On 1/14/24 13:47, gene heskett wrote:
Regardless of the sata port/card this 5th SSD is plugged into, it
appears to me that rsync is overpowering the SSD's write bandwidth and
somewhere between 13.5Gb of data to around 45Gb of data copied, I wind
up with a machine that begins to stutter a bit, and finally htop says
rsync is down to zero cpu, and maybe one more file locks everything but
the mouse up, it still moves but the clock and the rest of the machine
has stopped. This may take 5 minutes, maybe 15 but its the same story 5
times now. by the time I've rebooted, smartctl give the SSD a clean bill
of health. or did til this last try, now it says, for that drive:
ene@coyote:~/src/klipper-docs$ sudo smartctl -a /dev/sde
[sudo] password for gene:
smartctl 7.3 2022-02-28 r5338 [x86_64-linux-6.1.0-17-rt-amd64] (local
build)
,,,
SMART Attributes Data Structure revision number: 1
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED
WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x0032 100 100 050 Old_age
Always - 0
5 Reallocated_Sector_Ct 0x0032 100 100 050 Old_age
Always - 0
9 Power_On_Hours 0x0032 100 100 050 Old_age
Always - 912
12 Power_Cycle_Count 0x0032 100 100 050 Old_age
Always - 7
160 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 0
161 Unknown_Attribute 0x0033 100 100 050 Pre-fail Always
- 100
163 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 10
164 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 231
165 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 2
166 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 0
167 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 0
168 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 1500
169 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 100
175 Program_Fail_Count_Chip 0x0032 100 100 050 Old_age Always
- 0
176 Erase_Fail_Count_Chip 0x0032 100 100 050 Old_age Always
- 0
177 Wear_Leveling_Count 0x0032 100 100 050 Old_age Always
- 0
178 Used_Rsvd_Blk_Cnt_Chip 0x0032 100 100 050 Old_age Always
- 0
181 Program_Fail_Cnt_Total 0x0032 100 100 050 Old_age Always
- 0
182 Erase_Fail_Count_Total 0x0032 100 100 050 Old_age Always
- 0
192 Power-Off_Retract_Count 0x0032 100 100 050 Old_age Always
- 6
194 Temperature_Celsius 0x0022 100 100 050 Old_age Always
- 40
195 Hardware_ECC_Recovered 0x0032 100 100 050 Old_age Always
- 0
196 Reallocated_Event_Count 0x0032 100 100 050 Old_age Always
- 0
197 Current_Pending_Sector 0x0032 100 100 050 Old_age Always
- 0
198 Offline_Uncorrectable 0x0032 100 100 050 Old_age Always
- 0
199 UDMA_CRC_Error_Count 0x0032 100 100 050 Old_age Always
- 2
232 Available_Reservd_Space 0x0032 100 100 050 Old_age Always
- 100
241 Total_LBAs_Written 0x0030 100 100 050 Old_age
Offline - 5318
242 Total_LBAs_Read 0x0030 100 100 050 Old_age
Offline - 87
245 Unknown_Attribute 0x0032 100 100 050 Old_age Always
- 0
I believe smartctl(8) requests SMART data with binary commands, receives
binary replies, and must decode those replies based upon details from
the manufacturer. I expect that there are time delays between
smartctl(8) supporting a given drive and when that version of
smartctl(8) makes it into Debian stable.
Power_On_Hours raw value is 912. You have stated that this is a
relatively new drive. "Old_age" and "Pre-fail' do not make sense. I
would ignore them.
Another clue is the multiple "Unknown_Attribute" rows. This tells me
that your smartctl(8) does not fully support that Gigastone drive.
The drive is relatively new, so VALUE=100 and WORST=100 for all
attributes makes sense.
SMART Error Log Version: 1
ATA Error Count: 2
Note that "ATA Error Count"=2 matches "UDMA_CRC_Error_Count"=2 above.
That indicates communications problems between the drive and the
motherboard or HBA.
Please look for ATA error messages in dmesg and post anything related:
# dmesg | grep -i error
The most likely cause is the SATA cable. I would install a brand new
SATA III 6 Gbps cable with locking connectors.
Error -2 occurred at disk power-on lifetime: 0 hours (0 days + 0 hours)
More clues that smartctl(8) does not fully support that drive.
SMART Self-test log structure revision number 1
Num Test_Description Status Remaining
LifeTime(hours) LBA_of_first_error
# 1 Extended offline Completed without error 00% 901 -
The SMART long self-test completed without error, so the drive inards
are good.
Is there a way to throttle rsync to the write bandwidth of these SSD's?
Yes:
2024-01-15 00:17:44 dpchrist@laalaa ~/paul-christensen/g6950v
$ man rsync | grep bwlimit
--bwlimit=RATE limit socket I/O bandwidth
--bwlimit=RATE limit socket I/O bandwidth
--bwlimit=RATE
"--bwlimit=1.5m"). If no suffix is specified, the value
will be
--bwlimit=RATE
specify a smaller --bwlimit value, but no larger value
will be
But, that will not fix SATA hardware problems.
Or do I have a pile of duff SSD's?
I doubt it.
David
