see quite a bit of data is being used:

 

410 0.20000  1.00000  181G 23090M   158G 12.44 0.18

411 0.20000  1.00000  181G 29105M   152G 15.68 0.22

412 0.20000  1.00000  181G   110G 72223M 61.08 0.86

413 0.20000  1.00000  181G 42964M   139G 23.15 0.33

414 0.20000  1.00000  181G 33530M   148G 18.07 0.26

415 0.20000  1.00000  181G 38420M   143G 20.70 0.29

416 0.20000  1.00000  181G 92215M 93355M 49.69 0.70

417 0.20000  1.00000  181G 64730M   118G 34.88 0.49

418 0.20000  1.00000  181G 61353M   121G 33.06 0.47

419 0.20000  1.00000  181G 77168M   105G 41.58 0.59

 

That's ~560G of omap data for the .rgw.gc pool that isn't being reported in 'ceph df'.

 

Right now the cluster is still around while we wait to verify the new cluster isn't missing anything.  So if there is anything the RGW developers would like to try on it to speed up the gc process, we should be able to do that.

 

Bryan

 

From: ceph-users <ceph-users-bounces@xxxxxxxxxxxxxx> on behalf of David Turner <drakonstein@xxxxxxxxx>

Date: Tuesday, October 24, 2017 at 4:07 PM

To: Ben Hines <bhines@xxxxxxxxx>

Subject: Re: [ceph-users] Speeding up garbage collection in RGW

 

Thank you so much for chiming in, Ben.

 

Can you explain what each setting value means? I believe I understand min wait, that's just how long to wait before allowing the object to be cleaned up.  gc max objs is how many will be cleaned up during each period?  gc processor period is how often it will kick off gc to clean things up?  And gc processor max time is the longest the process can run after the period starts?  Is that about right for that?  I read somewhere saying that prime numbers are optimal for gc max objs.  Do you know why that is?  I notice you're using one there.  What is lc max objs?  I couldn't find a reference for that setting.

 

Additionally, do you know if the radosgw-admin gc list is ever cleaned up, or is it an ever growing list?  I got up to 3.6 Billion objects in the list before I killed the gc list command.

 

On Tue, Oct 24, 2017 at 4:47 PM Ben Hines <bhines@xxxxxxxxx> wrote:

I agree the settings are rather confusing. We also have many millions of objects and had this trouble, so i set these rather aggressive gc settings on our cluster which result in gc almost always running. We also use lifecycles to expire objects.

 

rgw lifecycle work time = 00:01-23:59

rgw gc max objs = 2647

rgw lc max objs = 2647

rgw gc obj min wait = 300

rgw gc processor period = 600

rgw gc processor max time = 600

 

 

-Ben

 

On Tue, Oct 24, 2017 at 9:25 AM, David Turner <drakonstein@xxxxxxxxx> wrote:

As I'm looking into this more and more, I'm realizing how big of a problem garbage collection has been in our clusters.  The biggest cluster has over 1 billion objects in its gc list (the command is still running, it just recently passed by the 1B mark).  Does anyone have any guidance on what to do to optimize the gc settings to hopefully/eventually catch up on this as well as stay caught up once we are?  I'm not expecting an overnight fix, but something that could feasibly be caught up within 6 months would be wonderful.

 

On Mon, Oct 23, 2017 at 11:18 AM David Turner <drakonstein@xxxxxxxxx> wrote:

We recently deleted a bucket that was no longer needed that had 400TB of data in it to help as our cluster is getting quite full.  That should free up about 30% of our cluster used space, but in the last week we haven't seen nearly a fraction of that free up yet.  I left the cluster with this running over the weekend to try to help `radosgw-admin --rgw-realm=local gc process`, but it didn't seem to put a dent into it.  Our regular ingestion is faster than how fast the garbage collection is cleaning stuff up, but our regular ingestion is less than 2% growth at it's maximum.

 

As of yesterday our gc list was over 350GB when dumped into a file (I had to stop it as the disk I was redirecting the output to was almost full).  In the future I will use the --bypass-gc option to avoid the cleanup, but is there a way to speed up the gc once you're in this position?  There were about 8M objects that were deleted from this bucket.  I've come across a few references to the rgw-gc settings in the config, but nothing that explained the times well enough for me to feel comfortable doing anything with them.

 

On Tue, Jul 25, 2017 at 4:01 PM Bryan Stillwell <bstillwell@xxxxxxxxxxx> wrote:

Excellent, thank you!  It does exist in 0.94.10!  :)

 

Bryan

 

From: Pavan Rallabhandi <PRallabhandi@xxxxxxxxxxxxxxx>

Date: Tuesday, July 25, 2017 at 11:21 AM

 

Subject: Re: [ceph-users] Speeding up garbage collection in RGW

 

I’ve just realized that the option is present in Hammer (0.94.10) as well, you should try that.

 

From: Bryan Stillwell <bstillwell@xxxxxxxxxxx>

Date: Tuesday, 25 July 2017 at 9:45 PM

Subject: EXT: Re: [ceph-users] Speeding up garbage collection in RGW

 

Unfortunately, we're on hammer still (0.94.10).  That option looks like it would work better, so maybe it's time to move the upgrade up in the schedule.

 

I've been playing with the various gc options and I haven't seen any speedups like we would need to remove them in a reasonable amount of time.

 

Thanks,

Bryan

 

From: Pavan Rallabhandi <PRallabhandi@xxxxxxxxxxxxxxx>

Date: Tuesday, July 25, 2017 at 3:00 AM

Subject: Re: [ceph-users] Speeding up garbage collection in RGW

 

If your Ceph version is >=Jewel, you can try the `--bypass-gc` option in radosgw-admin, which would remove the tails objects as well without marking them to be GCed.

 

Thanks,

 

On 25/07/17, 1:34 AM, "ceph-users on behalf of Bryan Stillwell" <ceph-users-bounces@xxxxxxxxxxxxxx on behalf of bstillwell@xxxxxxxxxxx> wrote:

 

     I'm in the process of cleaning up a test that an internal customer did on our production cluster that produced over a billion objects spread across 6000 buckets.  So far I've been removing the buckets like this:

 

     printf %s\\n bucket{1..6000} | xargs -I{} -n 1 -P 32 radosgw-admin bucket rm --bucket={} --purge-objects

 

     However, the disk usage doesn't seem to be getting reduced at the same rate the objects are being removed.  From what I can tell a large number of the objects are waiting for garbage collection.

 

     When I first read the docs it sounded like the garbage collector would only remove 32 objects every hour, but after looking through the logs I'm seeing about 55,000 objects removed every hour.  That's about 1.3 million a day, so at this rate it'll take a couple years to clean up the rest!  For comparison, the purge-objects command above is removing (but not GC'ing) about 30 million objects a day, so a much more manageable 33 days to finish.

 

     I've done some digging and it appears like I should be changing these configuration options:

 

     rgw gc max objs (default: 32)

     rgw gc obj min wait (default: 7200)

     rgw gc processor max time (default: 3600)

     rgw gc processor period (default: 3600)

 

     A few questions I have though are:

 

     Should 'rgw gc processor max time' and 'rgw gc processor period' always be set to the same value?

 

     Which would be better, increasing 'rgw gc max objs' to something like 1024, or reducing the 'rgw gc processor' times to something like 60 seconds?

 

     Any other guidance on the best way to adjust these values?

 

     Thanks,

     Bryan

 

 

     _______________________________________________

     ceph-users mailing list

 

 

 

_______________________________________________

ceph-users mailing list

 

_______________________________________________

ceph-users mailing list

 

 

_______________________________________________

ceph-users mailing list

 

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]

  Powered by Linux