<div dir="ltr">Hi Kotresh,<div><br></div><div>2280 is a brick process, i have not tried with dist-rep volume? </div><div><br></div><div>I have not seen any fd in bitd process in any of the node's and bitd process usage always 0% CPU and randomly it goes 0.3% CPU.</div><div><br></div><div><br></div><div><br></div><div>Thanks,</div><div>Amudhan</div><div><br>On Thursday, September 22, 2016, Kotresh Hiremath Ravishankar <<a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>> wrote:<br>> Hi Amudhan,<br>><br>> No, bitrot signer is a different process by itself and is not part of brick process.<br>> I believe the process 2280 is a brick process ? Did you check with dist-rep volume?<br>> Is the same behavior being observed there as well? We need to figure out why brick<br>> process is holding that fd for such a long time.<br>><br>> Thanks and Regards,<br>> Kotresh H R<br>><br>> ----- Original Message -----<br>>> From: "Amudhan P" <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>><br>>> To: "Kotresh Hiremath Ravishankar" <<a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>><br>>> Sent: Wednesday, September 21, 2016 8:15:33 PM<br>>> Subject: Re: [Gluster-users] 3.8.3 Bitrot signature process<br>>><br>>> Hi Kotresh,<br>>><br>>> As soon as fd closes from brick1 pid, i can see bitrot signature for the<br>>> file in brick.<br>>><br>>> So, it looks like fd opened by brick process to calculate signature.<br>>><br>>> output of the file:<br>>><br>>> -rw-r--r-- 2 root root 250M Sep 21 18:32<br>>> /media/disk1/brick1/data/G/<wbr>test59-bs10M-c100.nul<br>>><br>>> getfattr: Removing leading '/' from absolute path names<br>>> # file: media/disk1/brick1/data/G/<wbr>test59-bs10M-c100.nul<br>>> trusted.bit-rot.signature=<wbr>0x010200000000000000e9474e4cc6<wbr>73c0c227a6e807e04aa4ab1f88d374<wbr>4243950a290869c53daa65df<br>>> trusted.bit-rot.version=<wbr>0x020000000000000057d6af320001<wbr>2a13<br>>> trusted.ec.config=<wbr>0x0000080501000200<br>>> trusted.ec.size=<wbr>0x000000003e800000<br>>> trusted.ec.version=<wbr>0x0000000000001f40000000000000<wbr>1f40<br>>> trusted.gfid=<wbr>0x4c091145429448468fffe358482c<wbr>63e1<br>>><br>>> stat /media/disk1/brick1/data/G/<wbr>test59-bs10M-c100.nul<br>>> File: ‘/media/disk1/brick1/data/G/<wbr>test59-bs10M-c100.nul’<br>>> Size: 262144000 Blocks: 512000 IO Block: 4096 regular file<br>>> Device: 811h/2065d Inode: 402653311 Links: 2<br>>> Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/ root)<br>>> Access: 2016-09-21 18:34:43.722712751 +0530<br>>> Modify: 2016-09-21 18:32:41.650712946 +0530<br>>> Change: 2016-09-21 19:14:41.698708914 +0530<br>>> Birth: -<br>>><br>>><br>>> In other 2 bricks in same set, still signature is not updated for the same<br>>> file.<br>>><br>>><br>>> On Wed, Sep 21, 2016 at 6:48 PM, Amudhan P <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>> wrote:<br>>><br>>> > Hi Kotresh,<br>>> ><br>>> > I am very sure, No read was going on from mount point.<br>>> ><br>>> > Again i did same test but after writing data to mount point. I have<br>>> > unmounted mount point.<br>>> ><br>>> > after 120 seconds i am seeing this file fd entry in brick 1 pid<br>>> ><br>>> > getfattr -m. -e hex -d test59-bs10<br>>> > # file: test59-bs10M-c100.nul<br>>> > trusted.bit-rot.version=<wbr>0x020000000000000057bed574000e<wbr>d534<br>>> > trusted.ec.config=<wbr>0x0000080501000200<br>>> > trusted.ec.size=<wbr>0x000000003e800000<br>>> > trusted.ec.version=<wbr>0x0000000000001f40000000000000<wbr>1f40<br>>> > trusted.gfid=<wbr>0x4c091145429448468fffe358482c<wbr>63e1<br>>> ><br>>> ><br>>> > ls -l /proc/2280/fd<br>>> > lr-x------ 1 root root 64 Sep 21 13:08 19 -> /media/disk1/brick1/.<br>>> > glusterfs/4c/09/4c091145-4294-<wbr>4846-8fff-e358482c63e1<br>>> ><br>>> > Volume is a EC - 4+1<br>>> ><br>>> > On Wed, Sep 21, 2016 at 6:17 PM, Kotresh Hiremath Ravishankar <<br>>> > <a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>> wrote:<br>>> ><br>>> >> Hi Amudhan,<br>>> >><br>>> >> If you see the ls output, some process has a fd opened in the backend.<br>>> >> That is the reason bitrot is not considering for the signing.<br>>> >> Could you please observe, after 120 secs of closure of<br>>> >> "/media/disk2/brick2/.<wbr>glusterfs/6e/7c/6e7c49e6-094e-<wbr>4435-<br>>> >> 85bf-f21f99fd8764"<br>>> >> the signing happens. If so we need to figure out who holds this fd for<br>>> >> such a long time.<br>>> >> And also we need to figure is this issue specific to EC volume.<br>>> >><br>>> >> Thanks and Regards,<br>>> >> Kotresh H R<br>>> >><br>>> >> ----- Original Message -----<br>>> >> > From: "Amudhan P" <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>><br>>> >> > To: "Kotresh Hiremath Ravishankar" <<a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>><br>>> >> > Cc: "Gluster Users" <<a href="mailto:gluster-users@gluster.org" target="_blank">gluster-users@gluster.org</a>><br>>> >> > Sent: Wednesday, September 21, 2016 4:56:40 PM<br>>> >> > Subject: Re: [Gluster-users] 3.8.3 Bitrot signature process<br>>> >> ><br>>> >> > Hi Kotresh,<br>>> >> ><br>>> >> ><br>>> >> > Writing new file.<br>>> >> ><br>>> >> > getfattr -m. -e hex -d /media/disk2/brick2/data/G/<wbr>test58-bs10M-c100.nul<br>>> >> > getfattr: Removing leading '/' from absolute path names<br>>> >> > # file: media/disk2/brick2/data/G/<wbr>test58-bs10M-c100.nul<br>>> >> > trusted.bit-rot.version=<wbr>0x020000000000000057da8b23000b<wbr>120e<br>>> >> > trusted.ec.config=<wbr>0x0000080501000200<br>>> >> > trusted.ec.size=<wbr>0x000000003e800000<br>>> >> > trusted.ec.version=<wbr>0x0000000000001f40000000000000<wbr>1f40<br>>> >> > trusted.gfid=<wbr>0x6e7c49e6094e443585bff21f99fd<wbr>8764<br>>> >> ><br>>> >> ><br>>> >> > Running ls -l in brick 2 pid<br>>> >> ><br>>> >> > ls -l /proc/30162/fd<br>>> >> ><br>>> >> > lr-x------ 1 root root 64 Sep 21 16:22 59 -><br>>> >> > /media/disk2/brick2/.<wbr>glusterfs/quanrantine<br>>> >> > lrwx------ 1 root root 64 Sep 21 16:22 6 -><br>>> >> > /var/lib/glusterd/vols/<wbr>glsvol1/run/10.1.2.2-media-<wbr>disk2-brick2.pid<br>>> >> > lr-x------ 1 root root 64 Sep 21 16:25 60 -><br>>> >> > /media/disk2/brick2/.<wbr>glusterfs/6e/7c/6e7c49e6-094e-<wbr>4435-<br>>> >> 85bf-f21f99fd8764<br>>> >> > lr-x------ 1 root root 64 Sep 21 16:22 61 -><br>>> >> > /media/disk2/brick2/.<wbr>glusterfs/quanrantine<br>>> >> ><br>>> >> ><br>>> >> > find /media/disk2/ -samefile<br>>> >> > /media/disk2/brick2/.<wbr>glusterfs/6e/7c/6e7c49e6-094e-<wbr>4435-<br>>> >> 85bf-f21f99fd8764<br>>> >> > /media/disk2/brick2/.<wbr>glusterfs/6e/7c/6e7c49e6-094e-<wbr>4435-<br>>> >> 85bf-f21f99fd8764<br>>> >> > /media/disk2/brick2/data/G/<wbr>test58-bs10M-c100.nul<br>>> >> ><br>>> >> ><br>>> >> ><br>>> >> > On Wed, Sep 21, 2016 at 3:28 PM, Kotresh Hiremath Ravishankar <<br>>> >> > <a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>> wrote:<br>>> >> ><br>>> >> > > Hi Amudhan,<br>>> >> > ><br>>> >> > > Don't grep for the filename, glusterfs maintains hardlink in<br>>> >> .glusterfs<br>>> >> > > directory<br>>> >> > > for each file. Just check 'ls -l /proc/<respective brick pid>/fd' for<br>>> >> any<br>>> >> > > fds opened<br>>> >> > > for a file in .glusterfs and check if it's the same file.<br>>> >> > ><br>>> >> > > Thanks and Regards,<br>>> >> > > Kotresh H R<br>>> >> > ><br>>> >> > > ----- Original Message -----<br>>> >> > > > From: "Amudhan P" <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>><br>>> >> > > > To: "Kotresh Hiremath Ravishankar" <<a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>><br>>> >> > > > Cc: "Gluster Users" <<a href="mailto:gluster-users@gluster.org" target="_blank">gluster-users@gluster.org</a>><br>>> >> > > > Sent: Wednesday, September 21, 2016 1:33:10 PM<br>>> >> > > > Subject: Re: [Gluster-users] 3.8.3 Bitrot signature process<br>>> >> > > ><br>>> >> > > > Hi Kotresh,<br>>> >> > > ><br>>> >> > > > i have used below command to verify any open fd for file.<br>>> >> > > ><br>>> >> > > > "ls -l /proc/*/fd | grep filename".<br>>> >> > > ><br>>> >> > > > as soon as write completes there no open fd's, if there is any<br>>> >> alternate<br>>> >> > > > option. please let me know will also try that.<br>>> >> > > ><br>>> >> > > ><br>>> >> > > ><br>>> >> > > ><br>>> >> > > > Also, below is my scrub status in my test setup. number of skipped<br>>> >> files<br>>> >> > > > slow reducing day by day. I think files are skipped due to bitrot<br>>> >> > > signature<br>>> >> > > > process is not completed yet.<br>>> >> > > ><br>>> >> > > > where can i see scrub skipped files?<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > Volume name : glsvol1<br>>> >> > > ><br>>> >> > > > State of scrub: Active (Idle)<br>>> >> > > ><br>>> >> > > > Scrub impact: normal<br>>> >> > > ><br>>> >> > > > Scrub frequency: daily<br>>> >> > > ><br>>> >> > > > Bitrot error log location: /var/log/glusterfs/bitd.log<br>>> >> > > ><br>>> >> > > > Scrubber error log location: /var/log/glusterfs/scrub.log<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > > Node: localhost<br>>> >> > > ><br>>> >> > > > Number of Scrubbed files: 1644<br>>> >> > > ><br>>> >> > > > Number of Skipped files: 1001<br>>> >> > > ><br>>> >> > > > Last completed scrub time: 2016-09-20 11:59:58<br>>> >> > > ><br>>> >> > > > Duration of last scrub (D:M:H:M:S): 0:0:39:26<br>>> >> > > ><br>>> >> > > > Error count: 0<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > > Node: 10.1.2.3<br>>> >> > > ><br>>> >> > > > Number of Scrubbed files: 1644<br>>> >> > > ><br>>> >> > > > Number of Skipped files: 1001<br>>> >> > > ><br>>> >> > > > Last completed scrub time: 2016-09-20 10:50:00<br>>> >> > > ><br>>> >> > > > Duration of last scrub (D:M:H:M:S): 0:0:38:17<br>>> >> > > ><br>>> >> > > > Error count: 0<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > > Node: 10.1.2.4<br>>> >> > > ><br>>> >> > > > Number of Scrubbed files: 981<br>>> >> > > ><br>>> >> > > > Number of Skipped files: 1664<br>>> >> > > ><br>>> >> > > > Last completed scrub time: 2016-09-20 12:38:01<br>>> >> > > ><br>>> >> > > > Duration of last scrub (D:M:H:M:S): 0:0:35:19<br>>> >> > > ><br>>> >> > > > Error count: 0<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > > Node: 10.1.2.1<br>>> >> > > ><br>>> >> > > > Number of Scrubbed files: 1263<br>>> >> > > ><br>>> >> > > > Number of Skipped files: 1382<br>>> >> > > ><br>>> >> > > > Last completed scrub time: 2016-09-20 11:57:21<br>>> >> > > ><br>>> >> > > > Duration of last scrub (D:M:H:M:S): 0:0:37:17<br>>> >> > > ><br>>> >> > > > Error count: 0<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > > Node: 10.1.2.2<br>>> >> > > ><br>>> >> > > > Number of Scrubbed files: 1644<br>>> >> > > ><br>>> >> > > > Number of Skipped files: 1001<br>>> >> > > ><br>>> >> > > > Last completed scrub time: 2016-09-20 11:59:25<br>>> >> > > ><br>>> >> > > > Duration of last scrub (D:M:H:M:S): 0:0:39:18<br>>> >> > > ><br>>> >> > > > Error count: 0<br>>> >> > > ><br>>> >> > > > ==============================<wbr>===========================<br>>> >> > > ><br>>> >> > > ><br>>> >> > > ><br>>> >> > > ><br>>> >> > > > Thanks<br>>> >> > > > Amudhan<br>>> >> > > ><br>>> >> > > ><br>>> >> > > > On Wed, Sep 21, 2016 at 11:45 AM, Kotresh Hiremath Ravishankar <<br>>> >> > > > <a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>> wrote:<br>>> >> > > ><br>>> >> > > > > Hi Amudhan,<br>>> >> > > > ><br>>> >> > > > > I don't think it's the limitation with read data from the brick.<br>>> >> > > > > To limit the usage of CPU, throttling is done using token bucket<br>>> >> > > > > algorithm. The log message showed is related to it. But even then<br>>> >> > > > > I think it should not take 12 minutes for check-sum calculation<br>>> >> unless<br>>> >> > > > > there is an fd open (might be internal). Could you please cross<br>>> >> verify<br>>> >> > > > > if there are any fd opened on that file by looking into /proc? I<br>>> >> will<br>>> >> > > > > also test it out in the mean time and get back to you.<br>>> >> > > > ><br>>> >> > > > > Thanks and Regards,<br>>> >> > > > > Kotresh H R<br>>> >> > > > ><br>>> >> > > > > ----- Original Message -----<br>>> >> > > > > > From: "Amudhan P" <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>><br>>> >> > > > > > To: "Kotresh Hiremath Ravishankar" <<a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>><br>>> >> > > > > > Cc: "Gluster Users" <<a href="mailto:gluster-users@gluster.org" target="_blank">gluster-users@gluster.org</a>><br>>> >> > > > > > Sent: Tuesday, September 20, 2016 3:19:28 PM<br>>> >> > > > > > Subject: Re: [Gluster-users] 3.8.3 Bitrot signature process<br>>> >> > > > > ><br>>> >> > > > > > Hi Kotresh,<br>>> >> > > > > ><br>>> >> > > > > > Please correct me if i am wrong, Once a file write completes<br>>> >> and as<br>>> >> > > soon<br>>> >> > > > > as<br>>> >> > > > > > closes fds, bitrot waits for 120 seconds and starts hashing and<br>>> >> > > update<br>>> >> > > > > > signature for the file in brick.<br>>> >> > > > > ><br>>> >> > > > > > But, what i am feeling that bitrot takes too much of time to<br>>> >> complete<br>>> >> > > > > > hashing.<br>>> >> > > > > ><br>>> >> > > > > > below is test result i would like to share.<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > writing data in below path using dd :<br>>> >> > > > > ><br>>> >> > > > > > /mnt/gluster/data/G (mount point)<br>>> >> > > > > > -rw-r--r-- 1 root root 10M Sep 20 12:19 test53-bs10M-c1.nul<br>>> >> > > > > > -rw-r--r-- 1 root root 100M Sep 20 12:19 test54-bs10M-c10.nul<br>>> >> > > > > ><br>>> >> > > > > > No any other write or read process is going on.<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > Checking file data in one of the brick.<br>>> >> > > > > ><br>>> >> > > > > > -rw-r--r-- 2 root root 2.5M Sep 20 12:23 test53-bs10M-c1.nul<br>>> >> > > > > > -rw-r--r-- 2 root root 25M Sep 20 12:23 test54-bs10M-c10.nul<br>>> >> > > > > ><br>>> >> > > > > > file's stat and getfattr info from brick, after write process<br>>> >> > > completed.<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ stat<br>>> >> test53-bs10M-c1.nul<br>>> >> > > > > > File: ‘test53-bs10M-c1.nul’<br>>> >> > > > > > Size: 2621440 Blocks: 5120 IO Block: 4096<br>>> >> regular<br>>> >> > > file<br>>> >> > > > > > Device: 821h/2081d Inode: 536874168 Links: 2<br>>> >> > > > > > Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/<br>>> >> > > root)<br>>> >> > > > > > Access: 2016-09-20 12:23:28.798886647 +0530<br>>> >> > > > > > Modify: 2016-09-20 12:23:28.994886646 +0530<br>>> >> > > > > > Change: 2016-09-20 12:23:28.998886646 +0530<br>>> >> > > > > > Birth: -<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ stat<br>>> >> test54-bs10M-c10.nul<br>>> >> > > > > > File: ‘test54-bs10M-c10.nul’<br>>> >> > > > > > Size: 26214400 Blocks: 51200 IO Block: 4096<br>>> >> regular<br>>> >> > > file<br>>> >> > > > > > Device: 821h/2081d Inode: 536874169 Links: 2<br>>> >> > > > > > Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/<br>>> >> > > root)<br>>> >> > > > > > Access: 2016-09-20 12:23:42.902886624 +0530<br>>> >> > > > > > Modify: 2016-09-20 12:23:44.378886622 +0530<br>>> >> > > > > > Change: 2016-09-20 12:23:44.378886622 +0530<br>>> >> > > > > > Birth: -<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ sudo getfattr -m. -e<br>>> >> hex -d<br>>> >> > > > > > test53-bs10M-c1.nul<br>>> >> > > > > > # file: test53-bs10M-c1.nul<br>>> >> > > > > > trusted.bit-rot.version=<wbr>0x020000000000000057daa7b50002<wbr>e5b4<br>>> >> > > > > > trusted.ec.config=<wbr>0x0000080501000200<br>>> >> > > > > > trusted.ec.size=<wbr>0x0000000000a00000<br>>> >> > > > > > trusted.ec.version=<wbr>0x0000000000000050000000000000<wbr>0050<br>>> >> > > > > > trusted.gfid=<wbr>0xe2416bd1aae4403c88f44286273b<wbr>be99<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ sudo getfattr -m. -e<br>>> >> hex -d<br>>> >> > > > > > test54-bs10M-c10.nul<br>>> >> > > > > > # file: test54-bs10M-c10.nul<br>>> >> > > > > > trusted.bit-rot.version=<wbr>0x020000000000000057daa7b50002<wbr>e5b4<br>>> >> > > > > > trusted.ec.config=<wbr>0x0000080501000200<br>>> >> > > > > > trusted.ec.size=<wbr>0x0000000006400000<br>>> >> > > > > > trusted.ec.version=<wbr>0x0000000000000320000000000000<wbr>0320<br>>> >> > > > > > trusted.gfid=<wbr>0x54e018dd8c5a4bd79e0317729d8a<wbr>57c5<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > file's stat and getfattr info from brick, after bitrot signature<br>>> >> > > updated.<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ stat<br>>> >> test53-bs10M-c1.nul<br>>> >> > > > > > File: ‘test53-bs10M-c1.nul’<br>>> >> > > > > > Size: 2621440 Blocks: 5120 IO Block: 4096<br>>> >> regular<br>>> >> > > file<br>>> >> > > > > > Device: 821h/2081d Inode: 536874168 Links: 2<br>>> >> > > > > > Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/<br>>> >> > > root)<br>>> >> > > > > > Access: 2016-09-20 12:25:31.494886450 +0530<br>>> >> > > > > > Modify: 2016-09-20 12:23:28.994886646 +0530<br>>> >> > > > > > Change: 2016-09-20 12:27:00.994886307 +0530<br>>> >> > > > > > Birth: -<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ sudo getfattr -m. -e<br>>> >> hex -d<br>>> >> > > > > > test53-bs10M-c1.nul<br>>> >> > > > > > # file: test53-bs10M-c1.nul<br>>> >> > > > > > trusted.bit-rot.signature=<wbr>0x0102000000000000006de7493c5c<br>>> >> > > > > 90f643357c268fbaaf461c1567e033<wbr>4e4948023ce17268403aa37a<br>>> >> > > > > > trusted.bit-rot.version=<wbr>0x020000000000000057daa7b50002<wbr>e5b4<br>>> >> > > > > > trusted.ec.config=<wbr>0x0000080501000200<br>>> >> > > > > > trusted.ec.size=<wbr>0x0000000000a00000<br>>> >> > > > > > trusted.ec.version=<wbr>0x0000000000000050000000000000<wbr>0050<br>>> >> > > > > > trusted.gfid=<wbr>0xe2416bd1aae4403c88f44286273b<wbr>be99<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ stat<br>>> >> test54-bs10M-c10.nul<br>>> >> > > > > > File: ‘test54-bs10M-c10.nul’<br>>> >> > > > > > Size: 26214400 Blocks: 51200 IO Block: 4096<br>>> >> regular<br>>> >> > > file<br>>> >> > > > > > Device: 821h/2081d Inode: 536874169 Links: 2<br>>> >> > > > > > Access: (0644/-rw-r--r--) Uid: ( 0/ root) Gid: ( 0/<br>>> >> > > root)<br>>> >> > > > > > Access: 2016-09-20 12:25:47.510886425 +0530<br>>> >> > > > > > Modify: 2016-09-20 12:23:44.378886622 +0530<br>>> >> > > > > > Change: 2016-09-20 12:38:05.954885243 +0530<br>>> >> > > > > > Birth: -<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ sudo getfattr -m. -e<br>>> >> hex -d<br>>> >> > > > > > test54-bs10M-c10.nul<br>>> >> > > > > > # file: test54-bs10M-c10.nul<br>>> >> > > > > > trusted.bit-rot.signature=<wbr>0x010200000000000000394c345f0b<br>>> >> > > > > 0c63ee652627a62eed069244d35c4d<wbr>5134e4f07d4eabb51afda47e<br>>> >> > > > > > trusted.bit-rot.version=<wbr>0x020000000000000057daa7b50002<wbr>e5b4<br>>> >> > > > > > trusted.ec.config=<wbr>0x0000080501000200<br>>> >> > > > > > trusted.ec.size=<wbr>0x0000000006400000<br>>> >> > > > > > trusted.ec.version=<wbr>0x0000000000000320000000000000<wbr>0320<br>>> >> > > > > > trusted.gfid=<wbr>0x54e018dd8c5a4bd79e0317729d8a<wbr>57c5<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > (Actual time taken for reading file from brick for md5sum)<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ time md5sum<br>>> >> > > test53-bs10M-c1.nul<br>>> >> > > > > > 8354dcaa18a1ecb52d0895bf00888c<wbr>44 test53-bs10M-c1.nul<br>>> >> > > > > ><br>>> >> > > > > > real 0m0.045s<br>>> >> > > > > > user 0m0.007s<br>>> >> > > > > > sys 0m0.003s<br>>> >> > > > > ><br>>> >> > > > > > gfstst-node5:/media/disk2/<wbr>brick2/data/G$ time md5sum<br>>> >> > > > > test54-bs10M-c10.nul<br>>> >> > > > > > bed3c0a4a1407f584989b4009e9ce3<wbr>3f test54-bs10M-c10.nul<br>>> >> > > > > ><br>>> >> > > > > > real 0m0.166s<br>>> >> > > > > > user 0m0.062s<br>>> >> > > > > > sys 0m0.011s<br>>> >> > > > > ><br>>> >> > > > > > As you can see that 'test54-bs10M-c10.nul' file took around 12<br>>> >> > > minutes to<br>>> >> > > > > > update bitort signature (pls refer stat output for the file).<br>>> >> > > > > ><br>>> >> > > > > > what would be the cause for such a slow read?. Any limitation<br>>> >> in read<br>>> >> > > > > data<br>>> >> > > > > > from brick?<br>>> >> > > > > ><br>>> >> > > > > > Also, i am seeing this line bitd.log, what does this mean?<br>>> >> > > > > > [bit-rot.c:1784:br_rate_limit_<wbr>signer] 0-glsvol1-bit-rot-0:<br>>> >> [Rate<br>>> >> > > Limit<br>>> >> > > > > > Info] "tokens/sec (rate): 131072, maxlimit: 524288<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > Thanks<br>>> >> > > > > > Amudhan P<br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > ><br>>> >> > > > > > On Mon, Sep 19, 2016 at 1:00 PM, Kotresh Hiremath Ravishankar <<br>>> >> > > > > > <a href="mailto:khiremat@redhat.com" target="_blank">khiremat@redhat.com</a>> wrote:<br>>> >> > > > > ><br>>> >> > > > > > > Hi Amudhan,<br>>> >> > > > > > ><br>>> >> > > > > > > Thanks for testing out the bitrot feature and sorry for the<br>>> >> delayed<br>>> >> > > > > > > response.<br>>> >> > > > > > > Please find the answers inline.<br>>> >> > > > > > ><br>>> >> > > > > > > Thanks and Regards,<br>>> >> > > > > > > Kotresh H R<br>>> >> > > > > > ><br>>> >> > > > > > > ----- Original Message -----<br>>> >> > > > > > > > From: "Amudhan P" <<a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a>><br>>> >> > > > > > > > To: "Gluster Users" <<a href="mailto:gluster-users@gluster.org" target="_blank">gluster-users@gluster.org</a>><br>>> >> > > > > > > > Sent: Friday, September 16, 2016 4:14:10 PM<br>>> >> > > > > > > > Subject: Re: [Gluster-users] 3.8.3 Bitrot signature process<br>>> >> > > > > > > ><br>>> >> > > > > > > > Hi,<br>>> >> > > > > > > ><br>>> >> > > > > > > > Can anyone reply to this mail.<br>>> >> > > > > > > ><br>>> >> > > > > > > > On Tue, Sep 13, 2016 at 12:49 PM, Amudhan P <<br>>> >> > > <a href="mailto:amudhan83@gmail.com" target="_blank">amudhan83@gmail.com</a> ><br>>> >> > > > > > > wrote:<br>>> >> > > > > > > ><br>>> >> > > > > > > ><br>>> >> > > > > > > ><br>>> >> > > > > > > > Hi,<br>>> >> > > > > > > ><br>>> >> > > > > > > > I am testing bitrot feature in Gluster 3.8.3 with disperse<br>>> >> EC<br>>> >> > > volume<br>>> >> > > > > 4+1.<br>>> >> > > > > > > ><br>>> >> > > > > > > > When i write single small file (< 10MB) after 2 seconds i<br>>> >> can see<br>>> >> > > > > bitrot<br>>> >> > > > > > > > signature in bricks for the file, but when i write multiple<br>>> >> files<br>>> >> > > > > with<br>>> >> > > > > > > > different size ( > 10MB) it takes long time (> 24hrs) to see<br>>> >> > > bitrot<br>>> >> > > > > > > > signature in all the files.<br>>> >> > > > > > ><br>>> >> > > > > > > The default timeout for signing to happen is 120 seconds.<br>>> >> So the<br>>> >> > > > > > > signing will happen<br>>> >> > > > > > > 120 secs after the last fd gets closed on that file. So if<br>>> >> the<br>>> >> > > file<br>>> >> > > > > is<br>>> >> > > > > > > being written<br>>> >> > > > > > > continuously, it will not be signed until 120 secs after<br>>> >> it's<br>>> >> > > last<br>>> >> > > > > fd is<br>>> >> > > > > > > closed.<br>>> >> > > > > > > ><br>>> >> > > > > > > > My questions are.<br>>> >> > > > > > > > 1. I have enabled scrub schedule as hourly and throttle as<br>>> >> > > normal,<br>>> >> > > > > does<br>>> >> > > > > > > this<br>>> >> > > > > > > > make any impact in delaying bitrot signature?<br>>> >> > > > > > > No.<br>>> >> > > > > > > > 2. other than "bitd.log" where else i can watch current<br>>> >> status of<br>>> >> > > > > bitrot,<br>>> >> > > > > > > > like number of files added for signature and file status?<br>>> >> > > > > > > Signature will happen after 120 sec of last fd closure,<br>>> >> as<br>>> >> > > said<br>>> >> > > > > above.<br>>> >> > > > > > > There is not status command which tracks the signature<br>>> >> of the<br>>> >> > > > > files.<br>>> >> > > > > > > But there is bitrot status command which tracks the<br>>> >> number of<br>>> >> > > > > files<br>>> >> > > > > > > scrubbed.<br>>> >> > > > > > ><br>>> >> > > > > > > #gluster vol bitrot <volname> scrub status<br>>> >> > > > > > ><br>>> >> > > > > > ><br>>> >> > > > > > > > 3. where i can confirm that all the files in the brick are<br>>> >> bitrot<br>>> >> > > > > signed?<br>>> >> > > > > > ><br>>> >> > > > > > > As said, signing information of all the files is not<br>>> >> tracked.<br>>> >> > > > > > ><br>>> >> > > > > > > > 4. is there any file read size limit in bitrot?<br>>> >> > > > > > ><br>>> >> > > > > > > I didn't get. Could you please elaborate this ?<br>>> >> > > > > > ><br>>> >> > > > > > > > 5. options for tuning bitrot for faster signing of files?<br>>> >> > > > > > ><br>>> >> > > > > > > Bitrot feature is mainly to detect silent corruption<br>>> >> > > (bitflips) of<br>>> >> > > > > > > files due to long<br>>> >> > > > > > > term storage. Hence the default is 120 sec of last fd<br>>> >> > > closure, the<br>>> >> > > > > > > signing happens.<br>>> >> > > > > > > But there is a tune able which can change the default<br>>> >> 120 sec<br>>> >> > > but<br>>> >> > > > > > > that's only for<br>>> >> > > > > > > testing purposes and we don't recommend it.<br>>> >> > > > > > ><br>>> >> > > > > > > gluster vol get master features.expiry-time<br>>> >> > > > > > ><br>>> >> > > > > > > For testing purposes, you can change this default and<br>>> >> test.<br>>> >> > > > > > > ><br>>> >> > > > > > > > Thanks<br>>> >> > > > > > > > Amudhan<br>>> >> > > > > > > ><br>>> >> > > > > > > ><br>>> >> > > > > > > > ______________________________<wbr>_________________<br>>> >> > > > > > > > Gluster-users mailing list<br>>> >> > > > > > > > <a href="mailto:Gluster-users@gluster.org" target="_blank">Gluster-users@gluster.org</a><br>>> >> > > > > > > > <a href="http://www.gluster.org/mailman/listinfo/gluster-users" target="_blank">http://www.gluster.org/<wbr>mailman/listinfo/gluster-users</a><br>>> >> > > > > > ><br>>> >> > > > > ><br>>> >> > > > ><br>>> >> > > ><br>>> >> > ><br>>> >> ><br>>> >><br>>> ><br>>> ><br>>><br>>
</div></div>